|
|
|
| Diffusion oxygen supply PID control method based on cuckoo search-back propagation neural network |
| XU Xiaohui1, HAO Chunhao2, XU Chenghu2, ZHANG Maojie2, LI Weibo2 |
1. Wuhan Institute of Ship Electric Propulsion, Wuhan 430070;
2. School of Automation, Wuhan University of Technology, Wuhan 430070 |
|
|
|
|
Abstract Diffusion oxygen supply controller, as the core component of the diffusion oxygen supply control system, plays a significant role in refreshing gases, eliminating smoke and ash, and controlling active oxygen. Currently, most diffusion oxygen supply controllers rely on the upper and lower limits of oxygen concentration to adopt start stop control. Although they have the advantages of simple control, they have shortcomings such as low oxygen utilization rate and poor control accuracy. This paper establishes a mathematical model for the diffusion oxygen supply controller, and uses the cuckoo search (CS) algorithm to optimize the initial weights of the back propagation (BP) neural network adaptive control strategy. The analysis and simulation results show that compared with traditional proportional integral differential (PID) control methods, the adaptive PID control algorithm based on CS-BP neural network not only has good robustness and speed, but also can achieve higher oxygen concentration control accuracy. When there is strong external interference invasion, using the CS-BP neural network adaptive algorithm can automatically learn and train online and adjust control parameters, which has a broader application prospect.
|
|
Received: 29 May 2023
|
|
|
|
| Cite this article: |
|
XU Xiaohui,HAO Chunhao,XU Chenghu等. Diffusion oxygen supply PID control method based on cuckoo search-back propagation neural network[J]. Electrical Engineering, 2023, 24(8): 12-21.
|
|
|
|
| URL: |
|
http://dqjs.cesmedia.cn/EN/Y2023/V24/I8/12
|
[1] 赖焕宁. 一种室内弥散供氧控制系统: CN213581860U[P].2021-06-29.
[2] 刘柱, 卢剑锋, 王一达, 等. 微压富氧舱系统建模及控制算法研究[J]. 机械设计与制造, 2020(12): 167-170, 175.
[3] 李航, 杜璠, 胡晓兵, 等. 改进的BP神经网络PID控制器在气体浓度控制中的研究[J]. 四川大学学报(自然科学版), 2020, 57(6): 1103-1109.
[4] 裴承芝. 单人医疗高压氧舱自动控制系统研究与实现[D]. 武汉: 武汉理工大学, 2017.
[5] 范俞超, 孙青林, 董方酉, 等. 基于粒子群算法-反向传播神经网络自适应的氧调器控制系统[J]. 控制理论与应用, 2020, 37(3): 687-695.
[6] 约翰D. 安德森. 计算流体力学基础及应用[M]. 倪文锦, 刘赵森, 译. 北京: 高等教育出版社, 2022.
[7] 蒋朝明. 基于模糊PID的救生舱氧气自动控制系统的研究与设计[D]. 徐州: 中国矿业大学, 2014.
[8] 李勇, 孟芳兵, 吴琪, 等. 西藏高原制供氧发展现状存在问题及未来发展思考[J]. 低温与特气, 2022, 40(1): 1-5.
[9] 建筑外门窗气密、水密、抗风压性能检测方法: GB/T 7106—2019[S]. 北京: 中国标准出版社, 2019.
[10] 单红卫. 氧供给与氧消耗关系的研究及在危重病人救治中的意义[J]. 中国急救医学, 1995(1): 54-57, 22.
[11] 吴一全, 周建伟. 布谷鸟搜索算法研究及其应用进展[J]. 智能系统学报, 2020, 15(3): 435-444.
[12] 李娟. 基于学习的布谷鸟搜索算法研究[D]. 武汉: 武汉大学, 2019.
[13] 李刚. 基于改进多目标布谷鸟算法的潜艇消磁电流优化研究[D]. 武汉: 武汉理工大学, 2021.
[14] 娄宝磊. 灰色动态BP神经网络在光伏短期出力预测中的应用[J]. 电气技术, 2015, 16(12): 47-51.
[15] 徐扬, 张紫涛. 基于遗传模拟退火算法改进BP神经网络的中长期电力负荷预测[J]. 电气技术, 2021, 22(9): 70-76.
[16] 程苗苗, 翟朋辉, 张英杰, 等. 基于自学习非线性PID的音圈电机精密定位系统[J]. 电工技术学报, 2023, 38(6): 1519-1530.
[17] 兰洲. 基于分散控制系统的半水法湿法磷酸生产PID控制[J]. 电气技术, 2021, 22(5): 97-101.
[18] 陈亚, 李萍. 基于神经网络的短期电力负荷预测仿真研究[J]. 电气技术, 2017, 18(1): 26-29.
[19] 孙祥晟, 陈芳芳, 贾鉴, 等. 基于经验模态分解的神经网络光伏发电预测方法研究[J]. 电气技术, 2019, 20(8): 54-58.
[20] 康义, 师刘俊, 郭刚. 基于WT-IPSO-BPNN的电力系统短期负荷预测[J]. 电气技术, 2021, 22(1): 23-28, 62.
[21] 肖锋. BP神经网络在步进电机细分控制的应用[J]. 电气技术, 2015, 16(10): 120-122. |
|
|
|
2023, Vol. 24 
