58results about How to "Reduce estimation error" patented technology

The invention discloses a wide-speed-domain position-sensorless control method for a permanent magnet synchronous motor, and the method comprises the steps: building an extended state observer of the permanent magnet synchronous motor, and obtaining the counter electromotive force of the motor through the extended state observer; a self-adaptive vector filter is adopted to filter out higher harmonics in the back electromotive force obtained by the extended state observer, estimated back electromotive force is obtained, the obtained estimated back electromotive force serves as input, position information contained in the estimated back electromotive force is demodulated through a phase-locked loop position observer, and the rotating speed and the position angle of the motor are obtained; and controlling the permanent magnet synchronous motor according to the obtained rotating speed and position angle. The position observer is used for extracting position information from the rotor back electromotive force, a mechanical position sensor is omitted, the system structure is simplified, cost is reduced, the self-adaptive vector filter is used for filtering harmonic waves for estimating the back electromotive force, and estimation errors of the rotating speed and the position angle of the motor are reduced. And the high efficiency and the stability of position-sensorless control of the motor in a wide speed range are improved.

The invention relates to a method, a device and equipment for estimating the state of a power battery of a sweeper. The method comprises the following steps: performing impedance characteristic acquisition on a power battery of the sweeper under various working conditions, and performing random low-frequency modulation multi-sine excitation signal measurement to obtain battery working condition characteristic data; performing fitting operation through the equivalent circuit model to obtain a battery health factor model; performing charging process feature extraction analysis to obtain a battery charging curve reconstruction model; carrying out extended Kalman filtering operation to obtain a battery state-of-charge value; performing segment processing and Gaussian process regression calculation on voltage and current data in the charging process to obtain a battery health state value; and updating the polynomial mapping coefficient of the battery health factor model and the weight parameter of the battery charging curve reconstruction model to obtain a target health factor model and a target charging curve reconstruction model. According to the invention, the adaptability and accuracy of the state estimation method in the whole life cycle of the battery are ensured.

The invention provides a multi-dimensional fusion battery health assessment method, which comprises the following steps of: acquiring power consumption data of a battery in an energy storage power station, acquiring an SOH (state of health) predicted value at an edge end, and executing cloud estimation when a difference exceeds a threshold value; when the historical sequence exists, predicting the historical health data by using a recurrent neural network Bi-LSTM to obtain a battery SOH predicted value; and when the historical sequence does not exist, extracting battery parameter dimension feature data, inputting the trained ELM model, and outputting a battery SOH predicted value. According to the method, two data driving methods are combined, and health state estimation is carried out by using an ELM algorithm when historical health data are missing, so that a health state initial sequence with relatively high precision is obtained; when the health state historical sequence meets the Bi-LSTM requirement, health state prediction is carried out by using the Bi-LSTM; the method has the advantages of reliable precision, fewer monitoring parameters, low cost, better adaptability and easiness in online application.

The invention relates to the technical field of 5G communication modules, in particular to a 5G communication module with a self-adaptive frequency spectrum and a use method of the 5G communication module. Comprising a spectrum sensing and identification module, a spectrum measurement and reconstruction module based on compressed sensing, a self-adaptive spectrum selection and dynamic spectrum allocation control module, a dynamic channel modeling and prediction module, a comprehensive optimization algorithm module and a feedback-assisted channel estimation control module. Wherein the spectrum sensing and recognition module adopts a deep learning algorithm to improve the precision and speed of spectrum sensing, and meets the requirements of 5G high data rate and low delay; the specific implementation mode comprises a convolutional neural network (CNN) structure, the convolutional neural network is adopted for spectrum sensing, and the spectrum state can be accurately and rapidly recognized in a complex dynamic environment; by training a large amount of spectrum data, the CNN can extract spectrum features and effectively distinguish target signals and interference signals, and the precision and speed of spectrum sensing are significantly improved.

The invention provides a heat pump control system identification method based on an improved SABO algorithm, and belongs to the technical field of industrial control process system identification. The technical problem that an SABO algorithm is prone to falling into a local optimal solution in the system identification process under the condition of insufficient sample data and the system parameter identification process is solved, and the technical scheme includes the following steps that firstly, a single-input-single-output Hammerstein model of the air source heat pump control system with the dead zone characteristic is constructed, a Hammerstein system identification model of the air source heat pump control system with dead zone characteristics under the condition of insufficient sample data is obtained; and 2) constructing an identification process of the improved SABO algorithm. The air source heat pump control system parameter identification method has the advantages that the convergence speed is high, the identification precision is high, the output parameter estimation error is small, and meanwhile it is indicated that the identification method has good applicability to air source heat pump control system parameter identification.

The invention provides an improved sliding-mode observer for permanent magnet synchronous motor position sensorless control. A traditional sliding-mode observer can cause a jitter phenomenon of observation information in motor control. According to the method, the control equation of the sliding-mode observer is redesigned, the adaptive rate is combined, and a low-pass filter is replaced, so that the estimation precision of the back electromotive force is improved. A hyperbolic tangent function is used to replace a sign function to alleviate the jitter problem of the observer, and a phase-locked loop technology is used to replace an arc tangent function to reduce estimation errors and phase delay. The feasibility of the control system is verified by building a system simulation model based on a static coordinate system in MATLAB / Simulink. A simulation result shows that the control system reduces the rotor speed error and the rotor position error, so that the control performance and the stability of the permanent magnet synchronous motor are improved.

The invention relates to an adaptive sparse channel estimation method applied to a reconfigurable intelligent surface (RIS)-assisted millimeter wave large-scale MIMO system. According to the method, two progressive algorithms, namely an NLMS-LOG algorithm and an NLMS-NLMF-LOG algorithm, are designed, and the method aims at making full use of the sparsity of millimeter wave channels so as to improve the accuracy and convergence speed of channel estimation. According to the NLMS-LOG algorithm, a logarithm and a penalty term are innovatively introduced into a cost function, so that the convergence speed is effectively increased; the NLMS-NLMF-LOG algorithm fuses the fast convergence advantage of the NLMS algorithm and the excellent performance of the NLMF algorithm under the condition of low signal-to-noise ratio, and the precision of channel estimation is further improved. Simulation experiment results prove that the scheme provided by the invention is obviously superior to the prior art in the aspects of channel estimation precision and convergence speed.

The invention relates to a heat supply conversion load automatic optimization calculation method based on a load conversion coefficient method, which comprises the following steps of: acquiring data according to a heat supply working condition diagram designed by a unit, and fitting a relation formula; according to the relation formula, the generated power difference value of the heat supply steam extraction amount under the specific main steam flow is calculated; based on the difference value, the heat supply steam extraction converted load is calculated according to a relational expression between the heat supply steam extraction converted load and the heat supply steam extraction amount under different steam extraction amounts; designing a heat supply conversion load automatic optimization loop, determining target loads according to requirements, and setting optimal comprehensive valve positions under different target loads; the actual valve position is adjusted through a PID controller, the heat supply converted load correction coefficient is obtained when the actual valve position is the same as the optimal comprehensive valve position, and the optimal heat supply converted load is obtained; the method solves the problems that the heat supply conversion load calculation of the heat supply unit under the heat supply working condition is inaccurate and the heat supply unit cannot adapt to the full-load working condition, further solves the problem of poor heat supply working condition coordination control, and improves the safe and stable operation of the heat supply unit.

The invention discloses an orientation-pure target tracking method and device based on FUBKF. The method comprises the following steps: S1, collecting and storing target azimuth information; s2, filtering the target azimuth information by adopting a PLKF algorithm to obtain an estimated target position; s3, carrying out noise separation on the target azimuth information and then carrying out observation matrix accurate calculation; and S4, fusing the observation matrix and the estimated target position to obtain a final target position. According to the method, the tracking precision can be remarkably improved in pure azimuth target tracking, relatively high stability is kept, and the requirements of different application scenes can be met.

The invention discloses an electric cylinder friction force parameter and state simultaneous estimation method and device and a medium. Aiming at the stick-slip phenomenon and the oscillation phenomenon caused by friction force in low-speed movement, the friction force model of the servo electric cylinder is constructed by combining a traditional static friction force model and a dynamic LuGre friction force model. And on the basis, according to a moment balance equation, a dynamic model of the servo electric cylinder is established. A motion state predictor of the servo electric cylinder is designed by means of a kinetic model and a friction force model of the servo electric cylinder. And updating a friction force state estimation error by using the motion state prediction error, designing a friction force state observer, and estimating the friction force state. In combination with the estimation of the friction force state, the self-adaptive law of the friction force model parameters is constructed, and the friction force model parameters are estimated online, so that the precise estimation of the friction force borne by the servo electric cylinder is realized, and the precise compensation effect of the servo electric cylinder system on the friction force is realized.

The invention relates to the technical field of multi-carrier communication systems, and discloses a data transmission method, device and equipment based on a load data pilot pattern. The method is applied to the MIMO-PLC system. And obtaining the positions of the pilot frequency elements and the zero elements in the two-dimensional time-frequency resource grid according to the time-frequency domain positions of each pilot frequency element and each zero element in the subcarrier. And gathering pilot frequency elements and zero elements in the two-dimensional time-frequency resource grid to obtain a first load data pilot frequency pattern of a first sending port in the plurality of sending ports. And determining second load data pilot frequency patterns of other sending ports in the plurality of sending ports according to the load data pilot frequency pattern of the first sending port based on orthogonality between the subcarriers. Based on the first load data pilot frequency pattern and the second load data pilot frequency pattern, pilot frequency is inserted into the load data signal to be sent, the load data signal to be sent is transmitted based on the subcarrier, and the zero element position indicates that the corresponding subcarrier does not bear the load data signal to be sent.

The invention discloses a distributed time cooperative guidance method for a patrol missile cluster with limited control input, and belongs to the technical field of patrol missile cluster guidance control. Establishing a double-layer collaborative guidance framework of the patrol missile cluster; the individuals take the residual flight time estimation values as coordination variables, the respective residual flight time estimation values are interacted through communication among the projectiles, and expected coordination variable values of all the projectiles are obtained through coordination strategy calculation and serve as input of a lower-layer time constraint guidance law; decomposing a lower-layer time constraint guidance law into a transverse lateral plane and a longitudinal plane, calculating an attitude angle and an accelerator through a segmented guidance law, and inputting the attitude angle and the accelerator as guidance control variables into the autopilot; according to an input attitude angle and an accelerator instruction, obtaining a rudder amount and an accelerator amount, and controlling the attitude and the speed of the patrolling bomb to realize time coordination. The invention provides a distributed time cooperative guidance method for a patrolling bomb cluster with limited control input, and aims to solve the problem that the patrolling bomb cluster simultaneously strikes a stationary target on the ground when the control input is limited to an attitude angle and an accelerator.

The invention discloses a fast reflector hybrid control method based on a multivariable extended state observer, and relates to the technical field of precise motion control. The control method comprises the following steps: obtaining transfer functions of X and Y axes of a voice coil type fast reflector system by adopting a system identification method, and obtaining a fast reflector model; designing a model auxiliary multivariable expansion state observer according to the obtained fast reflector model; and designing a mixed state feedback controller on the basis of the model-assisted multivariable extended state observer. According to the method, the extended state observer is combined with hybrid control, known model information is added into one observer to design a model-assisted multivariable extended state observer, and X and Y axes are observed at the same time, so that the estimation error of disturbance of each channel is reduced, and the decoupling capability and robust performance of the extended state observer are improved.

The invention relates to the technical field of power distribution network voltage regulation, and provides a reactive voltage control processing method and device of a power distribution network, computer equipment, a readable storage medium and a program product. The method comprises the following steps: performing multiple rounds of operation according to initial observation state data; during each round of operation, the following steps are executed: obtaining a plurality of available reactive voltage control schemes of the current round according to observation state data of the current round and a plurality of pre-constructed integrated decision networks; according to the relative magnitude of the evaluation mean value corresponding to the scheme, determining a current-round candidate reactive voltage control scheme; obtaining a corresponding current round reward value according to an actual execution result of the current round candidate reactive voltage control scheme in the target power distribution network; when the reward value does not meet the condition, obtaining the observation state data of the next round according to the actual execution result; and when the reward value meets a condition, taking the candidate reactive voltage control scheme as a target reactive voltage control scheme. By adopting the method, the error of the target reactive voltage control scheme can be reduced.

The application discloses a metabolic equivalent driven endurance training intensity gradient generation system and method thereof, and belongs to the technical field of intelligent sports training. The system comprises a non-contact physiological signal acquisition module, a multi-dimensional metabolic state modeling module, a floating threshold generation module, a multi-channel feedback regulation module and an edge abnormality filtering module. Respiratory and heart rate and other multi-dimensional physiological parameters are collected through the fusion of a millimeter wave radar and a PPG sensor. A three-dimensional metabolic state dynamic evaluation model is constructed based on a GRU network, and real-time MET values are output. Intensity adjustment threshold values are adaptively generated according to MET deviation. The exercise intensity is cooperatively regulated through the tactile feedback of intelligent running shoes and the slope adjustment of a treadmill. Abnormal data are filtered at the edge by using a LOF algorithm. The application solves the problems of single physiological signal dimension, static metabolic state evaluation and abnormal data interference in the prior art, and realizes the precise real-time regulation of endurance training intensity.

A frequency modulation energy assessment method that considers the differences in the spatiotemporal distribution of wind speed in a wind farm relates to the technical field of wind farms and is used to solve the problem that only the kinetic energy of the wind turbine blade rotor is considered in the frequency modulation energy assessment of a wind farm, while the loss of mechanical power captured during the frequency modulation process is ignored, resulting in large errors in the assessment results. It includes: (1) constructing a minute-level wind speed probability prediction model for each wind farm group based on numerical weather forecasts; (2) constructing a typical wind speed prediction scenario; (3) evaluating the frequency modulation energy of a wind farm based on a typical wind speed prediction scenario. The frequency modulation energy assessment algorithm for a wind farm proposed in this patent can be achieved by analyzing the differences in the spatiotemporal distribution of wind speed and generating a typical wind speed prediction scenario using a probability prediction distribution function, which can effectively reduce estimation errors.

The invention relates to an SOC estimation method and device for a new energy vehicle, electronic equipment and a storage medium. The method comprises the steps that driver behavior data, vehicle operation environment data and temperature data are acquired; training a local convolutional network by using the acquired data, and sending network parameters of the trained local convolutional network to a central server; enabling the central server to cluster the received network parameters based on federal learning according to the vehicle operation environment data and the temperature data, and aggregating the network parameters of the same type; aggregation parameters sent by the central server are received, the local convolutional network is iteratively updated until preset conditions are met, in the updating process, network parameters of the local convolutional network are constrained according to preset global drift constraints, and the weight of the global drift constraints is gradually increased along with the number of training times; and estimating the SOC of the new energy vehicle by using the updated local convolutional network.

The driving range estimation method based on unit charge range and battery aging correction mainly includes four steps: online battery SOC estimation, periodic battery SOH update, unit SOC range estimation, and driving range estimation. This invention uses periodic battery SOH estimation to correct the battery SOC estimation, and combines unit SOC range estimation to achieve accurate driving range estimation. It has the advantages of simple model structure, low computational load, high estimation accuracy, and easy implementation in vehicle BMS. Under normal driving conditions, the maximum driving range estimation error of this invention is within 3km, which meets the operating requirements of electric vehicles.

The invention relates to the technical field of permanent magnet synchronous motor control, and discloses a permanent magnet synchronous motor sliding mode control method, device and equipment and a storage medium, and the method comprises the steps: constructing a motor state equation based on a permanent magnet synchronous motor mathematical model, taking a load torque as external disturbance, and constructing a novel adaptive nonlinear expansion state observer; based on a motor state equation, constructing a non-singular fast terminal sliding mode surface and a novel variable gain index reaching law; constructing a novel non-singular fast terminal sliding mode controller based on the novel adaptive nonlinear extended state observer, the non-singular fast terminal sliding mode surface and the novel variable gain index reaching law; and executing permanent magnet synchronous motor sliding mode control by using the novel nonsingular fast terminal sliding mode controller. Compared with the prior art, the novel sliding mode control strategy has the advantages that buffeting is greatly weakened, the control precision is improved, the convergence speed is obviously increased, and the system can be asymptotically converged to a balance point within finite time.

A colon endoscope camera pose estimation method based on an iterative refinement strategy relates to the technical field of medical image processing and computer vision, and comprises the steps of construction and preprocessing of an image data set, construction of an overall framework of a network model, design and implementation of a feature extraction network, and design and implementation of a camera motion classification network. Designing and realizing an iterative relative pose refining network; training and using a network model; and the like. According to the method, two camera motion modes of insertion and withdrawal are distinguished by using the camera motion classification network, the pose estimation precision is improved by combining a coarse-to-fine iteration refining strategy of the iteration relative pose refining network, the learning ability and generalization performance of the whole method are effectively improved, accurate estimation of the colon endoscope camera pose is realized, and the method is suitable for popularization and application. The method can be widely applied to the camera pose estimation task of the colon endoscope, and provides accurate camera pose support for clinical application scenes such as three-dimensional reconstruction and polyp screening of the colon endoscope.

The invention belongs to the field of multi-agent collaborative perception, and particularly discloses a cross-view scene-oriented multi-feature pose estimation method, which comprises the following steps that: an unmanned aerial vehicle and an unmanned vehicle acquire image information through binocular cameras respectively in a mapping process, and extract point features and line features in images respectively; a point-line combination body is found through an expansion algorithm; the pose estimation process is constrained through a point-line combination body in the single agent positioning process; in the process of exchanging map information by multiple agents, performing coarse registration on point clouds preferentially by combining a PCM algorithm with a point-line combination body; and finally, a distributed RANSAC algorithm is constructed through an octree map, so that high-precision multi-agent relative pose estimation is realized, and accurate relative pose estimation is provided for later multi-agent collaborative mapping, collaborative planning and the like.

The application provides a high-efficiency network traffic measurement architecture based on timing filtering and dynamic migration. When a data packet arrives, the flow activity is evaluated by timing filtering to filter out low-frequency transient flows, and the continuously active flow is connected to the main measurement structure. In combination with the data flow characteristics and the dynamic migration model, the history Sketch area and the active queue area are dynamically scheduled: the Sketch relies on compact hashing and probability counting to depict the global traffic profile; the active area is configured with independent counters to accurately track the active flow without loss. The frequency is updated according to the flow type difference: the continuously active flow is accurately counted in the active queue, the inactive flow is accumulated in the history Sketch area, and the low-frequency transient flow is directly discarded. If the promotion threshold is triggered, the hierarchical dynamic migration is completed through cyclic iteration until the measurement period ends. The architecture can adaptively allocate storage space according to the flow timing characteristics, reduce memory occupation and hash collision, and effectively improve the accuracy and running efficiency of large-scale network traffic measurement.

The present application relates to a method, device, computer equipment and storage medium for configuring train schedules in a mixed scenario. The method includes: obtaining schedule data, ticket routing data, ticket information data and special customer list data; determining a schedule base table according to the schedule data; obtaining first ticket preprocessing data according to the ticket routing data, ticket information data and special customer list data; determining special customer direct train schedules and special customer direct load capacity according to target data with customer labels as special customers in the first ticket preprocessing data; determining hub point direct invoices according to the special customer direct load capacity and the second ticket preprocessing data obtained from the first ticket preprocessing data; determining tickets for each schedule according to hub point direct invoices and the schedule base table; and determining the corresponding hub point direct train schedules according to the schedule labels based on the tickets for each schedule. The use of this method can improve the efficiency and accuracy of train schedule configuration in mixed scenarios.

This invention belongs to the field of data processing technology and relates to a method and system for error correction in the joint evaluation of battery SOC and SOH. The method includes: S1, preprocessing the acquired multi-source data; S2, constructing a joint SOH-SOC estimation model; S3, segmenting the preprocessed data from different time points to obtain first window data and second window data; S4, obtaining a fused SOC estimate based on the first and second window data using an ampere-hour integral algorithm and a quartile distance group detection algorithm; and S5, dynamically correcting the joint SOH-SOC estimation model using a gradient backpropagation mechanism based on the fused SOC estimate and the SOC value at the end of the second window data to obtain a corrected joint SOH-SOC estimation model. This invention solves the problems of low estimation accuracy and low reliability in existing methods by dynamically correcting the joint SOH-SOC estimation model.

The application relates to the technical field of vehicles, in particular to a vehicle speed estimation method and device, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring the state of each wheel at a current moment, wherein the state comprises a first state and a second state; if the state of all the wheels is the first state, acquiring the vehicle speed of the vehicle at a historical moment before all the wheels enter the second state, and estimating the vehicle speed of the vehicle at the current moment according to the vehicle speed of the vehicle at the historical moment; otherwise, estimating the vehicle speed of the vehicle at the current moment according to the wheel speed of the wheel in the second state. Thus, the problems of low accuracy of vehicle speed estimation and large estimation error in the related art are solved.

The invention provides a parameter identification method for a proton exchange membrane fuel cell system, belongs to the technical field of fuel cell identification, and solves the technical problem of low parameter identification precision caused by the fact that an internal electrochemical reaction of the proton exchange membrane fuel cell system cannot be accurately described by a traditional modeling method. According to the technical scheme, the method comprises the following steps: 1) establishing a fractional order multiple-input single-output state space model of the proton exchange membrane fuel cell system; and step 2) constructing an identification process of the hierarchical multi-information recursive minimum error entropy algorithm. The hierarchical multi-information recursive minimum error entropy algorithm provided by the invention has relatively high convergence speed and relatively high convergence precision, and can be well suitable for parameter identification of the proton exchange membrane fuel cell system.

The invention relates to the technical field of metallurgical process control, and discloses a molten pool smelting intelligent dynamic control system based on multi-parameter coupling, which comprises a global perception sensor network, a data fusion and state evaluation module and a precise execution control system. According to the system, heat-fluidization multivariable variables of a molten pool are obtained at high frequency through a global perception sensor network, a data fusion and state evaluation module completes prediction-updating through Kalman filtering, abnormal value elimination is carried out through a Mahalanobis distance threshold, working condition drifting is restrained in combination with self-adaptive R / Q, and the state of the molten pool is evaluated. State evaluation is carried out, the middle temperature, the copper matte grade, the liquid level, the change rate and the circulation strength are generated, an LSTM model is adopted for short-time prediction, control suggestions are generated, an amplitude / slope limiting function and a safety interlocking mechanism are matched, a closed-loop execution process is formed, the accurate execution control system converts the control suggestions into actual control actions, and the actual control actions are controlled. And the state of the molten pool is accurately adapted, operation feedback and state monitoring data are transmitted back, and the intelligent control operation efficiency is high.

The invention relates to a lithium battery SoC (state of charge) estimation method based on an RFCNet (residual full-connection neural network) model, and the method is suitable for the estimation of the state of charge of a lithium ion battery. The method specifically comprises the following steps: acquiring basic data of the lithium battery; the method comprises the following steps: carrying out an experiment to construct an original data set, namely carrying out a plurality of charging and discharging experiments on a plurality of lithium ion batteries with the same model under different temperature conditions, recording experimental data at equal time intervals, and stopping the experiment until SoH (State of Health) is reduced to 70%; preprocessing the data and calculating SoH and SoC; dividing a data set: randomly dividing the data set into a training set and a test set according to a ratio of 7: 3; model training: training the RFCNet model by using the training set; and estimating the SoC of the current lithium battery by using the RFCNet model. According to the method, the SoC of the lithium battery is estimated based on the data such as the electrical parameters and the temperature and the RFCNet model, and convenience is provided for intelligent monitoring and lean management of the lithium battery.

This invention discloses a signal processing, motion state estimation method, apparatus, vehicle-mounted equipment, and medium to solve the problem of the inevitable compromise between hysteresis and root mean square noise values ​​in the prior art. The method includes: acquiring the raw signals detected by each body sensor on the vehicle at the previous time step; the body sensors include different types of sensors, with multiple sensors of each type; estimating the signal increment value of another body sensor of the same type per unit time based on the raw signals detected by at least three of the multiple body sensors of the same type at the previous time step; calculating the signal estimate value of the body sensor at the current time step based on the raw signals and corresponding signal increment values ​​of the body sensors at the previous time step; and fusing the raw signals of the body sensors at the previous time step and the signal estimate value at the current time step to obtain the fused signal value of the body sensors at the current time step.

This invention discloses a network resilience evaluation method based on data fusion and adaptive weight update in the field of data processing technology. The method includes acquiring headquarters-branch office data of industries in a target region, classifying the headquarters-branch office data, fusing the classified data at the city level, preprocessing the fused data to obtain preprocessed data, setting corresponding KPIs based on the headquarters-branch office data, calculating the KPI change rate based on historical and newly added headquarters-branch office data, and calculating the updated coupling strength between headquarters-branch office data based on the KPI change rate. This invention constructs a hierarchical, multi-source spatiotemporal data industry network model, and combines it with an adaptive association strength update method and a spatiotemporal hierarchical weight adjustment mechanism to achieve real-time updates of headquarters-branch office coupling strength and node / edge capacity, thereby improving the accuracy of industry network resilience assessment.