使用卷积神经网络从原始振动信号中检测螺旋变速箱缺陷
Iulian Lupea1, Mihaiela Lupea2
1Faculty of Industrial Engineering, Robotics and Production Management, Technical University of Cluj-Napoca, 400641 Cluj-Napoca, Romania.
Sensors (Basel, Switzerland)
|November 14, 2023
概括
这项研究开发了卷积神经网络 (CNN) 模型,用于使用振动信号检测变速箱缺陷. 一个2D-CNN模型实现了99.63%的准确性,证明了有效的轮故障识别.
科学领域:
- 机械工程 机械工程
- 机器学习 机器学习
- 振动分析 振动分析
背景情况:
- 变速箱缺陷会影响机器的可靠性和性能.
- 早期检测轮故障对于防止灾难性故障至关重要.
- 振动分析是一种常见的状态监测技术.
研究的目的:
- 开发和评估卷积神经网络 (CNN) 模型用于变速箱缺陷检测.
- 评估使用原始振动信号的1D-CNN和2D-CNN架构的有效性.
- 为了确定缺陷分类的最佳传感器轴.
主要方法:
- 来自三轴加速度计的原始振动信号被分析.
- 1D-CNN和2D-CNN模型用于特征提取和分类.
- 模型被训练并测试了各种旋转速度和负载级别的数据.
主要成果:
- 最好的1D-CNN模型 (Y轴数据) 实现了98.91%的测试准确度.
- 来自X和Z轴的数据准确度略低 (97.15%和97%).
- 使用所有三个轴的2D-CNN模型达到99.63%的高精度.
结论:
- 基于CNN的模型在变速箱缺陷检测方面非常有效.
- 在2D-CNN架构中的多轴数据融合提高了检测准确性.
- 振动分析与深度学习相结合,为变速箱状态监测提供了强大的解决方案.
相关概念视频
Transmission Shafts: Problem Solving
241
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...
241
Angle of Twist: Problem Solving
283
An electric motor applies a torque of 700 N·m to an aluminum shaft, triggering a stable rotation. Two pulleys, B and C, are subjected to torques of 300 N·m and 400 N·m, respectively. The modulus of rigidity is provided as 25 GPa. With the knowledge of the length and diameter of each segment, the twist angle between the two pulleys can be computed. First, a section cut is made between pulleys B and C, and the cut cross-section is analyzed using a free-body diagram. Given that the...
283
Transformers with Off-Nominal Turns Ratios
162
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
162
Bearings: Problem Solving
287
Understanding the calculations and concepts related to double-collar bearings is essential for engineers and designers to optimize the performance of these components in various applications. By analyzing the bearing under different conditions, one can ensure that it can withstand the forces and moments experienced during operation. This knowledge enables better decision-making when designing and selecting bearings for specific purposes and configurations. Consider a double-collar bearing with...
287
Three-Winding Transformers
237
Three identical single-phase transformers can be configured to form a three-phase transformer connection, which involves high-voltage and low-voltage windings. The high-voltage windings are denoted by capital letters A-B-C, while the low-voltage windings are labeled with lowercase letters a-b-c, representing their respective phases. This notation helps distinguish between the high and low voltage sides of the transformer.
In the per-unit equivalent circuit of a grounded Y-Y three-phase...
In the per-unit equivalent circuit of a grounded Y-Y three-phase...
237
Simplified Synchronous Machine Model
243
The Synchronous Machine Model is a fundamental tool in analyzing and ensuring the transient stability of power systems. This model simplifies the representation of a synchronous machine under balanced three-phase positive-sequence conditions, assuming constant excitation and ignoring losses and saturation. The model is pivotal for understanding the behavior of synchronous generators connected to a power grid, particularly during transient events.
In this model, each generator is connected to a...
In this model, each generator is connected to a...
243


