Intelligent Machinery Fault Diagnosis Research Articles

Deep forest based intelligent fault diagnosis of hydraulic turbine

Deep neural networks (DNNs) for intelligent machinery fault diagnosis require a large amount of training data, powerful computational facilities and have many hyper-parameters that have to be carefully tuned to ensure maximum performance. Deep forest, as a novel alternative to the deep learning framework, has the potential to overcome these shortcomings. In this study, a deep forest-based end-to-end intelligent fault diagnosis method is proposed for hydraulic turbine, in which multi-grained scanning is first used to transform fault feature representations from raw data and enhance fault feature learning ability, and then cascade structure is constructed with different types of random forests to learn fault features level by level and classify faults. The effectiveness of the proposed method is validated using the experimental dataset under twelve conditions, and its practicability is validated using a simulated dataset generated by adding white Gaussian noise to raw experimental signals. The results show that the proposed method is able to adaptively mine available fault features from measured signals, and its diagnosis accuracy is better than that obtained by existing methods. More importantly, the proposed method has better robustness to noise and is less limited to the number of training data.

Feature selection tree for automated machinery fault diagnosis

Intelligent machinery fault diagnosis commonly utilises statistical features of sensor signals as the inputs for its machine learning algorithm. Due to the abundance of statistical features that can be extracted from raw signals and the accuracy of inserting all the available features into the machine learning algorithm for machinery fault classification, less accurate fault classification may inadvertently result due to overfitting issues. It is therefore only by selecting the most representative features that overfitting outcomes can be avoided and classification accuracy be improved. Currently, the genetic algorithm (GA) is regarded as the most commonly used and reliable feature selection tool for the improvement of accuracy for any machine learning algorithm. However, the greatest challenge for GA is that it may fall into a local optima and be computationally demanding. To overcome this limitation, a feature selection tree (FST) is here proposed. Numerous experimental dataset feature selections were executed using FST and GA; their performance is compared and discussed. Analysis showed that the proposed FST resulted in identical or superior optimal feature subsets when compared to the renowned GA method, but with a 20-time faster simulation period. The proposed FST is therefore more efficient in performing feature selection task than GA.

Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation

Intelligent machinery fault diagnosis system has been receiving increasing attention recently due to the potential large benefits of maintenance cost reduction, enhanced operation safety and reliability. This paper proposes a novel deep learning method for rotating machinery fault diagnosis. Since accurately labeled data are usually difficult to obtain in real industries, data augmentation techniques are proposed to artificially create additional valid samples for model training, and the proposed method manages to achieve high diagnosis accuracy with small original training dataset. Two augmentation methods are investigated including sample-based and dataset-based methods, and five augmentation techniques are considered in general, i.e. additional Gaussian noise, masking noise, signal translation, amplitude shifting and time stretching. The effectiveness of the proposed method is validated by carrying out experiments on two popular rolling bearing datasets. Fairly high diagnosis accuracy up to 99.9% can be obtained using limited training data. By comparing with the latest advanced researches on the same datasets, the superiority of the proposed method is demonstrated. Furthermore, the diagnostic performance of the deep neural network is extensively evaluated with respect to data augmentation strength, network depth and so forth. The results of this study suggest that the proposed intelligent fault diagnosis method offers a new and promising approach.

Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization

Abstract Deep learning has attracted attentions in intelligent fault diagnosis of machinery because it allows a deep network to accomplish the tasks of feature learning and fault classification automatically. Among deep learning models, convolutional neural networks (CNNs) are able to learn features from mechanical vibration signals and thus several studies have applied CNNs in intelligent fault diagnosis of machinery. However, these studies suffer from the following weaknesses. (1) The imbalanced distribution of machinery health conditions is not considered. (2) What CNNs have learned is not clear. Therefore, in this paper, a framework called deep normalized convolutional neural network (DNCNN) is proposed for imbalanced fault classification of machinery to overcome the first weakness. Meanwhile, neuron activation maximization (NAM) algorithm is developed to handle the second weakness. To verify the proposed methods, three bearing datasets containing single faults and compound faults are constructed with different imbalanced degrees. The classification accuracies of the three datasets demonstrate that DNCNN is able to deal with the imbalanced classification problem more effectively than the commonly used CNNs. By analyzing the kernels of the convolutional layers of DNCNN via NAM algorithm, we find that these kernels act as filters and they become complex when the layers go deeper. This result may help us understand what DNCNN has learned in intelligent fault diagnosis of machinery.

Adaptive machinery fault diagnosis based on improved shift-invariant sparse coding

In machinery fault diagnosis, it is common that one kind of fault may correspond to several conditions, these conditions may contain different loads, different speeds and so on. When using conventional intelligent machinery fault diagnosis methods on diagnosing this kind of faults, if only one condition among all of these conditions was trained, when using this trained classifier for diagnosing fault which containing all conditions, it would obtain a classification result with higher error, it is the problem of robustness; but if we train all these data in each condition, the robustness can be improved a lot, but the time would be wasted. In order to balance these two aspects of fault diagnosis which seem contradict with each other, someone proposed a new method which based on shift-invariant sparse coding (SISC) method, this method can learn features from each condition of the same fault, and these features are adaptive to other conditions, which solve the first problem, but time efficiency of this algorithm is lower, in this paper, by improving the efficiency of shift-invariant sparse coding, we can reduce a lot of time on learning features. Through the experiment testing, it showed that this new method proposed in this paper produced better performance than SISC algorithm.