1. Signal and information processing for sensing systems, Institute for Bioengineering of Catalonia (IBEC), Barcelona, Spain.
2. School of Measurements and Communication Engineering, Harbin University of Science and Technology, Harbin, China.
Dr. Yinsheng Chen
1. Signal and information processing for sensing systems, Institute for Bioengineering of Catalonia (IBEC), Barcelona, Spain.
2. School of Measurements and Communication Engineering, Harbin University of Science and Technology, Harbin, China.
Because of the low accuracy of the current machine olfactory algorithms in detecting two mixed gases, this study proposes a hybrid gas detection algorithm based on an extreme random tree to greatly improve the classification accuracy and time efficiency. The method mainly uses the dynamic time warping algorithm (DTW) to perform data pre-processing and then extracts the gas characteristics from gas signals at different concentrations by applying a principal component analysis (PCA). Finally, the model is established by using a new extreme random tree algorithm to achieve the target gas classification. The sample data collected by the experiment was verified by comparison experiments with the proposed algorithm. The analysis results show that the proposed DTW algorithm improves the gas classification accuracy by 26.87%. Compared with the random forest algorithm, extreme gradient boosting (XGBoost) algorithm and gradient boosting decision tree (GBDT) algorithm, the accuracy rate increased by 4.53%, 5.11% and 8.10%, respectively, reaching 99.28%. In terms of the time efficiency of the algorithms, the actual runtime of the extreme random tree algorithm is 66.85%, 90.27%, and 81.61% lower than that of the random forest algorithm, XGBoost algorithm, and GBDT algorithm, respectively, reaching 103.2568 s.
To improve the fault identification accuracy of rolling bearing and effectively analyze the fault severity, a novel rolling bearing fault diagnosis and severity analysis method based on the fast sample entropy, the wavelet packet energy entropy, and a multiclass relevance vector machine is proposed in this paper. A fast sample entropy calculation method based on a kd tree is adopted to improve the real-time performance of fault detection in this paper. In view of the non-linearity and non-stationarity of the vibration signals, the vibration signal of the rolling bearing is decomposed into several sub-signals containing fault information by using a wavelet packet. Then, the energy entropy values of the sub-signals decomposed by the wavelet packet are calculated to generate the feature vectors for describing different fault types and severity levels of rolling bearings. The multiclass relevance vector machine modeled by the feature vectors of different fault types and severity levels is used to realize fault type identification and a fault severity analysis of the bearings. The proposed fault diagnosis and severity analysis method is fully evaluated by experiments. The experimental results demonstrate that the fault detection method based on the sample entropy can effectively detect rolling bearing failure. The fault feature extraction method based on the wavelet packet energy entropy can effectively extract the fault features of vibration signals and a multiclass relevance vector machine can identify the fault type and severity by means of the fault features contained in these signals. Compared with some existing bearing rolling fault diagnosis methods, the proposed method is excellent for fault diagnosis and severity analysis and improves the fault identification rate reaching as high as 99.47%.
As a typical machine olfactory system index, the accuracy of hybrid gas identification and concentration detection is low. This paper proposes a novel hybrid gas identification and concentration detection method. In this method, Kernel Principal Component Analysis (KPCA) is employed to extract the nonlinear mixed gas characteristics of different components, and then K-nearest neighbour algorithm (KNN) classification modelling is utilized to realize the recognition of the target gas. In addition, this method adopts a multivariable relevance vector machine (MVRVM) to regress the multi-input nonlinear signal to realize the detection of the concentration of the hybrid gas. The proposed method is validated by using CO and CH4 as the experimental system samples. The experimental results illustrate that the accuracy of the proposed method reaches 98.33%, which is 5.83% and 14.16% higher than that of principal component analysis (PCA) and independent component analysis (ICA), respectively. For the hybrid gas concentration detection method, the CO and CH4 concentration detection average relative errors are reduced to 5.58% and 5.38%, respectively.
The k-nearest neighbour (kNN) rule, which naturally handles the possible non-linearity of data, is introduced to solve the fault detection problem of gas sensor arrays. In traditional fault detection methods based on the kNN rule, the detection process of each new test sample involves all samples in the entire training sample set. Therefore, these methods can be computation intensive in monitoring processes with a large volume of variables and training samples and may be impossible for real-time monitoring. To address this problem, a novel clustering-kNN rule is presented. The landmark-based spectral clustering (LSC) algorithm, which has low computational complexity, is employed to divide the entire training sample set into several clusters. Further, the kNN rule is only conducted in the cluster that is nearest to the test sample; thus, the efficiency of the fault detection methods can be enhanced by reducing the number of training samples involved in the detection process of each test sample. The performance of the proposed clustering-kNN rule is fully verified in numerical simulations with both linear and non-linear models and a real gas sensor array experimental system with different kinds of faults. The results of simulations and experiments demonstrate that the clustering-kNN rule can greatly enhance both the accuracy and efficiency of fault detection methods and provide an excellent solution to reliable and real-time monitoring of gas sensor arrays.
26 September 2024 in Measurement Science and Technology
In recent years, research on the intelligent fault diagnosis of rotating machinery has made remarkable progress, bringing considerable economic benefits to industrial production. However, in the industrial environment, the accuracy and stability of the diagnostic model face severe challenges due to the extremely limited fault data. Data augmentation methods have the capability to increase both the quantity and diversity of data without altering the key characteristics of the original data, which is particularly important for the development of intelligent fault diagnosis of rotating machinery under limited data conditions (IFD-RM-LDC). Despite the abundant achievements in research on data augmentation methods, there is a lack of systematic reviews and clear future development directions. Therefore, this paper systematically reviews and discusses data augmentation methods for IFD-RM-LDC. Firstly, existing data augmentation methods are categorized into three groups: synthetic minority over-sampling technique (SMOTE)-based methods, generative model-based methods, and data transformation-based methods. Then, these three methods are introduced in detail and discussed in depth: SMOTE-based methods synthesize new samples through a spatial interpolation strategy; generative model-based methods generate new samples according to the distribution characteristics of existing samples; data transformation-based methods generate new samples through a series of transformation operations. Finally, the challenges faced by current data augmentation methods, including their limitations in generalization, real-time performance, and interpretability, as well as the absence of robust evaluation metrics for generated samples, have been summarized, and potential solutions to address these issues have been explored.