46 results about "Fuzzy inference rules" patented technology

The invention provides a pressure-bearing equipment damage mode identification and risk assessment method and system, and relates to the technical field of safety engineering, and the method comprises the steps: collecting multi-source sensor data and image data, inputting the data into a deep neural network after preprocessing and feature extraction, extracting spatial features through a convolutional layer, and extracting time sequence features through a recurrent neural network. And using the attention mechanism to fuse the features to identify an injury pattern. And then, constructing a multi-level evaluation index system, performing combined weighting by adopting an analytic hierarchy process and an entropy weight method, inputting weights into an improved Bayesian network model based on a D-S evidence theory, dynamically updating a conditional probability table by the model by utilizing a deep neural network and a fuzzy inference rule, and finally obtaining a risk evaluation result. According to the invention, the damage mode of the pressure-bearing equipment can be effectively identified, risk assessment is carried out, and assessment precision and reliability are improved.

The invention relates to the technical field of computing power resource allocation, and particularly discloses a computing power resource allocation method and system based on multi-dimensional dynamic evaluation and a product. The method comprises the steps of obtaining evaluation index data of a to-be-scheduled task in multiple dimensions; dynamically configuring a weight value of each evaluation index according to a task attribute and a system state; the evaluation index data is fuzzified by using a preset membership function, a fuzzy evaluation matrix is constructed in combination with the weight value, and comprehensive calculation is performed through a fuzzy inference rule to obtain fuzzy comprehensive evaluation data of the task, so that an accurate evaluation result is generated; modeling a task execution process by adopting a multi-layer perceptron model, and predicting the execution performance of the task; and based on the evaluation result and the prediction result, dynamically selecting a proper strategy from a plurality of predefined task scheduling strategies, and scheduling the tasks to optimize computing power resource allocation. According to the method, the resource utilization efficiency is remarkably improved through multi-dimensional evaluation and a dynamic scheduling mechanism.

The invention discloses a method and a system for adjusting the internal environment of a mobile laboratory cabin, particularly relates to the technical field of environment control, and aims to solve the problem that the existing environment adjusting method adopts a fixed control target and cannot adapt to differentiated environment requirements in a multi-task scene of a mobile laboratory. The method comprises the following steps: acquiring a current task identifier of a mobile laboratory, identifying a corresponding experiment task execution stage, and dynamically generating an inter-parameter collaborative constraint relation matrix based on a fuzzy inference rule base; a regulation and control demand vector is generated by collecting a multi-dimensional environmental parameter measurement value and combining a pre-stored environmental parameter expected value; calculating a regulation and control conflict risk entropy value based on the matrix and the vector, and performing risk judgment; when the risk tolerance is exceeded, a roundabout regulation and control strategy is generated as an optimization guide parameter; finally, an environment control instruction is generated in a coordinated mode according to the optimized guiding parameters and sent to an executing mechanism; the dynamic adaptation of the environmental parameter regulation and control strategy and the experiment task is realized, and the precision and reliability of multi-parameter cooperative control are improved.

The invention relates to the field of resource optimization, and discloses a supply chain full-link-oriented logistics resource optimization and matching method and system, and the method comprises the steps: generating a multi-dimensional logistics state feature vector according to full-link multi-source data of a target supply chain, constructing a multi-target optimization model according to a fuzzy inference rule and a fuzzy weight system, and carrying out the optimization of the multi-target logistics state feature vector; performing preliminary matching degree analysis on the multi-dimensional logistics state feature vector, performing resource allocation on a target supply chain by using a preliminary logistics resource allocation scheme generated according to a comprehensive matching score, and performing weight online learning and dynamic self-adaptive adjustment on a fuzzy weight system according to a performance error value of an actual performance parameter value, so as to obtain a multi-dimensional logistics resource allocation scheme; and obtaining a target matching weight system, optimizing the preliminary logistics resource allocation scheme, and matching the logistics resources of the target supply chain to obtain a target resource matching result. According to the invention, in a dynamic scene of a full link of a supply chain, real-time learning of a multi-target tradeoff relation and adaptive updating of a fuzzy weight can be realized.

The invention discloses an integrated circuit source measurement unit control method for improving a raccoon algorithm and optimizing fuzzy PID. The method comprises the steps that an output voltage control system of an SMU is set up; acquiring output end voltage data of the SMU system in real time; calculating a voltage error and a voltage error change rate; a fuzzy inference rule base is constructed, fuzzy controller parameters are dynamically adjusted based on the fuzzy rule base according to the voltage deviation value and the voltage error change rate, and then PID parameters are dynamically adjusted; a control signal is generated according to the set PID parameter, and the output voltage of the SMU is adjusted; and S4, optimizing the fuzzy PID voltage controller obtained in the step S4 by adopting an improved raccoon algorithm, selecting a decision variable as a parameter of a fuzzy controller, and assigning the optimized parameter to the fuzzy PID voltage controller to realize control on the output voltage of the SMU. According to the invention, the improved raccoon optimization algorithm and the fuzzy PID controller are combined and applied to the integrated circuit source measurement unit, so that the control performance of the SMU system is improved.

The invention relates to the technical field of injection mold monitoring, and discloses an injection mold cavity state monitoring method, system, equipment and medium, the injection mold cavity state monitoring method comprises the following steps: multiple sensors collect mold state data in real time, and the mold state data are preprocessed and fused to generate a comprehensive data set; training a machine learning model based on historical samples, and updating model parameters in real time through an incremental learning algorithm; analyzing current data by adopting dynamic fuzzy logic reasoning, and outputting a state evaluation result; real-time data and results are uploaded to the cloud for deep analysis and distributed storage; a user feedback mechanism is integrated, and model parameters and a fuzzy inference rule base are optimized. According to the method, model parameters are updated in real time through an incremental learning algorithm, a multi-parameter nonlinear coupling relation is analyzed in combination with dynamic fuzzy logic reasoning, and based on cloud collaboration and a user feedback closed-loop mechanism, self-adaptive monitoring and continuous optimization of the injection mold state are achieved, and the anomaly detection precision and the system robustness are improved.

The invention discloses a fuzzy self-adaptive PID (Proportion Integration Differentiation) control method for a high-temperature environment of a small closed space. According to the method, a fuzzy logic controller and PID controller cooperative control architecture based on the variable universe theory is constructed, and PID parameters are adjusted on line by utilizing a fuzzy inference rule by collecting the temperature deviation and the change rate of the closed space in real time. The fuzzy rule base design adopts a variable universe theory, a membership function and a universe range are dynamically adjusted according to a system state, and the adjustment direction and amplitude of PID parameters are accurately mapped. A real-time monitoring mechanism based on feedback of a temperature sensor is introduced, high-frequency sampling is carried out on the temperature of the space, and timeliness and accuracy of control signals are ensured. According to the method, by setting a temperature threshold value and an overshoot limiting mechanism, the phenomena of temperature overshoot and oscillation are effectively avoided, and the stability and reliability of the system are improved. According to the invention, the temperature can be quickly and accurately controlled in a high-temperature environment of a complex small closed space, and the temperature fluctuation range is obviously reduced.

The invention relates to the field, and discloses a parallel power supply efficiency optimization method and system, and the method comprises the steps: collecting the output current of each power supply module in real time through a current sensor of each power supply module, and collecting the total output current of a parallel power supply system, and the input voltage and output voltage of each power supply module; calculating a current sharing error of each power supply module, and adjusting a proportionality coefficient, an integral coefficient and a differential coefficient of a fuzzy PID controller through a fuzzy inference rule; the voltage regulator is used for regulating the power supply module through the control signal; calculating the efficiency of each power supply module according to the input voltage, the output voltage and the output current of each power supply module, and determining the optimal working point of each power supply module and adjusting the input power of each power supply module according to the efficiency and the load condition of each power supply module so as to complete the efficiency optimization of the whole parallel power supply; according to the invention, the working state of the power supply module can be adjusted in real time under different working conditions, and the method has high adaptability and stability.

The invention relates to the technical field of molten salt conveying, and discloses a molten salt spherical tank heat storage and heat exchange gas pressure conveying regulation and control system and method.The method comprises the following steps that multi-source parameters are read in real time, the current pressure difference is calculated to be combined with the temperature to fit the real-time viscosity value, the pressure difference, the viscosity and the valve opening degree are used for dynamically updating the theoretical calculation value of viscosity time lag, and the viscosity time lag is calculated. Historical data of time lag, pressure difference and valve opening are stored, a time window sample is formed, a time lag change rule is learned through an LSTM network, model weight parameters are updated online, a current working condition sequence is input, and a predicted value of future time lag is output. According to the method, the influence of fluid transmission time lag on pressure control is reduced, valve actions are synchronized with actual requirements through dynamic prediction and a fuzzy compensation mechanism, overshoot or undershoot of pressure is avoided, the anti-interference capability and robustness are enhanced by combining an online learning prediction model and a fuzzy inference rule base, and the pressure control precision is improved. And a scheme integrating dynamic response quality and long-term stable operation is realized.

The present application relates to the technical field of data processing, in particular to a wireless satellite chain real-time early warning data processing method and system for landslides. It includes the following steps: collecting data affecting the occurrence of landslides, using historical data to learn time series patterns, selecting key time series features from different time windows, and finally assigning weights to each key time series feature; according to the real-time data affecting the occurrence of landslides, combined with the selected key time series features and the weights of the key time series features, a prediction model is generated, and using fuzzy reasoning rules, the probability is combined with the key time series features to evaluate the risk level in real time. In the wireless satellite chain real-time early warning data processing method and system for landslides, the most valuable features for landslide prediction can be more effectively selected, the correlation between these features is strengthened by calculating the interaction information between them, thereby improving the accuracy of the landslide prediction model.

The invention discloses a driving right distribution method and device based on man-machine sharing, equipment and a storage medium. The driving right distribution method based on man-machine sharing comprises the steps that current deviation information of a vehicle in the current driving process is acquired; determining a current target torque according to the current deviation information, wherein the current target torque is used for controlling the vehicle to correct the current deviation information; and determining the driving right according to the current deviation information, the current target torque and a preset fuzzy inference rule. According to the scheme, the accuracy of driving right distribution can be improved.

The present application relates to the technical field of solar power generation, in particular to a kind of solar street lamp's charge-discharge management system, including data acquisition unit, illumination intensity prediction unit, fuzzy inference unit, charging optimization unit, discharge optimization unit and battery management unit.The present application generates first data set by data acquisition unit collection and pre-processes the historical data of street lamp;Illumination intensity prediction unit applies SARIMA model to predict future illumination intensity;Fuzzy inference unit generates membership function according to first data set and predicted illumination intensity;Charging optimization unit constructs fuzzy inference rule base using membership function, calculates current charging power;Discharge optimization unit divides discharge period according to first data set and calculates discharge power;Battery management unit updates battery remaining capacity according to charging power and discharge power, and evaluates energy storage effect, which can improve the energy management effect of solar street lamp, thereby improving the adaptability of solar street lamp's charge-discharge management.

This invention belongs to the field of automotive braking technology, specifically relating to a method for assessing and warning of instability risk in automotive braking systems and a corresponding automotive vehicle. The method includes: calculating characteristic values ​​during vehicle braking. l t ; Calculate the proportion of flutter energy during vehicle braking or t ;according to l t and or t The precise probability of vehicle flutter during braking is obtained based on a fuzzy algorithm. P t ;judge P t Is it greater than or equal to the calibrated probability? P 0; when P t ≥ P At time 0, an early warning is issued regarding the risk of vehicle braking chatter instability; otherwise, no warning is required. The core advantages of this invention are: 1) It theoretically solves for real-time characteristic values ​​that characterize the stability of the vehicle braking system, while simultaneously collecting brake disc angular velocity signals to calculate the proportion of chatter energy; 2) It establishes fuzzy inference rules that integrate the mechanism model and measured data to assess the risk of vehicle braking chatter instability, providing technical support for the accurate prediction and control of vehicle braking chatter in engineering.

The application relates to the technical field of intelligent control of mining equipment, and in particular to a pick-type pick tooth rock breaking load space-time evolution analysis method and system. The method comprises the following steps: collecting multi-dimensional load signals in a rock breaking process through a sensor array; establishing a digital representation surface based on pick tooth geometric morphology and sensor coordinates; generating a load estimation value of any point on the surface by using a spatial interpolation algorithm; mapping to the surface to form a continuous space-time load distribution field; extracting rock breaking efficiency and pick tooth load state characteristic parameters; and generating equipment parameter optimization guidance information through a fuzzy inference rule base. The application solves the problem that traditional methods cannot represent the continuous space-time evolution of the load, realizes visual analysis of the load distribution in the rock breaking process and self-adaptive regulation and control of the equipment parameters, and significantly improves the rock breaking efficiency and the service life of the pick tooth.

The invention discloses a water conservancy project safety risk early warning method based on deep learning, and the method comprises the steps: S1, obtaining the monitoring data of a high-flow-rate reinjection well, and carrying out the normalization processing; s2, constructing a fuzzy logic reasoning model based on a Kailey manifold fuzzy reasoning algorithm, and determining an initial reasoning path; s3, based on a seepage Lagrange optimization model, optimizing a reasoning path in a high-dimensional Kailey manifold space; s4, calculating a seepage critical value, adjusting a fuzzy inference rule, and dynamically updating an inference path based on time sequence analysis; s5, performing historical data projection, and calculating the evolution trend of the seepage risk based on a time scale transformation method; s6, updating the reasoning path calculation weight according to different water injection pressures and permeability; and S7, based on a calculation result of the reasoning path, adjusting a calculation structure of the reasoning model. According to the invention, long-term reliable operation of water conservancy project risk early warning is effectively ensured.

The present application relates to the field, disclose a kind of parallel power supply efficiency optimization method and system, the output current of each power module is collected in real time by the current sensor of each power module, while collecting the total output current of parallel power supply system and the input voltage, output voltage of each power module;The current sharing error of each power module is calculated, the proportional coefficient, integral coefficient and differential coefficient of fuzzy PID controller are adjusted by fuzzy inference rule;The voltage regulator of power module is adjusted by control signal;According to the input voltage, output voltage and output current of each power module, the efficiency of each power module is calculated, according to the efficiency and load condition of each power module, the best working point of each power module is determined, the input power of power module is adjusted, to complete the efficiency optimization of entire parallel power supply;The present application can adjust the working state of power module in real time under different working conditions, has strong adaptability and stability.

The disclosure provides a kind of shielded mask mark detection method, comprising: S1, the mask mark image collected is converted into gray scale chart;Wherein, the image collected is at least partially shielded;S2, gray scale chart is carried out image segmentation, and non-mark part is filled as white;S3, the gray scale median of gray scale chart is obtained, as initial binary threshold value the gray scale chart is carried out binary processing;Carry out outline detection, and obtain the multiple minimum circumscribed rectangle of image outline;S4, according to the long and wide features of mask mark minimum circumscribed rectangle, determine fuzzy inference rule, obtain the probability that each minimum circumscribed rectangle is actual shielded mark circumscribed rectangle;S5, whether there is probability greater than preset threshold in probability;If not, adaptive adjustment binary threshold value, repeat S3-S5;If yes, determine the minimum circumscribed rectangle of maximum probability, as first detection target;S6, according to first detection target, determine first center coordinates, complete the positioning detection of mask mark.

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.

The invention provides a road recognition method and device based on fuzzy logic and geographic information and a medium, belongs to the field of intelligent traffic, and realizes dynamic recognition and slicing of road states through cooperative work of vehicle-mounted driving assistance map equipment and a TCU (traffic control unit). The method specifically comprises the following steps: installing equipment and ensuring that a TCU receives electronic map information; acquiring front road information in real time during driving and storing the information as a distance / gradient array; establishing a fuzzy inference rule to define nine road states; carrying out smooth processing and change rate calculation on the gradient data; the input fuzzy system outputs road state division; calculating the length of each state slice; and the processing flow is repeated during dynamic updating. Through real-time road state division, a vehicle control strategy can be accurately matched, and the driving safety and comfort are improved. A dynamic updating mechanism adapts to road condition changes, and energy consumption management is optimized; the fuzzy inference rule is compatible with complex road condition recognition, the robustness of the system is enhanced, and a reliable decision basis is provided for intelligent driving.

The invention provides a fuzzy self-adaptive Q learning control method and system for sewage treatment, and the method comprises the steps: obtaining the dissolved oxygen concentration as a system state, and constructing a nonlinear optimization problem; performing dynamic adjustment on proportion, integral and differential coefficients by adopting a Mamdani type fuzzy inference rule in combination with fuzzy logic, performing defuzzification through a centroid method to obtain adaptive PID parameters, and forming a fuzzy adaptive control strategy; an online Q learning framework is further constructed, a Q function is approximated by using the evaluation network, a network generation strategy adjustment amount is executed, and network weight is optimized based on a Bellman equation and a particle swarm algorithm; finally, fuzzy control and Q learning output are fused, control input is generated through a coupling coefficient to adjust an oxygen transfer coefficient, and tracking control over the dissolved oxygen concentration is achieved. According to the invention, the tracking control precision of the dissolved oxygen concentration and the system operation stability can be improved.

The invention belongs to the technical field of wind power generation, and particularly relates to a wind power blade icing state monitoring method and system based on fuzzy reasoning. The method comprises the following steps: acquiring non-icing historical operation data of a unit, averaging according to a wind speed interval by referring to an IEC standard, and fitting performance characteristics of the unit at different wind speeds; sCADA data of a unit in nearly four hours are acquired and cleaned, and whether the data are enough for monitoring is judged; averaging the cleaned data according to a fixed time period, dividing the data into two groups above a rated wind speed and below the rated wind speed, and respectively calculating performance average deviations; and in combination with a corresponding icing grade fuzzy inference rule, calculating two groups of icing grades by adopting a Mamdani inference algorithm, and weighting according to the number of the two groups of corresponding time periods to obtain an average blade icing grade of nearly 4 hours. The system comprises a performance feature fitting module, a data processing module, a performance average deviation calculation module and a blade icing grade calculation module.

The application discloses an engine air-fuel ratio control method, and relates to the technical field of engine control, and comprises the following steps: obtaining the accurate value of a first actuator adjustment increment and the accurate value of a second actuator adjustment increment through the accurate value of a mixer outlet pressure deviation value, the accurate value of a change rate of the mixer outlet pressure deviation value and the accurate value of an air flow and fuel flow ratio deviation value; and adjusting the air flow and fuel flow ratio according to the accurate value of the first actuator adjustment increment and the accurate value of the second actuator adjustment increment. The application adjusts the first actuator opening degree and the second actuator opening degree through fuzzy inference rules and fuzzy algorithms, and realizes the control of the engine air-fuel ratio.

The application discloses a damaged ancient Zhuang character detection and recognition method based on fuzzy logic and belongs to the technical field of ancient character intelligent recognition. First, the damaged ancient Zhuang character image is collected, and preprocessing is completed through adaptive denoising, stroke loss detection and completion; then, multi-dimensional fuzzy features such as stroke integrity, contour similarity, structural connectivity and texture consistency are extracted, corresponding membership functions are constructed, and membership values are calculated; fuzzy processing, rule matching and defuzzification processing are completed based on a fuzzy inference rule base, and the damage degree grade and candidate recognition confidence are output; then, high-dimensional semantic features are extracted through a deep learning model, and the fuzzy inference result is weighted and fused to obtain the final recognition result; finally, the modern character mapping database of ancient Zhuang characters is queried to output the interpretation. The application combines fuzzy logic and deep learning, effectively processes uncertain problems such as stroke loss and contour fuzziness, significantly improves the recognition accuracy and robustness of damaged ancient Zhuang characters, is suitable for damaged scenes such as epigraphy, ancient books and cliff inscriptions, and provides a reliable technical scheme for the digital protection of ancient Zhuang character cultural heritage.

The invention discloses an underground water level early warning method and system. The method comprises the following steps: acquiring an underground water level time sequence data set of all stations in a target area; a hierarchical clustering algorithm based on dynamic time warping is adopted to recognize spatial heterogeneity of underground water level changes, and all stations are classified; for each type of stations, acquiring the groundwater level mean value and the water level change rate of each type of stations as input variables, and standardizing the input variables; performing fuzzification processing on the standardized input variables through a Gaussian membership function to generate multiple pieces of input variable fuzzy data; performing fuzzy reasoning on the multiple pieces of input variable fuzzy data according to a preset fuzzy reasoning rule to obtain multiple pieces of output variable fuzzy data; the multiple pieces of output variable fuzzy data are converted into underground water level risk coefficients through a gravity center method; and determining the underground water level early warning level of the corresponding type of station according to the underground water level risk coefficient of each type of station.

The invention relates to the technical field of data processing, and discloses a flue gas desulfurization process-oriented data cross-modal characterization and modeling method, which comprises the following steps of: acquiring flue gas desulfurization cross-modal data, processing the cross-modal data based on a hierarchical model and a time sequence correlation model, constructing hierarchical branches by the hierarchical model based on a desulfurization system, and establishing a modeling model based on the time sequence correlation model. The time sequence association model takes a time sequence identifier as an index, determines a node identifier record of the hierarchical model and generates a cross-device association item and a cross-stage association item, the depth auto-encoder performs feature extraction on the processed cross-modal data based on the multi-layer feature extraction network, and outputs a target low-dimensional feature vector according to the adjusted depth auto-encoder; and constructing a fuzzy neural network model based on the target low-dimensional feature vector, the operation index, the emission index and the fuzzy inference rule. According to the method, the model can comprehensively reflect the global operation state, and the characterization capability of the model on the desulfurization process is improved.

The invention provides a charging remaining time determining method and device based on fuzzy reasoning, and the method comprises the steps: obtaining a state parameter of a power battery, carrying out the fuzzification of the state parameter through a membership function corresponding to the state parameter, and obtaining the membership corresponding to the state parameter; then, performing fuzzy reasoning on the charging remaining time of the power battery based on the membership degree corresponding to the state parameter by using a pre-constructed fuzzy reasoning rule to obtain a fuzzy reasoning result; and finally, performing defuzzification processing on the fuzzy reasoning result to obtain a charging remaining time determined value of the power battery. By monitoring the actual operation data of the power battery and adopting fuzzy reasoning, the charging remaining time estimation effect is improved, the internal characteristics of the battery do not need to be deeply understood, the modeling and maintenance cost is reduced, meanwhile, the change of the battery state can be quickly responded, and more accurate remaining time estimation is provided.

The invention discloses a converter control method and device, equipment, a storage medium and a program product. The method comprises the steps of obtaining an active power deviation value and a reactive power deviation value corresponding to a converter; respectively determining an active deviation change rate and a reactive deviation change rate according to the active power deviation value and the reactive power deviation value; inputting the active power deviation value and the active deviation change rate into a first fuzzy controller, and performing fuzzy reasoning on the active power deviation value and the active deviation change rate through a fuzzy reasoning rule corresponding to the first fuzzy controller to obtain an active droop coefficient; inputting the reactive power deviation value and the reactive power deviation change rate into a second fuzzy controller to obtain a reactive power droop coefficient; and generating a control signal of the converter according to the active droop coefficient and the reactive droop coefficient. According to the embodiment of the invention, the performance of the energy storage system can be improved.

The embodiment of the invention provides a meteorological window selection method and device and a computer readable medium. The method comprises the steps that at least one meteorological element of a target task and state grading standards corresponding to different meteorological states of each meteorological element are acquired; for any target meteorological element, counting meteorological variables corresponding to the target meteorological element in the current preset time period, and generating a current meteorological sequence; predicting a predicted meteorological state corresponding to the next preset time period based on the current meteorological sequence; and based on the fuzzy membership degree corresponding to the predicted meteorological state of each target meteorological element in the at least one meteorological element, analyzing the performability of the target task according to a fuzzy inference rule, and generating a meteorological window. According to the embodiment of the invention, the Markov chain model and the fuzzy inference rule are combined for selecting the meteorological window; the problem that the long-term meteorological window selection precision of a traditional method under complex meteorological conditions is not enough is solved, and the meteorological window selection precision is improved.

The invention relates to the technical field of driving behavior intelligent evaluation, in particular to a driving behavior evaluation method and system based on big data, and the method comprises the steps: extracting an absolute position coordinate, an instantaneous velocity vector and an acceleration vector of a vehicle to form an original track set; and calculating a speed change rate, an acceleration change rate and a track transverse offset, and constructing a multi-dimensional feature matrix. And inputting the matrix into a driving style classification model combining a long short-term memory network and an attention mechanism, outputting a driving style probability distribution vector, accurately capturing key characteristics of a driving time sequence, and presenting a dynamic transition state of the driving style. And determining a style label in combination with a preset threshold value, calling historical driving behavior baseline data to generate a deviation index containing a deviation direction and amplitude, and outputting an evaluation level through operation of a fuzzy inference rule base. According to the method, personalized characterization of the driving behavior deviation can be realized, so that the evaluation result better fits the individual operation habit of the driver.

This invention discloses a bidirectional fault assessment method for distribution networks combining correlation matrices and dynamic Bayesian methods. The method includes the following steps: constructing a correlation matrix based on the actual distribution network topology, and combining this with a fault information matrix to construct a fault assessment matrix; establishing fault criteria for both missed and false fault reports, thereby achieving top-down fault feeder identification; constructing a dynamic Bayesian network based on the actual distribution network topology and the "station-line-transformer-customer" relationship to infer the fault probability of each region; constructing membership functions and fuzzy inference rules to obtain a fuzzy inference system for adjusting fault probabilities; and finally inferring the most likely fault region, achieving bottom-up fault region assessment. Based on traditional matrix algorithms, this invention improves fault criteria by constructing a causal correlation matrix, effectively solving the feeder identification problem under conditions of missed and false fault reports, reducing computational load, and improving the accuracy of fault location.