Cyclic spectral correlation above the bifrequency plane for the received signal was calculated by the strip spectral correlation algorithm （SSCA）and then was normalized. The result was expressed by matrix. The sum o...Cyclic spectral correlation above the bifrequency plane for the received signal was calculated by the strip spectral correlation algorithm （SSCA）and then was normalized. The result was expressed by matrix. The sum of error-square was computed between corresponding elements for the theoretical sampling matrix of all kinds of modulated signals and calculated matrix. The modulation type was recognized by exploiting the minimum value of the sum of error-square. No extracted characteristic parameter and prior information are needed for identifying the modulation type compared to the conventional methods. In addition, the new method extends the recognition scope and has high recognition probability at low SNR. The simulation results obtained by means of Monter-Carlo method proved the presented algorithm.展开更多
Confirmation of basic technological parameters of tension levellers is the most important factor of leveling strip. Up to now, most factories have used experts’ experience to decide these parameters, without any esta...Confirmation of basic technological parameters of tension levellers is the most important factor of leveling strip. Up to now, most factories have used experts’ experience to decide these parameters, without any established rule to follow. For better quality of strip, a valid method is needed to decide technological parameters precisely and reasonably. In this paper, a method is used based on neural network and genetic algorithm. Neural network has a good ability to extract rules from work process of tension levellers. Then using neural network, which has learned from a lot of working samples, to be the evaluation of fitness, genetic algorithm could easily find the best or better technological parameters. At the end of this paper, examinations are given to show the effect of this method.展开更多
In order to make good use of the ability to approach any function of BP (backpropagation) network and overcome its local astringency, and also make good use of the overallsearch ability of GA (genetic algorithms), a p...In order to make good use of the ability to approach any function of BP (backpropagation) network and overcome its local astringency, and also make good use of the overallsearch ability of GA (genetic algorithms), a proposal to regulate the network's weights using bothGA and BP algorithms is suggested. An integrated network system of MGA (mended genetic algorithms)and BP algorithms has been established. The MGA-BP network's functions consist of optimizing GAperformance parameters, the network's structural parameters, performance parameters, and regulatingthe network's weights using both GA and BP algorithms. Rolling forces of 4-stand tandem cold stripmill are predicted by the MGA-BP network, and good results are obtained.展开更多
Mechanical property prediction of hot rolled strip is one of the hotspots in material processing research. To avoid the local infinitesimal defect and slow constringency in pure BP algorithm, a kind of global optimiza...Mechanical property prediction of hot rolled strip is one of the hotspots in material processing research. To avoid the local infinitesimal defect and slow constringency in pure BP algorithm, a kind of global optimization algorithm-particle swarm optimization （PSO） is adopted. The algorithm is combined with the BP rapid training algorithm, and then, a kind of new neural network （NN） called PSO-BP NN is established. With the advantages of global optimization ability and the rapid constringency of the BP rapid training algorithm, the new algorithm fully shows the ability of nonlinear approach of multilayer feedforward network, improves the performance of NN, and provides a favorable basis for further online application of a comprehensive model.展开更多
文摘Cyclic spectral correlation above the bifrequency plane for the received signal was calculated by the strip spectral correlation algorithm （SSCA）and then was normalized. The result was expressed by matrix. The sum of error-square was computed between corresponding elements for the theoretical sampling matrix of all kinds of modulated signals and calculated matrix. The modulation type was recognized by exploiting the minimum value of the sum of error-square. No extracted characteristic parameter and prior information are needed for identifying the modulation type compared to the conventional methods. In addition, the new method extends the recognition scope and has high recognition probability at low SNR. The simulation results obtained by means of Monter-Carlo method proved the presented algorithm.
文摘Confirmation of basic technological parameters of tension levellers is the most important factor of leveling strip. Up to now, most factories have used experts’ experience to decide these parameters, without any established rule to follow. For better quality of strip, a valid method is needed to decide technological parameters precisely and reasonably. In this paper, a method is used based on neural network and genetic algorithm. Neural network has a good ability to extract rules from work process of tension levellers. Then using neural network, which has learned from a lot of working samples, to be the evaluation of fitness, genetic algorithm could easily find the best or better technological parameters. At the end of this paper, examinations are given to show the effect of this method.
文摘In order to make good use of the ability to approach any function of BP (backpropagation) network and overcome its local astringency, and also make good use of the overallsearch ability of GA (genetic algorithms), a proposal to regulate the network's weights using bothGA and BP algorithms is suggested. An integrated network system of MGA (mended genetic algorithms)and BP algorithms has been established. The MGA-BP network's functions consist of optimizing GAperformance parameters, the network's structural parameters, performance parameters, and regulatingthe network's weights using both GA and BP algorithms. Rolling forces of 4-stand tandem cold stripmill are predicted by the MGA-BP network, and good results are obtained.
基金Natural Science Foundation of Anhui Provincial Education Depart ment of China (2006KJ080A)
文摘Mechanical property prediction of hot rolled strip is one of the hotspots in material processing research. To avoid the local infinitesimal defect and slow constringency in pure BP algorithm, a kind of global optimization algorithm-particle swarm optimization （PSO） is adopted. The algorithm is combined with the BP rapid training algorithm, and then, a kind of new neural network （NN） called PSO-BP NN is established. With the advantages of global optimization ability and the rapid constringency of the BP rapid training algorithm, the new algorithm fully shows the ability of nonlinear approach of multilayer feedforward network, improves the performance of NN, and provides a favorable basis for further online application of a comprehensive model.
文摘随着电子信息技术的快速发展,极薄带综合性能面临更高要求,尤其是不锈钢极薄带的表面形貌控制成为关键技术难点。针对这一问题,基于12辊精密极薄带轧机,采用磨削、喷砂和抛光3种典型表面处理的轧辊,对厚度为0.08 mm的304不锈钢极薄带开展单道次轧制试验,构建了适用于极薄带的表面粗糙度转印机理模型(roughness transfer mechanism model,RTM)。通过遗传算法对机理模型中的关键参数进行优化,系统揭示了压下率、张力、轧辊粗糙度以及原始带材粗糙度对轧制过程中表面粗糙度的影响规律。进一步将机理模型与机器学习方法深度融合,提出轧制转印机理约束的表面粗糙度预测模型,通过提取机理模型预测值与实际值的偏差作为机器学习输入,利用其非线性拟合能力捕捉传统机理模型未能解释的复杂非线性特征,最终通过偏差修正实现表面粗糙度的精准预测。试验结果表明,该融合模型充分发挥了2类模型优势,以算数平均粗糙度Ra为例,最优模型的预测准确率达到95.08%,相关系数达到0.9347,并最终在工业现场采集数据进行验证,预测精度依旧可以保持在90%以上。该模型兼具机器学习的高效预测性能与轧制转印机理的物理可解释性,为极薄带表面质量控制提供了新的方向,对深入探究表面粗糙度形成机理与极薄带的工艺参数优化具有重要工程意义。
