Manipulator robots hold significant importance for the development of intelligent manufacturing and industrial transformation. Manufacturers and users are increasingly focusing on fault diagnosis for manipulator robots. The voltage, current, speed, torque, and vibration signals of manipulator robots are often used to explore the fault characteristics from a frequency perspective, and temperature and sound are also used to represent the fault information of manipulator robots from different perspectives. Technically, manipulator robot fault diagnosis involving human intervention is gradually being replaced by new technologies, such as expert experience, artificial intelligence, and digital twin methods. Previous reviews have tended to focus on a single type of fault, such as analysis of reducers or joint bearings, which has led to a lack of comprehensive summary of various methods for manipulator robot fault diagnosis. Considering the needs of future research, a review of different fault types and diagnostic methods of manipulator robots provides readers with a clearer reading experience and reveals potential challenges and opportunities. Such a review helps new researchers entering the field avoid duplicating past work and provides a comprehensive overview, guiding and encouraging readers to commit to enhancing the effectiveness and practicality of manipulator robot fault diagnosis technologies.
Predominant fault diagnosis in industrial robots depends on dedicated vibration or acoustics sensors. However, their practical deployment is often limited by installation constraints, susceptibility to environmental noise, and cost considerations. Applying Energy-Based Maintenance (EBM) principles to achieve enhanced fault diagnosis under practical industrial conditions, we propose a hybrid deep learning framework, the Multi-head Graph Attention Network (MGAT) with Multi-scale CNNBiLSTM Fusion (MGAT-MCNNBiLSTM) for industrial robots. This approach obviates the need for additional dedicated sensors, effectively mitigating associated deployment complexities. The framework embodies four core innovations: (1) Based on the EBM paradigm, motor current is established as the most effective and practical choice for enabling cost-efficient and scalable industrial robot fault diagnosis. A corresponding dataset of motor current has been acquired from industrial robots operating under diverse fault scenarios. (2) An integrated MGAT-MCNNBiLSTM architecture that synergistically models multiscale local features and complex dynamics through its MCNNBiLSTM module while capturing nonlinear interdependencies via MGAT. This comprehensive feature representation enables robust and highly accurate fault detection. (3) The study found that the application of spectral preprocessing techniques yields a marked and statistically significant enhancement in diagnostic performance. A comprehensive and systematic analysis was undertaken to uncover the underlying reasons for this observed performance improvement. (4) To emulate challenging industrial settings and cost-sensitive implementations, noise signal injection was employed to evaluate model robustness in high-electromagnetic-interference environments and low-cost, low-resolution ADC implementations. Experimental validation on real-world industrial robot datasets demonstrates that MGAT-MCNNBiLSTM achieves a superior diagnostic accuracy of 90.7560%. This performance marks a significant absolute improvement of 1.51–8.55% over competing models, including LCNNBiLSTM, SCNNBiLSTM, MCCBiLSTM, GAT, and MGAT. Under challenging noise and low-resolution conditions, the proposed model consistently outperforms CNNBiLSTM variants, GAT, and MGAT with an improvement of 1.37–10.26% and enhanced industrial utility and deployment potential.
Power metal-oxide-semiconductor field-effect transistors (MOSFETs) provide numerous advantages and are widely utilized in various power circuits. The junction temperature plays a critical role in determining the reliability, performance, and operational lifetime of power MOSFETs. Therefore, accurate monitoring of the junction temperature of power MOSFETs is essential to ensure the safe operation of power circuit systems. In bridge or motor drive circuits, MOSFETs often operate in a freewheeling state via the body diode, where the freewheeling current is typically variable. The proposed method for junction temperature measurement utilizes the body diode and is designed to accommodate varying forward currents. It also accounts for the temperature-dependent ideality factor to improve measurement accuracy. By integrating the forward voltage and forward current of the body diode, this approach reduces the required sampling frequency. To validate the method’s effectiveness, three representative types of power MOSFETs, a Si MOSFET (IRF520), a SiC MOSFET (C2M0080120D), and an aerospace-grade radiation-hardened MOSFET (RSCS25045T1RH), were used to measure junction temperatures before and after irradiation. Following ideality factor correction, the maximum absolute error compared to reference measurements from thermocouples and a thermal imager remained within 2 K across the temperature range of 300 K to 420 K. Experimental results confirm the feasibility of the proposed method.
To overcome the problem of insufficient adaptability to the motion environment of lower limb exoskeleton robots, this paper introduces computer vision technology into the motion control of lower limb exoskeleton robots and studies an obstacle-crossing-motion method based on detecting obstacle feature information. Considering the feature information of different obstacles and the distance between obstacles and robots, a trajectory planning method based on direct point matching was used to generate offline adjusted gait trajectory libraries and obstacle-crossing gait trajectory libraries. A lower limb exoskeleton robot obstacle-crossing motion decision-making algorithm based on obstacle feature information is proposed by combining gait constraints and motion constraints, enabling it to select appropriate motion trajectories in the trajectory library. The proposed obstacle-crossing-motion method was validated at three distances between the obstacle and the robot and with the feature information of four obstacles. The experimental results show that the proposed method can select appropriate trajectories from the trajectory library based on the detected obstacle feature information and can safely complete obstacle-crossing motions.
Bearing fault diagnosis is vital for maintaining the reliability and security of industrial machinery. Although deep learning approaches are widely utilized, the scarcity of labeled fault data significantly hinders the effective training of large-parameter fault diagnosis models rooted in deep neural networks. Moreover, such models often exhibit a lack of interpretability. To tackle these challenges, this study proposes a novel hybrid-domain fault diagnosis framework for bearings, synergistically enhanced by adaptive feature optimization and Ensemble Learning (EL). The core methodology involves three principal innovations: (1) the extraction and fusion of condition-indicative features from different domains to construct a comprehensive representation, overcoming the insufficiency of single-domain analysis; (2) the development of an adaptive feature optimization mechanism that automatically selects the most discriminative features from the hybrid domain, enhancing diagnostic relevance and reducing dimensionality while providing physical insights into the diagnostic process; (3) the formulation of a robust diagnostic model that integrates the optimized hybrid-domain features with an ensemble learning strategy to significantly boost diagnostic accuracy and stability. Comparative experiments were conducted, comparing models utilizing single-domain features, simple hybrid-domain fusion, hybrid-domain with adaptive optimization, and the proposed framework. Experimental evidence indicates that the proposed hybrid-domain model possesses superior fault diagnosis performance, validating that the adaptive optimization within the hybrid domain effectively retains critical information while EL ensures reliable generalization. This work presents a data-efficient, interpretable, and high-performance methodology for intelligent bearing health management.