149 results about "Quantum particle swarm optimization" patented technology

The invention discloses a quantum-behaved particle swarm optimization (QPSO) based multi-objective dynamic workflow scheduling method, and belongs to the technical field of cloud computing. The method includes the steps: inputting a workflow and a QoS (quality of service) request; acquiring state information of virtual machines and transmission information among the virtual machines; setting a to-be-executed task set V', and setting objective functions of time, cost and reliability for a task schedule in the V'; allocating optimal resources to the to-be-executed tasks by the aid of QPSO, and judging whether total time, total cost and total reliability of task execution meet the QoS request of a user or not after the tasks are executed; dynamically updating the V', transmission speed among the virtual machines and operating speeds of the virtual machines. By means of dynamically partitioning the workflow and dynamically updating network bandwidth information, the optimal resources are allocated to the workflow tasks accurately, errors between the calculated time and actual execution time and the calculated cost and actual execution cost are reduced, time can be shortened, and cost is reduced while reliability is enhanced.

A method for diagnosing analog circuit fault based on vector-valued regularized kernel function approximation, includes steps of: step (1) acquiring a fault response voltage signal of an analog circuit; step (2) carrying out wavelet packet transform on the collected signal, and calculating a wavelet packet coefficient energy value as a characteristic parameter; step (3) utilizing a quantum particle swarm optimization algorithm to optimize a regularization parameter and kernel parameter of vector-valued regularized kernel function approximation, and training a fault diagnosis model; and step (4) utilizing the trained diagnosis model to recognize circuit faults.

The invention discloses a mobile robot path planning method based on the binary quantum particle swarm optimization, which is characterized by comprising steps of 1, simplifying a robot into a point moving in a two-dimensional space, and then sensing the present position of the robot and the present positions of obstacles via the visual system, 2, processing all the obstacles sensed by the visual system of the robot into convex polygons, 3, discretizing the two-dimensional space into series grids, and performing binary encoding for eight probable motion directions of the robot at each grid, 4, defining the distance of the path between the starting point and the destination point as a target function required to be solved by the method, and 5, overall optimizing the target function in the step 4 by utilizing the binary quantum particle swarm optimization aiming to the discrete characteristics of robot path planning problems to obtain the optimum mobile robot path. The invention has the advantages of simple process, easy realizing, good robustness, high solving efficiency and the like.

The invention provides a spatial robot prediction control method based on a quantum particle swarm optimization algorithm. Firstly, a lagrangian dynamic model of a spatial robot system is establishedon the basis of an extended mechanical arm method, and a discrete state space model is established by combining the dynamic model with a kinematic model; secondly, a corresponding discrete model prediction controller is designed on the basis of a system extended state space model and a Laguerre polynomial; finally, rolling optimization is conducted on performance indexes under the constraint condition through the quantum particle swarm optimization algorithm, and prediction errors are subjected to feedback correction, so that effective tracking of tail end desired trajectory is achieved. According to the control method, effective tracking of the tail end desired trajectory can be achieved under the given constraint condition, and task space trajectory planning does not need to be carried out in advance; the situation that a global optimum solution cannot be found through a conventional quadratic programming algorithm under multi-constraint conditions can be avoided; energy consumptioncan be optimized while the requirement of tracking precision is met.

The invention relates to a micro-grid load prediction system and method based on electricity purchased on-line and a dynamic correlation factor. The system includes an electric quantity purchased on line module, a load characteristic analysis module, a short period load prediction module and a prediction result output module. The method comprises the steps: pushing an initially-drafted order of electric quantity and a reference electricity price to an electric energy user by a micro-grid; correcting the initially-drafted order of electric quantity, and feeding back the corrected order of electric quantity to the micro-grid by the user; counting the statistical values of electric quantity purchased on line and the historical load data for various load users, determining the load type of the micro-grid and the correlation factor of the load type; establishing an RBF neural network mathematic model; utilizing a subtractive clustering K-means optimization algorithm based on the input data and the output data to acquire initial network parameters of the RBF neural network mathematic model; utilizing a quantum particle swarm optimization algorithm to optimize the initial network parameters; calculating the final predicted values of various loads of the micro-grid and the final predicted value of the total load; and outputting the final predicted values of various loads of the micro-grid and the final predicted value of the total load of the micro-grid.

The invention discloses an EMD-SVR-based ground surface settlement amount prediction method. The method is an EMD, QPSO-SVR and ARIMA model-based ground surface settlement time sequence prediction method. A ground surface settlement actual measurement sequence is decomposed and reconstructed into a fluctuation component and a trend component by utilizing EMD; data is classified into two categories by adopting a sliding window method, wherein one part is used for model training and the other part is used for testing; then an ARIMA model and a QPSO-SVM model are built for analyzing the two components; and finally predicted values are subjected to summation, thereby obtaining a final predicted result. Compared with other settlement prediction methods, the method has the characteristics of high prediction precision, satisfied construction requirements and wide application range.

The invention relates to a clustering method, in particular relates to an improved fuzzy C-mean clustering method based on quantum particle swarm optimization, and belongs to the technical field of data mining and artificial intelligence. The improved fuzzy C-mean clustering method comprises the steps of: firstly, based on the conventional fuzzy C-mean clustering algorithm, improving the fuzzy accuracy of the conventional clustering algorithm by using a novel distance standard in place of a Euclidean standard; meanwhile classifying singly and quickly through using an AFCM (Adaptive Fuzzy C-means) algorithm to replace a randomly distributed initial clustering center to reduce the sensitivity of the clustering algorithm on the initial clustering center; and finally, introducing a QPSO (AQPSO (Adaptive-Quantum Particle Swarm Optimization)) parallel optimization concept based on distance improvement in a clustering process, so that the clustering algorithm has relatively strong overall search capability, relatively high convergence precision, and can guarantee the convergence speed and obviously improve the clustering effect.

The invention discloses an electronic nose signal processing method based on a mixing characteristic matrix. The method comprises the steps that first, characteristic extraction is conducted on an original data matrix to establish the mixing characteristic matrix, then a binary quantum particle swarm optimization algorithm is used for conducting characteristic selection on the mixing characteristic matrix, at last, the mixing characteristic matrix is fed into a classifier, a decimal quantum particle swarm optimization algorithm is used for conducting synchronous optimization on mixing characteristic sub matrixes and the parameters of the classifier, mode recognition is conducted to determine the mixing characteristic sub matrix with the highest recognition rate, and the sensor characteristic corresponding to the mixing characteristic sub matrix is selected to be used as the optimized characteristic of an electronic nose signal for conducting mode recognition. The electronic nose signal processing method based on the mixing characteristic matrix has the advantages that the defect that the complete information of an entire response curve can not be reflected only by extracting a single characteristic is overcome; the operation complexity is lowered, the problem of redundancy between sensors is effectively solved, the recognition rate of wound infection detection of an electronic nose is improved, and beneficial guidance can be provided for a doctor to choose a proper treatment method.

The invention belongs to the technical field of power system disaster warning, and particularly relates to a power transmission line icing prediction method based on a relevance vector machine. According to the prediction method, according to features of an icing phenomenon, the input quantity and weight index of an icing prediction model are selected and processed in a targeted mode; a power transmission line icing prediction model is built through a relevance vector machine method; training is conducted on the model through sample data, and the model is optimized by the adoption of a quantum particle swarm optimization and a K-fold cross-validation method; the icing thickness and probability distribution of a power transmission line are predicted according to the test data, and correction is further conducted on the model through repeated training to improve prediction accuracy. The prediction method considers the influences, on power transmission line icing, of various factors comprehensively, can predict the icing thickness of the power transmission line precisely and has very high prediction accuracy and generalization ability.

The invention relates to the field of unmanned vehicle control, and provides a parallel design scheme using quantum particle swarm optimization, to ensure that the control output meets the physical constraints of the vehicle and the comfort requirement for a human body so as to enable the vehicle to preferably adapt to the current road condition. The technical scheme of the parallel design schemeusing quantum particle swarm optimization includes the steps: establishing a kinetic model based on an unmanned vehicle, and performing discretization on the kinetic model; based on the above step, constructing a generalized cost function with a punishment item and an encouragement item by using a generalized Lagrangian multiplier so as to convert the constraint problem into a nonrestraint problem; and performing parallel design of quantum particle swarm optimization, performing optimized solution on the cost function of model prediction control by means of the parallel design to obtain a series of controlled variables, and finally acting the first component of the controlled variables on the vehicle. The parallel design scheme using quantum particle swarm optimization is mainly applied tothe unmanned vehicle control occasion.

The invention discloses a graph-theory-based intelligent optimization method for failure recovery of a smart distribution grid. The method comprises the following steps of 1) inputting network parameters including an original structure of a distribution network, line parameters of each branch, load of each node, DG (Distributed Generation) data and other parameters; 2) inputting a number of the current faulty line and zeroing the corresponding switching state thereof; 3) setting dimensionality, iterations and corresponding parameter values of a quantum particle swarm optimization algorithm; 4) initializing a position value xk, a quantum bit, a rotation angle, a local optimal vector xp and a global optimal vector xg of each particle; 5) correcting the position value of each particle based on a graph theory; 6) updating a rotation angle guiding value, a quantum rotation angle and a bit of each quantum particle in sequence; 7) updating the position value xk of each quantum particle; 8) updating the local optimal vector and the global optimal vector of each particle; 9) carrying out convergence test; and 10) outputting an optimal particle position value x to obtain a corresponding failure recovery strategy.

The invention discloses a two-dimensional dual-threshold SAR image segmentation method based on quantum particle swarm optimization. The method comprises the realization steps: (1) initializing the particle swarm population size M and the maximum iterations Tmax and generating the initial position of each particle randomly; (2) calculating a fitness function, and obtaining the optimal position of a current particle and an overall optimal position of iteration of this time according to the maximum in-cluster variance value; (3) calculating Pid and mbestd; (4) constructing a random number set; (5) setting a definition value, judging the relation between the random number set and the definition value, and upgrading the position of each particle according to a formula; (6) checking whether the end condition is achieved, achieving the end if yes, or else executing the steps from two to five; (7) segmenting an SAR image according to a pair of searched optimal thresholds stored in two dimensions of the particle pointed by the overall optimal position. Compared with a classical segmentation method, the segmentation method is good in effect of dividing the SAR image, and relatively small in time complexity.

The invention discloses a quantum optimization parameter adjustment method for distributed deep learning under a Spark framework. The method comprises the following steps of data is collected, preprocessed and grouped and generative adversarial network structure parameters are determined; deep neural network is preliminary constructed, including, number of layers,, node number of each layer, weight and learning rate and the Spark master node broadcasts the parameter information to the slave node; a generative adversarial network model is trained in a data parallel mode; initializing Spark-based distributed quantum particle swarm optimization algorithm parameter information; and each slave node performs distributed independent evolution, summarizes the evolutions through the master node, calculates a fitness function value corresponding to each particle according to the individual optimal and global optimal update connection weights in the previous iteration, and evaluates the performance of the deep learning model. The invention can provide a reference method for how to find the optimal parameter for the distributed deep learning model, and can avoid the problems of priori knowledge required by manual parameter adjustment of the deep learning model and low efficiency.

The invention relates to a method for evaluating the income and risk of power grid power purchase portfolio under the constraints of peak regulation. The weighted conditional risk value is used to measure the power purchase risk of provincial power grid companies, and a multi-objective optimization model for power grid companies to maximize expected revenue and minimize risks is established. . Under the background of implementing peak-valley time-of-use electricity price on the electricity sales side, taking into account the constraints of the provincial power grid’s peak regulation and the power-quantity coupling equation of inter-provincial power purchases, the multi-objective quantum particle swarm algorithm is used to solve the problem, and different benefits and risks are obtained. The horizontal inter-provincial and intra-provincial optimal power purchase combination sets for various markets allow power purchase decision makers to make rational power purchase decisions based on their own risk preferences and allocate power purchases reasonably. The method proposed by the invention reflects the profit and risk level of power grid companies participating in inter-provincial power purchase transactions in the regional power market environment, and uses intuitive economic signals to reflect the risk value. Provide reference for power grid companies to coordinate and optimize inter-provincial and intra-provincial power purchases.

The invention discloses a road traffic capacity evaluation method based on cusp-catastrophe and quantum-behaved particle swarm optimization. The method comprises the following steps: establishing a catastrophic model by taking a vehicle speed of a traffic flow as a state variable and taking traffic and lane time occupancy as a control variable, determining model parameters by using partial time period data of the traffic flow, and obtaining the minimum velocity capable of maintaining a clear state on the selected road section by virtue of the determined model, thereby completing road evaluation. According to the method disclosed by the invention, the road evaluation accuracy and working efficiency can be effectively improved.

The invention relates to a continuous-laser-based method for obtaining spherical particle spectrum complex refractive index and particle system particle size distribution, belonging to the technical field of particle optical property measurement, and aiming at solving the problems that the conventional method for obtaining the spherical particle spectrum complex refractive index and the particle system particle size distribution can not be used for directly measuring and is not accurate in measuring results. According to the continuous-laser-based method, a model is solved by establishing forward problem and inverse problem of the measurement of a spherical particle system reflecting signal, a transmission signal and a collimating transmission signal, and the spherical particle spectrum complex refractive index and the particle system particle size distribution condition can be obtained by inversion. The method adopts the continuous laser, and a laser is low in price, simple in model and convenient in theory solution; the Mie theoretical model is adopted, so that the electromagnetic scattering property of particles can be accurately reflected; a quantum particle swarm optimization algorithm is adopted, so that the method has the advantages of being simple, efficient, high in sensitivity and the like. The method is suitable for measuring the particle optical properties.

The invention discloses a power transformer fault diagnosis method based on relative transformation and kernel entropy component analysis, which adopts the relative transformation kernel entropy component analysis method to extract features, constructs a training sample set and a test sample set of a kernel limit learning machine, and then trains a kernel limit learning machine classifier to forma final RTKECA-KELM diagnostic model; optimization of RTKECA by Adaptive Quantum Particle Swarm Optimization-KELM diagnoses the model parameters, obtains the optimal model parameter combination, and saves the optimal RTKECA-KELM diagnostic model; entering test samples or samples to be diagnosed into the trained optimal RTKECA-KELM diagnostic model. The invention not only can utilize the advantagesof nonlinear amplification and noise suppression of RT, but also can give play to the advantages of KECA non-linear feature extraction, has good feature extraction effect, has higher fault diagnosisaccuracy, and effectively improves the fault diagnosis accuracy of the model.

The invention introduces the fuzzy clustering technology according to the characteristics that boundaries between different soft tissues or the soft tissues and lesions are fuzzy and fine structure distribution is complex, performs optimization by using the improved quantum particle swarm optimization algorithm, and provides an image segmentation method on the above basis. The invention uses a newimproved quantum particle swarm optimization algorithm to effectively overcome the defect that the standard fuzzy C-means fuzzy clustering algorithm relies on an initial cluster center, which is prone to local optimum, so that the medical image is segmented well. Since the method can always effectively converge after initial conditions are given, the method has a good effect for dealing with problems such as blurring and unclear boundaries that are often present in medical images. The method can preserve more original information in the process of processing medical images, and the robustnessof the method is higher than that of other segmentation algorithms such as hard clustering.

The invention discloses a wind farm dynamic equivalent modeling method suitable for long-time domain wind speed fluctuation, which adopts quantum particle swarm optimization to optimize fuzzy C-mean clustering algorithm for clustering, A wind turbine generator set of the same group is equivalent to a wind turbine generator set (called equivalent wind turbine generator set), and the equivalent input wind speed of the equivalent wind turbine set is real-time equivalent, and the parameters of the wind turbine set are identified, and then the wind farm power collection system is equivalent, so that the wind farm dynamic equivalent model suitable for long-time wind speed fluctuation is obtained. The invention comprehensively considers the variation characteristics of wind speed of the wind farm with time, adopts the quantum particle swarm optimization fuzzy C with high clustering accuracy and strong global optimization searching ability, and adopts the quantum particle swarm optimization fuzzy C, Mean value clustering can obtain the wind farm dynamic equivalent model which can accurately reflect the external characteristics of the real wind farm.

The invention discloses an electronic nose parameter synchronous optimization algorithm based on an improved quantum particle swarm optimization algorithm. The method comprises performing wavelet transformation on obtained original electronic nose data; then performing weighting treatment of wavelet coefficients; through the improved quantum particle swarm optimization algorithm based on a novel local attractor computing manner, finding out a weighting coefficient corresponding to the highest electronic nose identifying rate, and classifier parameters to obtain a characteristic matrix of electronic nose signals; inputting the characteristic matrix into a classifier for mode identification. The electronic nose parameter synchronous optimization algorithm based on the improved quantum particle swarm optimization algorithm has the advantages of enhancing early-stage ergodicity and later-stage local optimizing capacity of particles, improving the capacity of quantum particle swarms in searching for global optimal values, and especially for wound infection detection, improving the identification rate of an electronic nose, thereby selecting appropriate treatment methods for doctors and providing beneficial guidance for promoting quick recovery of wounds.

The invention provides a method for identifying carbonate rock fluid based on a fuzzy C mean cluster in oil exploration. According to the method, chaotic quantum particle swarm optimization (CQPSO) and a fuzzy C mean (FCM) algorithm are organically bonded, chaotic particle swarm optimization is utilized to initialize a membership matrix, the problem that a traditional fuzzy C mean algorithm is sensitive to initialization can be effectively solved, high capability for searching global optimal solution is possessed, and fuzzy classification capability is remarkably improved. The method is introduced into carbonate rock fluid identification, the problem that rock physical analysis results and seismic inversion results are not matched due to frequency dispersion of seismic data can be effectively solved, and identification accuracy of the carbonate rock fluid is improved. Besides, by means of the method, probability of properties of various fluids can be calculated, evaluation on indeterminacy of fluid identification can be conducted so that exploration risks can be effectively reduced, and a new research thought for fully utilizing various prestack elastic information to achieve carbonate rock reservoir fluid identification is provided.

The present invention discloses a variational mode decomposition-based single-channel radio mixed signal separation method. According to the method, the component number and penalty factor of a variational mode decompositionn algorithm are improved simultaneously through an improved quantum particle swarm optimization algorithm, and the values of the component number and penalty factor of the variational mode decompositionn algorithm are determined; the parameter optimized variational mode decompositionn algorithm is adopted to separate single-channel radio mixed signals; since the signal-to-noise ratio of the single-channel radio signals to be processed is relatively low, the signal-to-noise ratio of radio signals obtained after the separation is increased, but a large quantity of noisesstill exist; therefore, the parameter-optimized variational mode decomposition algorithm is adopted to perform secondary separation on the radio signals; the reliability of radio signals obtained after the secondary separation is higher than that of the radio signals obtained after the first separation.

The invention discloses an access point selection and resource distribution combined self-healing method in an ultra-dense network, and belongs to the field of the ultra-dense network. The method comprises following steps that firstly, a WNCU judges whether faults appear in access points or not; the WNCU records a name list of communication damaged users served by the access points and broadcasts the name list to adjacent access points if the faults appear in the access points; the adjacent access points divide self-healing subchannels from own normal subchannels dynamically; then, the communication damaged users select suitable adjacent access points so as to obtain service continuously according to self-healing channel dividing results and own speed requests; and finally the access points distribute resources to original users and newly accessing communication damaged users again by using a quantum particle swarm optimization algorithm. The method has the advantages that the self-healing function in the ultra-dense network is realized; when the faults appear in the access points, the service demands of the communication damaged users can be effectively ensured; the system energy efficiency is improved; and the operation cost is reduced.

The invention relates to a reactive power optimization method of a photovoltaic system based on a quantum particle swarm algorithm, belonging to the technical field of reactive power regulation of a photovoltaic power station. The method of the invention comprises the following steps: (1) analyzing the influence of grid-connected photovoltaic power station on the voltage of the distribution network system; 2, establishing a mathematical model for optimizing that reactive power compensation of a distribution network of a photovoltaic power station; Step 3, solving the reactive power optimization model of the photovoltaic system by using the quantum particle swarm optimization algorithm. The reactive power optimization method of the photovoltaic system based on the quantum particle swarm algorithm provided by the invention can effectively reduce the active power network loss, obviously increase the voltage value of each node, and enable the distribution network system to run more economically and stably.

The invention discloses a method for scheduling a machine part processing line by adopting the discrete quantum particle swarm optimization, comprising the following steps: reading in the machine part processing process operation time, initializing a particle swarm, calculating the adaptation value of each particle, updating the individual optimal position and the global optimal position of each particle, carrying out global search on the basis of the discrete quantum particle optimization, carrying out local search and drawing a machine part processing sequence Gantt chart according to a global optimal scheduling scheme. The method disclosed by the invention improves the limitation of the traditional quantum particle swarm optimization in the production scheduling field, overcomes the defects that the quantum particle swarm is easy to be subjected to local optimization and has the advantages of high optimizing precision and high optimizing speed. The method is used for scheduling the machine part processing line, can solve to obtain an optimal scheduling scheme in a shorter time and is easy and convenient to operate. The principle has wide range of application and can be popularized to the producing and processing field of the manufacturing industry, the process industry and the like.

The invention discloses a quantum-behaved particle swarm optimization (QPSO) recurrent predictor neural network (RPNN) method for financial time series prediction, which relates to analysis and prediction on a time sequence. Chaos and phase space reconstruction theories are firstly applied, through a saturation correlation dimension (G-P) method, a chaotic financial time series attractor dimension is calculated, and the structure of the RPNN is determined; then, the RPNN is trained by the QPSO algorithm; and finally, the dynamic optimal weight and the threshold of the network are determined, and thus, the simulation prediction value of the RPNN and the actual value can reach the minimum error precision. The problem that optimization of the RPNN based on a gradient algorithm is easy to fall into local minimum can be solved, and the built QPSO-RPNN optimization prediction method can be widely applied in financial investment and social economy, and has the advantages that the convergence rate is quick, the searching is global, the programming is simple and efficient, and the prediction precision is high.

The invention provides a power transformer fault prediction and diagnosis method based on audio characteristics. The method specifically comprises the steps that S1, detecting effective signals of power transformer audio data under the noise background based on chaotic oscillators; S2, calculating a logarithm energy spectrum on the nonlinear Mel scale to serve as a characteristic quantity of the audio signal of a power transformer; S3, calculating a principal component of the audio signal characteristic quantity of the power transformer by adopting a principal component analysis method; S4, optimizing the optimal hyper-parameter training power transformer fault prediction model of the vector machine algorithm by adopting a quantum particle swarm optimization algorithm; and S5, if the powertransformer is in a fault state, adopting a 1 / 3 octave algorithm to extract the fault characteristic frequency range amplitude, comparing the fault characteristic frequency range amplitude with an expert experience rule base, and predicting / obtaining the fault type of the power transformer. According to the method, the identification precision of power transformer operation state fault predictioncan be improved, and the calculation amount is reduced; fault judgment can be carried out based on other measurement data or infrared images.

The invention discloses an Internet of Vehicles traffic flow prediction method (MPSO-RBF) based on a quantum particle swarm optimization strategy, and solves the problem of how to accurately predict the future traffic flow of urban roads. The method comprises the following steps: establishing a traffic flow prediction mathematical model, namely establishing a corresponding model according to traffic flow data characteristics, optimizing an initial clustering center by using a simulated annealing algorithm and a genetic algorithm, and training an RBF network by using a fuzzy mean clustering algorithm; an improved quantum particle swarm optimization strategy is used, the randomness of particle positions is increased, and optimized neural network parameters are output; and applying the optimized algorithm to parameter optimization of the radial basis function neural network prediction model, and obtaining a data result needing to be predicted through high-dimensional mapping of the radialbasis function neural network. Test results show that the algorithm provided by the invention can reduce prediction errors and obtain better and more stable prediction results.

A power plant boiler NOx prediction model device based on improved quantum particle swarm optimization disclosed by the present inventon is composed of an on-site data acquisition device, a computer device and a communication device. The on-site data acquisition device prepares for establishing the prediction model of NOx emission concentration of boiler in the next step. The computer device realizes the model algorithm operation, utilizes the improved quantum particle swarm optimization algorithm to optimize the initial parameters of the limit learning machine, takes the error minimization ofthe training data prediction value and the actual value as the goal, and then obtains the accurate NOx emission model. The invention has the advantages that the improved quantum particle swarm algorithm can efficiently and quickly calculate the optimal initial parameters of the limit learning machine, so that the accurate NOx emission model of a boiler of a thermal power plant is obtained, whichis of great significance for reducing the pollutant emission of a coal-fired unit.

A vector-valued regularized kernel function approximation (VVRKFA) based fault diagnosis method for an analog circuit comprises the following steps: (1) obtaining fault response voltage signals of an analog circuit; (2) performing wavelet packet transform on the collected signals, and calculating wavelet packet coefficient energy values as feature parameters; (3) optimizing regularization parameters and kernel parameters of VVRKFA by using a quantum particle swarm optimization algorithm and training a fault diagnosis model; and (4) identifying a circuit fault by using the trained diagnosis model. In the invention, the classification performance of the VVRKFA method is superior to other classification algorithms, and optimization of parameters by the quantum particle swarm optimization (QPSO) algorithm is also superior to the traditional method of obtaining parameters. The fault diagnosis method provided by the invention can efficiently diagnose the component faults of the circuit, including soft faults and hard faults.