Predict Performance Degradation Research Articles

PTS-FNN-Based Health Prediction Method for Flexible Photoelectric Film Material Processing Equipment

Roll-to-Roll (R2R) processing is a common processing method for flexible photoelectric film materials. Due to the physical properties of the materials, the change in the performance of the R2R processing equipment can easily cause deformation of the flexible film material, it is particularly important to predict the performance degradation of the processing equipment. Based on the accuracy and real-time requirements of performance degradation prediction, a PTS-FNN model for performance degradation prediction was proposed in this paper, which combines the Possibilistic C-Means (PCM) fuzzy clustering and Takagi–Sugeno Fuzzy Neural Network (TS-FNN). We also studied the PCM classification algorithm of input data of PTS-FNN model, the predecessor network of TS-FNN prediction model and the construction method of post-component network. Finally, the implementation process of PCM classification algorithm and TS-FNN prediction model were given. The R2R processing equipment health prediction experiment system was built and the PTS-FNN model experiment was carried out. The experimental results showed that the training time of PTS-FNN model was 50.37% less than the standard TS-FNN prediction model. The prediction accuracy increased by 5.48%, and the PTS-FNN had no error in the judgment of state 1 and state 4.

Predicting and reining in application-level slowdown on spatial multitasking GPUs

Predicting performance degradation of a GPU application at co-location on a spatial multitasking GPU without prior application knowledge is essential in public Clouds. Prior work mainly targets CPU co-location, and is inaccurate and/or inefficient for predicting performance of applications at co-location on spatial multitasking GPUs. Our investigation shows that hardware event statistics caused by co-located applications strongly correlate with their slowdowns. Based on this observation, we present Themis with a kernel slowdown model (Themis-KSM), which performs precise and efficient online application slowdown prediction without prior application knowledge. The kernel slowdown model is trained offline. When new applications co-run, Themis-KSM collects event statistics and predicts their slowdowns simultaneously. In addition, we also propose a two-stage slowdown prediction mechanism (Themis-TSP) for real-system GPUs without any hardware modification. Our evaluation shows that Themis has negligible runtime overhead, and both Themis-KSM and Themis-TSP can precisely predict application-level slowdown with prediction error smaller than 9.5% and 12.8%, respectively. Based on Themis, we also implement an SM allocation engine to rein in application slowdown at co-location. Case studies show that the engine successfully enforces fair sharing and QoS.

HKF-SVR Optimized by Krill Herd Algorithm for Coaxial Bearings Performance Degradation Prediction.

In real industrial applications, bearings in pairs or even more are often mounted on the same shaft. So the collected vibration signal is actually a mixed signal from multiple bearings. In this study, a method based on Hybrid Kernel Function-Support Vector Regression (HKF–SVR) whose parameters are optimized by Krill Herd (KH) algorithm was introduced for bearing performance degradation prediction in this situation. First, multi-domain statistical features are extracted from the bearing vibration signals and then fused into sensitive features using Kernel Joint Approximate Diagonalization of Eigen-matrices (KJADE) algorithm which is developed recently by our group. Due to the nonlinear mapping capability of the kernel method and the blind source separation ability of the JADE algorithm, the KJADE could extract latent source features that accurately reflecting the performance degradation from the mixed vibration signal. Then, the between-class and within-class scatters (SS) of the health-stage data sample and the current monitored data sample is calculated as the performance degradation index. Second, the parameters of the HKF–SVR are optimized by the KH (Krill Herd) algorithm to obtain the optimal performance degradation prediction model. Finally, the performance degradation trend of the bearing is predicted using the optimized HKF–SVR. Compared with the traditional methods of Back Propagation Neural Network (BPNN), Extreme Learning Machine (ELM) and traditional SVR, the results show that the proposed method has a better performance. The proposed method has a good application prospect in life prediction of coaxial bearings.

A Novel Deep Belief Network and Extreme Learning Machine Based Performance Degradation Prediction Method for Proton Exchange Membrane Fuel Cell

Lifetime and reliability seriously affect the applications of proton exchange membrane fuel cell (PEMFC). Performance degradation prediction of PEMFC is the basis for improving the lifetime and reliability of PEMFC. To overcome the lower prediction accuracy caused by uncertainty and nonlinearity characteristics of degradation voltage data, this article proposes a novel deep belief network (DBN) and extreme learning machine (ELM) based performance degradation prediction method for PEMFC. A DBN based fuel cell degradation features extraction model is designed to extract high-quality degradation features in the original degradation data by layer-wise learning. To tackle the issues of overfitting and instability in fuel cell performance degradation prediction, an ELM with good generalization performance is introduced as a nonlinear prediction model, which can get some enhancement of prediction precision and reliability. Based on the designed DBN-ELM model, the particle swarm optimization (PSO) algorithm is used in the model training process to optimize the basic network structure of DBN-ELM further to improve the prediction accuracy of the hybrid neural network. Finally, the proposed prediction method is experimentally validated by using actual data collected from the 5-cells PEMFC stack. The results demonstrate that the proposed approach always has better prediction performance compared with the existing conventional methods, whether in the cases of various training phase or the cases of multi-step-ahead prediction.

Performance Prediction Using High-Order Differential Mathematical Morphology Gradient Spectrum Entropy and Extreme Learning Machine

Performance prediction is significant to monitor the health status of rolling bearings, which can greatly reduce the loss caused by potential faults in the whole life cycle of rolling bearings. It is a very important part of Prognostic and Health Management (PHM). In this article, a new performance degradation prediction (HMEPEM) method based on high-order differential mathematical morphology gradient spectrum entropy (HOMMSE), phase space reconstruction, and extreme learning machine (ELM) is proposed to predict the performance degradation trend of rolling bearings. In the proposed HMEPEM method, the HOMMSE method is used to extract the initial features of performance degradation from the raw bearing vibration signals and divide working stages. Then the phase space reconstruction is used to further extract more useful features from the initial features of performance degradation in order to construct a feature matrix, which is input into the ELM in order to build the performance degradation prediction model for predicting the performance degradation trend of rolling bearings. The proposed HMEPEM method is validated on the performance degradation data of rolling bearings provided by the PRONOSTIA platform. The results show that the proposed HMEPEM method can efficiently track the evolution of degradation and predict the performance degradation trend of rolling bearings.

Performance degradation prediction of mechanical equipment based on optimized multi-kernel relevant vector machine and fuzzy information granulation

An operation condition evaluation and prediction method based on wavelet packet information entropy and multi-kernel relevance vector machine is proposed for mechanical equipment in this paper. Firstly, the vibration signals of mechanical equipment are decomposed into high-frequency signals and low-frequency signals with different scales by using the theory of wavelet packet decomposition. The complexity and irregularity of the frequency-varying signals are represented by information entropy. Then, these constructed characteristic indicators are input to the relevance vector machine for performance degradation prediction. Finally, two kinds of roller bearings used in the experiment are taken as an example to verify the effectiveness of the method. The results show that the proposed method for evaluating the operational state of mechanical equipment can fully extract the characteristic information representing the operational state of roller bearings. It provides a new theoretical and practical support for mechanical equipment operational state evaluation and prediction.

기계학습을 이용한 필터의 성능 저하 예측

기계학습을 이용한 필터의 성능 저하 예측

Performance Supervised Fault Detection Schemes for Industrial Feedback Control Systems and their Data-Driven Implementation

This article addresses performance supervised fault detection (PSFD) issues for industrial feedback control systems based on performance degradation prediction. To be specific, three performance indicators are first introduced based on Bellman equation to predict system performance degradations for industrial processes with the aid of machine learning techniques. Based on them, three PSFD schemes are proposed by embedding the performance indicators as supervising information. In this context, the data-driven implementation of PSFD schemes are investigated for linear systems with unmeasurable state variables. A case study on rolling mill process, a typical benchmark in the steel manufacturing processes, is given at the end of this article to illustrate the applications of the proposed fault detection schemes.

Lifetime Prediction of Anode-Supported Solid Oxide Fuel Cell on the Basis of Individual Components Degradation

Long-term stability is an essential requirement for the successful commercialization of solid oxide fuel cell (SOFC) technology. In the present work, the long-term performance degradation of the anode-supported SOFC short stack is analyzed under accelerated operating conditions. The voltage degradation of the short stack was caused by the increase in ohmic and polarization resistance with time. The coarsening of Ni particles in the Ni-cermet anode was found to be the dominant degradation mechanism which decreases the anode performance gradually during the long-term operation. On the cathode side, cation surface segregation and formation of resistive phase between cathode and electrolyte were responsible for the performance degradation. Mathematical correlations were developed for the prediction of performance degradation of SOFC components and integration of single effects degradation can be used to predict the lifetime of the SOFC cell and stack.

A Clustering-Based Framework for Performance Degradation Prediction of Slewing Bearing Using Multiple Physical Signals

Diagnosing the failure or predicting the performance state of low-speed and heavy-load slewing bearings is a practical and effective method to reduce unexpected stoppage or optimize the maintenances. Many literatures focus on the performance prediction of small rolling bearings, while studies on slewing bearings' health evaluation are very rare. Among these rare studies, supervised or unsupervised data-driven models are often used alone, few researchers devote to remaining useful life (RUL) prediction using the joint application of two learning modes which could fully take diversity and complexity of slewing bearings' degradation and damage into consideration. Therefore, this paper proposes a clustering-based framework with aids of supervised models and multiple physical signals. Correlation analysis and principle component analysis (PCA)-based multiple sensitive features in time-domain are used to establish the performance recession indicators (PRIs) of torque, temperature, and vibration. Subsequently, these three indicators are divided into several parts representing different degradation periods via optimized self-organizing map (OSOM). Finally, corresponding data-driven life models of these degradation periods are generated. Experimental results indicate that multiple physical signals can effectively describe the degradation process. The proposed clustering-based framework is provided with a more accurate prediction of slewing bearings' RUL and well reflects the performance recession periods.

MOSFET Small-Signal Model Considering Hot-Carrier Effect for Millimeter-Wave Frequencies

The hot-carrier effect, which is caused by the generation of interface states, is the main degradation mechanism for MOSFETs. Predicting the degradation of circuit performance due to the hot-carrier effect is important for practical circuit design. In this paper, we propose a small-signal model considering the hot-carrier effect by establishing time-dependent model parameters, which is verified by small-signal simulation and measurement for 40-nm-process MOSFETs at millimeter-wave (mmW) frequencies. In the proposed small-signal model, the shift of relaxation time of the non-quasi-static (NQS) effect is investigated and verified for mmW frequencies for the first time. By comparing simulation and measurement results, it is shown that the shift of relaxation time of the NQS effect should be considered for the prediction of MOSFETs performance degradation at mmW frequencies.

Performance degradation model and prediction method of real-time remaining life for high temperature ceramic filter tube

Performance degradation model and prediction method of real-time remaining life for high temperature ceramic filter tube

Performance Degradation Prediction and Reliability Evaluation of Rubber Aging in Natural Environment Under Alternating Cyclic Thermal Load

With a focus on predicting the degradation of rubber performance in the natural environment and evaluating its reliability, the distribution law of accelerated aging life is analyzed through the accelerated aging test of hot oxygen. A Weibull distribution model is then established to verify the consistency of the accelerated aging mechanism. Through the constant stress accelerated aging test data, the aging characteristics of the rubber under alternating thermal stress load in the natural environment are inferred. The concept of thermal stress amplitude coefficient is proposed, and its numerical value is calculated by the combination of numerical simulation and single-peak curve fitting. Under the principle of time-temperature equivalence, the segmentation time equivalent method and the overall temperature equivalent method are employed to calculate the rubber performance degradation curve under natural environment aging conditions. Finally, according to the Weibull distribution, the aging reliability of the rubber over time is simulated. This research can provide a reference for the aging reliability evaluation of products under alternating stress.

A framework for multi-variable, semi-adaptive predictive control system

In view of the degradation of predictive control performance caused by model mismatch, a multi-variable, semi-adaptive zone predictive control system framework is presented. The proposed framework changes the traditional control mode to testing mode and turns set-point to zone control, thereby realizing the constraint satisfaction of the output variables of the test process. For the constraint zone models predictive control in the integrated testing mode, the amplitude strength of testing input signals is introduced to realize the constraint guarantee function and signal-to-noise ratio maximization. The framework implements the open-loop test to improve test efficiency under the premise of production on the rails. The signal-to-noise ratio of the testing process is ensured by maximizing the test signal amplitude. Furthermore, the framework is extended from constrained to two-layer model predictive control, and the benefit balance coefficient is introduced to realize the balance between economic benefit and testing. The method proposed in the paper is a type of on-line open-loop identification, which solves the problem of the correlation between input signals and noises in closed-loop identification. The simulation results verify the effectiveness of the method.

Research on Prediction Method of Performance Degradation of Flexible Optoelectronic Film Material Processing Equipment Based on Adaptive Fuzzy Clustering

Flexible photoelectric film is an anisotropic material. The slight change of equipment performance during processing is prone to cause deformation of the material. Therefore, it is important to predict the degradation of processing equipment performance. Since the performance degradation of flexible photoelectric film material Roll-to-Roll (R2R) processing equipment is a nonlinear process, this paper introduces an adaptive fuzzy clustering method to construct a fuzzy membership function model for calculating the performance degradation index of R2R processing equipment and studies the parameter solving method such as the AFCM division of the roller vibration data, the category center value of the fuzzy membership function, and the input data division area width. Finally, the performance degradation index calculation algorithm is designed. The roller shaft accelerated life test was carried out using self-made equipment. The test data were 1000 sets. The results showed that the root mean square eigenvalues and the kurtosis eigenvalues of the roller vibration data are sensitive to the performance degradation. The equipment performance curve described by the first and second types of performance degradation indicators was very stable in the early stage. After the 800th group, the curve continued to decrease, and the change was more severe, indicating that the performance degradation of the equipment is more serious. In the 980th group, the longer-lasting roller shaft was damaged, and the performance index value was about zero, which proved the correctness of the performance degradation prediction method proposed in this paper in calculating the performance degradation value of the equipment.

Analysis of performance degradation and residual life prediction of batteries for electric vehicles under driving conditions

The analysis of residual life prediction of batteries for electric vehicles under driving conditions was performed based on the degradation data. This article, characteristics of lithium iron phosphate battery performance degradation as the object, mainly considers two factors about the charge–discharge rate and vibration stress, first, the lithium battery performance degradation test simulating a car in a real driving environment is designed, which provides the lithium battery performance test reference. Then, the model parameters were obtained based on the test data. Finally, the performance degradation model and residual life prediction model of the lithium battery based on the Wiener process are established. This method not only has a high prediction accuracy, but also avoids the construction of a complex battery mechanism degradation model. What is more, this article provides a good perspective for residual life prediction in simplified experiments saving cost. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Molecular dynamics study on the effect of salt environment on interfacial structure, stress, and adhesion of carbon fiber/epoxy interface

ABSTRACTEpoxy resins are widely used as matrices for bonding carbon fiber tightly together in fabricating carbon fiber reinforced polymer (CFRP), which has been increasingly used in marine and offshore applications. To analyze CFRP performance in salt environment, it requires a fundamental understanding of the behavior of carbon fiber/epoxy interface under saltwater exposure. Here the molecular interface model of carbon fiber/epoxy bonded system is constructed to analyze the interfacial integrity in salt environment. The simulation results show that salt solution leads to largest loss of interfacial adhesion, which correlates with structural and mechanical degradation of bonded interface, as indicated by the decreased epoxy density close to interface and reduced interfacial stress as compared to dry and wet case. Through examining interfacial structure and stress during pulling process, it is observed that epoxy detaches in a sequential manner and the final debonding occurs more easily under saltwater ingress. By simultaneously capturing mechanical degradation and interfacial deterioration, it is clear that strong mechanical properties of carbon fiber/epoxy bonded interface are critical for long-term interfacial integrity and performance of CFRP in salt environment. This study provides microscopic information of interfacial deterioration in CFRP composite, which forms basis for predicting performance degradation of macroscopic CFRP in consideration of environmental exposure.

Multivariable least squares support vector machine with time integral operator for the prediction of bearing performance degradation

The prediction of performance degradation is significant for the health monitoring of rolling bearing, which helps to greatly reduce the loss caused by potential faults in the entire life cycle of rotating machinery. As a new method of machine learning based on statistical learning theory, least squares support vector machine is developed and has achieved good results. However, it lacks the description of the time-sum effect and delay characteristics, which cannot fully describe the performance degradation process. To overcome the problem, a new time shift least squares support vector machine with integral operator is proposed. What is more, multivariable prediction model is introduced to describe the process from multiple perspectives. In this model, different features are extracted to construct sample pairs through a moving window. Then these features are decomposed in time domain using a set of orthogonal basis functions to simplify computation. Furthermore, the model adaptability is also improved through an iterative updating strategy. Bearing fault experiments show that the proposed model outperforms the general method.

A simplified approach to predict performance degradation of a solid oxide fuel cell anode

The agglomeration of nickel (Ni) particles in a Ni-cermet anode is a significant degradation phenomenon for solid oxide fuel cells (SOFCs). This work aims to predict the performance degradation of SOFCs due to Ni grain growth by using a simplified approach. Accelerated aging of Ni-scandia stabilized zirconia (SSZ) as an SOFC anode is carried out at 900 °C and subsequent microstructural evolution is investigated every 100 h up to 1000 h using scanning electron microscopy (SEM). The resulting morphological changes are quantified using a two-dimensional image analysis technique that yields the particle size, phase proportion, and triple phase boundary (TPB) point distribution. The electrochemical properties of an anode-supported SOFC are characterized using electrochemical impedance spectroscopy (EIS). The changes of particle size and TPB length in the anode as a function of time are in excellent agreement with the power-law coarsening model. This model is further combined with an electrochemical model to predict the changes in the anode polarization resistance. The predicted polarization resistances are in good agreement with the experimentally obtained values. This model for prediction of anode lifetime provides deep insight into the time-dependent Ni agglomeration behavior and its impact on the electrochemical performance degradation of the SOFC anode.

A Framework for Adaptive Predictive Control System Based on Zone Control

In view of the degradation of predictive control performance caused by model mismatch, a multi-variable adaptive predictive control system framework which is composed of zone model predictive control (MPC), identification module and performance monitoring module, is presented. The proposed framework synthesizes the traditional control mode and the test mode to construct a unified form, which is convenient to implement with the MPC software packages. Traditional setpoint control is switched to zone control to ensure that the process constraints remain satisfied in testing, while multi-variable test signals are introduced to guarantee the sufficient excitation of the plant. In addition, in order to maximize the signal-to-noise ratio, an adaptive method of determining the amplitude of test signals is proposed. All the online open-loop identification methods are suitable for this framework, as the testing is treated as “open-loop,” which solves the problem of the correlation between input signals and noises in the closed-loop identification. These characteristics of the proposed framework are illustrated via a simulation.