Basis Function Neural Network Algorithm Research Articles

Hierarchical Distributed Model‐Free Adaptive Fault‐Tolerant Vehicular Platooning Control

ABSTRACTIn this article, a hierarchical distributed model‐free adaptive fault‐tolerant vehicular platooning control scheme for nonlinear vehicular platooning systems (VPSs) is studied. First of all, the dynamic linearization technique (DLT) is utilized to acquire an equivalent linear data model for nonlinear VPSs. Secondly, a hierarchical control structure is developed to realize the vehicular platooning tracking control task, which consists of the upper‐layer adaptive distributed observer and the under‐layer decentralized model‐free adaptive vehicular platooning tracking controller. In order to make each follower vehicle get the leader's information, the adaptive distributed observer is employed to get the estimation value of leader's information. In addition, for the purpose of ensuring the safety of driving, the radial basis function neural network (RBFNN) algorithm is utilized to address the problem of sensor failures. Based on this, a novel hierarchical distributed model‐free adaptive fault‐tolerant vehicular platooning control scheme is designed to achieve simultaneous tracking of vehicular position and speed. Lastly, the validity of the theoretical control scheme is demonstrated through a realistic and detailed simulation example of a VPS.

Surface Mechanical Property Prediction and Process Optimization of 18CrNiMo7-6 Carburized Steel Stator Guide Based on Radial Basis Function Neural Network and NSGA-II Algorithm

The carburizing process is a key technology that affects the mechanical properties of the surface of the hydraulic motor stator guide rail, and the related process parameters have an important influence on surface hardness, the thickness of the carburized layer, and the deformation of the guide rail. However, at present, the relationship between the carburizing process parameters and the surface mechanical properties of the target is not clear. This paper proposes a “hardness prediction and process parameter optimization” method. Firstly, a finite element model is established, with carburizing time, temperature, and carbon potential as the three input factors; the optimal Latin hypercubic experimental design and sensitivity analysis are applied. Secondly, surface hardness, carburized layer thickness, and deformation are taken as the output values, and an RBF neural network is used to construct the prediction model. The results show that the RBF neural network can be accurately used for the prediction of surface hardness, the thickness of the carburized layer, and deformation, and for the optimization of process parameters. The optimized parameters of surface hardness and the thickness of the carburized layer were increased by 4.2% and 5.1%, respectively, and the deformation amount was reduced to 0.31 mm, achieving the goal of optimal design.

Spatial analysis and soft computational modeling for hazard assessment of potential toxic elements in potable groundwater

Swiftly increasing population and industrial developments of urban areas has accelerated the worsening of the water quality in recent years. Groundwater samples from different locations of the Doon valley, Garhwal Himalaya were analyzed to measure concentrations of six potential toxic elements (PTEs) viz. chromium (Cr), nickel (Ni), arsenic (As), molybdenum (Mo), cadmium (Cd), and lead (Pb) using Inductively Coupled Plasma Mass Spectrometer (ICP-MS) with the aim to study the spatial distribution and associated hazards. In addition, machine learning algorithms have been used for prediction of water quality and identification of influencing PTEs. The results inferred that the mean values (in the units of µg L−1) of analyzed PTEs were observed in the order of Mo (1.066) > Ni (0.744) > Pb (0.337) > As (0.186) > Cr (0.180) > Cd (0.026). The levels and computed risks of PTEs were found below the safe limits. The radial basis function neural network (RBF-NN) algorithms showed high level of accuracy in the predictions of heavy metal pollution index (HPI), heavy metal evaluation index (HEI), non-carcinogenic (N-CR) and carcinogenic (CR) parameters with determination coefficient values ranged from 0.912 to 0.976. However, the modified heavy metal pollution index (m-HPI) and contamination index (CI) predictions showed comparatively lower coefficient values as 0.753 and 0.657, respectively. The multilayer perceptron neural network (MLP-NN) demonstrated fluctuation in precision with determination coefficient between 0.167 and 0.954 for the prediction of computed indices (HPI, HEI, CI, m-HPI). In contrast, the proficiency in forecasting of non-carcinogenic and carcinogenic hazards for both sub-groups showcased coefficient values ranged from 0.887 to 0.995. As compared to each other, the radial basis function (RBF) model indicated closer alignments between predicted and actual values for pollution indices, while multilayer perceptron (MLP) model portrayed greater precision in prediction of health risk indices.

Hybrid Machine-Learning Model for Accurate Prediction of Filtration Volume in Water-Based Drilling Fluids

Accurately predicting the filtration volume (FV) in drilling fluid (DF) is crucial for avoiding drilling problems such as a stuck pipe and minimizing DF impacts on formations during drilling. Traditional FV measurement relies on human-centric experimental evaluation, which is time-consuming. Recently, machine learning (ML) proved itself as a promising approach for FV prediction. However, existing ML methods require time-consuming input variables, hindering the semi-real-time monitoring of the FV. Therefore, employing radial basis function neural network (RBFNN) and multilayer extreme learning machine (MELM) algorithms integrated with the growth optimizer (GO), predictive hybrid ML (HML) models are developed to reliably predict the FV using only two easy-to-measure input variables: drilling fluid density (FD) and Marsh funnel viscosity (MFV). A 1260-record dataset from seventeen wells drilled in two oil and gas fields (Iran) was used to evaluate the models. Results showed the superior performance of the RBFNN-GO model, achieving a root-mean-square error (RMSE) of 0.6396 mL. Overfitting index (OFI), score, dependency, and Shapley additive explanations (SHAP) analysis confirmed the superior FV prediction performance of the RBFNN-GO model. In addition, the low RMSE (0.3227 mL) of the RBFNN-NGO model on unseen data from a different well within the studied fields confirmed the strong generalizability of this rapid and novel FV prediction method.

An intelligent and portable fiber optic real-time fluorescence detection system for pathogenic microorganisms detection

The detection of pathogenic microorganisms poses an increasingly serious challenge to food safety. This paper proposes an intelligent fiber optic fluorescence sensing system for detection of pathogenic microorganisms. The system integrates light-emitting diodes and fiber optic sensing arrays. Compact and multi-channel detection is achieved by this kind of design. Environmental parameters such as temperature, humidity, and location are intelligently analyzed together with sampled fluorescence signal, which successfully achieved a high accuracy detection result without affected or interfered by environmental parameters. A Radial Basis Function Neural Network (RBFNN) algorithm is utilized for intelligent analysis and prediction of pathogenic microorganisms’ concentration with environmental parameters. Under different environmental parameters, the system has successfully detected African swine fever virus or salmonella in real-time with high accuracy and sensitivity. Since location of the sensing system can be determined by GPS module integrated in the system, the change of pathogenic microorganisms with different locations can be determined even during transportation. This innovative solution provides a convenient and accurate method for high accurate on-site real time sensing of pathogenic microorganisms.

Improving heat transfer prediction across catalytic SiC interface through a multiscale framework leveraging machine learning and data fusion techniques

Accurate aerothermal prediction under hypersonic flow conditions is crucial for any thermal protection materials design and engineering. The surface catalytic effect, where dissociated atoms recombine into their molecular forms at the air-solid interface, is an exothermic reaction and plays an important role in high-enthalpy aerodynamic environment prediction. Taking SiC, a widely recognized high-temperature thermal protection material as an example, a multiscale fusion approach for aerothermal prediction is proposed. The approach utilizes reactive molecular dynamics method to construct an interface catalysis model, and the Bayesian maximum entropy to integrate experimental and simulational data into an optimized database. Subsequently, using the radial basis function neural network algorithm, a machine learning-based reaction kinetics model with precise analysis of surface catalysis is trained. The obtained catalytic recombination efficiency is used as a boundary input for computational fluid dynamics simulation, enabling rapid and accurate prediction of hypersonic thermal environment. The result shows that the predicted surface heat flux by this novel approach is consistent with the benchmark studies, but comes with significantly reduced computation time. The stagantion heat flux predictions based on the assumptions of full catalytic wall, finite rate catalytic wall (from the proposed multiscale fusion method), and non-catalytic wall are determined to be 8.65×106 W/m2, 7.51×106 W/m2, and 4.02×106 W/m2, respectively. Comparing these with the wind tunnel benchmark value of 7.48×106 W/m2, the error from the proposed multiscale fusion method is 0.30 %, indicating significant enhancement in prediction accuracy through the proposed upscaling method. The new approach could not only reveal complex exothermic reaction processes at the interface, but also enhance the prediction accuracy at much higher computational efficiency, providing an alternative for multiscale modeling of complex flow and heat transfer at the interface.

Laser-Tracing Multi-Station Measurements in a Non-Uniform-Temperature Field

Due to the increasing requirements for the improvement of the accuracy of large coordinate-measuring machines (CMMs), the laser-tracing multi-station measurement technology, as one of the advanced precision measurement technologies, is worth studying in depth in terms of its practical application for the compensation of errors in large CMMs. Since it is difficult to maintain a constant temperature of about 20 °C in the actual workshop under the influence of solar radiation and convective heat transfer, there is a gradient in the spatial temperature distribution, and the overall temperature changes with the influence of external factors with synchronous hysteresis, it is difficult for the actual calibration environment to meet the standard environmental requirements. Therefore, the influence of temperature and other environmental factors on the accuracy of laser ranging and large-scale CMM calibration should not be ignored. In this paper, on the basis of analyzing the temperature distribution and change rule of large CMM measurement space under different working conditions, the radial basis function (RBF) neural network algorithm was used to build a non-uniform-temperature field model, and based on this model and the measurement principle of the laser-tracking instrument, the method of laser tracking and interferometric ranging accuracy enhancement was put forward under a non-uniform-temperature field. Finally, based on the multi-station technique of laser tracing, an accurate solution for the volumetric error of large CMMs under the condition of non −20 °C ambient temperature was realized. Simulation results proved that compared with the traditional temperature-compensation method, the proposed method improved the measurement accuracy of the volumetric error of a large-scale CMM using laser-tracing multi-station technology in a non-uniform-temperature field by 33.5%. This study provides a new approach for improving the accuracy of laser-tracer multi-station measurement systems.

Response of Gaussian white noise excited oscillators with inertia nonlinearity based on the RBFNN method

Although stochastic averaging methods have proven effective in solving the responses of nonlinear oscillators with a strong stiffness term under broadband noise excitations, these methods appear to be ineffective when dealing with oscillators that have a strong inertial nonlinearity term (also known as coordinate-dependent mass) or multiple potential wells. To address this limitation, a radial basis function neural network (RBFNN) algorithm is applied to predict the responses of oscillators with both a strong inertia nonlinearity term and multiple potential wells. The well-known Gaussian functions are chosen as radial basis functions in the model. Then, the approximate stationary probability density function (PDF) is expressed as the sum of Gaussian basis functions (GBFs) with weights. The squared error of the approximate solution for the Fokker-Plank-Kolmogorov (FPK) function is minimized using the Lagrange multiplier method to determine optimal weight coefficients. Three examples are presented to demonstrate how inertia nonlinearity terms and potential wells affect the responses. The mean square errors between Monte Carlo simulations (MCS) and RBFNN predictions are provided. The results indicate that RBFNN predictions align perfectly with those obtained from MCS.

A bionic design of oscillating wave surge energy converter based on scallops

Oscillating wave surge converters (OWSCs) are generally of rectangular geometries. What kind of flap shape is better is still not clear. Thus, this study proposes some bionic flaps by mimicking the scallops. Eight scallop-based bionic flaps were compared. The fluid pressure and velocity surrounding the bionic and the original flaps were compared to examine why the bionic flap was better. Then, a Sobol sensitivity analysis was conducted, which found that the wave period, water depth, OWSC damping, Bezier length ratio, and Bezier height ratio have notable influences on the OWSC. Parametric study of the OWSC tells that as the increase of the Bezier length ratio, the capture factor increases first and then converges. As the increases of the remaining parameters, the capture factor increases first and then decreases. Radial basis function neural network and genetic algorithm were utilized to optimize the OWSC under different environmental conditions, and the optimized OWSC structural parameters are presented. The Bezier length ratio can always be 1.0 when in real engineering. The seaside outward curved and leeside flat bionic flap performed the best, the maximum capture factor of which is 0.48. The bionic flap improved the capture factor by 30 % compared with the original flap.

An adding‐points strategy surrogate model for well control optimization based on radial basis function neural network

AbstractThis work introduces a new adding points strategy for augmenting the accuracy of reservoir proxy model and improving the effect of well control optimization. The method is based on the optimization process of a radial basis function neural network and genetic algorithm (GA), which aids in identifying the more important points to be included in the sample space. Notably, the uniqueness of this method lies in selecting the points of higher importance for subsequent optimization processes across the entire sample space. These selected points are then added to the surrogate model. The surrogate model is updated for each generation until the termination condition is satisfied, enabling the surrogate model to achieve improved accuracy. The results show that the new method is more effective, superior, and converges faster than the traditional method.

Multi-objective optimization design of aerodynamic and infrared characteristics of multi-stream serpentine nozzle

A multi-objective optimization design of multi-stream serpentine nozzle was carried out to improve the aerodynamic performance and reduce the infrared radiation signal. A numerical simulation was carried out to investigate the effects of nozzle pressure ratio (NPR), Aspect ratio (AR) and Ratio of length and diameter (L/D). Computational fluid dynamics (CFD) simulation was employed to study the aerodynamic performance of the multi-stream serpentine nozzle, and the narrow-band method with discrete transfer method were used to calculate its infrared radiation intensity distribution characteristics. A 3-factor, 21-level orthogonal table was designed based on the orthogonal experimental method, and multi-stream serpentine nozzle with different geometrical parameter and operating conditions were designed to obtain the aerodynamic performance and infrared radiation intensity data of each experimental sample point. Radial Basis Function (RBF) neural network and Multi-Objective Particle Swarm Optimization algorithm were used to optimize the geometry and operating conditions with better aerodynamic performance and weaker infrared signal. The result shows that the Pareto solutions obtained by the optimization have good accuracy compared with the numerical simulation results, with an aerodynamic performance error of 0.02% and an infrared radiation intensity error of 0.24%.

Damage detection of CFRP laminates based on Adamax-INN model for EIT

Carbon fiber reinforced polymer (CFRP) is electrically conductive, making it possible to detect structural damage of CFRP laminates with electrical impedance tomography (EIT). However, the inverse problem of EIT is severely non-linear, ill-posed, and underdetermined, thus limiting the resolution and accuracy of images reconstructed with EIT. This paper solves the inverse problem of EIT based on invertible neural networks (INN) and optimizes INN with Adamax gradient descent algorithm. Simulation and experimental results demonstrated that, compared with traditional EIT image reconstruction algorithms and radial basis function (RBF) neural network algorithm, the Adamax-INN model largely reduced the artifacts in reconstructed images, improved the damage recognition accuracy and edge clarity, and displayed good noise immunity.

Design and optimization of bionic Nautilus volute for a hydrodynamic retarder

To reduce the energy loss of volute and improve the emergency braking performance of hydrodynamic retarder under design condition, a bionic volute optimization design method is proposed based on the Nautilus shell. First, the accuracy of the numerical method is verified by grid convergence analysis and experiments. Thereafter, the bionic parametric expression is performed based on the cross-section shape of the Nautilus shell. Subsequently, sample points are created using the Optimal Latin Hypercube sampling method and numerically simulated. Radial basis function neural network and multi-objective genetic algorithm are used for optimization. Finally, the flow field inside the volute and the braking performance of the hydrodynamic retarder are compared by numerical calculation and experiment. Results show that the internal flow field of the bionic volute is more uniform, the energy loss is reduced by 78.95%, and the oil flow speed is increased by 40.61%. In addition, the stable flow field can be established faster during braking, the peak torque can be increased by 6.15%, and the onset time can be advanced by 6.58%. The analysis of energy characteristics shows that the improved performance of the bionic volute can be attributed to its improved internal oil flow conditions, thus reducing the energy loss.

Structural properties and diameter prediction of fine denier polyester fiber based on machine learning algorithms

Fine denier polyester fibers have attracted attention in electronic information industry owing to their unique structural properties and ultra fine diameters. Since there is a close connection between melt-spinning process parameters and their structural properties and diameters, the influence of process parameters on fiber structural properties and diameters is an issue worth further exploration. This study aims to construct prediction models based on the Gaussian process regression (GPR), radial basis function neural network (RBFNN) and extreme learning machine (ELM) algorithms to predict the structural properties and diameter of fine denier polyester fibers. For this purpose, firstly, fine denier polyester fibers with different structural properties (i.e., orientation degree and crystallinity) and diameters are produced by changing the key melt-spinning parameters, namely spinning temperature, take-up speed and metering pump speed. Then GPR, RBFNN and ELM methods are applied to predict the structural properties and diameter of fine denier polyester fibers based on the experimental data. Lastly, different predictive performance indicators, namely mean square error (MSE) and mean absolute error (MAE) are imported to evaluate the above three methods. The predicted results which the MSE values of GPR, RBFNN and ELM models are respectively 0.461, 0.358, 0.136, and the MAE values of GPR, RBFNN and ELM models are respectively 0.625, 0.564, 0.320 show that ELM model provided superior performance over the GPR and RBFNN models in predicting the structural properties and diameter of fine denier polyester fibers.

Neural network-based finite-time command-filtered adaptive backstepping control of electro-hydraulic servo system with a three-stage valve

This paper aims to improve the tracking control performance of the three-stage valve (TSV) controlled electro-hydraulic servo system (EHSS) with parameter uncertainties and other lumped unknown nonlinearities, including unknown dynamics and disturbances. A more accurate nonlinear model of the TSV-controlled EHSS is established and a neural network-based finite-time command-filtered adaptive backstepping control (NNFCABC) method is proposed for the EHSS. Adaptive control is used to deal with the system parameter uncertainties, and the radial basis function neural network (RBFNN) algorithm is introduced to approximate the lumped unknown nonlinearities. The prediction errors of serial-parallel estimation models (SPEMs) and the tracking errors are utilized together to design adaptive laws to estimate the system parameters and the weights of the RBFNNs. The entire control framework utilizes command-filtered control and backstepping techniques. By applying Levant differentiators as command filters and introducing fractional power terms into the virtual control laws and the SPEMs, the proposed NNFCABC theoretically guarantees the tracking performance of the closed-loop control system with finite-time convergence. Comparative simulations and experiments verify the feasibility and superiority of the proposed control scheme.

Electrical Impedance Tomography of Industrial Two-Phase Flow Based on Radial Basis Function Neural Network Optimized by the Artificial Bee Colony Algorithm.

In electrical impedance tomography (EIT) detection of industrial two-phase flows, the Gauss-Newton algorithm is often used for imaging. In complex cases with multiple bubbles, this method has poor imaging accuracy. To address this issue, a new algorithm called the artificial bee colony-optimized radial basis function neural network (ABC-RBFNN) is applied to industrial two-phase flow EIT for the first time. This algorithm aims to enhance the accuracy of image reconstruction in electrical impedance tomography (EIT) technology. The EIDORS-v3.10 software platform is utilized to generate electrode data for a 16-electrode EIT system with varying numbers of bubbles. This generated data is then employed as training data to effectively train the ABC-RBFNN model. The reconstructed electrical impedance image produced from this process is evaluated using the image correlation coefficient (ICC) and root mean square error (RMSE) criteria. Tests conducted on both noisy and noiseless test set data demonstrate that the ABC-RBFNN algorithm achieves a higher ICC value and a lower RMSE value compared to the Gauss-Newton algorithm and the radial basis function neural network (RBFNN) algorithm. These results validate that the ABC-RBFNN algorithm exhibits superior noise immunity. Tests conducted on bubble models of various sizes and quantities, as well as circular bubble models, demonstrate the ABC-RBFNN algorithm's capability to accurately determine the size and shape of bubbles. This outcome confirms the algorithm's generalization ability. Moreover, when experimental data collected from a 16-electrode EIT experimental device is employed as test data, the ABC-RBFNN algorithm consistently and accurately identifies the size and position of the target. This achievement establishes a solid foundation for the practical application of the algorithm.

Event-Triggered Cooperative Model-Free Adaptive Iterative Learning Control for Multiple Subway Trains With Actuator Faults.

This article investigates the issue of speed tracking and dynamic adjustment of headway for the repeatable multiple subway trains (MSTs) system in the case of actuator faults. First, the repeatable nonlinear subway train system is transformed into an iteration-related full-form dynamic linearization (IFFDL) data model. Then, the event-triggered cooperative model-free adaptive iterative learning control (ET-CMFAILC) scheme based on the IFFDL data model for MSTs is designed. The control scheme includes the following four parts: 1) the cooperative control algorithm is derived by the cost function to realize cooperation of MSTs; 2) the radial basis function neural network (RBFNN) algorithm along the iteration axis is constructed to compensate the effects of iteration-time-varying actuator faults; 3) the projection algorithm is employed to estimate unknown complex nonlinear terms; and 4) the asynchronous event-triggered mechanism operated along the time domain and iteration domain is applied to lessen the communication and computational burden. Theoretical analysis and simulation results show that the effectiveness of the proposed ET-CMFAILC scheme, which can ensure that the speed tracking errors of MSTs are bounded and the distances of adjacent subway trains are stabilized in the safe range.

Sliding mode control of antagonistically coupled pneumatic artificial muscles using radial basis neural network function

This study presents a novel approach to enhance the control of Pneumatic Artificial Muscle (PAM) systems by combining Sliding Mode Control (SMC) with the Radial Basis Function Neural Network (RBFNN) algorithm. PAMs, when configured antagonistically, offer several advantages in creating human-like actuators. However, their inherent nonlinearity and uncertainty pose challenges for achieving precise control, especially in rehabilitation applications where control quality is crucial for safety and efficacy. To address these challenges, we propose an RBF-SMC approach that leverages the nonlinear elimination capability of SMC and the adaptive learning ability of RBFNN. The integration of these two techniques aims to develop a robust controller capable of effectively dealing with the inherent disadvantages of PAM systems under various operating conditions. The suggested RBF-SMC approach is theoretically verified using the Lyapunov stability theory, providing a solid foundation for its effectiveness. To validate its performance, extensive multi-scenario experiments were conducted, serving as a significant contribution of this research. The results demonstrate the superior performance of the proposed controller compared to conventional controllers in terms of convergence time, robustness, and stability. This research offers a significant contribution to the field of PAM system control, particularly in the context of rehabilitation. The developed RBF-SMC approach provides an efficient and reliable solution to overcome the challenges posed by PAMs’ nonlinearity and uncertainty, enhancing control quality and ensuring the safety and efficacy of these systems in practical applications.

Comparison of Machine Learning Methods for Estimating Leaf Area Index and Aboveground Biomass of Cinnamomum camphora Based on UAV Multispectral Remote Sensing Data

UAV multispectral technology is used to obtain leaf area index (LAI) and aboveground biomass (AGB) information on Cinnamomum camphora (C. camphora) and to diagnose the growth condition of Cinnamomum camphora dwarf forests in a timely and rapid manner, which helps improve the precision management of Cinnamomum camphora dwarf forests. Multispectral remote sensing images provide large-area plant spectral information, which can provide a detailed quantitative assessment of LAI, AGB and other plant physicochemical parameters. They are very effective tools for assessing and analyzing plant health. In this study, the Cinnamomum camphora dwarf forest in the red soil area of south China is taken as the research object. Remote sensing images of Cinnamomum camphora dwarf forest canopy are obtained by the multispectral camera of an unmanned aerial vehicle (UAV). Extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), random forest (RF), radial basis function neural network (RBFNN) and support vector regression (SVR) algorithms are used to study the correlation and estimation accuracy between the original band reflectance, spectral indices and LAI and AGB of Cinnamomum camphora. The results of this study showed the following: (1) The accuracy of model estimation based on RF is significantly different for different model inputs, while the other four models have small differences. (2) The accuracy of the XGBoost-based LAI model was the highest; with original band reflectance as the model input, the R2 of the model test set was 0.862, and the RMSE was 0.390. (3) The accuracy of the XGBoost-based AGB model was the highest; with spectral indices as the model input, the R2 of the model test set was 0.929, and the RMSE was 587.746 kg·hm−2. (4) The XGBoost model was the best model for the LAI and AGB estimation of Cinnamomum camphora, which was followed by GBDT, RF, RFNN, and SVR. This research result can provide a theoretical basis for monitoring a Cinnamomum camphora dwarf forest based on UAV multispectral technology and a reference for rapidly estimating Cinnamomum camphora growth parameters.

Dynamic particle swarm optimization-radial function extremum neural network method of HCF probability analysis for compressor blade

The high cycle fatigue (HCF) of compressor rotor seriously affects the performance and reliability of gas turbine. Probabilistic HCF evaluation is an effective measure to quantify the uncertain traits of vibration stresses and assess the reliable HCF life for compressor rotor. To improve modeling accuracy and computational efficiency in transient probability analysis of HCF life of gas turbine compressor, radial basis function neural network (RBFNN) and dynamic particle swarm optimization (DPSO) algorithm were introduced into extreme response surface method (ERSM). In this paper, we propose a HCF life probability evaluation method for compressor blades based on the dynamic particle swarm optimization-radial basis function extremum neural network (DPSO-RBFENN) model. By selecting random input variables such as aerodynamic load, centrifugal load and material parameters, a prediction model was established based on DPSO-RBFENN sample learning, and the reliability evaluation of compressor blade HCF life was carried out. Distribution characteristics, reliability and sensitivity to fatigue life were obtained, which provided a basis for the structural design of compressor blades. The Monte Carlo method, ERSM, RBFNN and DPSO-RBFENN are compared.