59 results about "Fuzzy inference system" patented technology

The invention relates to a kitchen waste sewage accurate aeration control method, system and device based on fuzzy PID and deep learning and a medium, and the method comprises the steps: collecting parameters, and processing the parameters to obtain preprocessed data; predicting the oxygen demand through a deep learning time sequence prediction model, and generating a dissolved oxygen set value interval in combination with multi-target reinforcement learning; based on the deviation and the deviation change rate of a dissolved oxygen set value interval and a real-time measured value, an evolutionary fuzzy reasoning system is used for adjusting gain parameters of an aeration controller, PID control quantity is output and converted into an aeration equipment driving signal, and multi-area aeration intensity dynamic distribution is implemented in combination with a hydrodynamic mapping relation and preprocessed data. Through the synergistic effect of the technologies, the core defects of single sensing dimension, prediction lag, control target conflict, extensive execution and the like of a traditional method are systematically solved, and collaborative optimization of degradation efficiency, energy consumption economy and equipment operation life in the kitchen waste sewage treatment process is realized.

The invention relates to the technical field of heavy-load robot control, in particular to a self-adaptive robust control method of a heavy-load robot fusing differential homeomorphic mapping. According to the method, position information of each joint is collected in real time and accurately compared with an expected trajectory, a ternary input vector is output, differential homeomorphic mapping parameters are updated in real time through a T-S fuzzy inference system, and a joint space state is mapped to a new coordinate space based on the optimized parameters, so that the position information of each joint is accurately compared with the expected trajectory. Neighbor joint information is obtained through distributed communication to generate a cooperative control item, a sliding mode surface is constructed in combination with a local tracking error to generate a robust control item, a compensation item is generated based on adaptive law estimation parameter uncertainty, three-item parallel control output is formed, dynamic weight distribution and fusion are performed on the three control items, a basic control moment is obtained, and the control precision is improved. And then a feed-forward compensation item based on a nominal dynamical model is superposed to generate a final comprehensive control torque, and the comprehensive control torque optimizes energy distribution while ensuring the performance.

A power transformation equipment oil temperature prediction and abnormity early warning method based on a fuzzy algorithm comprises the following steps that real-time operation parameters and oil temperature historical data of power transformation equipment are collected, the data are preprocessed, and a high-quality input data set is constructed; constructing a fuzzy inference system considering multiple input factors, and setting a fuzzy membership function and an inference rule base; according to the fuzzy prediction result and the real-time oil temperature change, a self-adaptive dynamic safety threshold model is compared, a potential abnormal trend is identified, and automatic grading early warning is carried out according to the overtemperature grade; and corresponding exception type identifiers and disposal suggestions are generated and are pushed to the operation and maintenance platform through the communication module, so that remote operation and maintenance scheduling and response control are supported, and intelligent cooperative processing is realized. According to the invention, intelligent prediction of the oil temperature change trend under the influence of multiple factors is realized, the capability of sensing temperature rise abnormity in advance is improved, the accuracy of sensing the operation state of the equipment and the timeliness of early warning response are also remarkably improved, and the risk of equipment failure caused by the abnormal oil temperature is reduced.

The invention discloses a real-time closed-loop regulation and control method and system for the forming process of a stainless steel welded pipe. The method comprises the steps that multi-source heterogeneous data including a pipe shape image, a laser ranging sequence, temperature field distribution and roller pressure time sequence data in the forming process are synchronously collected through a distributed multi-source sensor network; performing space-time alignment and feature level fusion on the multi-source heterogeneous data, and constructing a multi-dimensional dynamic digital twinborn body in the forming process; on the basis of the multi-dimensional dynamic digital twins, an online rolling prediction model is adopted to deduce the development trend of weld forming quality and pipe diameter size deviation in real time; and according to the development trend, a cooperative regulation and control instruction set of the roller gap and the welding power is generated through a self-adaptive fuzzy inference system. By means of the embodiment of the invention, multivariable look-ahead perception and intelligent collaborative closed-loop regulation and control of technological parameters in the stainless steel welded pipe forming process can be achieved, and the stability and consistency of the forming quality are improved.

This invention discloses an adaptive neurofuzzy system for diabetes analysis and integration, comprising the following steps: S1: inputting the dataset into a CIR-ANFIS model, where the model first standardizes the dataset; S2: calculating the causal coefficient corresponding to the prediction result for each feature using causal inference, and using this coefficient as the feature weight; S3: randomly selecting multiple different subsets, constructing an adaptive fuzzy inference system for each subset, and obtaining the prediction result of each inference system; S4: obtaining the prediction result of the entire model through ensemble learning. This invention relates to the field of computer algorithm technology. The beneficial effect of this invention is that by introducing causal inference into feature selection and using causal coefficients as weights to randomly generate data subsets for training, the model training cost is reduced, and better model performance is achieved.

The present application relates to the technical field of three-dimensional point cloud data processing, in particular to a point cloud hole repairing method and system based on adaptive neighborhood and genetic fuzzy. For unorganized point cloud data, first, the curvature, normalized curvature and local density coefficient of each point are calculated through principal component analysis, and adaptive neighborhood with adaptive local geometric features is dynamically generated in combination with the reference neighborhood; then, based on the adaptive neighborhood, boundary features are extracted and hole boundary points are screened, and single-hole boundary sets are obtained through connected component division; subsequently, a single-hole local projection plane is constructed to generate two-dimensional repair points, after global overlap and deduplication, a fuzzy reasoning system optimized by a genetic algorithm is used to estimate the height coordinates of the repair points, three-dimensional repair points are generated to complete hole filling. The present application effectively improves the boundary recognition accuracy in high-curvature areas with uneven density, while taking into account the edge continuity and surface smoothness, and is suitable for complex topography unorganized point cloud hole repair scenarios.

The application discloses a kind of based on adaptive neural fuzzy inference fuel cell ship energy management strategy method, comprising the following steps: obtaining the topological structure of fuel cell ship hybrid power system, and its operating typical working condition information, the steps of obtaining the globally optimal hybrid power system load distribution by offline algorithm;By discrete solving working condition every moment optimal equivalent factor, the step of taking working condition calculation result as training sample;Build and train adaptive neural fuzzy inference system (ANFIS), calculate to obtain optimal equivalent factor, the step of bringing result into ECMS algorithm, on-line calculation ship sailing working condition obtains optimal distribution result, the improvement of the present application is realized on-line ideal power distribution by ANFIS calculation ECMS equivalent factor, combined with the calculation characteristics of three strategies, can on-line calculation obtain the optimal solution of ship real-time power distribution, with good global optimization ability.

The invention discloses an intelligent storage and accurate scheduling method for a multi-energy complementary power system. The method comprises the following steps: collecting and preprocessing wind and light output, energy storage state, load and meteorological data in real time; predicting a load demand based on a hybrid neural network of LSTM and an attention mechanism; the weight coefficients of the cost and the energy abandoning rate are dynamically adjusted through a fuzzy inference system; constructing a power generation, energy storage and power grid intelligent agent collaborative decision by adopting an improved depth deterministic strategy gradient algorithm, and generating a scheduling instruction in combination with a Pareto frontier storage pool and an attention mechanism; controlling the energy storage system to charge and discharge according to the instruction; and online updating of model parameters and dynamic correction of a scheduling strategy are realized through closed-loop feedback and cross-layer optimization. According to the method, the dynamic balance problem in multi-objective optimization is effectively solved, the energy utilization efficiency is improved, the operation cost and the energy abandoning rate are reduced, the system stability is enhanced, and the energy storage life is prolonged.

The present application belongs to the technical field of ship working condition prediction, and discloses a rotating speed prediction method for a ship gas-electric hybrid power system. A ship gas-electric hybrid power propeller rotating speed prediction model is constructed based on an adaptive neuro-fuzzy inference system (ANFIS); a difference between the obtained predicted rotating speed and the actual rotating speed is obtained; an improved rotating speed prediction model is constructed using the obtained difference and the used rotating speed information; and future rotating speed prediction is performed through the constructed improved rotating speed prediction model. The present application uses the initially constructed rotating speed prediction model to obtain the first-step predicted rotating speed, and provides the difference between the predicted rotating speed and the actual rotating speed for the improved prediction model; the improved rotating speed prediction model is constructed according to the obtained difference and the initial rotating speed information, so as to improve the rotating speed prediction accuracy and achieve the real-time prediction effect within a given time step.

The application discloses a self-diagnosis modular lightning arrester state monitoring system, which comprises a sensing module, an extension module, a power supply module, a communication module and a processing module; the sensing module is used for collecting full current signals, surface temperature signals and partial discharge signals of the lightning arrester; the extension module is used for accessing environmental humidity signals and internal pressure signals of the lightning arrester through a controller area network bus interface; the power supply module is used for extracting energy from induced current of a grounding down lead of the lightning arrester to provide electric energy required by system operation; the communication module is used for sending monitoring data to a remote operation and maintenance server; and the processing module is used for receiving various sensor signals, extracting a resistive current component by using a fast Fourier transform algorithm, constructing a three-dimensional feature vector containing a resistive current fundamental component, a partial discharge pulse number and a temperature change rate, and outputting a fault type recognition result through a honeybee algorithm optimization self-adaptive network fuzzy reasoning system classifier.

The application provides a medical data-oriented deep convolution fuzzy neural network and a training method thereof, and comprises a medical data explainability prediction model (IP-DCFNN) based on a deep convolution fuzzy neural network. The IP-DCFNN is composed of three parts: a fuzzy logic antecedent part, a deep convolution calculation part and a fuzzy result representation part. The fuzzy logic antecedent part extracts input data, and the input data is converted from a numerical value into a set of membership degree values for fuzzy language scalars through the operation of a membership function in the fuzzy logic antecedent part. The deep convolution calculation part extracts hidden features in input rule weights, and converts hidden layer weights into high latitude information representation. The fuzzy result representation part is used to process the defuzzification process in fuzzy reasoning. The application relates to the technical field of computer technology, and the IP-DCFNN adds the concept of a deep convolution neural network on the basis of a fuzzy reasoning system to achieve the explainability prediction capability for medical data.

An Adaptive Neuro-Fuzzy Inference System (ANFIS) for total intravenous anesthesia management is disclosed, enabling control over administration of anesthetic agents and dynamic adjustment according to patient physiological feedback. The system processes patient data, including processed EEG signals, hemodynamic information, capnography, and pulse oximetry, to facilitate real-time anesthetic dosage adjustments.

The invention discloses a helicopter ANFIS self-adaptive vibration isolation control method suitable for a plateau environment working condition, and relates to the technical field of vibration isolation control of rotor aircrafts such as helicopters, rotorcrafts and unmanned aerial vehicles, and the vibration isolation control method is based on helicopter fuselage vibration spectrum characteristic data of different altitudes (1600m, 2500m, 3200m, 3800m, 4500m and the like) of the plateau environment working condition. The method comprises the following steps of: constructing an adaptive fuzzy neural network control system (ANFIS) model according to the change of a working condition, realizing adaptive adjustment of control parameters along with the change of the working condition, and improving the stability and the universality of a vibration isolation effect; and secondly, a vibration response closed-loop control method is provided for a head-up display system (Head-up Display, Hud) additionally installed in a helicopter cockpit, and structural vibration caused by the complex aerodynamic environment of the plateau working condition is suppressed in real time through an ANFIS training nonlinear mapping network.

The invention discloses a bearing real-time anomaly detection method based on an adaptive network fuzzy inference system and related equipment, and the method comprises the steps: determining a first feature index group and a second feature index group according to a first sensor signal in a bearing data set and an anomaly detection result, designing a fuzzy inference rule, calculating an abnormal score of the first feature index group, taking the second feature index group as input of an adaptive network fuzzy inference system, and training the system according to the abnormal score; and extracting a third feature index group of the bearing to be detected, inputting the third feature index group into the trained adaptive network fuzzy inference system for inference, and completing anomaly detection according to a negative anomaly feature value prediction result obtained by inference and a preset decision rule. According to the embodiment of the invention, bearing anomaly detection can be realized by combining the fuzzy reasoning system and the adaptive network fuzzy reasoning system, and the prediction accuracy and the operation efficiency are relatively high. The method can be widely applied to the technical field of bearing anomaly detection.

This invention relates to providing automated systems and computer-implemented methods for detecting diseases such as nasopharyngeal carcinoma (NPC) based on the analysis of immunofluorescence assay (IFA) images using fuzzy inference (FI) systems or deep learning fuzzy inference (DeLFI) hybrid models. For NPC detection, the systems and methods of this invention will distinguish between Epstein-Barr virus (EBV) early antigen (EA) positive and negative cells and identify cellular patterns indicative of NPC. DeLFI hybrid models require less human evaluation and therefore have the potential to improve the scalability and accuracy of NPC detection.

The invention discloses an air-sea cross-domain network routing protocol method based on fuzzy logic and learning optimization, which belongs to the technical field of air-sea cross-domain network communication, and comprises the following steps: taking each node in a network as an independent agent, and constructing a candidate forwarding set by maintaining neighbor node information to reduce an action space; a fuzzy inference system is introduced, a reward function is designed by integrating a residual energy factor, a node forward factor and a link quality factor, an algorithm iteration update value is combined, an optimal next-hop node is selected to complete data packet forwarding, and a forwarding failure reselection mechanism is set. According to the method, the data packet delivery rate is remarkably improved, the end-to-end delay is reduced, the network life cycle is prolonged, and the method is suitable for high-reliability data transmission in a complex air-sea cross-domain environment.

The invention relates to the technical field of mobile mechanical arms, in particular to a mobile mechanical arm self-adaptive anti-noise motion planning method based on a fuzzy rule. Comprising the following steps: firstly, designing a motion planning scheme according to a kinematics model of the mobile mechanical arm; the motion planning scheme of the movable mechanical arm is converted into a quadratic programming problem; secondly, designing an anti-noise zero neural network model to solve a quadratic programming problem in real time; further, a fuzzy inference system is introduced to carry out optimization and adaptive adjustment on key parameters in the anti-noise zero neural network model; and finally, the result of the fuzzy inference system is transmitted to a lower computer in real time, and the mobile mechanical arm is driven to complete expected trajectory tracking and task execution. The motion planning method has good timeliness and robustness, interference of noise on motion planning can be effectively restrained, and it can still be guaranteed that the mechanical arm smoothly completes tasks in the complex noise environment.

The application discloses a kind of air-sea cross-domain network routing protocol methods based on fuzzy logic and learning optimization, belong to air-sea cross-domain network communication technical field, including: each node in network is regarded as independent intelligent agent, and candidate forwarding set is constructed by maintaining neighbor node information to narrow action space;Introduce fuzzy inference system, design reward function by comprehensively remaining energy factor, node advance factor and link quality factor three factors, update value by combining algorithm iteration, select optimal next hop node to complete data packet forwarding, and set reselection mechanism for forwarding failure.The present application significantly improves the data packet delivery rate, reduces end-to-end delay, while prolonging the network life cycle, suitable for high reliability data transmission in complex air-sea cross-domain environment.

The invention discloses a whole-process intelligent optimization regulation and control method for an SNCR-SCR coupled denitration device, and relates to the technical field of denitration device regulation and control. Comprising the steps of collecting and preprocessing multi-source data such as temperature and concentration; the NOx generation amount is predicted by using the LSTM-GRU hybrid network; according to the prediction result, the optimal ammonia nitrogen ratio is calculated through a reaction kinetic model, the CFD-DEM is adopted to optimize the spray gun layout, and a reducing agent is dynamically sprayed in a zoning mode; constructing a multi-objective function, and solving an optimal operation parameter by using an NSGA-II algorithm; and in combination with an expert knowledge base and a fuzzy reasoning system, real-time feedback regulation and control are realized, and extended strategies such as low-load adaptation and catalyst management are also covered. Intelligent regulation and control of the SNCR-SCR coupling denitration device are achieved, NOx emission and ammonia escape can be reduced, energy consumption is reduced, and the service life of a catalyst is prolonged by one time; the system adapts to all-working-condition operation, supports carbon emission optimization, effectively improves the denitration efficiency, reduces the cost, and meets the strict environmental protection requirements.

METHOD FOR TRANSFORMING A RADIAL BASED NEURAL NETWORK INTO A FUZZY INFERENCE SYSTEM The present invention relates to a method for transforming a radial basis neural network (RBFN) into a fuzzy inference system. This method comprises a step of dividing the network into distinct RBFN subnetworks and then separating (120) each of these subnetworks. A layer of inference nodes is then inserted (130) at the output of the subnetworks, each inference node applying an inference rule, and then the subnetworks with this inference layer are subjected to a training phase (140) on a training dataset. The activation functions of the neurons in the intermediate layer are then degraded (150), those relating to neurons connected to the same node of the input layer being degraded into membership functions representing a partitioning of the input variable space.A fuzzy inference system functionally equivalent to RBFN is finally generated (160) from the membership functions and inference rules previously adjointed. Figure for the abstract: Figure 1.

The application provides a process dynamic control method, device and system of a dividing wall column and a storage medium, and applies a chemical engineering rectification process. The method comprises the following steps: obtaining first parameter information of the dividing wall column, including a first heat load of a reboiler, a second heat load of a condenser, a temperature difference of a feed section and a temperature difference of a side line production section; performing joint processing on the first parameter information, an adaptive neuro-fuzzy inference system and an MPC model to obtain control information, wherein the control information comprises liquid phase flow allocated to the feed section by a common rectification section, a first production flow of the side line production section and reflux flow of a column top; and controlling the dividing wall column according to the control information. By adopting the joint control of the adaptive neuro-fuzzy inference system and the MPC model and taking the temperature difference as a control point, the control problems in the rectification process, such as difficult real-time measurement of components and strong coupling of variables, are solved, the dynamic control performance is improved, and disturbances of feed flow and feed composition are effectively resisted.

This disclosure provides a method and system for controlling SO2 emissions from a circulating fluidized bed unit. By constructing a dynamic SO2 emission prediction model that includes economic objectives and adopting a hierarchical collaborative optimization control architecture, the method first uses an optimization algorithm to calculate the economically optimal SO2 concentration setpoint in real time. Then, it uses a dual-loop generalized predictive controller (GPC) for precise tracking control. At the same time, a fuzzy inference system is introduced to dynamically and adaptively adjust the weight of the control objective. This achieves stable, economical, and environmentally friendly synergistic optimization control of SO2 emissions under complex operating conditions such as deep peak shaving. It effectively solves the problems of slow response, unstable control, and high cost of traditional methods, and achieves the beneficial effects of significantly reducing desulfurization operating costs, enhancing emission concentration stability, and improving the system's adaptive capability.

The invention also provides a six-degree-of-freedom dual-active full-bridge DC-DC converter modulation optimization method based on deep reinforcement learning and a DAB converter system. The method comprises the following core steps: constructing a 6-DoF modulation mathematical model and a ZVS constraint condition; designing a reward function containing constraint penalty and efficiency excitation; performing offline training on the intelligent agent through a DDPG algorithm; and a fuzzy inference system (FIS) is adopted to realize real-time deployment of the embedded platform. The method is high in modeling precision, the inductive current effective value (effective value) is remarkably reduced, zero voltage switching (ZVS) is achieved in a full-load range, the peak efficiency is improved by more than 3% compared with the traditional 5-DoF modulation efficiency, and the method is suitable for electric vehicle charging, energy storage systems and other scenes.

The invention discloses a dynamic attribute encryption access control method and system of a data element bearing network, and belongs to the technical field of data processing technology and information security. Comprising the following steps: receiving an access request, acquiring a multi-dimensional risk attribute associated with the access request in real time by a risk awareness engine RPE in a bearer network through a deterministic network method, and calculating a risk score of the access request by utilizing a preset fuzzy reasoning system; a dynamic policy decision point D-PDP dynamically generates a final ABE access policy matched with the risk score on the basis of a preset baseline ABE access policy according to the risk score output by the risk awareness engine; and executing access control. According to the method, the security and the credibility of the data elements in the full life cycle of circulation, transaction and application in the bearer network are remarkably improved.

The present application relates to heavy load robot control technical field, specifically, it is a kind of adaptive robust control method of heavy load robot fusing differential homeomorphism.The present application is by real-time acquisition each joint position information, and accurate comparison is carried out with expected trajectory, exports three input vectors, real-time updates differential homeomorphism parameters by T-S fuzzy reasoning system, and based on the parameters after optimization, joint space state is mapped to new coordinate space, generates collaborative control item through distributed communication to obtain neighbor joint information, constructs sliding surface to generate robust control item in combination with local tracking error, and generates compensation item based on adaptive law parameter uncertainty estimation, forms three parallel control outputs, carries out dynamic weight distribution and fusion to three control items, obtains basic control torque, then superimposes feedforward compensation item based on nominal dynamic model, generates final comprehensive control torque, and the comprehensive control torque guarantees performance while optimizing energy distribution.

The application provides a traffic trunk coordination signal timing optimization method, system, device and medium, belongs to the field of traffic control, and comprises the following steps: a dynamic model of traffic signal control is established by using a Markov decision process; a value function is obtained according to the traffic signal control model, and precise description of signal timing is realized. The value function is introduced into the brightness function and position updating function of the glowworm swarm optimization algorithm, and an adaptive light intensity absorption coefficient and a dynamic random disturbance factor are introduced to improve the glowworm swarm optimization algorithm, so that an improved glowworm swarm optimization algorithm is obtained, and the global search ability of the glowworm swarm optimization algorithm is improved. The adaptive neuro-fuzzy inference system is optimized and trained by using the improved glowworm swarm optimization algorithm, and a signal timing optimization model is obtained. According to the adjustment amount of the signal timing parameter output by the signal timing optimization model, adaptive intelligent control of the traffic signal timing is realized. The method can be applied to complex and variable traffic trunk environments, and can efficiently and accurately provide signal timing optimization strategies for traffic trunks.

The invention relates to the field of coal preparation of flotation machines, and particularly provides an ash content real-time linkage variable-speed foam scraping control method and device for a flotation machine, a terminal and a medium. The method comprises the steps that firstly, foam product ash content values, foam layer thicknesses and foam form images of all groove chambers of the flotation machine are obtained in real time; secondly, extracting a foam rupture rate feature through image processing, and constructing a comprehensive feature vector by combining a foam amount feature and an ash value accumulated in a time sequence; then, the vector is input into a preset fuzzy inference system, and the system outputs the adjustment amount of the rotating speed of the scraper of each groove chamber based on a fuzzy rule built in a flotation process knowledge base; and finally, controlling the variable frequency motor to drive the scraper to operate according to the adjustment amount. According to the method, the ash content, the foam amount and the foam stability are fused, intelligent decision making of the rotating speed of the driving system is conducted based on fuzzy reasoning, accurate sensing and self-adaptive regulation and control of the flotation state are achieved, and therefore the concentrate quality and yield are optimized while the separation process is stabilized and concentrate loss is prevented.

The invention discloses a progressive interaction guiding method based on behavior analysis and fuzzy matching. The progressive interaction guiding method comprises the following steps that multi-modal behavior data in the interaction process of a user and electronic equipment is collected; inputting the behavior data into a fuzzy reasoning system, and calculating to obtain a continuous comprehensive confusion index through fuzzification, rule reasoning and defuzzification processes; according to different intervals in which the comprehensive confusion index is located, dynamically triggering a corresponding interaction guide strategy from at least three predefined guide levels; monitoring the subsequent operation of the user on the interaction guide strategy, and taking the operation as a feedback signal to optimize the parameters of the fuzzy inference system or the subsequent guide decision; a complete, adaptive and intelligent interactive guidance closed loop is formed through a complete evaluation process of multi-modal perception and fuzzy evaluation, progressive decision based on a quantitative state and closed loop optimization based on feedback. The method can actively sense the dilemma of a user, intelligently adjust a guiding strategy, and continuously perform self-optimization.

The application provides a yellow rice wine fermentation prediction method and system based on an ANFIS and a random fractal search algorithm, the method comprising collecting data samples of a pre-fermentation process of different production batches of yellow rice wine; dividing the data samples into a training set and a test set, and performing normalization processing on the data samples; inputting the processed data samples into a multi-output adaptive neural fuzzy inference system model constructed in advance, identifying and optimizing model parameters of the multi-output adaptive neural fuzzy inference system model by using a hierarchical learning random fractal search algorithm, obtaining an optimized multi-output adaptive neural fuzzy inference system model, and predicting a yellow rice wine fermentation state. The application improves the precision and generalization ability of the model, and can achieve good prediction of the fermentation state of different production batches of yellow rice wine.

The invention discloses a rapid ramp parking method suitable for an electric fork-lift truck, which comprises the following steps: firstly, carrying out quality evaluation on a motor rotating speed signal acquired by an encoder, dynamically selecting a filtering strategy, outputting a preprocessed actual speed, extracting time domain, frequency domain and model correlation characteristics based on the speed, a motor torque direction and a target speed, and carrying out rapid ramp parking on the electric fork-lift truck. Calculating confidence coefficients of different road surface working conditions through a fuzzy inference system, further calculating a first-stage given speed according to a target speed and a given speed of a previous period, calculating an auxiliary function given speed by combining consistency judgment of a torque direction and a speed direction and the confidence coefficients of the working conditions, and generating a final given speed by utilizing a self-adaptive gain coefficient; and finally, the final given speed and the actual speed are subjected to closed-loop adjustment to drive a motor to execute parking, and meanwhile, graded safety intervention is implemented based on the working condition confidence coefficient and the real-time vehicle speed, so that deceleration delay in the ramp parking process is effectively eliminated, and the rapidity and stability of control are improved.