一个知识指南数据驱动模型,具有选择波形核融合神经网络,用于变速箱智能故障诊断
Nan Zhuang1, Zhaogang Ren1, Dongyao Yang2
1Department of Environmental Science and Engineering, China West Normal University, Nanchong 637000, China.
Sensors (Basel, Switzerland)
|December 31, 2025
概括
这项研究引入了一种新的以知识为导向的神经网络,用于变速箱故障诊断. 该方法通过将领域知识整合到深度学习模型中,提高了机器诊断的可解释性和准确性.
科学领域:
- 机械工程 机械工程
- 人工智能的人工智能
背景情况:
- 变速箱的操作可靠性对于工业系统至关重要.
- 使用加速度计和数据驱动方法的振动分析是故障诊断的常见方法.
- 深度学习方法提供高精度,但缺乏可解释性.
研究的目的:
- 开发用于变速箱的可解释和准确的智能故障诊断系统.
- 解决现有的深度学习方法的"黑子"限制.
主要方法:
- 提出了一个以知识为导向的选择性波纹核融合神经网络.
- 使用多核卷积模块将诊断领域的知识集成到现代时空卷积网络 (TCN) 中.
- 采用基于注意力的选择性波纹内核融合策略,用于自适应性内核合并.
主要成果:
- 与传统的深度学习模型相比,拟议的方法显示了增强的解释性.
- 在公共数据集上的实验验证显示了诊断准确度的提高.
- 成功克服了智能故障诊断中的"黑子"限制.
结论:
- 以知识为导向的方法有效地提高了解释性和诊断性能.
- 选择性波纹核融合策略提高了自适应性学习能力.
- 这种方法为开发更加透明和可靠的智能诊断系统提供了一个有希望的方向.
相关概念视频
01:09Transmission Shafts: Problem Solving
466
Designing a solid shaft that transmits power from a motor to a machine tool involves a series of calculations to ensure the shaft can withstand the stresses applied by bending moments and torques. First, calculate the torque exerted on the gear, considering the power transmitted by the shaft and its rotational speed. Following this, compute the tangential forces acting on the gears, which directly relate to the torque and the gear radius.
Next, use bending moment diagrams for the shaft to...
Next, use bending moment diagrams for the shaft to...
466
01:16Design of Transmission Shafts
712
The design of a transmission shaft is governed by two primary specifications: the power it transmits and its rotational speed. These parameters guide the selection of the shaft's material and cross-sectional dimensions, ensuring that the material's maximum shearing stress remains within the elastic limit while transmitting the desired power at the given speed. The system's power is intrinsically linked to the applied torque. The torque applied to the shaft can be calculated by reconfiguring the...
712