|
| 基于层次分析与BP神经网络的电梯安全评价模型 |
| Elevator Safety Evaluation Model Based on Analytic Hierarchy Process and BP Neural Network |
| |
| DOI：10.16018/j.cnki.cn32-1650/n.202302004 |
| 中文关键词: 层次分析法 BP神经网络 改进粒子群算法 电梯安全评价 |
| 英文关键词: analytic hierarchy process BP neural network improved particle swarm optimization elevator safety evaluation |
| 基金项目: |
|
| 摘要点击次数: 35 |
| 全文下载次数: 42 |
| 中文摘要: |
| 为高效评价在用电梯运行状态的安全性，提出基于层次分析法和BP神经网络的电梯安全评价模型。通过层次分析法建立电梯系统安全评价指标体系，采用BP神经网络构建电梯系统安全评价模型；通过改进粒子群算法和改进BP算法分别优化、训练BP神经网络；最后进行仿真验证。仿真结果表明，经过改进粒子群算法优化的BP神经网络模型训练速度最快，训练时间比BP算法快8. 45 s，比粒子群算法快5. 17 s；评价准确度最高，达92. 3%，分别比BP算法和粒子群算法提到了11. 7%、6. 8%；而训练误差最小，仅为0. 020 6。 |
| 英文摘要: |
| In order to efficiently evaluate the safety of the operating state of the elevator in use, an elevator safety evaluation model based on analytic hierarchy process and BP neural network is proposed. The safety evaluation index system of elevator system was established by analytic hierarchy process, the BP neural network was used to construct the elevator system safety evaluation model, and the BP neural network was optimized and trained by improving the particle swarm algorithm and the improved BP algorithm. Finally, the simulation is verified. The simulation results show that the BP neural network model optimized by improved particle swarm optimization has the fastest training speed, the training time is 8. 45 s faster than BP algorithm and 5. 17 s faster than PSO algorithm, it is 92. 3% , 11. 7% and 6. 8% higher than BP algorithm and PSO algorithm respectively, and the training error is the smallest, only 0. 020 6. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |