Search

It is significant to predict the vibration trend of a hydropower generator unit (HGU) based on historical data for the stable operation of units and the maintenance of power system safety. Therefore, a novel combined model based on ensemble empirical mode decomposition (EEMD), sample entropy (SE), a Gaussian process regression (GPR) model and an autoregressive moving average model (ARMA) is proposed. Firstly, according to the non-linear and non-stationary characteristics of the vibration series, the vibration time series is decomposed into a single component and relatively stable subsequences using EEMD. Then, the SE algorithm reconstructs the subsequences with similar complexity to reduce the number of prediction sequences. Moreover, after judging the stationarity test of the reconstructed sequence, the GPR model and ARMA model are used to predict the non-stationary and stable subsequences, respectively. Finally, the predicted values of each subsequence are synthesised. Furthermore, five related methods are employed to evaluate the effectiveness of the proposed approach. The results illustrate that: (1) compared with EEMD only, EEMD combined with SE can improve prediction accuracy; (2) the reconstruction strategy based on SE can reduce the influence of false modes and improve the prediction accuracy; and (3) the prediction effect of the hybrid prediction model, which reduces the influence of accidental factors, is better than that of a single model in predicting the vibration sequence of an HGU.

In this study, a new intelligent fault diagnosis approach based on composite multi-scale dimensionless indicators (CMDIs) and affinity propagation (AP) clustering is proposed to identify working conditions of mechanical components. For this goal, CMDIs as fault features are for the first time proposed to search more informative fault information hidden in the original vibration signals and useful variational mode decomposition signals. Next, two feature evaluation methods, Fisher criterion (FC) and self-weight criterion (SW), are introduced to search the top ranked CMDIs, respectively. Subsequently, AP clustering is applied to select the important CMDIs. The most important CMDI of each cluster is chosen as the final fault feature. Finally, these important CMDIs are fed into the following supervised learning classifiers to identify working conditions of mechanical components: k-nearest neighbors, linear discriminant analysis, naive Bayesian and random forests. Two experimental examples for different fault types of mechanical components are conducted. Experimental comparison results demonstrate that the combination diagnosis model based on CMDIs-FC-AP with naive Bayesian classifier would be most suitable for complex samples with a high dimensional feature set.

Machinery fault diagnosis methods based on dimensionless indicators have long been studied. However, traditional dimensionless indicators usually suffer a low diagnostic accuracy for mechanical components. Toward this end, an effective fault diagnosis method based on redefined dimensionless indicators (RDIs) and minimum redundancy maximum relevance (mRMR) is proposed to identify the health conditions of mechanical components. In the proposed method, the vibration signals are first processed by the variational mode decomposition, and multiple RDIs are constructed based on the decomposed signals. Subsequently, the mRMR approach is introduced to select the RDIs and several important RDIs can be obtained. Finally, the obtained RDIs are fed into a grid search support vector machine to perform fault pattern identification. To verify the superiority of the proposed method, two experimental examples for different fault types of mechanical components including rolling bearing and gearbox are conducted. The experimental results demonstrated that the RDIs as new fault features can effectively solve the deficiency of the traditional dimensionless indicator, and has stronger distinguishing ability for machinery faults. Additionally, our proposed method successfully differentiated 12 fault conditions of rolling bearings and nine fault conditions of gears with average accuracies of 97.47% and 97.12% with 11 and 5 RDIs, respectively.

Purpose Rotating machineries are widely used in manufacturing, petroleum, chemical, aircraft, and other industries. To accurately identify the operating conditions of such rotating machineries, this paper aims to propose a fault diagnosis method based on sensitive dimensionless parameters and particle swarm optimization (PSO)–support vector machine (SVM) for reducing the unexpected downtime and economic losses. Design/methodology/approach A relatively new hybrid intelligent fault classification approach is proposed by integrating multiple dimensionless parameters, the Fisher criterion and PSO–SVM. In terms of data pre-processing, a method based on wavelet packet decomposition (WPD), empirical mode decomposition (EMD) and dimensionless parameters is proposed for the extraction of the vibration signal features. The Fisher criterion is applied to reduce the redundant dimensionless parameters and search for the sensitive dimensionless parameters. Then, PSO is adapted to optimize the penalty parameter and kernel parameter for SVM. Finally, the sensitive dimensionless parameters are classified with the optimized model. Findings As two different time–frequency analysis methods, a method based on a combination of WPD and EMD used to extract multiple dimensionless parameters is presented. More vital diagnosis information can be obtained from the vibration signals than by only using a single time–frequency analysis method. Besides, a fault classification approach combining the sensitive dimensionless parameters and PSO-SVM classifier is proposed. The comparative experiment results show that the proposed method has a high classification accuracy and efficiency. Originality/value To the best of the authors’ knowledge, very few efforts have been performed for fault classification using multiple dimensionless parameters. In this paper, eighty dimensionless parameters have been studied intensively, which provides a new strategy in fault diagnosis field.

Fault diagnosis has received considerable attention because its implementation can effectively prevent costly and even catastrophic downtime. However, quickly identifying faults and accurately obtaining diagnosis results from a feature set of rotating machinery are still a problem. To this end, this paper proposes an effective method based on a weighted extreme learning machine (WELM) with wavelet packet decomposition (WPD) and kernel principal component analysis (KPCA). The feature set affecting classification accuracy can be obtained using WPD and KPCA. By taking feature reliability into consideration, a new type of improvement to the extreme learning machine (ELM), i.e., WELM, is proposed by associating the hidden layer and input layer with a weight matrix. The WELM model can help in guaranteeing a quick and an accurate identification of fault status. To verify the superiority of the fault identification speed and accuracy of the proposed method, results from other methods, namely, using the sensitive features based on WPD and KPCA with ELM, a back-propagation neural network, and a support vector machine, were compared. The experimental results indicate that the proposed method can effectively improve the accuracy and quickly diagnose the fault. The average accuracy of fault classification could reach 95.45%, and the computation time of WELM was only 0.0156 s.

For cross-domain fault diagnosis of rolling bearing, the method of how to find and select similar features between the source and target domains is still a key problem. Toward this end, this study proposes a novel cross-domain fault diagnosis method using similar features-based transfer. Specifically, modified composite multi-scale fuzzy entropies are firstly extracted from the source domain and target domain respectively. Subsequently, minimum redundancy maximum relevance is used to select the discriminative features from the source domain. Based on these discriminative features, the Kullback-Liebler divergence is applied to search the useful features in the target domain. Finally, the K nearest neighbor classifier is used to learn the discriminative features from the source domain and classify the unlabeled samples in the target domain. Experimental results demonstrated that the proposed method can successfully achieve cross-domain fault diagnosis for the rolling bearing under different speed conditions or with different types of damages.

Fault diagnosis methods based on dimensionless indicators have long been studied for rotating machinery. However, traditional dimensionless indicators frequently suffer a low accuracy of fault diagnosis for nonlinear and non-stationary dynamic signals of rotating machinery. In this paper, we propose an effective fault diagnosis method based on multi-scale dimensionless indicator (MSDI) and random forests. In the proposed method, the real-time vibration signals are first processed by the variational mode decomposition and then six types of MSDI are constructed based on the decomposed signals. Through utilizing the Fisher criterion, several top ranked MSDIs are selected as fault features. Based on the selected MSDIs, the random forests model is applied to determine fault types. To verify the superiority of the proposed method, several experiments on fault diagnosis are conducted on a centrifugal multi-level impeller blower. The results demonstrate that the proposed method can successfully identify different fault types and the average accuracy can reach 95.58%. In contrast with traditional dimensionless indicators based methods, the proposed method can improve the fault diagnosis accuracy by 7.25% and outperforms other techniques such as back propagation neural network, support vector machine and extreme learning machine. These results indicate that the MSDI can effectively solve the deficiency of the traditional dimensionless indicator, and has stronger distinguishing ability for the fault types.

Remaining useful life (RUL) prediction can provide early warnings of failure and has become a key component in the prognostics and health management of systems. Among the existing methods for RUL prediction, the Wiener-process-based method has attracted great attention owing to its favorable properties and flexibility in degradation modeling. However, shortcomings exist in methods of this type; for example, the degradation indicator and the first predicting time (FPT) are selected subjectively, which reduces the prediction accuracy. Toward this end, this paper proposes a new approach for predicting the RUL of rotating machinery based on an optimal degradation indictor. First, a genetic programming algorithm is proposed to construct an optimal degradation indicator using the concept of FPT. Then, a Wiener model based on the obtained optimal degradation indicator is proposed, in which the sensitivities of the dimensionless parameters are utilized to determine the FPT. Finally, the expectation of the predicted RUL is calculated based on the proposed model, and the estimated mean degradation path is explicitly derived. To demonstrate the validity of this model, several experiments on RUL prediction are conducted on rotating machinery. The experimental results indicate that the method can effectively improve the accuracy of RUL prediction.

Along with the continuous development of science and technology, the structures of rotating machinery become to be larger scale and more complicated, which results in higher probability of concurrent fault under actual working conditions. In order to achieve concurrent fault diagnosis for rotating machinery, an integrated method using artificial immune algorithm and evidence theory is proposed in this research work. The self-nonself recognition mechanism of artificial immune system for data analysis and processing has been derived from the negative selection algorithm. Five kinds of dimensionless immune detectors are generated based on negative selection algorithm, then the local diagnosis result of dimensionless immune detector is gotten. Combining with evidence theory fusion rules, the final diagnosis can be obtained. Experimental result demonstrates that the method can realize effectively concurrent fault diagnosis for rotating machinery.

Aiming at how to use the multiple fault features information synthetically to improve accuracy of compound fault diagnosis, an information fusion method based on the weighted evidence theory was proposed to effectively diagnose compound faults of rotating machinery. Firstly multiple fault features were extracted by the genetic programming. Each fault feature was separately used to act as evidence and the initial diagnosis accuracy was regarded as the weight coefficient of the evidence. Then through the negative selection algorithm, the diagnosis ability of the local diagnosis was advanced and an impersonal means of obtaining basic probability assignment was given. Finally the fusion result was obtained by utilizing the weighted evidence theory into the decision-making information fusion for the preliminary result. By comparing the diagnosis results with other artificial intelligence algorithm, experiment result indicates that using multiple weighted evidences fusion can improve the diagnostic accuracy of compound fault.

Real-time and accuracy fault diagnosis is the key technique to realize timely effective maintenance and health management for rotating machinery, most faults of which are compound under actual working conditions. Many compound faults are coupled with each other, fuzzy, object and some complex characteristics so it is a bottleneck problem which is very tough to break through in fault diagnosis field. Early research results indicate that diagnosis with dimensionless parameters have got good effects in single fault for rotating machinery, but under simulating actual working state of compound faults, there are obvious overlap in ranges of dimensionless parameters calculated by vibration monitoring data of each compound faults, that is to say, it is hard to distinguish the ranges of dimensionless parameters of each fault, causing complexity of diagnosis rise, and the existing method is hard to deal with this problem. To solve the difficult problem, an online fusion fault diagnosis method for rotating machinery based on dimensionless immune detector and evidence reasoning (ER) is proposed. Experimental result demonstrates that the method can realize effectively real-time fault diagnose for rotating machinery and has high potential applications in real project.

In this paper, an approach to apply genetic programming in combination with dimensionless parameter of time domain is proposed. According to this approach, new dimensionless parameter is constructed. The effectiveness of the new dimensionless parameter is validated by an illustrative experiment. Experimental result shows that the classification ability of new dimensionless parameter is better than that of existing ones.