Relevance Vector Machine Research Articles

Fault Diagnosis of Rotating Machinery Using Kernel Neighborhood Preserving Embedding and a Modified Sparse Bayesian Classification Model.

Fault diagnosis of rotating machinery plays an important role in modern industrial machines. In this paper, a modified sparse Bayesian classification model (i.e., Standard_SBC) is utilized to construct the fault diagnosis system of rotating machinery. The features are extracted and adopted as the input of the SBC-based fault diagnosis system, and the kernel neighborhood preserving embedding (KNPE) is proposed to fuse the features. The effectiveness of the fault diagnosis system of rotating machinery based on KNPE and Standard_SBC is validated by utilizing two case studies: rolling bearing fault diagnosis and rotating shaft fault diagnosis. Experimental results show that base on the proposed KNPE, the feature fusion method shows superior performance. The accuracy of case1 and case2 is improved from 93.96% to 99.92% and 98.67% to 99.64%, respectively. To further prove the superiority of the KNPE feature fusion method, the kernel principal component analysis (KPCA) and relevance vector machine (RVM) are utilized, respectively. This study lays the foundation for the feature fusion and fault diagnosis of rotating machinery.

Data driven modeling advancements for air temperature predictions in data centers

While data center cooling energy usage optimization studies have been performed through computational fluid dynamics/heat transfer (CFD/HT), and heuristic methods, data driven modeling techniques are now also being used for these applications. This paper investigates the air temperature prediction capabilities of static artificial neural network (ANN), Gaussian progress regression (GPR), support vector regression (SVR), relevance vector machine (RVM), linear regression, and regression trees; and transient long-short term memory (LSTM), and nonlinear autoregressive neural network with external input (NARX)) data driven modeling frameworks. The static study compared various models and found that GPR provided the best results (average error of 0.56 °C), closely followed by the ANN and SVR (average error of 0.60 °C and 0.68 °C respectively) methods. The transient study compared models based on an experimental data set and found that NARX outperforms LSTM for normal operations (0.83 °C and 1.07 °C average error respectively), and that data driven models are able to provide relatively good predictions, even if the input variables are slightly outside the training domain.

Multivariate classification based on large-scale brain networks during early abstinence predicted lapse among male detoxified alcohol-dependent patients.

Identifying biomarkers to predict lapse of alcohol-dependence (AD) is essential for treatment and prevention strategies, but remains remarkably challenging. With an aim to identify neuroimaging features for predicting AD lapse, 66 male AD patients during early-abstinence (baseline) after hospitalized detoxification underwent resting-state functional magnetic resonance imaging and were then followed-up for 6 months. The relevance-vector-machine (RVM) analysis on baseline large-scale brain networks yielded an elegant model for differentiating relapsing patients (n = 38) from abstainers, with the area under the curve of 0.912 and the accuracy by leave-one-out cross-validation of 0.833. This model captured key information about neuro-connectome biomarkers for predicting AD lapse.

Hybrid Algorithm of Backpropagation and Relevance Vector Machine with Radial Basis Function Kernel for Hydro-Climatological Data Prediction

Hydro-climatological data serves a pivotal role in monitoring climatic alterations and facilitating agricultural planning, inclusive of evapotranspiration estimation, water management, and crop pattern design. The necessity to accurately and expeditiously model and forecast this data underscores the need for effective methodologies. This paper introduces a hybrid algorithm, integrating backpropagation and relevance vector machine (BP-RVM) with a radial basis function (RBF) kernel. A comparative analysis was conducted between RBF and Logsig activation functions in conjunction with resilient backpropagation (trainrp) and Levenberg-Marquardt backpropagation (trainlm). The algorithm was employed to predict and categorize rainfall, temperature, wind speed, humidity, and sunshine duration data. Through extensive trials, the architecture parameters in the training-testing process of the BP-RVM algorithm were meticulously determined. Mean squared error (MSE) and mean absolute percentage error (MAPE) values were classified as indicating high forecast accuracy (<10%). Despite the RBF-trainlm kernel function combination exhibiting a faster epoch completion rate, the BP-RVM algorithm with the RBF-trainrp kernel function combination is recommended for future data prediction stages due to its lower error generation. The BP-RVM-RBF-trainrp algorithm outperformed BP-RVM-RBF-trainlm, with an average error difference of 1.39% in the training process and 2.28% in the testing process. The identified algorithms and architectures present potential for future applications in evapotranspiration calculation and crop pattern planning based on hydro-climatological data.

An active sparse polynomial chaos expansion approach based on sequential relevance vector machine

Polynomial chaos expansion (PCE) is a popular surrogate modeling approach employed in uncertainty quantification for a variety of engineering problems. However, the challenges for full PCE lie in the “curse of dimensionality” of the expansion coefficients. In this paper, we propose a new sparse PCE approach by introducing active learning technique and sequence relevance vector machine (SRVM). As an active learning technique, efficient loss function based on expected improvement (EI-based ELF) is introduced to search for the best next sampling point and enrich the training samples. Relevance vector machine (RVM) is a superior machine learning technique due to the sparsity of its adopted model. SRVM leads to the maximization of marginal likelihood by sequentially selecting basis functions. To assess the performance of the proposed method, four examples are investigated, and the results show that the proposed method outperforms the classical sparse PCE in terms of both accuracy and efficiency.

Explainable Prognostics Method through Differential Evolved RVR Ensemble of Relevance Vector Machines

Operating experience from various mechanical components indicates that their operating performance depends on non-well known physical mechanisms, while it is likely that various unexpected factors will act as catalysts for reaching the failure point. Therefore, one way to overcome the partially knowledge of physical mechanisms is the use of data-driven methods that estimate the degradation patterns and predict the failure point. Thus, there is a growing need to design and develop new and more sophisticated prognostic technologies that can estimate the remaining useful life of a mechanical component. In this work, a new method for prognostics is proposed that not only provides a prediction over the failure point but also provides an explanation over the rationale behind that prediction. The proposed method utilized tools from artificial intelligence and more specifically relevance vector machines (RVM) and differential evolution (DE). The cornerstone of the method is the assembly of an ensemble comprised of multiple RVM equipped with different kernels, and the subsequent evolution of the ensemble using the differential evolution. DE will provide a set of values for the coefficients of the ensemble. Then based on the coefficients together with their associated RVMs are used to provide an explanation over the prediction. The explanation stems from the kernels themselves as each kernel models different set of properties. The presented method is tested on a set of real-world degradation data taken from a Gas Turbine (GT) propulsion plant.

Robust state-of-charge estimation method for lithium-ion batteries based on the fusion of time series relevance vector machine and filter algorithm

Data-driven methods have been widely employed in the field of Lithium-ion battery state-of-charge (SOC) estimation. However, most of these methods do not impose constraints on the rate of change between adjacent output SOC values, which leads to the issue of output SOC fluctuations when the battery current undergoes significant variations. To address this issue, a fusion algorithm is proposed in this study, which combines the multi-kernel Incremental relevance vector machine (MIRVM) and seasonal autoregressive integrated moving average (SARIMA) within an adaptive Kalman filter (AKF) framework, called SARIMA_AKF_MIRVM(SFR) algorithm. Employing the MIRVM algorithm, we aim to construct a data-driven model capturing the intricate relationship between voltage, current, and SOC of batteries under varying operating conditions. Furthermore, we shall leverage the SARIMA algorithm to establish a time series forecasting model for the adjacent SOC values. Subsequently, we shall introduce the AKF algorithm to filter prediction results associated with the MIRVM algorithm. Additionally, we shall integrate the whale optimization algorithm to obtain the optimal parameter combination for SFR algorithm. The experimental results demonstrate that the SFR algorithm exhibits exceptional generalization capabilities and robustness. The RMSE and MAE for four experimental test conditions remain below 0.3 %, with the maximum MAE reaching a mere 0.14 %.

A Bayesian Lasso based sparse learning model

The Bayesian Lasso is constructed in the linear regression framework and applies the Gibbs sampling to estimate the regression parameters. This paper develops a new sparse learning model, named the Bayesian Lasso Sparse (BLS) model, that takes the hierarchical model formulation of the Bayesian Lasso. The main difference from the original Bayesian Lasso lies in the estimation procedure; the BLS uses a learning algorithm based on the type-II maximum likelihood procedure. Opposed to the Bayesian Lasso, the BLS provides sparse estimates of the regression parameters. The BLS is also derived for nonlinear supervised learning problems by introducing kernel functions. We compare the BLS model to the well known Relevance Vector Machine, the Fast Laplace, the Bayesian Lasso, and the Lasso, on both simulated and real data. The numerical results show that the BLS is sparse and precise, especially when dealing with noisy and irregular dataset.

Quality control prediction of electrolytic copper using novel hybrid nonlinear analysis algorithm

Traditional linear regression and neural network models demonstrate suboptimal fit and lower predictive accuracy while the quality of electrolytic copper is estimated. A more dependable and accurate model is essential for these challenges. Notably, the maximum information coefficient was employed initially to discern the non-linear correlation between the nineteen factors influencing electrolytic copper quality and the five quality control indicators. Additionally, the random forest algorithm elucidated the primary factors governing electrolytic copper quality. A hybrid model, integrating particle swarm optimization with least square support vector machine, was devised to predict electrolytic copper quality based on the nineteen factors. Concurrently, a hybrid model combining random forest and relevance vector machine was developed, focusing on primary control factors. The outcomes indicate that the random forest algorithm identified five principal factors governing electrolytic copper quality, corroborated by the non-linear correlation analysis via the maximum information coefficient. The predictive accuracy of the relevance vector machine model, when accounting for all nineteen factors, was comparable to the particle swarm optimization—least square support vector machine model, and surpassed both the conventional linear regression and neural network models. The predictive error for the random forest-relevance vector machine hybrid model was notably less than the sole relevance vector machine model, with the error index being under 5%. The intricate non-linear variation pattern of electrolytic copper quality, influenced by numerous factors, was unveiled. The advanced random forest-relevance vector machine hybrid model circumvents the deficiencies seen in conventional models. The findings furnish valuable insights for electrolytic copper quality management.

Sparse Bayesian machine learning for the interpretable identification of nonlinear structural dynamics: Towards the experimental data-driven discovery of a quasi zero stiffness device

Data-driven discovery of governing laws for complex nonlinear structural dynamic systems remains a challenging issue of paramount importance. This work addresses the above issue by leveraging the available noisy data and integrating sparse Bayesian machine learning (ML) techniques to discover the governing equations. The problem of discovery is re-cast as the automatic relevance determination of models (model selection) from the library of potential candidate basis terms and their coefficients are determined (parameter identification) using sparse Bayesian linear regression. Two sparsity promoting ML algorithms based on relevance vector machines have been employed. Both these approaches use Bayesian statistics and quantify the uncertainty associated with the model predictions. Results from four representative numerical examples of nonlinear structural dynamics illustrate excellent performance of both proposed approaches. The results have been validated with the true governing equations and time response data. Comparison has also been made with a recent and popular sparse discovery approach. Finally, the proposed framework is applied to real datasets that were generated from an in-house designed experimental setup of a quasi zero stiffness device and good performance has been observed.

Remaining Useful Life Prediction Method of PEM Fuel Cells Based on a Hybrid Model

To predict the remaining useful life (RUL) of the proton exchange membrane fuel cell (PEMFC) in advance, a prediction method based on the voltage recovery model and Bayesian optimization of a multi-kernel relevance vector machine (MK-RVM) is proposed in this paper. First, the empirical mode decomposition (EMD) method was used to preprocess the data, and then MK-RVM was used to train the model. Next, the Bayesian optimization algorithm was used to optimize the weight coefficient of the kernel function to complete the parameter update of the prediction model, and the voltage recovery model was added to the prediction model to realize the rapid and accurate prediction of the RUL of PEMFC. Finally, the method proposed in this paper was applied to the open data set of PEMFC provided by Fuel Cell Laboratory (FCLAB), and the prediction accuracy of RUL for PEMFC was obtained by 95.35%, indicating that this method had good generalization ability and verified the accuracy of the method when predicting the RUL of PEMFC. The realization of long-term projections for PEMFC RUL not only improves the useful life, reliability, and safety of PEMFC but also reduces operating costs and downtime.

Comparison of improved relevance vector machines for streamflow predictions

AbstractThis study investigates the feasibility of relevance vector machine tuned with dwarf mongoose optimization algorithm in modeling monthly streamflow. The proposed method is compared with relevance vector machines tuned by particle swarm optimization, whale optimization, marine predators algorithms, and single relevance vector machine methods. Various lagged values of hydroclimatic data (e.g., precipitation, temperature, and streamflow) are used as inputs to the models. The relevance vector machine tuned with dwarf mongoose optimization algorithm improved the efficiency of single method in monthly streamflow prediction. It is found that the integrating metaheuristic algorithms into single relevance vector machine improves the prediction efficiency, and among the input combinations, the lagged streamflow data are found to be the most effective variable on current streamflow whereas precipitation has the least effect.

Groundwater level monitoring network design with machine learning methods

This research introduces a method combining groundwater models and machine learning (ML) algorithms to locate observation wells and design optimal Groundwater Level Monitoring Networks (GLMNs). Groundwater models and stochastic simulations are used to extract required hydrogeological datasets for ML algorithms. In addition to data generation, the stochastic simulations minimize the uncertainties in the aquifer characterization, leading to a precise design of GLMNs. In this research, K-means clustering and relevance vector machine (RVM) are the ML algorithms employed to determine the optimal configuration of observation wells in terms of number and location in a monitoring network. This study proposes three GLMNs (K-mean, RVM, modified RVM), compares them with the existing observation wells, and investigates their effects on the accuracy of groundwater modeling and running time. The groundwater model with a K-mean network runs faster than other configurations, while the model with a modified RVM network shows a significant decrease in errors.

Smart prediction of liquefaction-induced lateral spreading

The prediction of liquefaction-induced lateral spreading/displacement (Dh) is a challenging task for civil/geotechnical engineers. In this study, a new approach is proposed to predict Dh using gene expression programming (GEP). Based on statistical reasoning, individual models were developed for two topographies: free-face and gently sloping ground. Along with a comparison with conventional approaches for predicting the Dh, four additional regression-based soft computing models, i.e. Gaussian process regression (GPR), relevance vector machine (RVM), sequential minimal optimization regression (SMOR), and M5-tree, were developed and compared with the GEP model. The results indicate that the GEP models predict Dh with less bias, as evidenced by the root mean square error (RMSE) and mean absolute error (MAE) for training (i.e. 1.092 and 0.815; and 0.643 and 0.526) and for testing (i.e. 0.89 and 0.705; and 0.773 and 0.573) in free-face and gently sloping ground topographies, respectively. The overall performance for the free-face topology was ranked as follows: GEP > RVM > M5-tree > GPR > SMOR, with a total score of 40, 32, 24, 15, and 10, respectively. For the gently sloping condition, the performance was ranked as follows: GEP > RVM > GPR > M5-tree > SMOR with a total score of 40, 32, 21, 19, and 8, respectively. Finally, the results of the sensitivity analysis showed that for both free-face and gently sloping ground, the liquefiable layer thickness (T15) was the major parameter with percentage deterioration (%D) value of 99.15 and 90.72, respectively.

Tool wear condition monitoring method based on relevance vector machine

Tool wear condition monitoring method based on relevance vector machine

Remaining useful life prediction for rolling bearings based on RVM-Hausdorff distance

To address the shortcomings of existing bearing remaining useful life (RUL) prediction process such as low accuracy and reliance on expert experience for parameter estimation, this paper proposes a bearing RUL prediction method combining relevance vector (RV) machine (RVM) and hybrid degradation model. The bearing degradation characteristics are extracted from the acquired vibration acceleration signals, the time-varying 3σ criterion is then used to determine the bearing first predicting time, and the sequence from initial failure time point to the inspection time is regressed by differential kernel parameter RVM to obtain the different sparse RVs. A mixed degenerate model combined single exponential, weighted double exponential, and polynomial is used to fit the sparse RVs to obtain the fitted curve clusters. The similarity based on bidirectional Hausdorff distance is used to select the best degradation curve, and to extrapolate the best degradation curve to the failure threshold. The experimental results indicate that the proposed method overcomes the widespread drawbacks of monotonicity and trend bias in model-based methods, and has better prediction efficiency than the conventional exponential models.

Sparse Bayesian Learning With Weakly Informative Hyperprior and Extended Predictive Information Criterion.

This article considers the regression problem with sparse Bayesian learning (SBL) when the number of weights P is larger than the data size N, i.e., P》 N. The situation induces overfitting and makes regression tasks, such as prediction and basis selection, challenging. We show a strategy to address this problem. Our strategy consists of two steps. The first is to apply an inverse gamma hyperprior with a shape parameter close to zero over the noise precision of automatic relevance determination (ARD) prior. This hyperprior is associated with the concept of a weakly informative prior in terms of enhancing sparsity. The model sparsity can be controlled by adjusting a scale parameter of inverse gamma hyperprior, leading to the prevention of overfitting. The second is to select an optimal scale parameter. We develop an extended predictive information criterion (EPIC) for optimal selection. We investigate the strategy through relevance vector machine (RVM) with a multiple-kernel scheme dealing with highly nonlinear data, including smooth and less smooth regions. This setting is one form of the regression task with SBL in the P》 N situation. As an empirical evaluation, regression analyses on four artificial datasets and eight real datasets are performed. We see that the overfitting is prevented, while predictive performance may be not drastically superior to comparative methods. Our methods allow us to select a small number of nonzero weights while keeping the model sparse. Thus, the methods are expected to be useful for basis and variable selection.

The SRVM: A Similarity-Based Relevance Vector Machine for Remaining Useful Lifetime Prediction in the Industrial Internet of Things

With the continuous advancement of industry 4.0 and intelligent manufacturing, remaining useful lifetime (RUL) prediction can forecast the future degradation state of machinery and then estimate the remaining service time before it loses its safe operation ability. Accordingly, a series of predictive maintenance strategies can be regulated in advance for the equipment in the industrial Internet of things (IIOT). To tackle the challenges of insufficiency of failure data and lack of confidence level in the RUL prediction results, a similarity-based relevance vector machine (SRVM) is proposed in this article. Primarily, the relationship among latent variables in SRVM is learned adaptively through similarity computation to fully utilize the limited degradation data. Furthermore, these internal variables in SRVM are treated as time-varying variables and re-estimated dynamically to provide RUL prediction with reliable confidence. The experiment results show that the prediction accuracy of SRVM is higher than that of other baseline methods.

State-of-charge of lithium-ion battery based on equivalent circuit model – Relevance vector machine fusion model considering varying ambient temperatures

Ambient temperature significantly impacts battery characteristics and state-of-charge (SOC) accuracy, so it is crucial to estimate SOC under various temperatures. Most circuit models of lithium-ion batteries have poor temperature adaptability, especially at low temperatures. To solve this challenge, this paper proposes a fusion model of the Equivalent Circuit Model-Relevance Vector Machine to enhance SOC estimation under various temperatures. First, a second-order equivalent circuit model based on the forgetting factor recursive least squares is built to obtain the SOC value. Second, build a data-driven battery model based on the relevance vector machine (RVM) algorithm with a moving window method, and the SOC value is obtained based on the RVM model and the unscented Kalman filter algorithm. The weights of the models are merged using the Bayesian principle. The experiments verify that the fusion model accurately estimates SOC for different types of batteries under variable ambient temperature environments and exhibits strong robustness.

A Hybrid Prediction Model for Local Resistance Coefficient of Water Transmission Tunnel Maintenance Ventilation Based on Machine Learning

Multiple ducts in the working shaft and main body of tunnels form a combined tee structure. An efficient and accurate prediction method for the local resistance coefficient is the key to the design and optimization of the maintenance ventilation scheme. However, most existing studies use numerical simulations and model experiments to analyze the local resistance characteristics of specific structures and calculate the local resistance coefficient under specific ventilation conditions. Therefore, there are shortcomings of low efficiency and high cost in the ventilation scheme optimization when considering the influence of the local resistance. This paper proposes a hybrid prediction model for the local resistance coefficient of water transmission tunnel maintenance ventilation based on machine learning. The hybrid prediction model introduces the hybrid kernel into a relevance vector machine to build the hybrid kernel relevance vector machine model (HKRVM). The improved artificial jellyfish search algorithm (IAJS), which utilizes Fuch chaotic mapping, lens-imaging reverse learning, and adaptive hybrid mutation strategies to improve the algorithm performance, is applied to the kernel parameter optimization of the HKRVM model. The results of a case study show that the method proposed in this paper can achieve the efficient and accurate prediction of the local resistance coefficient of maintenance ventilation and improve the prediction accuracy and prediction efficiency to a certain extent. The method proposed in this paper provides a new concept for the prediction of the ventilation local resistance coefficient and can further provide an efficient prediction method for the design and optimization of maintenance ventilation schemes.