Predictive Maintenance and Fault Detection for Motor Drive Control Systems in Industrial Robots Using CNN-RNN-Based...

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Machine Learning

Background:

• Industrial robots rely on DC motor drives for precise operation.
• Predictive maintenance is crucial for minimizing operational breakdowns and ensuring system longevity.
• Existing fault detection methods often lack the accuracy and speed required for real-time applications.

Purpose of the Study:

• To develop and evaluate a novel hybrid deep learning framework for enhanced fault detection and predictive maintenance in DC motor drives.
• To improve the accuracy and efficiency of fault prediction in industrial robot motor systems.
• To establish a robust AI model capable of determining optimal maintenance strategies.

Main Methods:

• Integration of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) into a hybrid CNN-RNN model.
• Utilizing sensor data (e.g., temperature, rotational speed) for training and validation.
• Comparative analysis against CNN-LSTM, individual CNNs, LSTMs, and traditional methods.

Main Results:

• The proposed CNN-RNN model demonstrated superior accuracy in fault prediction and detection compared to existing methods.
• The CNN-RNN framework achieved higher precision in fault diagnosis.
• The model exhibited a simpler architecture and lower complexity, leading to faster processing speeds than CNN-LSTM.

Conclusions:

• The hybrid CNN-RNN model offers a practical and efficient solution for real-time fault detection in industrial robot motor drives.
• This AI-driven approach enhances predictive maintenance, reducing operational downtime.
• The model's ability to extract dynamic features and process sequential data ensures reliable performance.