# Condition-Adaptive CNN with Spatiotemporal Fusion for Enhanced Motor Fault Diagnosis

## TL;DR

This paper introduces a new CNN-based framework for diagnosing motor faults in industrial settings, using adaptive optimization and spatiotemporal fusion to improve accuracy and robustness.

## Contribution

The novel integration of the bee colony algorithm with CNNs and a spatiotemporal fusion architecture for motor fault diagnosis.

## Key findings

- The proposed CNN-BCA-ISA framework achieved 96.4% diagnostic accuracy on mixed datasets.
- The model demonstrated stable performance under varying noise levels and operating conditions.
- A real-time fault diagnosis system was successfully implemented in industrial environments.

## Abstract

Electric motors are widely used in industrial production systems, and various fault modes may occur during long-term operation under complex and noisy conditions. Accurate fault diagnosis remains challenging, especially when signal characteristics vary depending on the operating state. To address this issue, this paper presents a fault diagnosis framework based on a convolutional neural network (CNN), which features adaptive parameter optimization and enhanced feature representation. This method integrates the bee colony algorithm (BCA) into CNN training, adaptively adjusts the model parameters based on signal conditions, and shortens the convergence time compared to traditional gradient-based optimization. In order to improve the extraction of high-frequency and transient fault features, a spatiotemporal fusion architecture is designed, which combines large-kernel convolution, a bottleneck layer, and an improved self-attention (ISA) mechanism. In addition, an engineering-oriented data augmentation strategy based on multi-scale window offset and noise superposition has been applied to one-dimensional vibration signals to improve the robustness of the model. The proposed CNN-BCA-ISA framework is evaluated using a mixed dataset consisting of on-site data collected from a steel plant and a public dataset from Case Western Reserve University (CWRU). The experimental results show that the diagnostic accuracy is 96.4%, and the performance is stable under different noise levels, indicating good generalization abilities under various operating conditions. In addition, a real-time fault diagnosis system based on the proposed framework has been implemented and validated in industrial environments, confirming its feasibility in practical state monitoring applications.