5G and industrial Internet have been combined with many aspects of the iron and steel industry under nation policies and practical needs,they have played a positive role in realizing the development of various links of iron and steel industry from decentralization and automation to centralization,intelligence and green. However,5G and industrial Internet stay in the production auxiliary link and have not yet entered the real production core link. Informatization and industrialization have not really been integrated. The development direction and key technologies of 5G + industrial Internet and industrial control were described in detail from this perspective,new network convergence technical architecture was proposed,which includes cloud PLC technology,5G+TSN end-to-end low delay and deterministic network supporting PLC cloud deployment key technology. Finally,the theory and technical framework of industrial control,computing and communication integration was put forward, and the latest progress in the scene test of mutual integration of 5G+TSN and cloud based PLC technology was introduced. 

With the concepts of " carbon peak" " carbon neutrality" and " low-carbon metallurgy" ,green intelligent manufacturing in the iron and steel industry has become the general trend. The process before ironmaking is the front end of the iron and steel metallurgy process,and it is also the primary energy consumption link. Therefore,the realization of green intelligent manufacturing for the process before ironmaking has crucial economic value and environmental protection significance. Focusing on the green intelligent manufacturing for the process before ironmaking in the iron and steel metallurgy process, taking the low-carbon metallurgical technology of " smart carbon use" as the core,and it summarizes the research progress of the intelligent perception of operating state,the intelligent control of operating parameters,the intelligent optimization of operating performance,and the intelligent collaborative management and control. The intelligent perception of operating state is the main method to obtain information about the operating state that is difficult to detect,including operating state monitoring and operating state recognition. The intelligent control of operating parameters is a prerequisite for the normal operation of the process before ironmaking,which mainly includes intelligent control based on human experience,intelligent control based on parameter prediction,and integrated intelligent control for multiple objectives. The intelligent optimization of operating performance is the main measure to improve the performance of operating state,including intelligent optimization of operating parameters and intelligent optimization of operating indicators. The intelligent collaborative management and control for the iron and steel metallurgy process focuses on the collaborative integration of perception,control,and optimization technologies. Finally,the current opportunities and challenges are analyzed. The big data analysis and intelligent perception of operating state,the integrated intelligent collaborative management and control,and performance improvement and optimization control of the whole process may become the prospects of green intelligent manufacturing for the process before ironmaking.

Traditional mechanical properties prediction and optimization methods are mostly based on experience and mechanisms, and do not fully consider the value contained in the data. One of the current research hot spots is how to explore the linear and nonlinear transfer relationship between steel performance and related process parameters, construct high-precision performance prediction models, and achieve process optimization. Based on the high-dimensional process quality dataset of the throughout manufacturing process of hot rolled strip, this paper proposes a performance optimization method for hot rolled strip steel that integrates machine learning performance prediction model and Shapley additive explanation (SHAP) interpretation framework. This method first uses MIC metrics to select effective variables that have a significant impact on mechanical performance indicators from high-dimensional process parameters dataset; Then, by comparing the prediction accuracy of performance prediction models based on MSVR, SVR, and random forest, the optimal performance prediction model is selected; Finally, based on the SHAP interpretation framework and optimal prediction model, process parameter evaluation is conducted to measure the quantitative impact of each process parameter on the final performance, and the operational variables are adjusted according to the results of SHAP analysis to verify the effectiveness of performance optimization. The experimental results indicate that the performance optimization method proposed in this paper can significantly improve performance indicators according to demand, and has guiding significance for mechanical performance control in steel production processes.

In automation control for metallurgical unmanned overhead cranes,a critical challenge lies in balancing operational speed and anti-swing measures to enhance crane efficiency while ensuring safe operation. A metallurgical unmanned crane anti-swing full-range speed control method was pro- posed based on controller parameter switching derived from human expertise under multi-run states in this article. The method first plans the full-range speed control for the overhead crane linked by a large and small vehicle under anti-swing conditions. Then anti-swing control is optimized by switching PID parameters based on human crane operation experience under different running states,forming an integrated feedforward-feedback hybrid control for the unmanned overhead crane. Simulation experi- ments demonstrate that,compared to the commonly used manual operation of large and small vehicle linkage control,this method reduces overall operation time by 24. 9% . Field experiments show thatthe maximum swing angle is controlled within the range of 0. 45°-0. 85 °,and positioning accuracy is maintained within 10 mm. The relevant indicators are in a leading position in similar domestic scenar- ios. This method has been successfully applied and validated in the steel industry in China.

The iron and steel industry plays an important role in national economy. However,due to the characteristics of the iron and steel industry, such as long process, mutual coupling between processes,extreme production conditions,complex internal physical changes and chemical reactions, the process modeling,production control and prediction optimization of the iron and steel industry are severely limited,which further affects the improvement of production quality and production efficiency. In recent years,the vigorous development of digital twin in the industrial scenes has provided new ideas for the transformation and upgrading of the iron and steel industry. This paper first introduced the definition and connotation of digital twin,then analyzed the research hotspots of digital twin in the iron and steel industry,sorted out the relevant research results,and finally analyzed the current shortcomings in the application and development of digital twin,providing ideas for researchers'subsequent research,so as to promote the digital twin to play a greater role in the intelligent manufacturing of iron and steel. 

The hot metal pretreatment desulfurization process in modern converter steelmaking process can improve the efficiency of impurity removal,reduce the burden of converter blowing,and shorten smelting time.It is a necessary process for smelting variety steel and clean steel.The pretreatment process of molten iron undergoes complex high-temperature physical and chemical reactions,which is a black box process,making precise control of the smelting process very difficult.Establishing an accurate process control model is the core of achieving precise control of the hot metal pretreatment process,which is of great significance for enterprises to reduce steel production costs,promote digital and green transformation.This paper summarizes the modeling principles,characteristic and research progress of various models,such as mechanism model,statistical regression model,expert system and machine learning model,established by domestic and foreign researchers for hot metal pretreatment desulfurization process.Based on the different uses of the model,the development process of application in practice and prospects of the hot metal pretreatment desulfurization model were proposed,focusing on the prediction of endpoint sulfur content and desulfurization rate,prediction and optimization of smelting process parameters,and prediction of desulfurization agent consumption and utilization rate.

Problems in quality,cost,environment,stability and other aspects of the iron and steel industry need to be solved urgently,and " uncertainty" has become a major challenge faced by the iron and steel production process. With the development of digital economy and digital technology,data analysis technology has become the most effective method to solve the uncertainty problem. By giving full play to the advantages of application scenarios and data resources in the iron and steel industry, take the industrial Internet as the carrier,take the digital twin as the core,conquer key generic technologies,and build a future oriented digital innovative application. Relying on the full-process and full-scene digital transformation of iron and steel,accelerate the construction of iron and steel material innovation infrastructure,grasp the core competitiveness of enterprises,promote China忆s iron and steel industry to realize digital transformation and high-quality development

Byproduct gas,steam and electricity are important secondary energy source for the iron and steel production process. With the advancement of the "carbon peak" and " carbon neutrality" policies,the iron and steel industry has a growing need for fine-grained management of multi-medium energy systems,including by-product gas,steam and electricity,in order to control production costs and reduce energy consumption. However,due to the complexity and decentralised nature of the generation and consumption of each energy medium,it is vital to establish a comprehensive and rational scheduling model. In addition,in recent years,the development of renewable energy technologies such as photovoltaic and wind power has provided new ways for the iron and steel industry to make a low-carbon energy transition. Firstly,the multi-medium energy system was introduced,involving buffer equipment such as gas holders and boilers. Secondly,the research characteristics and results of each model were analyzed and summarized through the classification of energy scheduling models. Finally, the characteristics of the energy system in the iron and steel industry after the introduction of renewable energy was analyzed,and the concept of multi-energy microgrid in the iron and steel industry was introduced,providing ideas for subsequent research to promote energy-saving and low-carbon development in the iron and steel industry.

The content of FeO in the sintering process is an important reference index affecting the performance of sintering ore.Real-time observation and monitoring of changes in FeO content can reduce sintering energy consumption and improve sintering effect.Aiming at the current situation that the means of real-time observation of FeO content in enterprises is relatively single,the prediction model of FeO content in sinter based on bi-directional long short-term memory (BiLSTM) neural network algorithm was studied.The source of the data is partial process data generated in 2021 by the six-type sintering machine of Panzhihua Iron and Steel Co.,Ltd.After filtering,optimizing and other data processing,the BiLSTM neural network is selected for training,parameter adjustment,and combined with the on-site sintering process of the enterprise,which improves the prediction accuracy of the model.The accuracy rate basically realized the prediction of sintered FeO.The test results show that within the allowable range of enterprise error,the accuracy rate reaches 90.2%,so it can give　effective opinions on sinter production in the enterprise.

The prediction of sulfur content of liquid steel in ladle furnace (LF) is of great significance for the precise control of the composition of refined molten steel and the improvement of product quality.In view of the complex mechanism,multi-variable,and nonlinear characteristics of LF,a prediction method of sulfur content in LF was proposed based on autoencoder-back propagation neural network (AE-BPNN).Firstly,the effects of noise and missing values are eliminated through AE network for data reduction and feature extraction.Then,the BPNN is used for predicting the sulfur content of liquid steel in LF.The actual on-site data validation show that the E_RMS,E_MA and the correlation coefficient R² are respectively up to 1.403,1.083 and 0.824,which has good prediction performance.

Continuous casting slabs are raw materials of steel production.The defect of slab will lead to quality defect of final steel product.The low and high frequency data collected from continuous casting process on site were studied.Cleaning methods of complex process industrial data and feature extraction methods of high frequency industrial data were proposed.Based on machine learning theory,four kinds of slab surface defect prediction models,namely classification and regression tree (CART),AdaBoost,random forest (RF),and optimal classification tree (OCT) were established.Feature selection were carried out using Relief and RF model.The prediction accuracy of different models was compared and analyzed through a large number of experiments.The experimental results show that the RF model gives the best prediction accuracy.The top 10 features,such as liquidus temperature,tundish (TD) lower limit temperature and TD target temperature,which play a key role in slab surface defects are found out.The method in this paper can be extended to industrial data analysis and utilization modeling in other scenarios,which has important reference value for using industrial data to improve product quality.

Based on the continuous development of industrial smart manufacturing and the wide application of cloud-edge-end and digital twin technologies,the digital twin structure and key technologies for hot rolling production based on cloud-edge-end were proposed. Among them,the three-layer architecture in the digital twin structure realizes the digital management and intelligent control of hot rolling production and equipment. The key technology of hot rolling digital twin is the data communication between equipment based on 5G + edge computing technology. At the same time,the cloud-edge-end technology of data processing,storage and computing modeling is combined to solve the problems of low speed and poor privacy security of direct communication between physical entity and cloud. Finally,the hot rolling digital twin system is gradually constructed.

Sintering is a pre-process of blast furnace ironmaking,and the quality of sintered ore directly affects the quality and quantity of hot metal in the ironmaking process. Intelligent prediction and control of key parameters plays an important role in improving the quality of sintering ore in the sintering process. Firstly,the flowchart is introduced and its process characteristics is analyzed. Then, the predictive modeling research status for quality indicators and state parameters in the sintering process are reviewed. On this basis,the control methods about burn through point and ignition temperature in detail is illustrated. Finally,conclusions and prospects for the predictive and control modeling of key parameters in the sintering process are made.

The converter heat loss rate is one of the important parameters that affect the prediction accuracy of material consumption.Based on the calculation of heat loss rate,the historical production data of 1 900 heats of a 150 t converter in a steel plant was applied to accurately predict the converter heat loss rate using machine learning algorithm.The prediction results show that light gradient boosting machine (LightGBM) algorithm has the highest prediction accuracy compared with support vector regression (SVR) and random forest (RF) algorithms.Considering the influence of the last furnace,after adding the final smelting temperature variable of the last furnace,the determination coefficient R² of LightGBM algorithm increases from 0.89 to 0.93,and within the range of ±0.005 and ±0.01,the prediction hit rate of heat loss rate increased from 85%,89% to 90%,93% respectively.In addition,the prediction accuracy of the model can be further improved by optimizing the internal parameters of the algorithm.For the LightGBM algorithm,the determination coefficient R² and root mean square error (RMSE) further reach 0.94 and 0.009,and the prediction hit rate of the heat loss rate further increases to 91% and 94% within the range of ±0.005 and ±0.01.Based on historical data of converter smelting,intelligent algorithms can be used to predict the heat loss rate of the converter,which can provide support for the prediction of the material consumption of the converter.

The precise control of the end-point carbon content and temperature of Consteel electric arc furnace is extremely important to ensure the high-quality liquid steel. Different machine learning models including prediction models and hyper-parameter optimization models were used to fit the actual production data from the smelting process of Consteel electric arc furnace in a domestic steel plant. Based on the prediction results of machine learning models,the end-point carbon content and temperature prediction model of the Consteel electric arc furnace based on Bayesian optimization algorithm (BOA) and gradient boosting decision tree (GBDT) was established. Through the verification by using the collected data,this model achieves better prediction performance for the end-point carbon content and temperature of Consteel electric arc furnace smelting,which can provide certain guidance for the actual production process.

Hoist is the key equipment of dry quenching coke charging system,which has large load,frequent start and stop,unstable working condition,complex gear box structure and large reduction ratio.Therefore,the continuity and reliability of the hoist has always been the focus of production and equipment managers.An artificial intelligence algorithm based on multi-dimensional perception and neural network was proposed by the paper to identify the instantaneous fault of hoist equipment in real-time and monitor the hoist life cycle.By extracting and identifying the acoustic and vibration characteristics of the hoist gear box,combined with convolutional neural network (CNN) and long-short term memory (LSTM) neural network algorithm,extracting vibration space characteristics and time operating characteristics,judge and predict the operating state of equipment,so as to achieve real-time monitoring of equipment operating state,fault diagnosis and predictive maintenance.Engineering application practice shows that the method can effectively achieve 95.3% accuracy of fault identification,and can quantify the specific stage of the hoist′s operation life cycle,so as to remind maintenance personnel to respond to equipment faults in time,achieve predictive maintenance of hoist,reduce equipment failure rate,reduce maintenance costs,achieve continuous safe production,promote equipment professional management and smart factory construction.

In order to ensure the effective use of rolling equipment capacity,taking the mill motor load data of a bar production line in a steel plant as the object of study,PyTorch was used to build a prediction model based on long short term memory ( LSTM) network,define the initial grid structure parameters of the model,and select the cell structure activation function. For the problem of model hyper-parameters selection,the adaptive moment estimation ( Adam) algorithm was used to optimize the parameters,iteratively reduce the loss value and improve the prediction accuracy of the model.Through the experimental design,the mill load data for two bar sizes were used to verify,and that the mean square error SME is reduced by 3. 28 and 1. 76,respectively,compared with the unoptimized load prediction models. The results show that the established models have better prediction effect and higher stability.

It is of great significance to clarify the phase distribution and lining erosion characteristics of blast furnace by the damage investigation,and the information on various phase parameters of the damage-investigation samples can be obtained rapidly and cost-effectively through the image-processing technology.The coke information of the residual iron section in the hearth,the three-dimensional structure of slag-iron-coke and the damage degree of the refractories were characterized quantitatively based on the damage-investigation work of a large blast furnace in China combining Photoshop (PS),Image-Pro Plus (IPP) software and industrial CT equipment.The process of image acquisition and binarization processing was firstly introduced,as well as "calculation method of pixel proportion" and the trend distribution of deadman voidage by grid partitioning were then characterized.At the same time,the correlation between two and three dimensional voidage was verified through detecting　the three-dimensional phase distribution and voxel ratio of slag-iron-coke in the deadman.Furthermore,the correction coefficient C was introduced based on the basis of "coke size calculated by equivalent circle" which reduced the influence of coke irregular morphology on particle size.The distribution,size,and depth of the refractory material′s cracks in surface macroscopic and internal microscopic were intuitively characterized by the binary images,and the number,volume,and porosity of pores in refractory materials can be also characterized by the three-dimensional structure,then determined the damage situation of refractory materials in the hearth quantitatively.

With the deepening of the transformation of the steel industry towards automation and intelligence,intelligent equipment systems based on machine vision have been widely applied due to their outstanding advantages of low cost,high accuracy,stability and reliability. Based on extensive practical experience in industrial sites,this article studies and designs an intelligent equipment software platform for the steel industry. It adopts a layered structure,builds underlying libraries,development templates,communication protocols,instruction sets,etc. as the basic support,and provides essential software functional modules in the intelligent equipment system to assist in the rapid construction of new applications. The platform module involves a comprehensive process of data acquisition,storage, image algorithm processing,device control,data display,and fault diagnosis,fully considering the structural requirements and functional support for intelligent equipment in industrial scenarios. Through this software platform,the development time of specific intelligent equipment applications can be greatly reduced,and the requirements for application implementation can be met while ensuring system stability.

With the development of information technology,big data,internet of things and computing power,the third wave of artificial intelligence has begun to appear in academic research and industrial applications. The iron and steel industry is a complex process industry,where the internal production process is complex with many influencing factors,thus artificial intelligence in the iron and steel industry has a high application value. With the promotion and implementation of the national policy of integration of informatization and industrialization,China's iron and steel industry has gradually improved its informatization degree and level. This lays a solid foundation for the implementation of artificial intelligence technology in iron and steel industry. This paper first explored the research fields of artificial intelligence technology,including expert system,neural network,intelligent robot,machine learning,intelligent optimization,etc.,and then studied the main application scenarios and research results of these technologies in the field of iron and steel. Finally,this paper looked forward to the artificial intelligence technology from production optimization to strategic management to help the high-quality development of iron and steel industry.

The accurate prediction of the Linz Donawitz converter gas (LDG) holder level in iron and steel enterprises can provide an important basis for gas system scheduling.Given the impact of LDG recovery,scheduling workers are particularly concerned about the problem of exceeding the upper limit of the holder level.Based on a large amount of on-site actual data,a cost-sensitive learning-based support vector machine (SVM) method for predicting the level of LDG holder was proposed,which can improve the prediction accuracy of the situation when the level exceeds the upper limit.This method takes the recovery and consumption flow of LDG as inputs,and the future holder level value as output.By using the KKT equation,the original constraint conditions are transformed into equation constraints,different costs are set for the gas holder level exceeding the limit and false alarms.Finally,by minimizing the model′s false alarm error,the original prediction problem is transformed into a series of linear equations and solved.A simulation experiment was conducted on data　from a domestic steel plant,and the results showed that the proposed method can effectively reduce the false alarm rate of converter gas holder level exceeding the limit to 0.16%,providing more rapid and effective guidance for scheduling workers to develop reasonable scheduling strategies.

In iron and steel enterprises,refined energy management and intelligent scheduling operations are important technical means to achieve efficient energy utilization. Based on a detailed analysis of the integrated energy system of iron and steel enterprises and the integration of advanced technologies from other industries,the design of an intelligent implementation path for the scheduling and operation of the integrated energy system was completed. Based on the theory of metallurgical process network,a networked modeling of integrated energy systems was conducted. A hybrid reasoning method based on serialized case sections was proposed,including the definition,management,search,and design of hybrid reasoning engines. A practical intelligent driving engine was constructed. Finally,according to the actual needs of a steel enterprise's integrated energy system scheduling operation,an intelligent scheduling decision support system was designed and developed,which achieved good economic benefits in practical applications and provided beneficial practice for the development of intelligent energy in iron and steel enterprises. 

The development of high-efficient continuous casting with the core aim of high speed and defect-free is a key basis for hot charging and direct rolling of continuous casting strand,and also an important measurement to achieve CO2 emissions and green development of the iron and steel industry. Thus, the traditional continuous casting must be transformed into digital continuous casting to achieve the high-efficient production,and finally a digital twin of caster with high precise,independent judgement,decision-making and intelligent control is developed to be in charge of the whole continuous casting process without manual intervention. Based on the current situation of continuous casting digital development both at home and abroad,the author believes that the following problems need to be solved urgently in the development of high-efficient digital continuous caster. Firstly,in order to improve the state perception ability of continuous casting,the reliability and detection accuracy of the sensor should be improved to ensure the authenticity and reliability of the data. In view of the knotty problem that some continuous casting parameters cannot be directly measured,relevant digital testing equipment development is imperative to ensure the state perception of the entire continuous casting process. Secondly,more advanced AI algorithms are needed to analyze the big data for the continuous casting process and establish the nonlinear coupling relationship between the industrial big data, equipment operation status and the strand quality. Finally,the high-precision digital twin models for continuous caster,which combines state perception,high-performance computation,process control, artificial intelligence and traditional multi-scale modeling methods, are developed to eliminate the hysteresis problem commonly existing in the current models,overcome the difficulties of multi-physical field coupling,and consequently the high-efficient continuous casting with defect-free strand production is achieved by multi-objective optimization based on the new developed high-precise digital twin models. 

Based on the analysis of current situation,bottleneck and development trend of key production equipment management in iron and steel industry, the exploration and practical experience of equipment predictive maintenance in large foreign steel enterprise such as NIPPON STEEL,BigRiverSteel and POSCO were summarized. Aiming at the difficult problems of online monitoring of key equipment under complex working conditions such as low speed,variable speed,instantaneous operation,heavy load impact and bearing floating,the solution was explored,and the digital remote monitoring network architecture and intelligent operation and maintenance action plan in Masteel were designed. Based on the industrial Internet architecture,the remote operation and maintenance management system which integrates " critical equipment condition monitoring,intelligent fault early warning,intelligent diagnosis and analysis,and mobile application" was constructed. The application practice of this system will realize the interconnection of upstream and downstream enterprises and the overall improvement of asset benefits through the whole life cycle data process,and provide an exploration direction for the management of key production equipment in the iron and steel industry.

It is a big dream of ironmaking workers to achieve the intelligent control of blast furnace. In recent 30 years,a large number of developments and practices have been implemented in many blast furnaces. Due to the complexity of blast furnace process control,it is difficult to obtain a good intelligent control system for realizing stable performance of blast furnace in despite of good performance for intelligent control system with single function. Some problems,such as range of study,contents,operational requirement, key issues to be addressed, have been deliberated based on the requirements of high efficiency smelting in blast furnace. Some proposals,such as emphasizing on the research of blast furnace with features of " multivariate, large time delay, nonlinear, full time and space" ,building high level data platform,using the simplest and most practical technologies,paying attention to the development and use of platform tools,constructing reasonable intelligent control development mode,simulating blast furnace experts,accurate positioning and priority to the easy,setting up a special software development team for blast furnace whole campaign optimization,have been proposed,a good object for upgrading one generation in 3 - 5 years will be achieved.

Under the dual influence of environmental protection and de-capacity,Chinese steel has begun to transform into a high-quality,intelligent and green production model. The traditional concept of blast furnace smelting with high energy consumption and high pollution is no longer applicable to the development of the " 14th Five-Year Plan" direction. With the rise of big data and artificial intelligence technology,the new generation of iron and steel industry is moving towards green manufacturing under the impetus of intelligent manufacturing,and it has become a major trend to establish various prediction models by analyzing the data accumulated by iron and steel enterprises for many years. This paper firstly took the blast furnace intelligent transformation as the research background,and the prediction model of smelting index and monitoring system of smelting process of the current blast furnace were introduced in a simple to complex manner. Then,the importance of data processing and expert decision optimization strategy was analyzed,and the current construction of blast furnace big data cloud platforms in various enterprises was briefly expounded. Finally,the corresponding conclusions and prospects were made for the intelligent transformation of blast furnace.

In the hot rolling strip process,the coiling temperature is an important process parameter and the main control objective,which can to some extent determine the strip steel microstructure,and affect the mechanical properties and usability of the product.To improve the accuracy of hot strip coiling temperature,based on the actual production data of a hot strip rolling line,a data driven coiling temperature prediction model for hot strip rolling was established using random forest (RF) algorithm.The Bayesian optimization algorithm is used to determine the optimal hyper-parameter of the RF model,and the grid search is used to determine the Bayesian algorithm hyper-parameters.At the same time,an decision tree model (DT) optimized by Bayesian optimization algorithm,support vector regression model (SVR) and mechanism model based on classical heat transfer theory are used for comparison and verification.The model testing results show that over 97% of the prediction results of the RF model have a prediction error within -10-10 ℃ for sample points.Compared to on-site models,it can predict the coiling temperature and further improve the control accuracy of coiling temperature.

With the rapid development of the engineering machinery manufacturing industry,the heat treatment process of steel plates has higher requirements for plate shape. The quenching process is a key factor in determining the shape quality of heat-treated plates. Since steel plates experience both phase change stress and thermal stress during the quenching process,defects are prone to appear on quenched plates,affecting the quality of the final product shape. Therefore,there is an urgent need for a method that can identify the shape of steel plates to provide meaningful guidance for controlling the quenching shape of steel plates. To address the shape recognition problem,a quenching process shape recognition neural network based on an attention mechanism and lightweight design was proposed. Additionally,the plate shape image is processed using K-means to enhance defect characterization. Tests were conducted on the slab shape dataset,and the experimental results demonstrate that this lightweight network module has higher recognition accuracy mean and a single inference speed im- provement of 20-50 ms compared to other networks. 

The digitalization of the whole steelmaking-rolling process has an important impact on expanding product varieties,improving quality and efficiency,reducing manufacturing costs and emissions,and is an important means to realize intelligent manufacturing and enhance the core competitiveness of enterprises. Combined with the characteristics of the steel process,the system architecture of the digital application integration platform for the whole steelmaking-rolling process and the main functions of edge computing,data integration and application services were introduced. The overall solutions of various businesses digitalization were proposed from four fields,such as intelligent control of process quality,intelligent control of energy medium,intelligent operation and maintenance of equipment,digital process simulation and optimization design. Additionally,taking the hot wide strip rolling line as the object,a digital hot rolling intelligent factory has been built,which 100 000 data points support the visualization of all elements of the factory. The production stability was improved by 20% . The reliability of the one click analysis of quality defect achieved 95% . The defective product rate was reduced by 20% . The percent of fine management and control of cost and energy consumption to each coil was up to 100% . Finally,the future digitization development of whole steelmakingrolling process was prospected.

During the continuous casting process,the instantaneous abnormal mold level fluctuation has great detrimental effects on slab quality,thus the mold level fluctuation is a key parameter for continuous casting process of high-quality steel.In the present study,the slab continuous casting process data for low carbon steel,medium carbon steel,hypo-peritectic steel and peritectic steel were collected,the fast Fourier transform (FFT) and continuous wavelet transform (CWT) were used to analyze the data characteristics,and then the influence of process parameters on the instantaneous abnormal mold level fluctuation was studied.The results of FFT analysis indicate that bulging has no significant effect on the instantaneous abnormal mold level fluctuation.The time-frequency characteristics of instantaneous abnormal mold level fluctuation and stopper-rod position were analyzed by CWT,and the results show that under different steel grades and casting speeds,before the instantaneous abnormal mold level fluctuation occurrence,the CWT coefficients in high-frequency region of stopper-rod position shows a linear increase trend.Therefore,by conducting CWT analysis of the high-frequency region of the stopper-rod position,it is possible to predict the instantaneous abnormal　mold level fluctuation.

Aiming at the outstanding problems of insufficient digitization of iron making process,low degree of intelligence,lack of a unified intelligent platform,and far from adapting to the development needs of intensification,digitization and intelligence,Angang Steel Co.,Ltd. established a big data centre for intensive control of blast furnace with blast furnace group as the core and covering other processes. The big data centre breaks the information silos of each regional information system,releases the effectiveness of data. The blast furnace group and subsidiary process form a centralized control and management centre for data sharing and efficient collaboration,realizing the blast furnace process upgrading from an intelligent unit to an intelligent platform. At the same time,the intelligent application model of blast furnace is built,which realizes the visualized intelligent monitoring of the safe production and operation of blast furnace,and guides the production operation of blast furnace,as well as improves the digitization and intelligence level of the production,technology and management of the blast furnace of Angang Steel Co., Ltd.

In order to achieve more accurate calculation of alloy addition amount,a comprehensive al- gorithm based on genetic algorithm ( GA) optimization for BP neural network was adopted. During the training process of the BP neural network,the refining starting composition of the molten steel was used as input parameters for the BP neural network model. Then,the fitness function of the GA was used to optimize and adjust the weight and threshold of BP neural network,predicting the refining endpoint steel composition of the LF furnace. By comparing the prediction results of BP neural net- work algorithm and GA-BP neural network algorithm, it was found that the GA-BP algorithm has smaller mean absolute error (MAE) and mean square error (MSE) ,and the prediction results aremore accurate and basically consistent with the actual steel composition,indicating that this model can be used in production. Based on the GA-BP neural network model,the alloy addition amount was determined according to the composition of the molten steel at the beginning of LF refining and con- trol composition requirements. After deploying a predictive model in the 140 ton ladle LF refining sys- tem of a steel plant and tracking 188 furnace data,the difference between the actual amount of alloy added and the predicted amount was within ±30 kg,then the prediction accuracy of high manganese alloy was 91. 3% ,high chromium alloy was 90. 4% ,ferrosilicon alloy was 90. 2% ,and the predic- tion accuracy of carburant was 91% in furnaces,from which can guide the determination of alloy ad- dition amount in the actual refining process. 

With the continuous improvement of the level of industrial information technology, datadriven process monitoring has become a key technology for improving the safety,quality and operating efficiency of the process industry. Blast furnace ironmaking is the core process with the largest energy consumption and emission in the iron and steel manufacturing process. The research and application of fault monitoring technology is of great significance to the running security,energy saving and emission reduction of blast furnace ironmaking process. Firstly,the research status of data-driven blast furnace fault monitoring algorithms is summarized from the perspective of non-linear,non-gaussian and time-varying characteristics of blast furnace process and operating data. Then,compared with the current cutting-edge research algorithms in the monitoring field,the advantages and disadvantages of various algorithms are analyzed,and the real requirement and development directions of the blast furnace monitoring algorithm are proposed. Finally,based on the requirements of monitoring the online operation of the algorithm,a platform architecture that can realize the online operation and regular update of the algorithm is developed,and the visualization results of the algorithm are displayed.

Steel manufacturing is a typical process industry. Multiple uncertainties in its complicated production process bring huge challenges for production scheduling. Facing the disturbances caused by uncertain events,how to design dynamic scheduling strategies to achieve fast response is a key and practical issue to be solved in iron and steel enterprises. Existing work proposes many dynamic scheduling methods based on Petri net,heuristic algorithms,mathematical programming,dynamic constraint satisfaction,human-computer interaction, case-based reasoning,robust and fuzzy optimization to solve various dynamic scheduling problems in iron and steel production scheduling scenarios,such as ironmaking,steelmaking-continuous casting, hot rolling, and steelmaking-continuous casting-hot rolling processes. An overview of dynamic scheduling in iron and steel production systems is given. The main process of iron and steel production and its dynamic disturbance factors are introduced. Existing research on dynamic scheduling problems and their solution methods in iron and steel production systems are summarized. The desired demands of the iron and steel industry and the limitations of existing work are analyzed. Finally,the key scientific issues to be solved and future research directions to be explored are indicated, which include knowledge and data-driven high-performance dynamic scheduling algorithms, multi-process collaboration dynamic scheduling problems and their solution methods,and configurable decision support systems.

Iron and steel industry plays an important role in the national industrial economy. As an important link in steel production,BOF steelmaking directly determines the quality of steel production. BOF steelmaking is a multi-element,multi-phase and high-temperature physical and chemical reaction process with many influencing factors and complicated process. It is always a difficult problem to be solved in metallurgical industry to realize accurate control of BOF steelmaking endpoint.The goal is to improve the hit rate of carbon content and temperature at the endpoint of BOF steelmaking. Aiming at the lack of prediction performance of the traditional global model,it is difficult to solve the problem of multiple working conditions,a local model integration online monitoring method based on just-in-time learning ( JITL) is proposed. Under the framework of JITL, using similarity measurement methods under different criteria,select corresponding sub-sample sets,build local regression models respectively,and finally output the prediction results of each local model through ensemble learning. In the verification of actual converter steelmaking data,using the proposed method,the prediction accuracy of endpoint temperature in ± 15 ℃ is 92. 7% and the prediction accuracy of endpoint carbon mass fraction in ± 0. 02% is 95. 7% ,which can provide reference for endpoint control and other operations in actual production process.

Improving the operation efficiency of cranes in the steelmaking area can reduce energy consumption for transportation while effectively linking the preceding and succeeding processes, which is of certain value for green production,cost reduction,and efficiency increase. In this regard, this article proposed a crane scheduling optimization method driven by simulation modeling and machine learning. Firstly,multi-agent is used to establish a production simulation model for the steelmaking area,which is driven by historical production plans and crane scheduling workflows. Subsequently,the simulation model is run multiple times to obtain a large number of high-quality crane operation samples through built-in sample evaluation formulas. Finally,a random forest model is employed to learn from the samples and obtain a machine learning model for matching cranes with transportation tasks. Experimental analysis shows that applying the machine learning model to crane scheduling decisions can increase the proportion of effective transportation time,thereby reducing energy consumption losses caused by mismatched transportation tasks,path avoidance,etc. This advantage is particularly significant under heavy production loads. Furthermore,the crane scheduling machine learning model is decoupled from the steelmaking plan,exhibiting high flexibility in practical app lications.

In the process of blast furnace smelting,under the influence of dynamic changes of working conditions and complex factors at the production site,the fluctuation of differential pressure has a certain time lag,and it is still difficult to realize the accurate forecast of differential pressure based on real-time online data. To address this problem,based on the actual smelting process of the blast furnace,which has the characteristics of multivariate and time-dependent time series data,the volatility analysis and decision tree feature importance analysis methods that can effectively reflect the degree of fluctuation of the production process parameters are adopted,and different subsets of the model input features are selected,so as to establish the temporal pressure difference prediction model based on the long short-term memory (LSTM). The comparison results of the two methods show that the LSTM prediction model based on volatility analysis to determine the input features has an improved hit rate of 0. 761% within the prediction error range[ - 5, + 5] kPa. The feature selection method based on the volatility analysis of production parameters can effectively improve the prediction accuracy of the LSTM model,and verify the validity of the input feature selection method of the temporal differential pressure prediction model under the condition of oxygen-enriched blast furnace.