Interactive Prognosis Framework Between Deep Learning and a Stochastic Process Model for Remaining Useful Life Prediction.

Uncertainty quantification of the remaining useful life (RUL) for degraded systems under the big data era has been a hot topic in recent years. A general idea is to execute two separate steps: deep-learning-based health indicator (HI) construction and stochastic process-based degradation modeling. However, there exists a critical matching defect between the constructed HI and a degradation model, which seriously affects the RUL prediction accuracy. Toward this end, this article proposes an interactive prognosis framework between deep learning and a stochastic process model for the RUL prediction. First, we resort to stacked contractive autoencoders to fuse multiple sensor information of historical systems for constructing the HI in a typical unsupervised manner. Then, considering the nonlinear characteristic of the constructed HI, an exponential-like degradation model is introduced to construct its degradation evolving model, and theoretical expressions of the prediction results are derived under the concept of the first hitting time. Furthermore, we design an optimization objective function by integrating the HI construction and degradation modeling for the RUL prediction. To minimize the designed objective function of the proposed interactive prognosis framework, a gradient descent algorithm is employed to update the model parameters. Based on the well-trained interactive prognosis model, we can obtain the HI of a field system from stacked contractive autoencoders with sensor data and the probability density function (pdf) of the predicted RUL on the basis of the estimated parameters. Finally, the effectiveness and superiority of the proposed interactive prognosis method are verified by two case studies associated with turbofan engines.

Wearable multisource quantitative gait analysis of Parkinson's diseases.

As the motor symptoms of Parkinson's disease (PD) are complex and influenced by many factors, it is challenging to quantify gait abnormalities adequately using a single type of signal. Therefore, a wearable multisource gait monitoring system is developed to perform a quantitative analysis of gait abnormalities for improving the effectiveness of the clinical diagnosis. To detect multisource gait data for an accurate evaluation of gait abnormalities, force sensitive sensors, piezoelectric sensors, and inertial measurement units are integrated into the devised device. The modulation circuits and wireless framework are designed to simultaneously collect plantar pressure, dynamic deformation, and postural angle of the foot and then wirelessly transmit these collected data. With the designed system, multisource gait data from PD patients and healthy controls are collected. Multisource features for quantifying gait abnormalities are extracted and evaluated by a significance test of difference and correlation analysis. The results show that the features extracted from every single type of data are able to quantify the health status of the subjects (p < 0.001, ρ > 0.50). More importantly, the validity of multisource gait data is verified. The results demonstrate that the gait feature fusing multisource data achieves a maximum correlation coefficient of 0.831, a maximum Area Under Curve of 0.9206, and a maximum feature-based classification accuracy of 88.3%. The system proposed in this study can be applied to the gait analysis and objective evaluation of PD.

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

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.

Transfer Relation Network for Fault Diagnosis of Rotating Machinery With Small Data.

Many deep-learning methods have been developed for fault diagnosis. However, due to the difficulty of collecting and labeling machine fault data, the datasets in some practical applications are relatively much smaller than the other big data benchmarks. In addition, the fault data come from different machines. Therefore, on some occasions, fault diagnosis is a multidomain problem with small data, where satisfactory transfer performance is difficult to obtain and has been rarely explored from the few-shot learning viewpoint. Different from the existing deep transfer learning solutions, a novel transfer relation network (TRN), combining a few-shot learning mechanism and transfer learning, is developed in this study. Specifically, the fault diagnosis problem has been treated as a similarity metric-learning problem instead of solely feature weighted classification. A feature net and a relation net have been, respectively, constructed for feature extraction and relation computation. The Siamese structure has been borrowed to extract the features of the source and the target domain samples with shared weights. Multikernel maximum mean discrepancy (MK-MMD) is employed on several higher layers with different tradeoff parameters to enable an efficient domain feature transfer considering different feature properties. To implement efficient diagnosis based on small data, an episode-based few-shot training strategy is adopted to train TRN. Average pooling has been adopted to suppress the noise influence from the vibration sequence which turns out to be important for the success of time sequence-based fault diagnosis. Transfer experiments on four datasets have verified the superior performance of TRN. A significant improvement of classification accuracy has been made compared with the state-of-the-art methods on the adopted datasets.

Incipient Fault Detection for Rolling Element Bearings under Varying Speed Conditions.

Varying speed conditions bring a huge challenge to incipient fault detection of rolling element bearings because both the change of speed and faults could lead to the amplitude fluctuation of vibration signals. Effective detection methods need to be developed to eliminate the influence of speed variation. This paper proposes an incipient fault detection method for bearings under varying speed conditions. Firstly, relative residual (RR) features are extracted, which are insensitive to the varying speed conditions and are able to reflect the degradation trend of bearings. Then, a health indicator named selected negative log-likelihood probability (SNLLP) is constructed to fuse a feature set including RR features and non-dimensional features. Finally, based on the constructed SNLLP health indicator, a novel alarm trigger mechanism is designed to detect the incipient fault. The proposed method is demonstrated using vibration signals from bearing tests and industrial wind turbines. The results verify the effectiveness of the proposed method for incipient fault detection of rolling element bearings under varying speed conditions.

Stochastic resonance subject to multiplicative and additive noise: The influence of potential asymmetries.

The influence of potential asymmetries on stochastic resonance (SR) subject to both multiplicative and additive noise is studied by using two-state theory, where three types of asymmetries are introduced in double-well potential by varying the depth, the width, and both the depth and the width of the left well alone. The characteristics of SR in the asymmetric cases are different from symmetric ones, where asymmetry has a strong influence on output signal-to-noise ratio (SNR) and optimal noise intensity. Even optimal noise intensity is also associated with the steepness of the potential-barrier wall, which is generally ignored. Moreover, the largest SNR in asymmetric SR is found to be relatively larger than the symmetric one, which also closely depends on noise intensity ratio. In addition, a moderate cross-correlation intensity between two noises is good for improving the output SNR. More interestingly, a double SR phenomenon is observed in certain cases for two correlated noises, whereas it disappears for two independent noises. The above clues are helpful in achieving weak signal detection under heavy background noise.

Early Fault Diagnosis of Bearings Using an Improved Spectral Kurtosis by Maximum Correlated Kurtosis Deconvolution.

The early fault characteristics of rolling element bearings carried by vibration signals are quite weak because the signals are generally masked by heavy background noise. To extract the weak fault characteristics of bearings from the signals, an improved spectral kurtosis (SK) method is proposed based on maximum correlated kurtosis deconvolution (MCKD). The proposed method combines the ability of MCKD in indicating the periodic fault transients and the ability of SK in locating these transients in the frequency domain. A simulation signal overwhelmed by heavy noise is used to demonstrate the effectiveness of the proposed method. The results show that MCKD is beneficial to clarify the periodic impulse components of the bearing signals, and the method is able to detect the resonant frequency band of the signal and extract its fault characteristic frequency. Through analyzing actual vibration signals collected from wind turbines and hot strip rolling mills, we confirm that by using the proposed method, it is possible to extract fault characteristics and diagnose early faults of rolling element bearings. Based on the comparisons with the SK method, it is verified that the proposed method is more suitable to diagnose early faults of rolling element bearings.

A data-driven multiplicative fault diagnosis approach for automation processes.

This paper presents a new data-driven method for diagnosing multiplicative key performance degradation in automation processes. Different from the well-established additive fault diagnosis approaches, the proposed method aims at identifying those low-level components which increase the variability of process variables and cause performance degradation. Based on process data, features of multiplicative fault are extracted. To identify the root cause, the impact of fault on each process variable is evaluated in the sense of contribution to performance degradation. Then, a numerical example is used to illustrate the functionalities of the method and Monte-Carlo simulation is performed to demonstrate the effectiveness from the statistical viewpoint. Finally, to show the practical applicability, a case study on the Tennessee Eastman process is presented.

Fault diagnosis of rotating machinery based on an adaptive ensemble empirical mode decomposition.

The vibration based signal processing technique is one of the principal tools for diagnosing faults of rotating machinery. Empirical mode decomposition (EMD), as a time-frequency analysis technique, has been widely used to process vibration signals of rotating machinery. But it has the shortcoming of mode mixing in decomposing signals. To overcome this shortcoming, ensemble empirical mode decomposition (EEMD) was proposed accordingly. EEMD is able to reduce the mode mixing to some extent. The performance of EEMD, however, depends on the parameters adopted in the EEMD algorithms. In most of the studies on EEMD, the parameters were selected artificially and subjectively. To solve the problem, a new adaptive ensemble empirical mode decomposition method is proposed in this paper. In the method, the sifting number is adaptively selected, and the amplitude of the added noise changes with the signal frequency components during the decomposition process. The simulation, the experimental and the application results demonstrate that the adaptive EEMD provides the improved results compared with the original EEMD in diagnosing rotating machinery.

Tacholess envelope order analysis and its application to fault detection of rolling element bearings with varying speeds.

Vibration analysis is an effective tool for the condition monitoring and fault diagnosis of rolling element bearings. Conventional diagnostic methods are based on the stationary assumption, thus they are not applicable to the diagnosis of bearings working under varying speed. This constraint limits the bearing diagnosis to the industrial application significantly. In order to extend the conventional diagnostic methods to speed variation cases, a tacholess envelope order analysis technique is proposed in this paper. In the proposed technique, a tacholess order tracking (TLOT) method is first introduced to extract the tachometer information from the vibration signal itself. On this basis, an envelope order spectrum (EOS) is utilized to recover the bearing characteristic frequencies in the order domain. By combining the advantages of TLOT and EOS, the proposed technique is capable of detecting bearing faults under varying speeds, even without the use of a tachometer. The effectiveness of the proposed method is demonstrated by both simulated signals and real vibration signals collected from locomotive roller bearings with faults on inner race, outer race and rollers, respectively. Analyzed results show that the proposed method could identify different bearing faults effectively and accurately under speed varying conditions.

Waveform design for high-resolution damage detection using lamb waves.

Dispersion is encountered very often in ultrasonic guided waves, and may decrease the performance for damage detection significantly. For this reason, many signal processing methods have been proposed to obtain each mode under serious dispersion. In this paper, a new scheme is established for waveform design to suppress the dispersion such that each wave packet can be separated clearly. In this method, the dispersion effect of the guided wave is pre-compensated for a particular distance as it propagates through the structure. The relationship between the resolvable resolution and the waveform parameters is discussed; this relationship is employed as a guide to separately identify the wave packets caused by different structural features. Subsequently, an experiment is carried out to compare the performance of the proposed method with the time-reversal method. By using the proposed method, closely distributed structural features can be recognized with ease in the time domain.

A method based on multi-sensor data fusion for fault detection of planetary gearboxes.

Studies on fault detection and diagnosis of planetary gearboxes are quite limited compared with those of fixed-axis gearboxes. Different from fixed-axis gearboxes, planetary gearboxes exhibit unique behaviors, which invalidate fault diagnosis methods that work well for fixed-axis gearboxes. It is a fact that for systems as complex as planetary gearboxes, multiple sensors mounted on different locations provide complementary information on the health condition of the systems. On this basis, a fault detection method based on multi-sensor data fusion is introduced in this paper. In this method, two features developed for planetary gearboxes are used to characterize the gear health conditions, and an adaptive neuro-fuzzy inference system (ANFIS) is utilized to fuse all features from different sensors. In order to demonstrate the effectiveness of the proposed method, experiments are carried out on a planetary gearbox test rig, on which multiple accelerometers are mounted for data collection. The comparisons between the proposed method and the methods based on individual sensors show that the former achieves much higher accuracies in detecting planetary gearbox faults.