Search

Metro stray currents flowing into transformer-neutral points cause the high neutral DC and a transformer to operate in the DC bias state.Because neutral DC caused by stray current varies with time, the neutral DC value cannot be used as the only characteristic indicator to evaluate the DC bias risk level. Thus, unified characteristic extraction and assessment methods are proposed to evaluate the DC bias risk of a transformer caused by stray current, considering the signals of transformer-neutral DC and vibration. In the characteristic extraction method, the primary characteristics are obtained by comparing the magnitude and frequency distributions of transformer-neutral DC and vibration with and without metro stray current invasion. By analyzing the correlation coefficients, the final characteristics are obtained by clustering the primary characteristics with high correlation. Then, the magnitude and frequency characteristics are extracted and used as indicators to evaluate the DC bias risk. Moreover, to avoid the influence of manual experience on indicator weights, the entropy weight method (EWM) is used to establish the assessment model. Finally, the proposed methods are applied based on the neutral DC and vibration test data of a certain transformer. The results show that the characteristic indicators can be extracted, and the transformer DC bias risk can be evaluated by using the proposed methods. [ABSTRACT FROM AUTHOR]

To solve the difficulty in correctly identifying a compound fault of rolling bearing, a method combining variational mode decomposition (VMD) and harmonic fusion vector bispectrum (HFVB) is proposed. Firstly, to achieve adaptive decomposition of signals, the characteristic ability of envelope entropy to represent signal sparsity is utilized. By employing the minimum envelope entropy as the fitness function for the sparrow search algorithm (SSA), the decomposition levels and penalty factors of VMD are adaptively determined. Secondly, root-mean-square value is treated as fault feature index to self-adaptively choose from intrinsic mode function (IMF) which can embody fault features of bearings. Thirdly, to further highlight fault features, HFVB is used to blend chosen IMFs. Finally, faults of bearings were recognized with spectrum of signals. To verify the effectiveness of proposed method, an analysis was given to vibration signals in different situations, and SSA-VMD-HFVB was compared with classical method. The results demonstrate that the proposed SSA-VMD-HFVB method facilitates the adaptive decomposition of VMD, enabling the selection and effective integration of sensitive fault component signals. This approach enhances the accuracy of complex fault diagnosing in rolling bearings. [ABSTRACT FROM AUTHOR]

Liquor has a complex system with high dimensional components. The trace components in liquor are varied and have low content and complex coordination relationships. This study aimed to solve the problem of reliance on smell and taste. Based on the characteristics of near-infrared spectrum response to hydrogen-containing groups, qualitative analysis was carried out in combination with machine learning technology. Firstly, an iterative adaptive weighted penalized least squares algorithm with spectral peak discrimination was used for baseline correction to effectively retain useful information in the feature absorption peaks. Then, the convolution smoothing algorithm was used to filter the noise, and the spectral curve smoothness was adjusted using the convolution window width. The near-infrared spectrum has a high dimension. Monte Carlo random sampling combined with an improved competitive adaptive reweighting method was used to evaluate the importance of spectral sampling points. According to the importance coefficient, the dimension of the spectral data set was optimized by using an exponential attenuation function through an iterative operation, and the data set with the smallest root-mean-square error was taken as the characteristic spectrum. The nonlinear separability of characteristic spectra was further improved by kernel principal component analysis. Finally, a liquor quality recognition model based on principal component analysis was established by using the hierarchical multiclass support vector machine method. Our key findings revealed that the prediction accuracy of the model reached 96.87% when the number of principal components was 5–12, with more than 95% of the characteristic information retained. These results demonstrated that this rapid nondestructive testing method resolved the challenge posed by relying on subjective sensory evaluation for liquor analysis. The findings provide a reliable analytical approach for studying substances with high-dimensional component characteristics. [ABSTRACT FROM AUTHOR]

In scenarios involving photovoltaic power generation and electrical dynamic loads, complex electricity metering signals often exhibit strong randomness and rapid fluctuations. These characteristics frequently lead to substantial errors in electricity metering, thereby affecting fair and equitable energy transactions. This paper presents a novel modal decomposition theory in the run-length domain. Such a theory is developed to map signals from the amplitude domain to run sequences in the run-length domain. Subsequently, it decomposes signals into a quasi-steady, slowly varying mode, and another dynamic, rapidly fluctuating mode, facilitating the extraction of sensitive characteristics over prolonged durations. Furthermore, the paper proposes characteristics representation method for complex electricity metering signals by constructing parameters and characteristic functions in the run-length domain. Additionally, the paper specifically extracts sensitive characteristics for photovoltaic complex electricity metering signals using the modal decomposition theory in the run-length domain. Finally, experimental validation is conducted to elucidate the impact of these sensitive characteristics on electricity meter errors with the maximum dynamic error observed at −15.53%.

Evaluating typical rural characteristics reveals certain advantages of rural revitalization and is crucial for understanding rural disparities and promoting development. Field research and statistical data can reflect the spatial distribution of local resources and development models. However, due to cost limitations and statistical constraints, it is impossible to effectively compare and evaluate the characteristics of rural development at the long time series, large scale and fine granularity required for sustainable regeneration. This study proposes a web-based method for the extraction and evaluation of rural revitalization characteristics (WERRC). The BERT-BiLSTM-Attention model categorizes rural web texts according to five themes: industrial prosperity, ecological livability, rural civilization, effective governance, and prosperous life. The Term Frequency-Inverse Document Frequency (TF-IDF) algorithm extracts rural characteristics, and the relative advantages of these features are compared among 100 Chinese villages. WERRC extracts the typical characteristics, obtains the spatial distribution and relative advantage, and then ranks them according to the five themes. The relationship between national policy guidance and rural development is explored. The results support further exploration of differentiated, high-quality development modes that incorporate rural advantages into policy, adjust industrial structure, and optimise revitalization strategies at the rural scale. [ABSTRACT FROM AUTHOR]

To address issues relating to the advantages of varieties of sorghum in construction, breeding, and brewing of the seed repository, a visible–near-infrared hyperspectral imaging (VNIR-HSI) non-destructive technique was proposed to detect different varieties of sorghum. The VNIR-HSI system was used to collect spectrum images for 27 types of varieties of sorghum, and the spectral data were pre-processed using Savitzky–Golay (S–G) smoothing filters, the standard normal variate (SNV), and multiplicative scatter correction (MSC). Competitive adaptive reweighted sampling (CARS) was used for dimensionality reduction. Based on full-spectrum and characteristic spectral data, classification models were developed using a random forest (RF) algorithm. The tested results indicated that precisions of calibration and prediction sets of the RF model established based on the full-spectrum reach 94.58% and 64.44%, respectively. The CARS algorithm was adopted to extract 20 characteristic wavelengths from sorghum spectra. The precisions of the calibration and prediction sets for the CARS-RF model reach 95.00% and 84.07%, respectively. Using the confusion matrix to calculate Cohen's kappa values, the calibration and prediction Cohen's kappa values for the full sample were 0.9212 and 0.9231 respectively, indicating that the evaluation results are almost identical to the correctness results. The applied model can achieve favorable effects when detecting each cultivar of sorghum. The results show that the modeling method integrating VNIR-HSI technique with CARS-RF can provide a rapid non-destructive testing method for detection of varieties of sorghum, and offer an idea for detecting cultivars of coarse cereal crops. [ABSTRACT FROM AUTHOR]

Metro stray currents flowing into transformer-neutral points cause the high neutral DC and a transformer to operate in the DC bias state.Because neutral DC caused by stray current varies with time, the neutral DC value cannot be used as the only characteristic indicator to evaluate the DC bias risk level. Thus, unified characteristic extraction and assessment methods are proposed to evaluate the DC bias risk of a transformer caused by stray current, considering the signals of transformer-neutral DC and vibration. In the characteristic extraction method, the primary characteristics are obtained by comparing the magnitude and frequency distributions of transformer-neutral DC and vibration with and without metro stray current invasion. By analyzing the correlation coefficients, the final characteristics are obtained by clustering the primary characteristics with high correlation. Then, the magnitude and frequency characteristics are extracted and used as indicators to evaluate the DC bias risk. Moreover, to avoid the influence of manual experience on indicator weights, the entropy weight method (EWM) is used to establish the assessment model. Finally, the proposed methods are applied based on the neutral DC and vibration test data of a certain transformer. The results show that the characteristic indicators can be extracted, and the transformer DC bias risk can be evaluated by using the proposed methods.

Liquor has a complex system with high dimensional components. The trace components in liquor are varied and have low content and complex coordination relationships. This study aimed to solve the problem of reliance on smell and taste. Based on the characteristics of near-infrared spectrum response to hydrogen-containing groups, qualitative analysis was carried out in combination with machine learning technology. Firstly, an iterative adaptive weighted penalized least squares algorithm with spectral peak discrimination was used for baseline correction to effectively retain useful information in the feature absorption peaks. Then, the convolution smoothing algorithm was used to filter the noise, and the spectral curve smoothness was adjusted using the convolution window width. The near-infrared spectrum has a high dimension. Monte Carlo random sampling combined with an improved competitive adaptive reweighting method was used to evaluate the importance of spectral sampling points. According to the importance coefficient, the dimension of the spectral data set was optimized by using an exponential attenuation function through an iterative operation, and the data set with the smallest root-mean-square error was taken as the characteristic spectrum. The nonlinear separability of characteristic spectra was further improved by kernel principal component analysis. Finally, a liquor quality recognition model based on principal component analysis was established by using the hierarchical multiclass support vector machine method. Our key findings revealed that the prediction accuracy of the model reached 96.87% when the number of principal components was 5–12, with more than 95% of the characteristic information retained. These results demonstrated that this rapid nondestructive testing method resolved the challenge posed by relying on subjective sensory evaluation for liquor analysis. The findings provide a reliable analytical approach for studying substances with high-dimensional component characteristics.

The fault diagnosis method of planetary gearbox based on machine learning relies on the artificial selection of the eigenvectors. The quality of eigenvectors selection largely determines the accuracy of the diagnosis method. The convolutional neural network (CNN) can extract characteristics automatically. But it is difficult to accurately diagnose the fault from a single vibration signal when it is used for the planetary gearbox fault diagnosis. To solve the above problems, a fault diagnosis method of planetary gearbox based on multi-information fusion and CNN is proposed. The method performs data layer fusion on three-dimensional (horizontal radial direction, vertical radial direction and axial direction) vibration signals and sound signals of the planetary gearbox. The one-dimensional vibration signals and sound signals are integrated into two-dimensional signals in a parallel connection mode. The two-dimensional signals are used as the input of CNN. The multiple convolutional layers and maximum pooling layers are used for depth characteristic extraction and information filtering. Finally, the Softmax classifier is used to achieve fault classification. The fault diagnosis experiment platform of the planetary gearbox is built. The vibration signals and sound signals of normal and fault states of the planetary gearbox under different speed and load conditions are collected and input into CNN for training and verification. Four single-source information of horizontal radial vibration signal, vertical radial vibration signal, axial vibration signal and sound signal are selected under the same conditions and combined with CNN respectively for comparison. The experiment is used to verify the superiority of the fault diagnosis method for planetary gearbox based on multi-information fusion and CNN. The experimental results show that the fault identification accuracy of the two methods of axial vibration signal+CNN and sound signal+CNN is 74.07% and 75.13% respectively. The fault identification accuracy of the two methods of horizontal radial vibration signal+CNN and vertical radial vibration signal+CNN is 89.70% and 87.09% respectively. The method based on multi-information fusion and CNN has the fastest convergence speed and the highest fault identification accuracy, which is 93.33%.

In coal mine, the dust concentration is high and the illumination is low. The image acquisition quality and characteristic extraction effect are greatly affected by dust concentration. However, the camera parameters and image processing parameters cannot be adjusted adaptively according to the change of dust concentration. Therefore, it is easy to cause problems such as unstable point-line characteristic extraction and image frame loss. In order to solve the above problems, the position and posture measurement system for boom-type roadheader based on machine vision is improved. The mine-used explosion-proof industrial camera is used to collect the laser point-line images under different dust concentrations. The relationship model between the image gray value and the dust concentration level is established through the transmittance. The optimal camera parameters and image processing parameters under different dust concentration levels are obtained through experiments. A parameter adaptive adjustment algorithm is proposed, and the parameter values are adjusted adaptively according to the dust concentration levels. Therefore, the image collection quality and the stability and precision of the point-line characteristic extraction are improved. Moreover, the precision of position and posture measurement system for roadheader based on machine vision is improved. The experimental result show that the average measurement errors in X, Y and Z directions of the improved vision detection system for boom-type roadheader are 28.26 mm, 30.58 mm and 22.54 mm respectively. The number of usable images is increased from 75 to 90 after processing 100 images. These results show that the parameter adaptive adjustment algorithm can effectively improve the precision of image characteristic extraction and the data availability. The algorithm ensures the precision and stability of position and posture measurement system for boom-type roadheader based on machine vision.

The wire rope damage signal is a kind of non-stationary and non-periodic impact signal, and the noise reduction processing and characteristic extraction of its characteristic signal become difficult problems to be solved urgently. If the wavelet base or decomposition layer number of wavelet transform method is not suitable, which will introduce other noise interference while reducing signal noise, and affect the effect of signal processing and characteristic extraction. Compared with the wavelet transform, the moving average method only needs to select a certain shift window width to achieve effective noise reduction, but the shift window width needs to be selected artificially, and the blindness is large. In order to solve the above problems, a noise reduction method of wire rope damage signal under strong noise background is proposed. Different types of broken wire data are collected by magnetic flux leakage (MFL) sensor of wire rope, and strong Gaussian white noise is added to the signal to simulate the strong noise background. The adaptive moving average method is used to reduce the noise of the wire rope damage signal, and the quantum particle swarm optimization (QPSO) algorithm is used to optimize the window width of the moving average method. The signal-to-noise ratio (SNR) of the damage signal is used as the fitness function, and the SNR of damage characteristic signal is maximized by the QPSO algorithm, so as to achieve the optimal signal noise reduction effect. The experimental results show that compared with wavelet transform, the adaptive moving average method has more obvious noise reduction effect, higher signal-to-noise ratio and smoother signal for wire rope stationary and fluctuating signals under strong noise background. The measured results show that the noise reduction effect of the adaptive moving average method is also better than that of the wavelet transform for the wire rope damage signals with relatively weak noise on site, which verifies that the adaptive moving average method has good universality.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent year, the identification of characteristics of earthquake and explosion is one of the key technologies for earthquake event classification and recognition, and has made to a considerable development and progress. The overall review of existing identification and characteristic extraction method is carried out, in order to establish a platform for identification of characteristics of earthquake and explosion future researches.

Pedestrian detection is a key technology for unmanned driving in underground coal mine, which is affected by uneven illumination, complex background, infrared interference, dim light and small and dense targets in images, etc. The existing methods are not ideal for detecting pedestrians in underground mines. In order to solve the above problems, a multi-sensor fusion method for underground mine pedestrian detection is proposed. This method uses a step-by-step multi-characteristic fusion method to fuse the image characteristics collected by the visible light sensor, infrared sensor and depth sensor to obtain richer image characteristics. On the basis of RetinaNet, Dense connection is added to ResNet to form a Dense-ResNet with a hierarchical connected structure, which is able to extract the deep image characteristics from the multi-sensor fusion results and enhance the detection capability of small targets. The experimental results show that multi-sensor fusion images can obtain richer target characteristics compared with a single image, which is beneficial to improve the target detection accuracy. Compared with RetinaNet, Dense-RetinaNet can improve the accuracy of multi-target and small target detection.

The growth and partial discharge (PD) characteristics of electrical tree in crosslinked polyethylene (XLPE) needle-plate electrode samples are investigated under constant dc voltage at different temperatures. The results reveal that under the experimental conditions, the electrical trees are all branch trees, and the discharge intensity fluctuates with time. The increase in temperature promotes the growth of electrical tree as well as the intensity of PD. Five texture features of PD ${q}$ - ${t}$ histogram are extracted and used as the elements to evaluate the insulation status of XLPE needle-plate electrode under dc voltage based on the gray correlation degree. The area ratio and lateral tree ratio of electrical tree is extracted based on the gray histogram. The lateral tree ratio increases with the increase in temperature, which is closely related to the intensity of PD. Gray correlation theory is used to evaluate the status of XLPE insulation. The results reveal that the evaluated insulation statuses based on the gray correlation degree are the same as those based on experience, which indicates that the proposed diagnosis method of XLPE insulation status based on the gray correlation degree with ${q}$ - ${t}$ histogram texture features as elements has a high accuracy. [ABSTRACT FROM AUTHOR]

Intelligent identification of personnel in underground video monitoring in coal mines is of great significance for improving the efficiency of personnel supervision and reducing the occurrence of safety accidents. Affected by the complex underground environment and the performance limitations of monitoring video equipment, the underground video monitoring images have problems such as low resolution, occlusion and background interference, resulting in small differences among underground personnel and low accuracy of personnel re-identification. In order to solve the above problems, a network structure based on distance metric and channel attention is proposed. The structure is used for personnel re-identification in complex underground environments. In order to solve the problem that it is not easy to distinguish personnel from background in monitoring images, a channel attention module is introduced into the backbone network to make it pay more attention to the foreground characteristics of personnel and suppress the background information. Moreover, the size of the characteristic map output from the last layer of the backbone network is doubled so as to obtain more fine-grained characteristics, enrich the characteristic information of personnel and enhance the network's ability to learn characteristics. On the basis of realizing the classification of personnel with different identities, using the absolute distance information between the images of personnel, the distance metric module is used to sample and weight the personnel images who are difficult to identify, increase the weight of the difficult samples in the back propagation, and make the network pay more attention to the discriminative personnel characteristics. The identity loss and distance metric loss are jointly used to optimize the characteristic layer, so that the network can extract more discriminative personnel characteristics to improve the re-identification accuracy. The Miner-CUMT data set is used to verify the proposed method for personnel re-identification in complex underground environments. The results show that the method can make full use of the key information of personnel with different identities in the underground, so that the identification network has stronger discrimination ability and improves the accuracy of personnel identification in the underground.

The existing manual detection method of bolt abnormality can only perform random inspection on a single bolt, cannot check the bolt abnormality comprehensively, and has low efficiency. When the bolt is abnormal, the exposed section of the bolt often changes in length or angle, or even falls off. According to the characteristics that the length and angle of the exposed section change when the bolt is abnormal, and taking the roadway inspection robot as a platform, a non-contact bolt abnormality detection method consisting of bolt image matching and extraction and bolt characteristic detection is designed based on machine vision technology. In the bolt image matching and extraction stage, perceptual hash algorithm is used to match the collected image with the original image, histogram equalization is used to achieve image enhancement, and YOLOv3 algorithm is used to locate and extract the bolt area. In the bolt characteristic detection stage, bilateral filtering and Canny edge detection algorithm are used to extract bolt image edge information, and line segment detection algorithm is used to extract straight line segments of bolt images. Combined with the characteristic that bolt contour can be regarded as a group of parallel lines, the method can achieve the length and angle characteristic extraction, and compare with the original image bolt characteristics to realize abnormality detection. The laboratory-made data set is used to conduct experiments on the rapid bolt abnormality detection method, and the results shows that the method can detect bolt abnormality quickly and accurately.

Metal magnetic memory testing (MMMT) is an effective nondestructive technique for fatigue damage monitoring of weldments because of its capacity for stress evaluation. An experimental investigation of the effect of the applied fatigue stress on MMMT signals, including the tangential component Bx and the normal component Bz, during tension–compression fatigue tests in welded joints was carried out systematically. The Bx and Bz signals at different fatigue cycles and fatigue stresses were collected and analyzed, and the results showed that there was a peak of Bx and abnormal peaks of Bz that existed at the welded joint before loading. After loading, the peak of Bx and the abnormal peaks of Bz reversed, and the Bx signals moved upward and the Bz signals rotated anticlockwise dramatically in the first few fatigue cycles. After the fatigue cycle number was larger than 1000, Bx and Bz were stable, with very little fluctuation. In addition, the characteristics of Bx signals, the mean value, and the peak value of the average of Bx had an extremely significant linear relationship with the applied fatigue stress during the stable stage of the fatigue test, which indicates that MMMT is a feasible method for fatigue stress evaluation and even residual fatigue life estimation for weldments in service. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Intrinsic time-scale decomposition and graph signal processing are combined to effectively identify a rotor–stator rubbing fault. The vibration signal is decomposed into mutually independent rotational components, and then, the Laplacian energy index is obtained by the graph signal of the autocorrelation function of rotational components, and the signal is reconstructed by an autocorrelation function of each proper rotation (PR) component relative to smaller Laplacian energy index (less complexity). Finally, characteristics are extracted from rotor–stator rubbing faults in an aeroengine according to square demodulation spectrum of a reconstructed signal. To validate the effectiveness of the algorithm, a comparative analysis is made among traditional intrinsic time-scale decomposition algorithm, combination of intrinsic time-scale decomposition and autocorrelation function, and the proposed intrinsic time-scale decomposition–graph signal processing algorithm. Comparative result shows that the proposed intrinsic time-scale decomposition–graph signal processing algorithm is more precise and effective than the traditional intrinsic time-scale decomposition and intrinsic time-scale decomposition and autocorrelation function algorithms in extracting characteristic frequency and frequency multiplication of rotor–stator rubbing faults and can greatly reduce the number of noise components irrelevant to faults. [ABSTRACT FROM AUTHOR]

When the traditional semantic segmentation network is used to segment the small coal dust particles, there are some problems such as easy loss of deep information and unclear detail extraction. In order to solve this problem, a coal dust image segmentation method based on improved DeepLabV3+ is proposed. DeepLabV3+ network model is improved in three aspects. ① In the encoder, the CA-MobileNetV3 lightweight module is used to replace Xception to achieve characteristic extraction and ensure more detailed and accurate characteristic extraction. ② The atrous rate is improved in the atrous spatial pyramid pooling(ASPP) module to make it more suitable for extracting small coal dust particles. ③ A global attention up-sample(GAU) module is introduced into the decoder to weight the low-level characteristic information when the calculation amount is small. And the high-level characteristic information is used to guide the low-level characteristic information to realize characteristic fusion. The GAU module uses a global up-sampling mechanism to replace the up-sampling mechanism of the decoder. The characteristic information of the coal dust particles is not attenuated after long-distance transmission. And the method is more conducive to capture the edge detail information of the coal dust particles. The experimental results show that the recall rate of the improved DeepLabV3+ network model on the coal dust data set is 90.26%, and the accuracy is 89.23%. Compared with other network models, the improved DeepLabV3+ network model can effectively enhance the learning ability of coal dust characteristics, obtain more detailed information, greatly shorten the training time, and has better segmentation effect on small targets.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

For the problem that rolling bearing fault characteristics are difficult to extract accurately and the fault diagnosis accuracy is not high, an unsupervised characteristic selection method of refined composite multiscale fluctuation-based dispersion entropy (RCMFDE) combined with self-paced learning and low-redundant regularization (SPLR) is proposed, for which the fault diagnosis is carried out by support vector machine (SVM) optimized by the marine predator algorithm (MPA). First, we extract the entropy characteristics of the bearings under different fault states by RCMFDE and the introduction of the fine composite multiscale coarse-grained method and fluctuation strategy improves the stability and estimation accuracy of the bearing characteristics; then, a novel dimensionality-reduction method, SPLR, is used to select better entropy characteristics, and the local flow structure of the fault characteristics is preserved and the redundancy is constrained by two regularization terms; finally, using the MPA-optimized SVM classifier by combining Levy motion and Eddy motion strategies, the preferred RCMFDE is fed into the MPA–SVM model for fault diagnosis, for which the obtained bearing fault diagnosis accuracy is 97.67%. The results show that the RCMFDE can effectively improve the stability and accuracy of the bearing characteristics, the SPLR-based low-dimensional characteristics can suppress the redundancy characteristics and improve the effectiveness of the characteristics, and the MPA-based adaptive SVM model solves the parameter randomness problem and, therefore, the proposed method has outstanding superiority.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Considering the difficulty in the diagnosis of compound faults in rolling bearings, the paper combines Intrinsic Time-scale Decomposition (ITD) and Singular Value Decomposition (SVD) for extracting the characteristics of compound faults from rolling bearings. Rotational components obtained from ITD decomposition are denoised according to Singular Value Decomposition algorithm; signal is reconstructed by denoised rotational components; at last, characteristics of compound faults of rolling bearings are extracted by Hilbert spectrum envelope of reconstructed signal. In validation, the paper has made a comparative study on the proposed ITD-SVD method and conventional one based on ITD algorithm and PCA method, and the result shows that ITD-SVD method works better on noise control and thereby provides more precise extraction of characteristic frequency of compound faults from rolling bearings of aero-engine. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Metal magnetic memory testing (MMMT) is an effective nondestructive technique for fatigue damage monitoring of weldments because of its capacity for stress evaluation. An experimental investigation of the effect of the applied fatigue stress on MMMT signals, including the tangential component Bx and the normal component Bz, during tension–compression fatigue tests in welded joints was carried out systematically. The Bx and Bz signals at different fatigue cycles and fatigue stresses were collected and analyzed, and the results showed that there was a peak of Bx and abnormal peaks of Bz that existed at the welded joint before loading. After loading, the peak of Bx and the abnormal peaks of Bz reversed, and the Bx signals moved upward and the Bz signals rotated anticlockwise dramatically in the first few fatigue cycles. After the fatigue cycle number was larger than 1000, Bx and Bz were stable, with very little fluctuation. In addition, the characteristics of Bx signals, the mean value, and the peak value of the average of Bx had an extremely significant linear relationship with the applied fatigue stress during the stable stage of the fatigue test, which indicates that MMMT is a feasible method for fatigue stress evaluation and even residual fatigue life estimation for weldments in service.

Quality identification of multi-component mixtures is essential for production process control. Artificial sensory evaluation is a conventional quality evaluation method of multi-component mixture, which is easily affected by human subjective factors, and its results are inaccurate and unstable. This study developed a near-infrared (NIR) spectral characteristic extraction method based on a three-dimensional analysis space and establishes a high-accuracy qualitative identification model. First, the Norris derivative filtering algorithm was used in the pre-processing of the NIR spectrum to obtain a smooth main absorption peak. Then, the third-order tensor robust principal component analysis (TRPCA) algorithm was used for characteristic extraction, which effectively reduced the dimensionality of the raw NIR spectral data. Finally, on this basis, a qualitative identification model based on support vector machines (SVM) was constructed, and the classification accuracy reached 98.94%. Therefore, it is possible to develop a non-destructive, rapid qualitative detection system based on NIR spectroscopy to mine the subtle differences between classes and to use low-dimensional characteristic wavebands to detect the quality of complex multi-component mixtures. This method can be a key component of automatic quality control in the production of multi-component products.

Copyright of Journal of Measurement Science & Instrumentation is the property of Journal of Measurement Science & Instrumentation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Prevention and treatment of diseases are critical to improve grape yield and quality. Automatic identification of grape diseases is important to prevent insect pests timely and effectively. This study proposed an automatic detection method for grape leaf diseases based on image analysis and back–propagation neural network (BPNN). The Wiener filtering method based on wavelet transform was applied to denoise the disease images. The grape leaf disease regions were segmented by Otsu method, and morphological algorithms were used to improve the lesion shape. Prewitt operator was utilized to extract the complete edge of lesion region. Five effective characteristic parameters, namely, perimeter, area, circularity, rectangularity, and shape complexity, were extracted. The proposed recognition model for grape leaf diseases based on BPNN could efficiently inspect and recognize five grape leaf diseases: leaf spot, Sphaceloma ampelinum de Bary, anthracnose, round spot, and downy mildew. Results indicated that the proposed detection system for grape leaf diseases could be used to inspect grape diseases with high classification accuracy. [ABSTRACT FROM AUTHOR]

Traditional automatic characteristic extraction technology of engine vibration signals for hybrid electric vehicles (HEV) only focuses on the analysis of engine vibration signals in time domain and frequency domain. Single time domain analysis or single frequency domain analysis cannot accurately analyse the vibration signals, while both time domain analysis and frequency domain analysis have cross-analysis. As a result, the analysis results are repetitive and conflicting, which makes it difficult to extract the characteristics of engine vibration signals. The final extraction accuracy is not high and the extraction efficiency is low. For this reason, an automatic characteristic extraction technology of HEV engine vibration signal based on wavelet packet energy analysis is proposed. Firstly, the mechanical vibration of engine is converted into corresponding voltage and current signals by various sensors and then converted into digital signals by A/D (analogue/digital) conditioner. The data of vibration signals are often mixed with various noises, which have a great impact on the final analysis of vibration signals. Data interception and pre-filtering are adopted. Wave, zero-mean, elimination of trend term and elimination of staggered points are used to pre-treat the vibration signals with mixed noise. Short-Time Fourier Transform (STFT) algorithm is introduced to analyse the pre-processed engine vibration signals and the fundamental properties of the non-stationary vibration signals in actual operation of the engine are obtained. The energy distribution of the analysed engine vibration signal is calculated by the wavelet packet energy analysis method. The calculated parameters of the energy distribution of the wavelet packet are taken as the characteristic parameters of the vibration signal. The vibration signal characteristics of the engine are automatically extracted. The experiment is carried out in the form of comparison with the traditional method. The experimental results show that the time-frequency joint analysis applied in the proposed technology can accurately analyse the essential characteristics of the engine vibration signal of HEV. The wavelet packet energy analysis method can ensure the extraction accuracy of the engine vibration signal characteristics. [ABSTRACT FROM AUTHOR]

• A new Mel feature fusion method has been extracted. • From the perspective of joint time–frequency processing, voiceprint slicing statistical features have been proposed, which effectively utilize time information and perform better than Mel features. This approach addresses the issue of insufficient time utilization in Mel feature extraction.This method fully utilizes the temporal information. • The two types of features proposed in this article demonstrated strong performance in both simulated and actual data processing. Mel-Frequency Cepstral Coefficients (MFCC) and its differential coefficients are widely used as a typical non-linear spectral envelope feature in passive sonar target recognition. MFCC emphasizes the frequency domain information at the low-frequency end of the target, while the differential coefficients add dynamic characteristics of MFCC in the time domain. However, the utilization of time information is not sufficient. In response to this issue, we propose two solutions: one is the characteristic fusion method of Weighted Mel-Frequency Cepstral Coefficient based on Bhattacharyya Distance (BD-WMFCC); the other is the characteristic extraction method of VoicePrint Slice Statistics (VPSS) based on time–frequency joint processing. BD-WMFCC combines weighted differential coefficients with MFCC using Bhattacharyya distance, maximizing the utilization of time information. VPSS is a linear spectral feature that utilizes the stability of the spectral intensity within a certain bandwidth over continuous time. It extracts the steady-state characteristics of the target's spectrum with respect to time changes at equidistant bandwidths. Simulation and real data analysis have shown that VPSS demonstrates outstanding separability and classification performance in both non-linear and linear spectral features, with strong stability. In practical data analysis, the accuracy of VPSS features under the AlexNet algorithm is 3.8 % and 5.7 % higher than the spectral (Fre) and Mel features, respectively. [ABSTRACT FROM AUTHOR]

When acoustic method is used in leak detection for natural gas pipelines, the external interferences including operation of compressor and valve, pipeline knocking, etc., should be distinguished with acoustic leakage signals to improve the accuracy and reduce false alarms. In this paper, the technologies of extracting characteristics of acoustic signals were summarized. The acoustic leakage signals and interfering signals were measured by experiments and the characteristics of time-domain, frequency-domain and time-frequency domain were extracted. The main characteristics of time-domain are mean value, root mean square value, kurtosis, skewness and correlation function, etc. The features in frequency domain were obtained by frequency spectrum analysis and power spectrum density, while time-frequency analysis was accomplished by short time Fourier transform. The results show that the external interferences can be removed effectively by the characteristics of time domain, frequency domain and time-frequency domain. It can be drawn that the acoustic leak detection method can be applied to natural gas pipelines and the characteristics can help reduce false alarms and missing alarms. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper puts forward one kind of behavioral characteristic extraction and detection method of malicious code based on semantic; it extracts the key behavior and dependence relations among behaviors by combining with stain spread analysis in command layer and semantic analysis in behavior layer. And then it uses anti-confusion engine identification semantic irrelevance and semantic equivalence behavior to obtain malicious code behavior characteristic with certain capacity of resisting disturbance, as well as realize characteristic extraction and detection on prototype system. It completes experimental demonstration on this system through analysis and detection on plenty of malicious code samples. The test result indicates that extraction characteristic based on the above methods has characteristic such as stronger capacity of resisting disturbance etc., detection based on this characteristic has better identification ability for malicious code. [ABSTRACT FROM AUTHOR]

Chatter affects the surface topography and functional performance of work pieces significantly. The surface topography of work pieces is multi-scale, and the characteristics of different levels of the surface topography are closely connected to the different functional performance of the work piece. The relationship between chatter vibration and surface micro-topography is complicated and not specified. By investigating and understanding this relationship clearly, the manufacturing process can be directed to be controlled more actively and accurately, which helps complete the product with expected surface topography and functional performance. This paper aims to reveal the effect of chatter on the surface micro-topography of gears in grinding. Grinding processes considering different machining states and surface topographies of gears under each process were analyzed comprehensively. The following findings were observed. First, chatter causes significant increase of the tooth flank surface roughness in low frequency and increase of the profile roughness, whereas in a different manner in the different gear flank directions. Second, the influence of chatter mainly concentrates on certain frequency bands of the surface topography, and the effect of chatter on the 3D surface topography is within a frequency range. Third, chatter vibration with its multi-frequency-band characteristics shows a multi-scale influence on the work piece surface topography. The possible mechanisms for the formation of these effects were also discussed. [ABSTRACT FROM AUTHOR]

A navel orange disease & pest image recognition algorithm based on convention neutral network is proposed. Firstly, characteristics of navel orange diseases & pests are described on the basis of various colors and forms of diseases & pests and their data are collected and extracted. Secondly, the Convolution Neutral Network (CNN) is described: i) input data are expressed in two-dimensional array and CNN operates in the input image window in the training and test stages, ii) the characteristics are observed by weight via the window in the input data, and iii) CNN training and recognition of navel orange disease & pest image are realized. Finally, the effectiveness of the method is verified by experiments. [ABSTRACT FROM AUTHOR]

In this paper, the author researched on the face recognition in color picture using the characteristic extraction based on the kernel algorithm. A variety of methods are proposed in the frame of the sparse representation and dictionary learning to improved algorithms, essentially, which is an extension for the sparse representation to study the problem of face recognition and under different conditions for imaging face. In fact, the sparse representation based classification model is the linear combination through training samples and has great reconstruction powers to represent unknown testing samples. [ABSTRACT FROM AUTHOR]

Target high resolution and fully polarimetric information is of important application in such fields as remote sensing, target classification, recognition and so on. In order to extract the one-dimensional fully polarimetric and high resolution of moving targets, fully polarimetric Orthogonal Frequency Diversion Multiplex (OFDM) waveform is designed, based on the principle of simultaneous polarization measurement scheme. Its signal processing algorithm is advanced. Firstly, the fully polarimetric OFDM transmitted and received signal models are established. Using the orthogonality of each sub-carriers, the coupling interference between different polarization channels can be eliminated. Then fully polarimetric MUSIC (P-MUSIC) algorithm is used to obtain target high resolution range profile and extract the fully polarimetric information of each scattering centers. Meanwhile, target movement effect on sub-carrier orthogonality is analyzed. Finally, simulations are performed using the measured data of a target model in anechoic chamber to verify the effectiveness of corresponding signal process, and its measurement performance is also simulated. This study here is of valuable reference for designing new polarimetric imaging radar system. [ABSTRACT FROM AUTHOR]

For the problem that rolling bearing fault characteristics are difficult to extract accurately and the fault diagnosis accuracy is not high, an unsupervised characteristic selection method of refined composite multiscale fluctuation-based dispersion entropy (RCMFDE) combined with self-paced learning and low-redundant regularization (SPLR) is proposed, for which the fault diagnosis is carried out by support vector machine (SVM) optimized by the marine predator algorithm (MPA). First, we extract the entropy characteristics of the bearings under different fault states by RCMFDE and the introduction of the fine composite multiscale coarse-grained method and fluctuation strategy improves the stability and estimation accuracy of the bearing characteristics; then, a novel dimensionality-reduction method, SPLR, is used to select better entropy characteristics, and the local flow structure of the fault characteristics is preserved and the redundancy is constrained by two regularization terms; finally, using the MPA-optimized SVM classifier by combining Levy motion and Eddy motion strategies, the preferred RCMFDE is fed into the MPA-SVM model for fault diagnosis, for which the obtained bearing fault diagnosis accuracy is 97.67%. The results show that the RCMFDE can effectively improve the stability and accuracy of the bearing characteristics, the SPLR-based low-dimensional characteristics can suppress the redundancy characteristics and improve the effectiveness of the characteristics, and the MPA-based adaptive SVM model solves the parameter randomness problem and, therefore, the proposed method has outstanding superiority.

Quality identification of multi-component mixtures is essential for production process control. Artificial sensory evaluation is a conventional quality evaluation method of multi-component mixture, which is easily affected by human subjective factors, and its results are inaccurate and unstable. This study developed a near-infrared (NIR) spectral characteristic extraction method based on a three-dimensional analysis space and establishes a high-accuracy qualitative identification model. First, the Norris derivative filtering algorithm was used in the pre-processing of the NIR spectrum to obtain a smooth main absorption peak. Then, the third-order tensor robust principal component analysis (TRPCA) algorithm was used for characteristic extraction, which effectively reduced the dimensionality of the raw NIR spectral data. Finally, on this basis, a qualitative identification model based on support vector machines (SVM) was constructed, and the classification accuracy reached 98.94%. Therefore, it is possible to develop a non-destructive, rapid qualitative detection system based on NIR spectroscopy to mine the subtle differences between classes and to use low-dimensional characteristic wavebands to detect the quality of complex multi-component mixtures. This method can be a key component of automatic quality control in the production of multi-component products. [ABSTRACT FROM AUTHOR]