Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619237
Haojie Sun, Jianbang Liu, Jingyang Wang, Zhijia Yang, Tao Zou
In order to solve the problem of the high sensitivity of conventional double-layer model predictive control (DLMPC) algorithm to the process white noise and disturbance, we proposed an improved strategy integrating the tunnel control, which sacrifices a small part of the economic performance for a more smooth and stable control effect. By selecting an appropriate robust factor, an allowable economic performance zone is determined. The tunnel control strategy is implemented by selecting an appropriate weighting matrix for the output error in the control cost function. When the economic performance index (EPI) of output prediction is inside its zone, the corresponding weight is zeroed. When the EPI of prediction lies outside the performance zone, the error weight is made equal to a specified value and the distance between the output prediction and the ideal steady-state set-point is minimized. Finally, the feasibility and effectiveness of the proposed algorithm are verified by simulating based on the Wood-Berry model.
{"title":"Double-Layer model predictive control combined with funnel zone control","authors":"Haojie Sun, Jianbang Liu, Jingyang Wang, Zhijia Yang, Tao Zou","doi":"10.1109/IAI53119.2021.9619237","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619237","url":null,"abstract":"In order to solve the problem of the high sensitivity of conventional double-layer model predictive control (DLMPC) algorithm to the process white noise and disturbance, we proposed an improved strategy integrating the tunnel control, which sacrifices a small part of the economic performance for a more smooth and stable control effect. By selecting an appropriate robust factor, an allowable economic performance zone is determined. The tunnel control strategy is implemented by selecting an appropriate weighting matrix for the output error in the control cost function. When the economic performance index (EPI) of output prediction is inside its zone, the corresponding weight is zeroed. When the EPI of prediction lies outside the performance zone, the error weight is made equal to a specified value and the distance between the output prediction and the ideal steady-state set-point is minimized. Finally, the feasibility and effectiveness of the proposed algorithm are verified by simulating based on the Wood-Berry model.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124060526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619315
H. Bian, Jialiang Yu, Jie Tian, Junqing Li
The Expected Improvement(EI) criterion is regularly used to balance global search and local search to further optimize the current optimal solution. However, the uncertainty measure proposed by surrogated model probably lose efficacy in medium-scale problems. As uncertainty measurement is an important component of the infill criterion, Bayesian optimization may get a wrong optimization directin with the uncertainty measurement failure. To solve this problem, we propose a modified Expected Improvement based on Information Entropy(IEEI), which is used to select candidate solutions that need to use the original function for real calculation. The main idea is to replace the root mean square error provided by the surrogate model with the prediction error obtained by the information entropy model. In each test problem, the improved EI criterion can obtain more competitive optimization results in performance evaluation compared with the standard EI criterion. It can effectively and stably approach the global optimal solution and improve the accuracy of the model.
{"title":"A Modified Expected Improvement Criterion for Multi-objective Bayesian Evolutionary Optimization","authors":"H. Bian, Jialiang Yu, Jie Tian, Junqing Li","doi":"10.1109/IAI53119.2021.9619315","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619315","url":null,"abstract":"The Expected Improvement(EI) criterion is regularly used to balance global search and local search to further optimize the current optimal solution. However, the uncertainty measure proposed by surrogated model probably lose efficacy in medium-scale problems. As uncertainty measurement is an important component of the infill criterion, Bayesian optimization may get a wrong optimization directin with the uncertainty measurement failure. To solve this problem, we propose a modified Expected Improvement based on Information Entropy(IEEI), which is used to select candidate solutions that need to use the original function for real calculation. The main idea is to replace the root mean square error provided by the surrogate model with the prediction error obtained by the information entropy model. In each test problem, the improved EI criterion can obtain more competitive optimization results in performance evaluation compared with the standard EI criterion. It can effectively and stably approach the global optimal solution and improve the accuracy of the model.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130100005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619444
Shan Gao, Jing Xu, Wei Dan, Qixian Li, Yu Huang
Selective Catalytic Reduction (SCR) is the most widely used and most mature denitrification technology in thermal power plants in my country. In view of the strong interference characteristics in the SCR denitrification system, this paper applies the fractional order PIλDμ controller to the outer loop control of the denitrification system. Because the fractional order PIλDμ controller has many parameters and the adjustment process is complicated and cumbersome, this paper proposes an Optuna optimization algorithm with CMA-ES sampler. This algorithm introduces the sampling principle of the CMA-ES algorithm into Optuna, and uses the strong parameter search ability of CMA-ES to determine the parameters of the fractional order PIλDμ controller. The experimental results show that the fractional order PIλDμ controller has good tracking, anti-interference and robustness in the denitrification control system of thermal power plants.
{"title":"Research on Optimal Control of Fractional Order PIλDμ Parameters of SCR Denitrification System","authors":"Shan Gao, Jing Xu, Wei Dan, Qixian Li, Yu Huang","doi":"10.1109/IAI53119.2021.9619444","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619444","url":null,"abstract":"Selective Catalytic Reduction (SCR) is the most widely used and most mature denitrification technology in thermal power plants in my country. In view of the strong interference characteristics in the SCR denitrification system, this paper applies the fractional order PIλDμ controller to the outer loop control of the denitrification system. Because the fractional order PIλDμ controller has many parameters and the adjustment process is complicated and cumbersome, this paper proposes an Optuna optimization algorithm with CMA-ES sampler. This algorithm introduces the sampling principle of the CMA-ES algorithm into Optuna, and uses the strong parameter search ability of CMA-ES to determine the parameters of the fractional order PIλDμ controller. The experimental results show that the fractional order PIλDμ controller has good tracking, anti-interference and robustness in the denitrification control system of thermal power plants.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129073652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619422
Kaibei Peng, Xiaoming Sun, Haowei Chen, Zhen He, Jianrong Wang
Noise has great harm to speech. Therefore, speech enhancement plays a vital role in speech signal processing. To further improve the effect of speech enhancement, a speech enhancement method based on a gated recurrent unit with an attention mechanism (AGRU) is proposed. Firstly, the attention mechanism is used to extract important features in the speech signals. Then the gated recurrent unit (GRU) is used to map the complex relationship between noisy speech and pure speech. The collected speeches of different emotions are used for simulation. The results show that the method proposed in this paper can remove speech noise and is better than other methods. The method proposed in this paper can provide some references for the application of deep learning in speech enhancement.
{"title":"A Speech Enhancement Method Using Attention Mechanism and Gated Recurrent Unit","authors":"Kaibei Peng, Xiaoming Sun, Haowei Chen, Zhen He, Jianrong Wang","doi":"10.1109/IAI53119.2021.9619422","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619422","url":null,"abstract":"Noise has great harm to speech. Therefore, speech enhancement plays a vital role in speech signal processing. To further improve the effect of speech enhancement, a speech enhancement method based on a gated recurrent unit with an attention mechanism (AGRU) is proposed. Firstly, the attention mechanism is used to extract important features in the speech signals. Then the gated recurrent unit (GRU) is used to map the complex relationship between noisy speech and pure speech. The collected speeches of different emotions are used for simulation. The results show that the method proposed in this paper can remove speech noise and is better than other methods. The method proposed in this paper can provide some references for the application of deep learning in speech enhancement.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122373185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619351
Zheng Zhang, Decai Li, Yuqing He
Based on the rapid development of deep learning, semantic information has gradually become a research hotspot in the field of SLAM (Simultaneous Location and Mapping). The noise problem caused by the environment and sensor results in the lack of consistency of semantic maps, and affects the accuracy of the algorithms. Loss function can adjust the weights assigned to the outliers, so it can reduce the impact of the outliers. However, the model of loss function used by most semantic SLAM is fixed and cannot adapt well to the changing environment. To solve this problem, this paper proposes a improved noise-adapted semantic SLAM, which uses Gaussian mixture correntropy weight function as loss function. Its model structure is variable by adjusting the parameters in changing environment, so it can adapte the noise distribution to the greatest extent, which is more conducive to reducing the weight of the algorithm for outliers and improving robustness to the outliers. Experiments on the public KITTI dataset show that the average relative translation and rotation error of the proposed method are reduced by 4.08% and 5.55%, the constructed semantic maps are more consistent.
基于深度学习的快速发展，语义信息逐渐成为SLAM (Simultaneous Location and Mapping)领域的研究热点。由环境和传感器引起的噪声问题导致语义图缺乏一致性，影响算法的准确性。损失函数可以调整分配给离群值的权重，因此可以减少离群值的影响。然而，大多数语义SLAM使用的损失函数模型是固定的，不能很好地适应变化的环境。为了解决这一问题，本文提出了一种改进的噪声适应语义SLAM，该SLAM采用高斯混合熵权函数作为损失函数。它的模型结构在变化的环境中通过调整参数而变化，因此可以最大程度地适应噪声分布，这更有利于降低算法对离群值的权重，提高对离群值的鲁棒性。在KITTI公共数据集上的实验表明，该方法的平均相对平移和旋转误差分别降低了4.08%和5.55%，构建的语义图更加一致。
{"title":"Improved noise-adapted semantic SLAM","authors":"Zheng Zhang, Decai Li, Yuqing He","doi":"10.1109/IAI53119.2021.9619351","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619351","url":null,"abstract":"Based on the rapid development of deep learning, semantic information has gradually become a research hotspot in the field of SLAM (Simultaneous Location and Mapping). The noise problem caused by the environment and sensor results in the lack of consistency of semantic maps, and affects the accuracy of the algorithms. Loss function can adjust the weights assigned to the outliers, so it can reduce the impact of the outliers. However, the model of loss function used by most semantic SLAM is fixed and cannot adapt well to the changing environment. To solve this problem, this paper proposes a improved noise-adapted semantic SLAM, which uses Gaussian mixture correntropy weight function as loss function. Its model structure is variable by adjusting the parameters in changing environment, so it can adapte the noise distribution to the greatest extent, which is more conducive to reducing the weight of the algorithm for outliers and improving robustness to the outliers. Experiments on the public KITTI dataset show that the average relative translation and rotation error of the proposed method are reduced by 4.08% and 5.55%, the constructed semantic maps are more consistent.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":" 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120937437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619249
Haifeng Song, Minjie Zhang, Kai Feng, Jianfeng Cheng, Datian Zhou
The terrain of undulation might lead to change the slope of a route. During a vehicle moving in different section of such route, the attitude of the vehicle might fluctuate respectively. It is a novel principle of using the attitude data of pitch to determine a vehicle’s position. This paper presents a method based on DTW (Dynamic Time Warping), which augments the location algorithm based on accumulating data from IMU (Inertial Measurement Unit). This method is designed to recognize a match between pitch angle sequence by time and a digital map storing undulatory characters of a route. The effectiveness of the presented method is validated by estimating errors of distance accumulated in periods.
起伏的地形可能导致路线坡度的改变。当车辆在该路线的不同路段行驶时，车辆的姿态可能会有所波动。利用俯仰姿态数据确定车辆位置是一种新颖的原理。本文提出了一种基于DTW (Dynamic Time Warping)的方法，对惯性测量单元(IMU)数据积累的定位算法进行了改进。该方法用于识别时序俯仰角序列与存储路线波动特征的数字地图之间的匹配。通过对周期累积距离误差的估计，验证了该方法的有效性。
{"title":"Kalman filter Based Vehicle Running Data Estimation","authors":"Haifeng Song, Minjie Zhang, Kai Feng, Jianfeng Cheng, Datian Zhou","doi":"10.1109/IAI53119.2021.9619249","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619249","url":null,"abstract":"The terrain of undulation might lead to change the slope of a route. During a vehicle moving in different section of such route, the attitude of the vehicle might fluctuate respectively. It is a novel principle of using the attitude data of pitch to determine a vehicle’s position. This paper presents a method based on DTW (Dynamic Time Warping), which augments the location algorithm based on accumulating data from IMU (Inertial Measurement Unit). This method is designed to recognize a match between pitch angle sequence by time and a digital map storing undulatory characters of a route. The effectiveness of the presented method is validated by estimating errors of distance accumulated in periods.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"515 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116216447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619286
Wen Xu, Jian Tang, Heng Xia
Dioxin (DXN) is a kind of persistent organic pollutant with a cumulative effect. It is also one of the main reasons for "not in my back yard" effect in Municipal solid waste incineration (MSWI) plants. Real-time detection of DXN is helpful to realize emission reduction, optimize control, and eliminate oppose effect in MSWI process. However, there are very tiny label process data that can be used to construct data-driven prediction models due to the time and economic cost. In order to utilize the process data, this article presents a collaborative training decision trees (CTDTs) method for dioxin emission concentration prediction. First, the raw label process data is used to train the decision tree model, after that the process data is labeled. Second, the root mean square error of the labeled sample is calculated to select the optimal labeled and process data. Third, the DXN emission prediction model is constructed by cross-combination of the raw labels and labeled process data. Simulation results of the benchmark dataset and practical DXN data verify the effectiveness of the proposed method.
{"title":"Prediction of dioxin emission concentration based on collaborative training decision tree","authors":"Wen Xu, Jian Tang, Heng Xia","doi":"10.1109/IAI53119.2021.9619286","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619286","url":null,"abstract":"Dioxin (DXN) is a kind of persistent organic pollutant with a cumulative effect. It is also one of the main reasons for \"not in my back yard\" effect in Municipal solid waste incineration (MSWI) plants. Real-time detection of DXN is helpful to realize emission reduction, optimize control, and eliminate oppose effect in MSWI process. However, there are very tiny label process data that can be used to construct data-driven prediction models due to the time and economic cost. In order to utilize the process data, this article presents a collaborative training decision trees (CTDTs) method for dioxin emission concentration prediction. First, the raw label process data is used to train the decision tree model, after that the process data is labeled. Second, the root mean square error of the labeled sample is calculated to select the optimal labeled and process data. Third, the DXN emission prediction model is constructed by cross-combination of the raw labels and labeled process data. Simulation results of the benchmark dataset and practical DXN data verify the effectiveness of the proposed method.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133768205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619263
Meng-Qi Wang, Xiaoheng Chang
This paper investigates the $H_{infty}$ control problem for a class of discrete-time systems with state quantization. Firstly, a state feedback controller is taken into the discrete-time systems in this paper. Then, the quantizer considered here is dynamic quantizer, which can be considered to be composed of a dynamic scaling and a static quantizer. The closed loop control system is asymptotically stable and satisfies the $Hinfty$ performance index. Furthermore, the closed loop control system can achieve the same the $Hinfty$ performance under the dynamic quantizer is taken into consideration. In addition, this paper uses the strategy to design the dynamic parameter of the quantizer which is dependent on some auxiliary scalars. The effectiveness of the controller with the state quantization design method is demonstrated by a simulation example.
{"title":"H∞ Control for Discrete-Time System With State Quantization","authors":"Meng-Qi Wang, Xiaoheng Chang","doi":"10.1109/IAI53119.2021.9619263","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619263","url":null,"abstract":"This paper investigates the $H_{infty}$ control problem for a class of discrete-time systems with state quantization. Firstly, a state feedback controller is taken into the discrete-time systems in this paper. Then, the quantizer considered here is dynamic quantizer, which can be considered to be composed of a dynamic scaling and a static quantizer. The closed loop control system is asymptotically stable and satisfies the $Hinfty$ performance index. Furthermore, the closed loop control system can achieve the same the $Hinfty$ performance under the dynamic quantizer is taken into consideration. In addition, this paper uses the strategy to design the dynamic parameter of the quantizer which is dependent on some auxiliary scalars. The effectiveness of the controller with the state quantization design method is demonstrated by a simulation example.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123548578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619194
Qiang Huang, Changchun Pan, Haichun Liu
Conveyor belts are some key equipments for transmission in the process industry. Belt wear is inevitable in the process of conveying. In order to evaluate the state of the belt, the inspection workers regularly check the belt. However, it can’t be tested comprehensively. Also, a lot of labor costs occur. In this paper, we propose a multi-sensor fusion method for the detection of conveyor belt surface damage, and builds a data acquisition system combining camera and lidar to obtain image data and point cloud data on the conveyor belt surface. On the basis of using traditional machine vision algorithms to detect surface damages, combined with the depth information obtained from the lidar points cloud, the fusion detection of the damage detection of two kinds of sensors is realized. Experiments show that the use of multi-sensor detection can effectively reduce misdetection caused by vision and improve the reliability of detection.
{"title":"A Multi-sensor Fusion Algorithm for Monitoring the Health Condition of Conveyor Belt in Process Industry","authors":"Qiang Huang, Changchun Pan, Haichun Liu","doi":"10.1109/IAI53119.2021.9619194","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619194","url":null,"abstract":"Conveyor belts are some key equipments for transmission in the process industry. Belt wear is inevitable in the process of conveying. In order to evaluate the state of the belt, the inspection workers regularly check the belt. However, it can’t be tested comprehensively. Also, a lot of labor costs occur. In this paper, we propose a multi-sensor fusion method for the detection of conveyor belt surface damage, and builds a data acquisition system combining camera and lidar to obtain image data and point cloud data on the conveyor belt surface. On the basis of using traditional machine vision algorithms to detect surface damages, combined with the depth information obtained from the lidar points cloud, the fusion detection of the damage detection of two kinds of sensors is realized. Experiments show that the use of multi-sensor detection can effectively reduce misdetection caused by vision and improve the reliability of detection.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"1204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124483205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619314
Wei Liu, Xinfu Pang, Zongfu Hou, Shenping Yu, Haibo Li
In steel-making and continuous casting production processes, the starting time delay happens frequently, which may lead to casting break or processing conflict so that the static scheduling plan becomes unrealizable. The ladle rescheduling of steel-making and continuous casting production aims at continuously casting many charges with the same cast and avoiding conflicts of adjacent charges on the same machine. It decides the selected processing machines, the starting time and the completion time for not started charges at the steel-making stage and the refining stage. The completion time also should be decided for being processed charges. Then, based on the production equipment scheduling plan of the heat, the requirements of the processing equipment (converter, refining furnace and continuous casting machine) of the heat are met. Under the conditions of the start and end time of the equipment, a ladle carrying molten steel is selected, and determine the route of transporting the ladle. Since ladle scheduling must meet multiple conflicting goals and conflicting constraints, it is difficult to adopt existing optimal scheduling methods. This paper proposes a method of ladle scheduling in the production process of steelmaking-refining-continuous casting. First, scheduling optimization model of the steel-making and continuous casting production is built, which aims at minimizing the waiting time of all charges. The scheduling strategy of steel-making and continuous casting production is proposed by interval processing time of charges and scheduling expert experience. Then, the first-order rule learning is used to select the optimization target to establish the ladle optimal scheduling model. the ladle matching rules are extracted by the rule reasoning of the minimum general generalization; the ladle optimization scheduling method consisting of the optimal selection of the ladle and the preparation of the optimal path of the ladle is proposed. Ladle selection is based on the production process and adopts rule-based reasoning to select decarburized ladle, or select decarburized ladle after selecting dephosphorized ladle. Ladle path preparation, a multi-priority heuristic method is designed to decide the path of the ladle from the converter to the refining furnace to the continuous casting machine. Finally, based on a large-scale steel company in Shanghai, China, the method was actually verified, and the results showed that the production efficiency of steelmaking-refining-continuous casting was improved.
{"title":"Research on a Method of Ladle Scheduling Based on Rule Learning*","authors":"Wei Liu, Xinfu Pang, Zongfu Hou, Shenping Yu, Haibo Li","doi":"10.1109/IAI53119.2021.9619314","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619314","url":null,"abstract":"In steel-making and continuous casting production processes, the starting time delay happens frequently, which may lead to casting break or processing conflict so that the static scheduling plan becomes unrealizable. The ladle rescheduling of steel-making and continuous casting production aims at continuously casting many charges with the same cast and avoiding conflicts of adjacent charges on the same machine. It decides the selected processing machines, the starting time and the completion time for not started charges at the steel-making stage and the refining stage. The completion time also should be decided for being processed charges. Then, based on the production equipment scheduling plan of the heat, the requirements of the processing equipment (converter, refining furnace and continuous casting machine) of the heat are met. Under the conditions of the start and end time of the equipment, a ladle carrying molten steel is selected, and determine the route of transporting the ladle. Since ladle scheduling must meet multiple conflicting goals and conflicting constraints, it is difficult to adopt existing optimal scheduling methods. This paper proposes a method of ladle scheduling in the production process of steelmaking-refining-continuous casting. First, scheduling optimization model of the steel-making and continuous casting production is built, which aims at minimizing the waiting time of all charges. The scheduling strategy of steel-making and continuous casting production is proposed by interval processing time of charges and scheduling expert experience. Then, the first-order rule learning is used to select the optimization target to establish the ladle optimal scheduling model. the ladle matching rules are extracted by the rule reasoning of the minimum general generalization; the ladle optimization scheduling method consisting of the optimal selection of the ladle and the preparation of the optimal path of the ladle is proposed. Ladle selection is based on the production process and adopts rule-based reasoning to select decarburized ladle, or select decarburized ladle after selecting dephosphorized ladle. Ladle path preparation, a multi-priority heuristic method is designed to decide the path of the ladle from the converter to the refining furnace to the continuous casting machine. Finally, based on a large-scale steel company in Shanghai, China, the method was actually verified, and the results showed that the production efficiency of steelmaking-refining-continuous casting was improved.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130764984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：