Bin Wu

Bio: Bin Wu is an academic researcher from Northwestern Polytechnical University. The author has contributed to research in topics: Shock (mechanics) & Accelerometer. The author has an hindex of 3, co-authored 12 publications receiving 37 citations.

On Fault Diagnosis for High-G Accelerometers via Data-Driven Models

Abstract: Shock test is a pivotal stage for designing and manufacturing space instruments. As the essential components in shock test systems to measure shock signals accurately, high-g accelerometers are usually exposed to hazardous shock environment and could be subjected to various damages. Owing to that these damages to the accelerometers could result in erroneous measurements which would further lead to shock test failures, accurately diagnosing the fault type of each high-g accelerometer can be vital to ensure the reliability of the shock test experiments. Additionally, in practice, an accelerometer in one malfunction form usually outputs mutable signal waveforms, so that it is difficult to empirically judge the fault type of the accelerometer based on the erroneous readings. Moreover, traditional hardware diagnosis approaches require disassembling the sensor’s package shell and manually observing the damage of the elements inner the sensor, which are less-efficient and uneconomical. Aiming at these problems, several data-driven approaches are incorporated to diagnose the fault types of high-g accelerometers in this work. Firstly, several high-g accelerometers with most frequent types of damage are collected, and a shock signal dataset is gathered by conducting shock tests on these faulty accelerometers. Then, the obtained dataset is used to train several base classifiers to identify the fault types in a supervised fashion. Lastly, a hybrid ensemble learning model is established by integrating these base classifiers with both heterogeneous and homogeneous models. Experimental results show that these data-driven methods can accurately identify the fault types of high-g accelerometers from their mutable erroneous readings.

Self-validating high-g accelerometers through data-driven methods

Abstract: In the aerospace industry, pyroshock testing is an indispensable step in designing space electronics. Yet, damages in high-g accelerometers, the core measuring instruments in pyroshock test systems, could result in various failures of pyroshock tests. To ensure the reliability of pyroschock tests for space electronics, a machine learning system is proposed to perform self-validation for high-g accelerometers. In this work, self-validation refers to the capability of identifying five key parameters, namely the validated shock signal, the validated uncertainty, the measurement status, the raw shock signal and the fault type, synchronously during measuring shock signals in pyroshock tests. To achieve the highest performance, we accomplish these tasks through combining an ensemble learning model and a deep neural network (DNN). The ensemble learning model, which integrates several k-nearest neighbors with different k values, is used to identify the sensors’ health conditions from their measurements and diagnose their fault types synchronously if damaged. The DNN, a deep autoencoder-based neural network, is designed to correct corrupted measurements through constructing the mapping between faulty signals and their corresponding reference counterparts. Experimental results show that the proposed machine learning system is capable of not only accurately identifying the health conditions and fault types of the damaged high-g accelerometers from their measurements, but also recovering the corrupted shock signals to a large extent, and, meanwhile, outputting the five self-validation parameters.

A Deep Learning Approach to Recover High-g Shock Signals From the Faulty Accelerometer

Abstract: A deep learning based approach is proposed to accurately recover shock signals measured from a damaged high-g accelerometer without modifying the hardware. We first conducted shock tests and collected a large dataset of shock signals with different levels of acceleration by using an efficient experimental apparatus. The training data is composed of a pair of signals simultaneously obtained from a faulty accelerometer and a high-end accelerometer (served as the ground truth). A customized autoencoder neural network is designed and trained on this dataset, aiming to map the faulty signals to their reference counterparts. Experimental results show that, with the help of deep learning, shock signals can be accurately recovered from the faulty measurements. Compared with conventional approaches that require diagnosing and replacing faulty parts, the proposed data-driven method demonstrates a highly promising solution that allows recovering corrupted signals without introducing extra work to upgrade the hardware at almost zero cost. The dataset and code of this work are made publicly available on GitHub at https://github.com/hope-yao/Sensor_Calibration .

Low-cost Measurement of Industrial Shock Signals via Deep Learning Calibration

Abstract: Special high-end sensors with expensive hardware are usually needed to measure shock signals with high accuracy. In this paper, we show that cheap low-end sensors calibrated by deep neural networks are also capable to measure high-g shocks accurately. Firstly we perform drop shock tests to collect a dataset of shock signals measured by sensors of different fidelity. Secondly, we propose a novel network to effectively learn both the signal peak and overall shape. The results show that the proposed network is capable to map low-end shock signals to its high-end counterparts with satisfactory accuracy. To the best of our knowledge, this is the first work to apply deep learning techniques to calibrate shock sensors.

Data-driven early fault diagnostic methodology of permanent magnet synchronous motor

Abstract: Permanent magnet synchronous motor (PMSM) is one of the common core power components in modern industrial systems. Early fault diagnosis can avoid major accidents and plan maintenance in advance. However, the features of early faults are weak, and the symptoms are not obvious. Meanwhile, the fault signal is often overwhelmed by noise. Accordingly, fault diagnosis for early faults is difficult, and the diagnostic accuracy is generally low. A Bayesian-network-based data-driven early fault diagnostic methodology of PMSM is proposed with vibration and acoustic emission data. The wavelet threshold denoising and minimum entropy deconvolution methods are used to improve the signal-to-noise ratio. The complementary ensemble empirical mode decomposition method is used to extract signal eigenvalues, and Bayesian networks are applied to identify the early, middle, and permanent faults. Experimental data carried out with Tyco ST8N80P100V22E medium PMSM are used to train the fault diagnostic model and validate the proposed fault diagnostic methodology. Result shows that the accuracy for early faults is more than 90% when acoustic emission signal is used, and it is higher than the accuracy with vibration signal. The influence of load on diagnostic accuracy is also investigated, and it indicates that the accuracy with acoustic emission signal is higher than that with vibration signal under different loads.

Influence of process parameter and strain rate on the dynamic compressive properties of selective laser-melted Ti-6Al-4V alloy

Abstract: Dynamic compressive mechanical responses of selective laser-melted Ti-6Al-4V alloy were studied in terms of the influences of scanning speed, building angle as well as impacting strain rate. It was found that the ultimate flow stress and energy absorption increased first and then dropped sharply as the scanning speed increased from 1.0 to 1.6 m/s, showing that the sample built at scanning speed of 1.2 m/s possessed the best dynamic mechanical properties. They increased straightly up as the building angle increased from 0° to 90°, but only the sample built at 45° ruptured with shearing fracture pattern. Moreover, the samples exhibited distinct strain rate hardening effect, as the applied strain rate increased from 900 to 2100/s, and the sample ruptured ultimately with mixed ductility/brittle fracture pattern. Volume fraction of LAGBs in samples increased from 9.1 to 18.9% and 21.4% after impacting at strain rates of 900/s and 2100/s, indicating that intenser dislocation was activated at a higher strain rate impacting, this is the main cause of enhancement in strength. This study provided an insight into the influence of high strain rate impact loading on the dynamic mechanical responses of SLMed TC4 alloy, which is conducive to further exploiting the performance potential of the SLMed materials.

On Fault Diagnosis for High-G Accelerometers via Data-Driven Models

Abstract: Shock test is a pivotal stage for designing and manufacturing space instruments. As the essential components in shock test systems to measure shock signals accurately, high-g accelerometers are usually exposed to hazardous shock environment and could be subjected to various damages. Owing to that these damages to the accelerometers could result in erroneous measurements which would further lead to shock test failures, accurately diagnosing the fault type of each high-g accelerometer can be vital to ensure the reliability of the shock test experiments. Additionally, in practice, an accelerometer in one malfunction form usually outputs mutable signal waveforms, so that it is difficult to empirically judge the fault type of the accelerometer based on the erroneous readings. Moreover, traditional hardware diagnosis approaches require disassembling the sensor’s package shell and manually observing the damage of the elements inner the sensor, which are less-efficient and uneconomical. Aiming at these problems, several data-driven approaches are incorporated to diagnose the fault types of high-g accelerometers in this work. Firstly, several high-g accelerometers with most frequent types of damage are collected, and a shock signal dataset is gathered by conducting shock tests on these faulty accelerometers. Then, the obtained dataset is used to train several base classifiers to identify the fault types in a supervised fashion. Lastly, a hybrid ensemble learning model is established by integrating these base classifiers with both heterogeneous and homogeneous models. Experimental results show that these data-driven methods can accurately identify the fault types of high-g accelerometers from their mutable erroneous readings.