Showing papers by "Yaguo Lei published in 2023"

Remaining Useful Life Prediction With Partial Sensor Malfunctions Using Deep Adversarial Networks

Abstract: In recent years, intelligent data-driven prognostic methods have been successfully developed, and good machinery health assessment performance has been achieved through explorations of data from multiple sensors. However, existing data-fusion prognostic approaches generally rely on the data availability of all sensors, and are vulnerable to potential sensor malfunctions, which are likely to occur in real industries especially for machines in harsh operating environments. In this paper, a deep learning-based remaining useful life (RUL) prediction method is proposed to address the sensor malfunction problem. A global feature extraction scheme is adopted to fully exploit information of different sensors. Adversarial learning is further introduced to extract generalized sensor-invariant features. Through explorations of both global and shared features, promising and robust RUL prediction performance can be achieved by the proposed method in the testing scenarios with sensor malfunctions. The experimental results suggest the proposed approach is well suited for real industrial applications.

A review for control theory and condition monitoring on construction robots

Abstract: The application of robotic technologies in building construction leads to great convenience and productivity improvement, and construction robots (CRs) bring enormous opportunities for the way we conduct design and construction. To get a better understanding of the trends and track the application of CRs for on‐site conditions, this paper conducts a systematic review of control models and status monitoring of CRs, which are two key aspects that determine construction accuracy and efficiency. Control accuracy and flexibility are primary needs for CRs applied in different scenes, so the control methods based on driving models are vitally important. Status monitoring on CRs contains knowledge in fault detection, intelligence maintenance, and fault‐tolerant control, and multiple objectives need to be met and optimized in the whole drive chain. Moreover, the state‐of‐the‐art is comprehensively summarized, and new insights are also provided to carry on promising researches.

Intelligent Machinery Fault Diagnosis With Event-Based Camera

Abstract: Event-based cameras are the emerging bio-inspired technology in vision sensing. Different from the traditional standard cameras, the event-based cameras asynchronously record the brightness change per pixel, and have the great merits of high temporal resolution, low energy consumption, high dynamic range, etc . While the event-based cameras have been initially exploited in several common vision-based tasks in the recent years, the investigation on machine condition monitoring problem is quite limited. This paper offers the first attempt in the current literature on exploring the contactless event vision data for machine fault diagnosis. A vibration event representation is proposed to transform the event records into typical data samples, and a deep convolutional neural network model is used for processing the event information. To enhance the model robustness against environmental noisy vision events, an event data augmentation method is proposed to introduce variations of the event patterns. A deep representation clustering method is further proposed to improve the pattern recognition performance with respect to different machine health conditions. Experiments on the event vision-based rotating machine fault diagnosis problem are carried out. It is extensively validated that high fault diagnosis accuracies can be obtained using the vision data from the event-based cameras, which are competitive with the popular accelerometer data. Considering the properties of flexibility, portability and data recognizability, the event-based cameras thus provide a promising new tool for contactless machine health condition monitoring and fault diagnosis.

Big Data-Driven Intelligent Fault Diagnosis and Prognosis for Mechanical Systems

Abstract: This book presents systematic overviews and bright insights into big data-driven intelligent fault diagnosis and prognosis for mechanical systems

Deep Targeted Transfer Learning Along Designable Adaptation Trajectory for Fault Diagnosis Across Different Machines

Abstract: Deep transfer learning-based fault diagnosis has been developed to correct the data distribution shift, promoting a diagnosis knowledge transfer across related machines. However, there are two weaknesses: first, the assumption that all the target domain data are unlabeled is strict for robust applications of deep transfer learning to diagnosis across different machines; and second, the successes of existing methods are mostly achieved under the same conditional label distribution. For the weaknesses, this article relaxes a reasonable assumption that one-shot target domain samples called anchors are labeled, and further presents a deep targeted transfer learning (DTTL) method for tasks with different conditional label distributions. DTTL includes three parts. First, a domain-shared residual network is constructed to represent features from cross-domain data. Second, a target-domain clustering module gathers unlabeled target domain samples toward anchors. Third, a targeted adaptation module designs adaptation trajectories of target domain samples according to the associated labels of anchors and source domain data, and then corrects the joint distribution shift. The DTTL is demonstrated on transfer diagnosis tasks across different bearings. The results show that cross-domain data can be aligned by following the designable adaptation trajectories. Compared with other methods, the DTTL achieves higher diagnosis accuracy.

Prognostics and Remaining Useful Life Prediction of Machinery: Advances, Opportunities and Challenges

Abstract: As the fundamental and key technique to ensure the safe and reliable operation of vital systems, prognostics with an emphasis on the remaining useful life (RUL) prediction has attracted great attention in the last decades. In this paper, we briefly discuss the general idea and advances of various prognostics and RUL prediction methods for machinery, mainly including data-driven methods, physics-based methods, hybrid methods, etc. Based on the observations from the state of the art, we provide comprehensive discussions on the possible opportunities and challenges of prognostics and RUL prediction of machinery so as to steer the future development.

Remaining Useful Life Prediction of Lubricating Oil With Small Samples

Abstract: The remaining useful life (RUL) prediction of lubricating oil is essential for the preventive maintenance of machines, while the prediction accuracy has been severely limited by sparse and truncated data. Stochastic process modeling can provide a potential solution. However, two main challenges are encountered: 1) the nonlinear parameter estimation is prone to overfitting due to sparse data and 2) the lack of failure samples for threshold determination with truncated data. In the article, a novel RUL prediction model is developed based on the Wiener process and the oil degradation mechanism. Primarily, data augmentation is adopted to enhance data quantity for reliable nonlinear parameter estimation. Furthermore, the run-to-failure prediction based on the probability density function is performed to obtain the threshold with the truncated data. With the well-trained model, the RUL prediction is accomplished by updating the parameters and the thresholds with monitoring data. Furthermore, the prediction accuracy is validated with the oil data collected from both simulations and bench tests.

Wearable sensors and features for diagnosis of neurodegenerative diseases: A systematic review

Abstract: Objective Neurodegenerative diseases affect millions of families around the world, while various wearable sensors and corresponding data analysis can be of great support for clinical diagnosis and health assessment. This systematic review aims to provide a comprehensive overview of the existing research that uses wearable sensors and features for the diagnosis of neurodegenerative diseases. Methods A systematic review was conducted of studies published between 2015 and 2022 in major scientific databases such as Web of Science, Google Scholar, PubMed, and Scopes. The obtained studies were analyzed and organized into the process of diagnosis: wearable sensors, feature extraction, and feature selection. Results The search led to 171 eligible studies included in this overview. Wearable sensors such as force sensors, inertial sensors, electromyography, electroencephalography, acoustic sensors, optical fiber sensors, and global positioning systems were employed to monitor and diagnose neurodegenerative diseases. Various features including physical features, statistical features, nonlinear features, and features from the network can be extracted from these wearable sensors, and the alteration of features toward neurodegenerative diseases was illustrated. Moreover, different kinds of feature selection methods such as filter, wrapper, and embedded methods help to find the distinctive indicator of the diseases and benefit to a better diagnosis performance. Conclusions This systematic review enables a comprehensive understanding of wearable sensors and features for the diagnosis of neurodegenerative diseases.

Machinery Health Prognostics With Multimodel Fusion Degradation Modeling

Abstract: Degradation modeling aims to formulate the health state degradation process of machinery. Commonly used degradation models pay more attention to describing the global increasing or decreasing trend without considering the local fluctuation in the degradation process. To deal with the above-mentioned issue, this article proposes a multimodel fusion degradation modeling method. The basic idea is to fuse multiple models to describe various degradation trends of machinery involving the global trend as well as the local fluctuation. A generalized statistical degradation modeling framework is constructed, wherein the degradation process is formulated by fusing multiple models with various degradation trends. The failure event is reinterpreted under the condition of state observations fluctuating around the failure threshold. The probability density functions of the time when the state observation exceeds and drops below the failure threshold are derived, respectively. An iterative matching pursuit algorithm is developed to select the optimal models adaptively. A numerical illustration and an experimental study are conducted to verify the proposed method. The results demonstrate its superiority in health prognostics compared with two benchmark methods in cases where the degradation process has dominant local fluctuation.

A new method for calculating time‐varying torsional stiffness of RV reducers with variable loads and tooth modifications

Abstract: Rotate vector (RV) reducers have advantages of high torque ratio, and extremely reliable functioning under dynamic load conditions, and so forth, and they are extensively used in precision transmissions, such as industrial robots. The torsional stiffness of RV reducers is a main parameter affecting the meshing vibration and transmission performance. In addition, the variable loads and tooth modifications have significant influence on the torsional stiffness of RV reducers. In this paper, a new method of calculating torsional stiffness for RV reducers considering variable loads and tooth modifications is presented. The dynamic stress and deformation of meshing teeth are calculated based on Hertz formulation, and the number of meshing teeth is determined by analyzing the dynamic stress of meshing teeth. Then, the torsional stiffness of RV reducers is obtained. Finite element method is applied to calculate the deformation of cycloidal-pin gear in the maximum force position δmax. The influence of variable applied loads and different tooth modifications of cycloidal-pin gear transmission on torsional stiffness are also studied. The results show that variable applied loads and different tooth modifications influence the torsional stiffness of RV reducers by changing teeth deformation and clearance, respectively.

Improved subspace modal identification of industrial robots

Abstract: Industrial robots have become key components for manufacturing automations due to their larger workspaces and flexibility. However, low stiffness and high compliance of industrial robots may inevitably lead to vibration by self-excitation or periodic force dependent on workspace configuration. Therefore, the knowledge of the robot's modal properties should be accurately required to enhance the operation accuracy of industrial robots. To improve the identification accuracy of experimental modal parameters of field industrial robots, an improved subspace identification method is proposed to perform nonlinear iterative optimization for updating the state parameters of industrial robots. Experimental response measurement of a six-degrees-of-freedom industrial robot is carried out to obtain modal parameters under various poses. The identification results of the improved subspace modal method are preferable to that of the traditional method. Moreover, the reconstructed three-dimension working frequency space is presented to exactly characterize experimental modal frequencies throughout its workspace. The proposed method effectively improves the identification accuracy of modal parameters when compared with the traditional algorithms and the influence of robots' pose change on modal parameters is also investigated by experimental modal measurements.