Fault Diagnosis Method for Wind Turbine Gearbox Based on Ensemble-Refined Composite Multiscale Fluctuation-Based Reverse Dispersion Entropy.

The diagnosis of faults in wind turbine gearboxes based on signal processing represents a significant area of research within the field of wind power generation. This paper presents an intelligent fault diagnosis method based on ensemble-refined composite multiscale fluctuation-based reverse dispersion entropy (ERCMFRDE) for a wind turbine gearbox vibration signal that is nonstationary and nonlinear and for noise problems. Firstly, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and stationary wavelet transform (SWT) are adopted for signal decomposition, noise reduction, and restructuring of gearbox signals. Secondly, we extend the single coarse-graining processing method of refined composite multiscale fluctuation-based reverse dispersion entropy (RCMFRDE) to the multiorder moment coarse-grained processing method, extracting mixed fault feature sets for denoised signals. Finally, the diagnostic results are obtained based on the least squares support vector machine (LSSVM). The dataset collected during the gearbox fault simulation on the experimental platform is employed as the research object, and the experiments are conducted using the method proposed in this paper. The experimental results demonstrate that the proposed method is an effective and reliable approach for accurately diagnosing gearbox faults, exhibiting high diagnostic accuracy and a robust performance.

Research on transformer fault diagnosis method based on ACGAN and CGWO-LSSVM.

This paper proposes a transformer fault diagnosis method based on ACGAN and CGWO-LSSVM to address the problem of misjudgment and low diagnostic accuracy caused by the small number and uneven distribution of some fault samples in transformer fault diagnosis. Firstly, generate adversarial networks through auxiliary classification conditions, The ACGAN method expands a small and imbalanced number of samples to obtain balanced and expanded data; Secondly, the non coding ratio method is used to construct the characteristics of dissolved gases in oil, and kernel principal component analysis is used, KPCA method for feature fusion; Finally, using the improved cubic gray wolf optimization algorithm, CGWO for least square support vector machines, optimize the parameters of the LSSVM model and construct a transformer fault diagnosis model. The results show that the proposed method has a low false alarm rate and a diagnostic accuracy of 97.66%, compared to IGOA-LSSVM the IChOA-LSSVM and PSO-LSSVM methods improved accuracy by 0.12, 1.76, and 2.58%, respectively. This method has been proven to solve the problems of misjudgment and low diagnostic accuracy caused by small sample sizes and uneven distribution. It is suitable for multi classification fault diagnosis of transformer imbalanced datasets and is superior to other methods.

Development and validation of colorimetric-assisted chemometrics methods based on the localized gold nanoparticles surface plasmon resonance for fast simultaneous estimation of anti-hepatitis C virus drugs in their combined dosage form: A comparative study with HPLC method.

The present work describes a developed analytical method based on a colorimetric assay using gold nanoparticles (AuNPs) along with chemometric techniques for the simultaneous estimation of sofosbuvir (SOF) and ledipasvir (LED) in their synthetic mixtures and tablet dosage form. The applied chemometric approaches were continuous wavelet transform (CWT) and least squares support vector machine (LS-SVM). Characterization of AuNPs and AuNPs in combination with the drug was performed by UV-vis spectrophotometer, transmission electron microscopy (TEM), dynamic light scattering (DLS), and Fourier transform infrared (FTIR) spectroscopy. In the CWT method, the zero amplitudes were determined at 427 nm with Daubechies wavelet family for SOF (zero crossing point of LED) and 440 nm with Symlet wavelet family for LED (zero crossing point of SOF) over the concentration range of 7.5-90.0 µg/L and 40.0-100.0 µg/L with coefficients of determination (R2) of 0.9974 and 0.9907 for SOF and LED, respectively. The limit of detection (LOD) and limit of quantification (LOQ) of this method were found to be 7.92, 9.96 µg/L and 12.02, 30.2 µg/L for SOF and LED, respectively. In the LS-SVM model, the mean percentage recovery of SOF and LED in synthetic mixtures was 98.29 % and 99.25 % with root mean square error of 2.392 and 1.034, which were obtained by the optimization of regularization parameter (γ) and width of the function (σ) based on the cross-validation method. The proposed methods were also applied for the determination concentration of SOF and LED in the combined dosage form, recoveries were higher than 95 %, and relative standard deviation (RSD) values were lower than 0.4 %. The achieved results were statistically compared with those obtained from the high-performance liquid chromatography (HPLC) technique for the concurrent estimation of components through one-way analysis of variance (ANOVA), and no significant difference was found between the suggested approaches and the reference one. According to these results, simplicity, high speed, lack of time-consuming process, and cost savings are considerable benefits of colorimetry along with chemometrics methods compared to other ways.

Pipeline Leak Detection: A Comprehensive Deep Learning Model Using CWT Image Analysis and an Optimized DBN-GA-LSSVM Framework.

Detecting pipeline leaks is an essential factor in maintaining the integrity of fluid transport systems. This paper introduces an advanced deep learning framework that uses continuous wavelet transform (CWT) images for precise detection of such leaks. Transforming acoustic signals from pipelines under various conditions into CWT scalograms, followed by signal processing by non-local means and adaptive histogram equalization, results in new enhanced leak-induced scalograms (ELIS) that capture detailed energy fluctuations across time-frequency scales. The fundamental approach takes advantage of a deep belief network (DBN) fine-tuned with a genetic algorithm (GA) and unified with a least squares support vector machine (LSSVM) to improve feature extraction and classification accuracy. The DBN-GA framework precisely extracts informative features, while the LSSVM classifier precisely distinguishes between leaky and non-leak conditions. By concentrating solely on the advanced capabilities of ELIS processed through an optimized DBN-GA-LSSVM model, this research achieves high detection accuracy and reliability, making a significant contribution to pipeline monitoring and maintenance. This innovative approach to capturing complex signal patterns can be applied to real-time leak detection and critical infrastructure safety in several industrial applications.

Modeling and Optimization of an Enhanced Soft Sensor for the Fermentation Process of Pichia pastoris.

This paper proposes a novel soft sensor modeling approach, MIC-TCA-INGO-LSSVM, to address the decline in performance of soft sensor models during the fermentation process of Pichia pastoris, caused by changes in working conditions. Initially, the transfer component analysis (TCA) method is utilized to minimize the differences in data distribution across various working conditions. Subsequently, a least squares support vector machine (LSSVM) model is constructed using the dataset adapted by TCA, and strategies for improving the northern goshawk optimization (INGO) algorithm are proposed to optimize the parameters of the LSSVM model. Finally, to further enhance the model's generalization ability and prediction accuracy, considering the transfer of knowledge from multiple-source working conditions, a sub-model weighted ensemble scheme is proposed based on the maximum information coefficient (MIC) algorithm. The proposed soft sensor model is employed to predict cell and product concentrations during the fermentation process of Pichia pastoris. Simulation results indicate that the RMSE of the INGO-LSSVM model in predicting cell and product concentrations is reduced by 47.3% and 42.1%, respectively, compared to the NGO-LSSVM model. Additionally, TCA significantly enhances the model's adaptability when working conditions change. Moreover, the soft sensor model based on TCA and the MIC-weighted ensemble method achieves a reduction of 41.6% and 31.3% in the RMSE for predicting cell and product concentrations, respectively, compared to the single-source condition transfer model TCA-INGO-LSSVM. These results demonstrate the high reliability and predictive performance of the proposed soft sensor method under varying working conditions.

Comparing visible and near infrared 'point' spectroscopy and hyperspectral imaging techniques to visualize the variability of apple firmness.

In this work, visible and near-infrared 'point' (Vis-NIR) spectroscopy and hyperspectral imaging (Vis-NIR-HSI) techniques were applied on three different apple cultivars to compare their firmness prediction performances based on a large intra-variability of individual fruit, and develop rapid and simple models to visualize the variability of apple firmness on three apple cultivars. Apples with high degree of intra-variability can strongly affect the prediction model performances. The apple firmness prediction accuracy can be improved based on the large intra-variability samples with the coefficient variation (CV) values over 10%. The least squares-support vector machine (LS-SVM) models based on Vis-NIR-HSI spectra had better performances for firmness prediction than that of Vis-NIR spectroscopy, with the with the Rc2 over 0.84. Finally, The Vis-NIR-HSI technique combined with least squares-support vector machine (LS-SVM) models were successfully applied to visualize the spatial the variability of apple firmness.

Soft-sensing modeling of mother liquor concentration in the evaporation process based on reduced robust least-squares support-vector machine.

The evaporation process is vital in alumina production, with mother liquor concentration serving as a critical control parameter. To address the challenge of online detection, we propose the introduction of a soft measurement strategy. First, due to the significant fluctuations in the production process variables and inter-variable coupling, comprehensive grey correlation analysis and kernel principal component analysis are employed to reduce the input dimension and computational complexity of the data, enhancing the efficiency of the soft sensing model. The reduced robust least-squares support-vector machine (LSSVM), with its commendable predictive performance, is used for modeling and predicting the principal components. Concurrently, an improved Pattern Search-Differential Evolution (PS-DE) algorithm is proposed for optimizing the pivotal parameters of the LSSVM network. Lastly, on-site industrial data validation indicates that the new model offers superior tracking capabilities and heightened accuracy. It is deemed aptly suitable for the online detection of mother liquor concentration.

A new prognostic model of esophageal squamous cell carcinoma based on Cloud-least squares support vector machine.

Background: In view of the low accuracy of the prognosis model of esophageal squamous cell carcinoma (ESCC), this study aimed to optimize the least squares support vector machine (LSSVM) algorithm to determine the uncertain prognostic factors using a Cloud model, and consequently, to establish a new high-precision prognosis model of ESCC. Methods: We studied 4,771 ESCC patients(training samples) from the Surveillance, Epidemiology, and End Results (SEER) database and 635 ESCC patients(validation samples) from the Henan Provincial Center for Disease Control and Prevention (HCDC) database, with the same exclusion criteria and inclusion criteria for both databases, and obtained permission to obtain a research data file in the SEER database from the National Cancer Institute. The independent risk factors were analyzed using the log-rank method, survival curves, univariate and multivariate Cox analysis. Finally, the independent prognostic factors were used to construct the nomogram, random forest and Cloud-LSSVM prognostic models were utilized for validation. Results: The overall median survival time of the SEER database was 14 months (HCDC samples was 46 months), the mean survival time was 26.5 months (HCDC samples was 36.8 months), and the 3-year survival rate was 65.8%. This is because most of the patients with Henan samples are early ESCC, and most of the Seer patients are T3 and T4 people. The multivariate Cox analysis showed that age at diagnosis (P<0.001), sex (P=0.001), race (P=0.002), differentiation grade (P<0.001), pathologic T category (P<0.001), and pathologic M category (P<0.001) were the factors affecting the prognosis of ESCC patients. The SEER data and HCDC database results showed that the accuracy of the Cloud-LSSVM (C-index =0.71, 0.689) model is higher than the differentiation grade (C-index =0.548, 0.506), random forest (C-index =0.649, 0.498), and nomogram (C-index =0.659, 0.563). This new model can realize the unity of the randomness and fuzziness of the Cloud model and utilize the powerful learning and non-linear mapping abilities of LSSVM. Conclusions: Due to the difference of clans between training samples and test samples, the accuracy of prediction is generally not high, but the accuracy of Cloud-LSSVM model is much higher than other models. The new model provides a clear prognostic superiority over the random forest, nomogram, and other models.

Temperature Drift Compensation of Fiber Optic Gyroscopes Based on an Improved Method.

This study proposes an improved multi-scale permutation entropy complete ensemble empirical mode decomposition with adaptive noise (MPE-CEEMDAN) method based on adaptive Kalman filter (AKF) and grey wolf optimizer-least squares support vector machine (GWO-LSSVM). By establishing a temperature compensation model, the gyro temperature output signal is optimized and reconstructed, and a gyro output signal is obtained with better accuracy. Firstly, MPE-CEEMDAN is used to decompose the FOG output signal into several intrinsic mode functions (IMFs); then, the IMFs signal is divided into mixed noise, temperature drift, and other noise according to different frequencies. Secondly, the AKF method is used to denoise the mixed noise. Thirdly, in order to denoise the temperature drift, the fiber gyroscope temperature compensation model is established based on GWO-LSSVM, and the signal without temperature drift is obtained. Finally, the processed mixed noise, the processed temperature drift, the processed other noise, and the signal-dominated IMFs are reconstructed to acquire the improved output signal. The experimental results show that, by using the improved method, the output of a fiber optic gyroscope (FOG) ranging from -30 °C to 60 °C decreases, and the temperature drift dramatically declines. The factor of quantization noise (Q) reduces from 6.1269 × 10-3 to 1.0132 × 10-4, the factor of bias instability (B) reduces from 1.53 × 10-2 to 1 × 10-3, and the factor of random walk of angular velocity (N) reduces from 7.8034 × 10-4 to 7.2110 × 10-6. The improved algorithm can be adopted to denoise the output signal of the FOG with higher accuracy.

Development and Optimization of a Novel Soft Sensor Modeling Method for Fermentation Process of Pichia pastoris.

This paper introduces a novel soft sensor modeling method based on BDA-IPSO-LSSVM designed to address the issue of model failure caused by varying fermentation data distributions resulting from different operating conditions during the fermentation of different batches of Pichia pastoris. First, the problem of significant differences in data distribution among different batches of the fermentation process is addressed by adopting the balanced distribution adaptation (BDA) method from transfer learning. This method reduces the data distribution differences among batches of the fermentation process, while the fuzzy set concept is employed to improve the BDA method by transforming the classification problem into a regression prediction problem for the fermentation process. Second, the soft sensor model for the fermentation process is developed using the least squares support vector machine (LSSVM). The model parameters are optimized by an improved particle swarm optimization (IPSO) algorithm based on individual differences. Finally, the data obtained from the Pichia pastoris fermentation experiment are used for simulation, and the developed soft sensor model is applied to predict the cell concentration and product concentration during the fermentation process of Pichia pastoris. Simulation results demonstrate that the IPSO algorithm has good convergence performance and optimization performance compared with other algorithms. The improved BDA algorithm can make the soft sensor model adapt to different operating conditions, and the proposed soft sensor method outperforms existing methods, exhibiting higher prediction accuracy and the ability to accurately predict the fermentation process of Pichia pastoris under different operating conditions.

A New Method for Erosion Prediction of 90° Elbow Based on Non-Axisymmetric Ultrasonic-Guided Wave and the PSO-LSSVM Algorithm.

The non-axisymmetric exciting guided wave can detect the thinning section of the elbow, and the time domain energy value of the signal collected at the outer arch position of the receiving end displays a downward trend as the remaining thickness of the erosion area decreases. To address the difficulty in detecting the erosion degree of the elbow with high accuracy, this paper uses the linear frequency modulation (LFM) signal to excite a non-axisymmetric guided wave that propagates in the 90° elbow and collects signals through four PZT receivers. To predict the erosion degree, the corresponding relationship between the energy value of the four signals after fractional Fourier filtering and the degree of elbow erosion is established through the particle swarm optimization (PSO)-least squares support vector machine (LSSVM) algorithm. The results show that the method proposed has an average accuracy rate of 98.1864%, 94.7167%, 99.119%, and 99.9593% for predicting the erosion degree of four elbow samples, and 94.0039%. and 81.2976% for two new erosion degrees, which are higher than the nonlinear regression model, LSSVM algorithm, and BP neural network algorithm. This study has guiding significance for real-time monitoring of elbow erosion.

ß-cyclodextrin grafted multi-walled carbon nanotubes/chitosan (MWCNT/Cs/CD) nanocomposite for treatment of methylene blue-containing aqueous solutions.

ß-cyclodextrin (CD) was grafted with multi-walled carbon nanotubes/chitosan (MWCNTs/Cs) to obtain MWCNTs/Cs/CD nanocomposite (NC) for methylene blue (MB) adsorption from aqueous media. TEM, XRD, TGA, Raman spectra, and BET & BJH analyses were utilized to characterize and confirm the successful synthesis of as-prepared NC. MB capture was investigated by considering the parameters of pH (1.9-9.0), temperature (∼16-63 °C), sonication time (∼5-15 min), MB concentration (∼1.2-48 mg/L), and NC dose (0.03-0.26 mg). The obtained responses were then modelled using CCD, generalized regression neural network (GRNN), and least squares support vector machine (LS-SVM), of which the latter found to provide most reliable and accurate results (RMSE = 0.0235, MAE = 0.020, AAD = 0.0047, and R2 = 0.999). Moreover, the genetic algorithm-based optimization results showed that under the respective values of 7.05, 45.5 °C, 10 min, 23 mg/L, 0.12 g, MWCNTs/Cs/CD NC would be able to remove 96.75% of MB with an adsorption capacity of 603 mg/g, through different mechanisms mainly electrostatic interactions. Following from Dubinin-Radushkevich (D-R) isotherm (qs = 460.66 ± 8.9 and R2 > 0.99) and intraparticle diffusion kinetic (R2 = 0.75-0.90) models indicated a chemical adsorption mechanism. Besides, thermodynamic parameters (ΔH◦ = -66.9 kJ/mol, ΔG◦ = between -3.77 kJ/mol and -8.52 kJ/mol, and ΔS◦ = 237.1818 J/mol K) confirmed an endothermic and spontaneous nature for the adsorption. These findings along with appropriate recyclability (five times), turn the as prepared NC to a promising material in removing MB from aqueous solutions.

Machine learning approach for estimating the human-related VOC emissions in a university classroom.

Indoor air quality becomes increasingly important, partly because the COVID-19 pandemic increases the time people spend indoors. Research into the prediction of indoor volatile organic compounds (VOCs) is traditionally confined to building materials and furniture. Relatively little research focuses on estimation of human-related VOCs, which have been shown to contribute significantly to indoor air quality, especially in densely-occupied environments. This study applies a machine learning approach to accurately estimate the human-related VOC emissions in a university classroom. The time-resolved concentrations of two typical human-related (ozone-related) VOCs in the classroom over a five-day period were analyzed, i.e., 6-methyl-5-hepten-2-one (6-MHO), 4-oxopentanal (4-OPA). By comparing the results for 6-MHO concentration predicted via five machine learning approaches including the random forest regression (RFR), adaptive boosting (Adaboost), gradient boosting regression tree (GBRT), extreme gradient boosting (XGboost), and least squares support vector machine (LSSVM), we find that the LSSVM approach achieves the best performance, by using multi-feature parameters (number of occupants, ozone concentration, temperature, relative humidity) as the input. The LSSVM approach is then used to predict the 4-OPA concentration, with mean absolute percentage error (MAPE) less than 5%, indicating high accuracy. By combining the LSSVM with a kernel density estimation (KDE) method, we further establish an interval prediction model, which can provide uncertainty information and viable option for decision-makers. The machine learning approach in this study can easily incorporate the impact of various factors on VOC emission behaviors, making it especially suitable for concentration prediction and exposure assessment in realistic indoor settings.

Quantitative Detection of Tank Floor Defects by Pseudo-Color Imaging of Three-Dimensional Magnetic Flux Leakage Signals.

Highly integrated three-dimensional magnetic sensors have just been developed and have been used in some fields, such as angle measurement of moving objects. The sensor used in this paper is a three-dimensional magnetic sensor with three Hall probes highly integrated inside; 15 sensors are used to design the sensor array and then measure the magnetic field leakage of the steel plate; the three-dimensional component characteristics of the magnetic field leakage are used to determine the defect area. Pseudo-color imaging is the most widely used in the imaging field. In this paper, color imaging is used to process magnetic field data. Compared with analyzing the three-dimensional magnetic field information obtained directly, this paper converts the magnetic field information into color image information through pseudo-color imaging and then obtains the color moment characteristic values of the color image in the defect area. Moreover, the least-square support-vector machine and particle swarm optimization (PSO-LSSVM) algorithm are used to quantitatively identify the defects. The results show that the three-dimensional component of the magnetic field leakage can effectively determine the area range of defects, and it is feasible to use the color image characteristic value of the three-dimensional magnetic field leakage signal to identify defects quantitatively. Compared with a single component, the three-dimensional component can effectively improve the identification rate of defects.

Rapid simultaneous analysis of anti human immunodeficiency virus drugs in pharmaceutical formulation by smart spectrophotometry based on multivariate calibration and least squares support vector machine methods.

In this study, two chemometrics methods, including partial least squares regression (PLS) and least squares support vector machine (LS-SVM) were applied for the simultaneous determination of zidovudine (ZDV) and lamivudine (LMV) in synthetic mixtures and anti-HIV pharmaceutical formulation. These approaches along with the spectrophotometric method were used to solve spectral overlapping problems between mentioned components. The results of PLS showed that the number of components for ZDV and LMV were 10 and 10 with mean square prediction error (MSPE) of 0.4045 and 2.1189, respectively. This method revealed recoveries ranging from 99.48% to 100.40% and 99.55% to 101.25% for ZDV and LMV, respectively. By applying leave-one-out cross-validation (LOO-CV), γ (regularization parameter) and σ2 (width of the function) values were found to be 50, 1500 and 210, 20 with root mean square error (RMSE) of 0.6156 and 0.3163 for ZDV and LMV, respectively. The mean recoveries obtained by the LS-SVM were 100.82% and 98.93% for ZDV and LMV, respectively. A comparison between the suggested methods and high-performance liquid chromatography (HPLC) as a reference technique was implemented, which did not show a significant difference. The results obtained in this research revealed that the chemometrics approaches can be efficient, simple, inexpensive, and precise for routine analysis and quality control of the drug.

Coupling machine learning with signal process techniques and particle swarm optimization for forecasting flood routing calculations in the Eastern Black Sea Basin, Türkiye.

With the effect of global warming, the frequency of floods, one of the most important natural disasters, increases, and this increases the damage it causes to people and the environment. Flood routing models play an important role in predicting floods so that all necessary precautions are taken before floods reach the region, loss of life and property in the region is prevented, and agricultural lands are protected. This research aims to compare the performance of hybrid machine learning models such as least-squares support vector machine technique hybridized with particle swarm optimization, empirical mode decomposition, variational mode decomposition, and discrete wavelet transform processes for flood routing estimation models in Ordu, Eastern Black Sea Basin, Türkiye. In addition, it is aimed to examine the effect of data division in flood forecasting. Accordingly, 70%, 80%, and 90% of the data were used for training, respectively. For this purpose, the flood data of 2009 and 2013 in Ordu were used. The performance of the established models was evaluated with the help of statistical indicators such as mean bias error, mean absolute percentage error, determination coefficient, Nash-Sutcliffe efficiency, Taylor Diagrams, and boxplot. As a result of the study, the particle swarm optimization least-squares support vector machine technique was chosen as the most successful model in predicting flood routing results. In addition, the optimum data partition ratio was found to be Train:70:Test:30 in the flood routing calculation. The findings are essential regarding flood management and taking necessary precautions before the flood occurs.

Identification of adulterated milk based on auto-correlation spectra.

A qualitative analysis of melamine-adulterated milk was proposed based on two-trace two-dimensional (2T2D) auto-correlation spectra. The concentration of melamine was used as external perturbation, and 40 adulterated samples of each brand with different concentrations of melamine (0.01 g/L to 1 g/L) were configured. Four brands of milk were used to configure experimental samples, including Guangming brand, Mengniu brand, Sanyuan brand and Wandashan brand. Spectroscopic data of pure milk and melamine-adulterated milk were measured by infrared (IR) (80-4000 cm-1) spectrophotometer. 2T2D auto-correlation spectral technology combined with least squares support vector machine (LS-SVM) method was used for qualitative analysis. The two strongest auto-correlation peaks in the auto-correlation spectra were selected for modeling. For Guangming brand, the intensities of auto-correlation at two wave numbers 2898 cm-1 and 2972 cm-1 were selected as independent variables. For Mengniu brand, the intensities of auto-correlation at two wave numbers 2852 cm-1 and 2920 cm-1 were selected. For Sanyuan brand, the intensities of auto-correlation at two wave numbers 2900 cm-1 and 2974 cm-1 were selected. For Wandashan brand, the intensities of auto-correlation at two wave numbers 2900 cm-1 and 2974 cm-1 were selected. For four brands fused together, the intensities of auto-correlation at two wave numbers 2900 cm-1 and 2974 cm-1 were selected. For each brand, the accuracy of qualitative analysis was 100 %. For four brands fused together, the accuracy of qualitative analysis was 99.05 %. In this way, it greatly reduced the amount of data to be processed. This study showed that 2T2D auto-correlation spectral technology combined with LS-SVM method was perfect for the discrimination of melamine-adulterated milk.

Sleep stage classification in EEG signals using the clustering approach based probability distribution features coupled with classification algorithms.

Sleep scoring is one of the primary tasks for the classification of sleep stages in Electroencephalogram (EEG) signals. Manual visual scoring of sleep stages is time-consuming as well as being dependent on the experience of a highly qualified sleep expert. This paper aims to address these issues by developing a new method to automatically classify sleep stages in EEG signals. In this research, a robust method has been presented based on the clustering approach, coupled with probability distribution features, to identify six sleep stages with the use of EEG signals. Using this method, each 30-second EEG signal is firstly segmented into small epochs and then each epoch is divided into 60 sub-segments. Each sub-segment is decomposed into five levels by using a discrete wavelet transform (DWT) to obtain the approximation and detailed coefficient. The wavelet coefficient of each level is clustered using the k-means algorithm. Subsequently, features are extracted based on the probability distribution for each wavelet coefficient. The extracted features then are forwarded to the least squares support vector machine classifier (LS-SVM) to identify sleep stages. Comparisons with several existing methods are also made in this study. The proposed method for the classification of the sleep stages achieves an average accuracy rate of 97.4%. It can be an effective tool for sleep stages classification and can be useful for doctors and neurologists for diagnosing sleep disorders.

Research on soft sensing method of photosynthetic bacteria fermentation process based on ant colony algorithm and least squares support vector machine.

Photosynthetic bacteria wastewater treatment is an efficient water pollution treatment method, but photosynthetic bacteria fermentation is a multivariable, non-linear, and time-varying process. So it is difficult to establish an accurate model. Aiming at the difficulty of online measurement of key parameters, such as bacterial concentration and matrix concentration in photosynthetic bacteria fermentation process, an improved ant colony algorithm least squares support vector machine (AC-LSSVM) soft sensing model method is proposed in this paper. Firstly, the virtual sensing subsystem of the photosynthetic bacteria fermentation process is proposed, with measurable parameters as input and unmeasurable key parameters as output, and the left inverse soft sensing model of virtual sensing is constructed. Then, the ant colony algorithm can quickly find the shortest path to optimize the parameters of the traditional PI regulation, to improve the dynamic performance and accuracy of parameter measurement in the fermentation process. After that, the ant colony algorithm is used to optimize penalty parameters C and kernel parameters σ of LSSVM, which effectively avoids the local optimization and improves the computing power and global optimization ability. Finally, the soft sensing prediction model of the photosynthetic bacteria fermentation process based on AC-LSSVM is established. Compared with SVM and LSSVM prediction models, the root mean square error of bacterial concentration and matrix concentration based on the AC-LSSVM model are 0.468 and 0.126, respectively. The simulation analysis shows that this model has less error and better prediction ability, and it can meet the needs of online prediction of key parameters of photosynthetic bacteria fermentation.

Research on the Fault Diagnosis Method of an Internal Gear Pump Based on a Convolutional Auto-Encoder and PSO-LSSVM.

The raw signals produced by internal gear pumps are susceptible to noises brought on by mechanical vibrations and the surrounding environment, and the sample count collected during the various operating periods is not distributed evenly. Accurately diagnosing faults in internal gear pumps is significantly complicated by these factors. In light of these issues, accelerated life testing was performed in order to collect signals from an internal gear pump during various operating periods. Based on the architecture of a convolutional auto-encoder network, preprocessing of the signals in the various operating periods was performed to suppress noise and enhance operating period-representing features. Thereafter, variational mode decomposition was utilized to decompose the preprocessed signal into multiple intrinsic mode functions, and the multi-scale permutation entropy value was extracted for each intrinsic mode function to form a feature set. The feature set was subsequently divided into a training set and a test set, with the training set being trained to utilize a particle swarm optimization-least squares support vector machine network. For pattern recognition, the test set samples were fed into the trained model. The results demonstrated a 99.2% diagnostic accuracy. Compared to other methods of fault diagnosis, the proposed method is more effective and accurate.