Gate control method and system based on dynamic cooperative scheduling and storage medium

Abstract

The invention relates to the technical field of gate control, and discloses a gate control method and system based on dynamic cooperative scheduling and a storage medium. The method comprises the following steps: carrying out fatigue quantification on gate torque change and adjustment times through a strain sensor to obtain a comprehensive health index; establishing an adjustment frequency and equipment degradation correlation model according to the health index to obtain degradation prediction data; coupling and fusing the water level flow data and the degradation prediction data to obtain a water regimen-equipment coupling prediction result; a coupling prediction result is optimized through an adaptive weight algorithm, and a differentiated scheduling strategy of the healthy gate and the aged gate is obtained; and performing corresponding control processing on the healthy gate and the aging gate to generate a cooperative control instruction sequence. The technical problem that in an existing gate control technology, water regimen changes and equipment state evolution are independently processed, and differentiated collaborative scheduling based on equipment health constraints cannot be achieved is solved.

Description

Technical Field

[0001] The present application relates to the field of gate control technology, and in particular to a gate control method, system and storage medium based on dynamic collaborative scheduling. Background Art

[0002] Existing gate control technologies primarily utilize methods based on preset scheduling rules. These methods utilize real-time monitoring of upstream and downstream hydrological data, such as water levels and flow rates, combined with water scheduling plans to use mathematical models to predict water regime trends. Gate opening adjustment strategies are then formulated and executed through automated control systems. This type of technology plays a vital role in water level and flow regulation, enabling coordinated gate control based on multiple scheduling objectives, such as flood control, power generation, and irrigation, and incorporating feedback adjustment mechanisms to optimize control effectiveness.

[0003] However, existing technologies have significant shortcomings, primarily due to the independence of gate equipment status monitoring and flow control decisions, ignoring the impact of equipment performance degradation on control effectiveness during long-term gate operation. Existing control systems typically assume that gate equipment always maintains its designed performance parameters, failing to account for actual flow capacity degradation and changes in response characteristics caused by factors such as equipment wear and aging. Furthermore, they lack a quantitative assessment of the cumulative effects of gate fatigue, making it impossible to adjust scheduling strategies based on equipment health.

[0004] Existing technologies are unable to establish a coupling relationship between water regime changes and the evolution of gate equipment status. Frequent water regime fluctuations require high-intensity gate regulation, accelerating equipment fatigue accumulation and performance degradation. This degradation in equipment performance, in turn, affects the precision and stability of water flow control, forming a complex coupled system of water regime-equipment interactions. Existing independent processing methods are unable to accurately predict this coupling effect, resulting in a lack of consideration of equipment health constraints when formulating coordinated gate scheduling strategies. This fails to fully utilize the regulation potential of healthy equipment and effectively protects aging equipment, ultimately affecting the coordinated control effectiveness and equipment life of the entire gate group. Summary of the Invention

[0005] The present application provides a gate control method, system and storage medium based on dynamic collaborative scheduling, which solves the technical problem in existing gate control technology that water situation changes and equipment status evolution are handled independently and differentiated collaborative scheduling based on equipment health constraints cannot be achieved.

[0006] In the first aspect, the present application provides a gate control method based on dynamic collaborative scheduling, which includes: quantifying the changes in the gate opening and closing torque and the accumulation of the number of adjustments through a strain sensor array to obtain a comprehensive gate health index; correlating the gate adjustment frequency with the equipment degradation rate based on the comprehensive gate health index to obtain equipment health degradation prediction data; coupling and fusing the upstream and downstream water level flow data with the equipment health degradation prediction data to obtain a water condition-equipment coupling prediction result; performing multi-gate collaborative optimization processing on the water condition-equipment coupling prediction result through an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy; processing the healthy gate opening control according to the first scheduling strategy, and correcting the aging gate opening control according to the second scheduling strategy to obtain a collaborative control instruction sequence.

[0007] Optionally, the fatigue quantification processing of the gate opening and closing torque change and the cumulative number of adjustment times is performed by the strain sensor array to obtain the gate comprehensive health index, including: The torque sensor signal of the gate opening and closing mechanism is collected and processed in real time to obtain the current opening and closing torque value and the initial design torque value; Performing a difference calculation based on the current opening and closing torque value and the initial design torque value to obtain a torque change rate and a wear degree coefficient; Input the gate adjustment operation history records into the cumulative counter for statistical analysis and processing to obtain the cumulative adjustment times and fatigue index; A weighted fusion calculation is performed based on the wear degree coefficient and fatigue index to obtain a comprehensive gate health index.

[0008] Optionally, the correlation modeling process of gate adjustment frequency and equipment degradation rate is performed according to the gate comprehensive health index to obtain equipment health degradation prediction data, including: Inputting the gate comprehensive health index into a nonlinear regression algorithm to calculate the adjustment frequency impact factor to obtain the frequency-degradation correlation coefficient; Performing fitting analysis on historical adjustment amplitude data based on the frequency-degradation correlation coefficient to obtain a degradation rate calculation model; Input the current gate adjustment frequency and adjustment amplitude parameters into the degradation rate calculation model for prediction and calculation processing to obtain equipment degradation trend data for future time periods; The remaining life of the gate is evaluated and calculated based on the equipment degradation trend data in the future period to obtain equipment health degradation prediction data.

[0009] Optionally, coupling and fusing the upstream and downstream water level flow data with the equipment health degradation prediction data to obtain a water regime-equipment coupling prediction result includes: Perform time series difference calculation on the water level data collected by upstream and downstream water level sensors to obtain water level change trend parameters and flow rate change rate parameters; Performing matrix combination and permutation processing on the equipment health degradation prediction data and the water level and flow data to obtain a coupled state vector containing the equipment state; Performing partial derivative calculation processing on the coupling state vector based on the water level change trend parameter to obtain a water regime-equipment interaction coefficient; Inputting the flow rate change parameter into the extended Kalman filter algorithm for recursive estimation processing to obtain a predicted state value of the coupling system; A covariance matrix updating process is performed on the predicted state value of the coupling system according to the interaction influence coefficient to obtain a water regime-equipment coupling prediction result.

[0010] Optionally, performing multi-gate collaborative optimization processing on the water regime-equipment coupling prediction result by an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy includes: Performing water level control deviation and equipment health classification calculation on the water regime-equipment coupling prediction result to obtain initial values ​​of multi-objective optimization weights; Based on the water regime-equipment coupling prediction result, threshold judgment processing is performed on the health of each gate, and gates with health higher than the safety threshold are classified into a healthy gate group, and gates with health lower than the safety threshold are classified into an aging gate group; Perform load distribution calculation based on the healthy gate group and the aged gate group to obtain a healthy gate adjustment weight coefficient and an aged gate protection weight coefficient; Performing adaptive adjustment operation on the multi-objective optimization weight initial value and the adjustment weight coefficient to obtain a dynamic weight allocation matrix; Optimizing and solving the health gate scheduling target based on the dynamic weight allocation matrix to obtain a first scheduling strategy; The aging gate scheduling constraint is subjected to restrictive optimization processing according to the protection weight coefficient to obtain a second scheduling strategy.

[0011] Optionally, the optimizing and solving the health gate scheduling target based on the dynamic weight allocation matrix to obtain a first scheduling strategy includes: The weight coefficients of the healthy gates in the dynamic weight distribution matrix are processed by objective function construction to obtain a multi-objective optimization function including a water level control deviation term, an adjustment stability constraint term, and an inter-gate coordination penalty term; Perform multi-level constraint condition setting processing on the optimization function based on the physical opening limit and adjustment rate constraint of the healthy gate group to obtain a healthy gate scheduling constraint set including upper and lower limits of opening, adjustment range limit and response time constraint; The current water level deviation, flow demand parameters and predicted water regime change trends are input into the improved particle swarm algorithm for global optimization iterative processing to obtain the optimal opening adjustment sequence of the healthy gate that meets the constraints. According to the optimal opening adjustment sequence of the healthy gate, load balancing and response delay compensation are performed on the opening and closing timing of each gate to obtain a healthy gate time allocation scheme that takes into account the response characteristics of the equipment; Based on the healthy gate time allocation scheme, hierarchical control instruction encoding and execution priority sorting are performed to obtain a first scheduling strategy including an opening target value, an adjustment rate and an execution time.

[0012] Optionally, the healthy gate opening control is processed according to the first scheduling strategy, and the aged gate opening control is corrected according to the second scheduling strategy to obtain a coordinated control instruction sequence, including: Performing instruction parsing on the target value of the healthy gate opening in the first scheduling strategy to obtain a healthy gate opening control instruction and an adjustment timing arrangement; Based on the second scheduling strategy, a progressive correction process is performed on the aging gate opening control instruction to obtain an aging gate protective control instruction that limits the adjustment range and extends the adjustment time; Perform time conflict detection and processing based on the healthy gate adjustment timing arrangement and the aging gate protective control instruction to obtain a collaborative scheduling time window allocation plan; The collaborative scheduling time window allocation scheme is input into the control instruction arrangement algorithm for serialization generation processing to obtain a collaborative control instruction sequence.

[0013] In a second aspect, the present application provides a gate control system based on dynamic collaborative scheduling, the gate control system based on dynamic collaborative scheduling comprising: The quantification module is used to perform fatigue quantification on the gate opening and closing torque changes and the accumulated adjustment times through the strain sensor array to obtain the gate comprehensive health index; A correlation module is used to perform correlation modeling processing on the gate adjustment frequency and the equipment degradation rate according to the gate comprehensive health index to obtain equipment health degradation prediction data; A fusion module is used to couple and fuse the upstream and downstream water level flow data with the equipment health degradation prediction data to obtain a water condition-equipment coupling prediction result; a collaborative module, configured to perform multi-gate collaborative optimization processing on the water regime-equipment coupling prediction result by using an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy; The correction module is used to process the healthy gate opening control according to the first scheduling strategy and to correct the aging gate opening control according to the second scheduling strategy to obtain a coordinated control instruction sequence.

[0014] In a third aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the above-mentioned gate control method based on dynamic collaborative scheduling.

[0015] In the technical solution provided by the present application, the present invention uses a strain sensor array to perform fatigue quantification on the changes in the gate opening and closing torque and the accumulation of the number of adjustments, establishes an accurate quantitative evaluation system for the health status of the equipment, and overcomes the technical defects of the separation of equipment status monitoring and control decision-making in the prior art. The introduction of the comprehensive health index of the gate enables the system to grasp the actual performance status of each gate in real time, providing a reliable data basis for subsequent differentiated scheduling. Based on the comprehensive health index, the correlation modeling processing of the gate adjustment frequency and the equipment degradation rate is carried out, and the quantitative relationship between the gate usage intensity and the equipment life attenuation is established for the first time, so that the system can predict the long-term impact of different scheduling schemes on the health of the equipment. The coupled fusion processing of water level flow data and equipment health degradation prediction data breaks through the limitations of traditional independent processing of hydrological prediction and equipment monitoring, and constructs a bidirectional coupling prediction model of water situation changes and equipment status evolution, which significantly improves the system's prediction accuracy for the coordinated control of gate groups under complex working conditions.

[0016] The application of the adaptive weight adjustment algorithm in the field of coordinated control of multiple gates in water conservancy projects fully utilizes its technical advantages of dynamic optimization. By adjusting the weight ratio of water level control and equipment protection in real time, the algorithm achieves an intelligent balance between flood control scheduling goals and equipment life protection, avoiding the scheduling imbalance problem of traditional fixed weight methods under extreme working conditions. The differentiated design of the first scheduling strategy and the second scheduling strategy reflects the invention's accurate identification and targeted treatment of individual differences in equipment. Healthy gates undertake the main adjustment tasks to fully utilize their adjustment potential, and aging gates perform protective scheduling to extend their service life. This hierarchical scheduling strategy effectively solves the problems of excessive equipment wear and uneven adjustment efficiency caused by the unified scheduling mode adopted by all gates in the existing technology. The generation of collaborative control instruction sequences realizes the precise coordination of multiple gates in time and space dimensions. Through the efficient adjustment of healthy gates and the protective use of aging gates, it not only ensures the accuracy of water level control but also significantly extends the overall service life of the equipment group. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 Schematic diagram of an embodiment of a gate control method based on dynamic collaborative scheduling in an embodiment of the present application; Figure 2 This is a schematic diagram of an embodiment of a gate control system based on dynamic collaborative scheduling in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The embodiments of the present application provide a gate control method, system and storage medium based on dynamic collaborative scheduling. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiments of the present application, an embodiment of a gate control method based on dynamic collaborative scheduling includes: Step S101: performing fatigue quantification on the gate opening and closing torque change and the accumulated adjustment times through a strain sensor array to obtain a comprehensive gate health index; Step S102: performing correlation modeling on the gate adjustment frequency and the equipment degradation rate according to the gate comprehensive health index to obtain equipment health degradation prediction data; Step S103: coupling and fusing the upstream and downstream water level flow data with the equipment health degradation prediction data to obtain a water regime-equipment coupling prediction result; Step S104: performing multi-gate collaborative optimization processing on the water regime-equipment coupling prediction result by using an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy; Step S105: Process the healthy gate opening control according to the first scheduling strategy, and correct the aging gate opening control according to the second scheduling strategy to obtain a coordinated control instruction sequence.

[0021] It is understandable that the execution subject of the present application can be a gate control system based on dynamic collaborative scheduling, or a terminal or a server, which is not limited here. The embodiment of the present application is described by taking the server as the execution subject as an example.

[0022] Specifically, the strain sensor array is installed at the key position of the gate opening and closing mechanism to monitor the changes in the torque sensor signal in real time, obtain the current opening and closing torque value and the initial design torque value, and obtain the torque change rate through difference calculation. At the same time, the cumulative counter counts the historical adjustment operation records of the gate, calculates the cumulative number of adjustments, and performs weighted fusion calculation on the wear degree coefficient and fatigue index to finally obtain a comprehensive health index reflecting the overall health status of the gate.

[0023] A correlation model between gate adjustment frequency and equipment degradation rate is established, the comprehensive health index is input into the nonlinear regression algorithm, the adjustment frequency influencing factor is calculated through historical data fitting analysis, and the frequency-degradation correlation coefficient is obtained. Based on this coefficient, the historical adjustment amplitude data is fitted and analyzed to construct a degradation rate calculation model. The current gate adjustment frequency and adjustment amplitude parameters are substituted into the model for prediction calculation to obtain the equipment degradation trend data for the future period. Then, the remaining life of the gate is calculated through evaluation to form equipment health degradation prediction data.

[0024] The coupling and fusion of water condition data and equipment status is realized. The water level data collected by upstream and downstream water level sensors are calculated by time-series difference. The water level change trend parameters and flow change rate parameters are extracted. The equipment health degradation prediction data and water level and flow data are combined and arranged in a matrix to construct a coupled state vector containing the equipment status. The partial derivative of the coupled state vector is calculated based on the water level change trend parameter to obtain the water condition-equipment interaction coefficient. The flow change rate parameter is then input into the extended Kalman filter algorithm for recursive estimation to obtain the predicted state value of the coupled system. Finally, the covariance matrix of the predicted state value is updated according to the interaction influence coefficient to form the water condition-equipment coupling prediction result.

[0025] Multi-gate collaborative optimization is achieved through an adaptive weight adjustment algorithm. The water level control deviation and equipment health grade calculation are performed on the coupled prediction results to obtain the initial value of the multi-objective optimization weight. Then, a threshold judgment is made on the health of each gate. Gates with health higher than the safety threshold are classified into the healthy gate group, and those below the threshold are classified into the aging gate group. Load distribution calculation is performed based on the two groups to obtain the healthy gate adjustment weight coefficient and the aging gate protection weight coefficient. The initial optimization weight value and the adjustment weight coefficient are adaptively adjusted to form a dynamic weight distribution matrix. Based on this matrix, the healthy gate scheduling target is optimized and solved to obtain the first scheduling strategy. At the same time, the aging gate scheduling constraint is restrictively optimized according to the protection weight coefficient to obtain the second scheduling strategy.

[0026] Execute differentiated gate control strategies, perform instruction parsing on the healthy gate opening target value in the first scheduling strategy, obtain the healthy gate opening control instruction and adjustment timing arrangement, perform progressive correction on the aging gate opening control instruction based on the second scheduling strategy, form an aging gate protective control instruction that limits the adjustment range and extends the adjustment time, perform time conflict detection based on the healthy gate adjustment timing arrangement and the aging gate protective control instruction, obtain a collaborative scheduling time window allocation scheme, and finally input the scheme into the control instruction scheduling algorithm for serialization generation to form a collaborative control instruction sequence including execution time, opening increment and adjustment rate.

[0027] In a specific embodiment, the process of executing step S101 may specifically include the following steps: The torque sensor signal of the gate opening and closing mechanism is collected and processed in real time to obtain the current opening and closing torque value and the initial design torque value; Performing a difference calculation based on the current opening and closing torque value and the initial design torque value to obtain a torque change rate and a wear degree coefficient; Input the gate adjustment operation history records into the cumulative counter for statistical analysis and processing to obtain the cumulative adjustment times and fatigue index; A weighted fusion calculation is performed based on the wear degree coefficient and fatigue index to obtain a comprehensive gate health index.

[0028] Specifically, obtaining the gate's comprehensive health index is achieved through four key data processing steps. First, during the real-time acquisition and processing of torque sensor signals, a strain sensor array installed on the gate's opening and closing mechanism continuously monitors torque changes during gate operation. The sensor converts mechanical strain into an electrical signal. After amplification and filtering by the signal conditioning circuit, the data acquisition card converts the analog signal into a digital signal, obtaining the current opening and closing torque value. Simultaneously, the gate's initial design torque value is retrieved from the equipment's technical archive as a reference value. The difference calculation processing step performs a mathematical operation on the current opening and closing torque value and the initial design torque value. The absolute difference is obtained by subtracting the two, and then divided by the initial design torque value to obtain the torque change rate. The torque change rate reflects the degree of wear on the gate's opening and closing mechanism. A greater torque change rate indicates more severe wear on the gate's mechanical components. The wear degree coefficient is calculated by the ratio of the torque change rate to a preset wear threshold. A value closer to 1 indicates that the equipment wear is approaching the design limit.

[0029] The cumulative counter statistical analysis and processing link extracts all adjustment operation records from the gate control history database, including the timestamp and adjustment amplitude information of each gate opening and closing. The cumulative counter scans and counts these operation records one by one, and calculates the cumulative number of adjustments of the gate from the time it was put into use to the current moment. The fatigue index is obtained by calculating the ratio of the cumulative number of adjustments to the expected number of adjustments within the design service life. The larger the fatigue index value, the higher the degree of gate fatigue.

[0030] The weighted fusion calculation and processing link mathematically fuses the wear coefficient and fatigue index according to the preset weight distribution. The wear coefficient weight reflects the impact of mechanical wear on the health of the equipment, and the fatigue index weight reflects the impact of the frequency of use on the life of the equipment. The sum of the two weights is equal to 1. The comprehensive health index of the gate is obtained by weighted average calculation. The index value range is between 0 and 1. The closer the value is to 1, the better the health of the gate. The closer the value is to 0, the more serious the aging of the gate. The comprehensive health index of the gate serves as the core basis for subsequent equipment status classification and scheduling strategy formulation.

[0031] In a specific embodiment, the process of executing step S102 may specifically include the following steps: Inputting the gate comprehensive health index into a nonlinear regression algorithm to calculate the adjustment frequency impact factor to obtain the frequency-degradation correlation coefficient; Performing fitting analysis on historical adjustment amplitude data based on the frequency-degradation correlation coefficient to obtain a degradation rate calculation model; Input the current gate adjustment frequency and adjustment amplitude parameters into the degradation rate calculation model for prediction and calculation processing to obtain equipment degradation trend data for future time periods; The remaining life of the gate is evaluated and calculated based on the equipment degradation trend data in the future period to obtain equipment health degradation prediction data.

[0032] Specifically, the nonlinear regression algorithm calculates the influencing factor of the adjustment frequency on the comprehensive health index of the gate. The nonlinear regression algorithm first collects the paired data of the comprehensive health index of the gate and the adjustment frequency of the corresponding period in the historical time series. The algorithm iteratively searches for the best fitting curve through the least squares method to identify the nonlinear law of the change of the health index with the adjustment frequency. During the calculation process, the algorithm establishes a polynomial regression model, takes the adjustment frequency as the independent variable, and the change of the health index as the dependent variable. Through repeated iterations to optimize the regression coefficient, the frequency-degradation correlation coefficient is finally obtained. This coefficient quantifies the impact of the gate adjustment frequency on the health status of the equipment.

[0033] Based on the frequency-degradation correlation coefficient, the historical adjustment amplitude data is fitted and analyzed. The fitting analysis extracts the amplitude records of all historical adjustment operations from the gate operation archive, including the specific numerical value of each opening change. The algorithm correlates the adjustment amplitude data with the equipment degradation rate in the corresponding period. The frequency-degradation correlation coefficient is used as a weight factor to correct the contribution of the adjustment amplitude to equipment degradation. The fitting analysis uses curve fitting technology to establish a mathematical relationship between the adjustment amplitude and the degradation rate, forming a degradation rate calculation model. The model contains two core variables: adjustment frequency and adjustment amplitude.

[0034] The current gate adjustment frequency and adjustment amplitude parameters are input into the degradation rate calculation model for predictive operation processing. The predictive operation processing first obtains the actual adjustment frequency data and adjustment amplitude data of the gate during the current operation cycle, and substitutes these real-time parameters into the established degradation rate calculation model. The model calculates the equipment degradation rate under the current operating mode according to the historical fitting law, and then predicts the equipment health change trend in different time periods in the future through time integration operation, and obtains the equipment degradation trend data in the future time period. This data reflects the evolution trajectory of the health status of the equipment under the current usage intensity.

[0035] The remaining life of the gate is evaluated and calculated based on the equipment degradation trend data in the future period. The remaining life evaluation calculation sets a safety threshold for the equipment health. When the predicted health drops to the threshold, it is determined to be the end of the equipment life. The evaluation calculation performs a time series analysis on the equipment degradation trend data in the future period to find the time node when the health reaches the safety threshold. The remaining service life of the equipment is calculated by the difference between the current time and the time node, and finally the equipment health degradation prediction data is formed.

[0036] In a specific embodiment, the process of executing step S103 may specifically include the following steps: Perform time series difference calculation on the water level data collected by upstream and downstream water level sensors to obtain water level change trend parameters and flow rate change rate parameters; Performing matrix combination and permutation processing on the equipment health degradation prediction data and the water level and flow data to obtain a coupled state vector containing the equipment state; Performing partial derivative calculation processing on the coupling state vector based on the water level change trend parameter to obtain a water regime-equipment interaction coefficient; Inputting the flow rate change parameter into the extended Kalman filter algorithm for recursive estimation processing to obtain a predicted state value of the coupling system; A covariance matrix updating process is performed on the predicted state value of the coupling system according to the interaction influence coefficient to obtain a water regime-equipment coupling prediction result.

[0037] Specifically, the time series difference calculation performs numerical processing on the water level data collected by the upstream and downstream water level sensors. The time series difference calculation is a time series analysis method that identifies the water level change pattern by calculating the difference between the water level data at adjacent time points. The specific operation is to subtract the water level value at the previous moment from the current moment to obtain the water level change per unit time. This change reflects the rising or falling trend of the water level and forms a water level change trend parameter. At the same time, the flow change rate parameter is calculated by the ratio of the water level change to the time interval. The flow change rate parameter quantifies the intensity of the dynamic change of the water flow.

[0038] The equipment health degradation prediction data and water level and flow data are structured and integrated. The matrix combination and permutation processing first arranges the equipment health degradation prediction data into column vectors according to the time series, and then arranges the water level data and flow data of the corresponding time period into column vectors. Then, the three column vectors are horizontally spliced ​​according to the time correspondence to form a multi-dimensional data matrix. Each row of the matrix represents the system status at a specific moment, including equipment health information and water condition information. Finally, the coupled state vector containing the equipment status is obtained. The coupled state vector is a comprehensive carrier of water condition and equipment status information.

[0039] Partial derivative calculation is performed based on the water level trend parameter. Partial derivative calculation is a method used in mathematical analysis to study the rate of change of multivariable functions. In this scheme, the coupled state vector is regarded as a multivariate function, and the water level trend parameter is used as the independent variable. By solving the partial derivatives of each component of the coupled state vector with respect to the water level trend parameter, the sensitivity coefficients of each state variable to water level changes are calculated. These sensitivity coefficients reflect the degree of influence of water regime changes on the equipment status, forming the water regime-equipment interaction coefficient, which quantifies the interaction strength between hydrological conditions and equipment performance.

[0040] The flow rate change parameter is input into the extended Kalman filter algorithm for recursive estimation processing. The extended Kalman filter algorithm is a state estimation algorithm suitable for nonlinear systems. The algorithm first uses the dynamic model of the system to predict the current state, and then corrects the prediction result in combination with the observation data. The recursive estimation processing uses the flow rate change parameter as the observation input, calculates the state prediction value of the system at the next moment through the prediction step of the algorithm, and then uses the flow rate change parameter through the update step to correct the prediction error. After multiple iterative recursive calculations, the predicted state value of the coupled system is obtained. This state value integrates the comprehensive prediction results of historical information and current observations.

[0041] The covariance matrix is ​​updated based on the interaction coefficient. Covariance matrix updating is a key step in the extended Kalman filter algorithm for quantifying the uncertainty of state estimation. The update process uses the water regime-equipment interaction coefficient as a regulating factor for system noise. When the interaction coefficient is large, it indicates that the water regime has a significant impact on the equipment state, which correspondingly increases the uncertainty of state estimation. The diagonal elements of the covariance matrix reflect the estimated variance of each state variable, and the off-diagonal elements reflect the correlation between state variables. The covariance matrix is ​​dynamically adjusted through the interaction coefficient, and finally a coupled prediction result that considers the water regime-equipment interaction is obtained.

[0042] In a specific embodiment, the process of executing step S104 may specifically include the following steps: Performing water level control deviation and equipment health classification calculation on the water regime-equipment coupling prediction result to obtain initial values ​​of multi-objective optimization weights; Based on the water regime-equipment coupling prediction result, threshold judgment processing is performed on the health of each gate, and gates with health higher than the safety threshold are classified into a healthy gate group, and gates with health lower than the safety threshold are classified into an aging gate group; Perform load distribution calculation based on the healthy gate group and the aged gate group to obtain a healthy gate adjustment weight coefficient and an aged gate protection weight coefficient; Performing adaptive adjustment operation on the multi-objective optimization weight initial value and the adjustment weight coefficient to obtain a dynamic weight allocation matrix; Optimizing and solving the health gate scheduling target based on the dynamic weight allocation matrix to obtain a first scheduling strategy; The aging gate scheduling constraint is subjected to restrictive optimization processing according to the protection weight coefficient to obtain a second scheduling strategy.

[0043] Specifically, the water level control deviation and equipment health grading calculation are performed on the water condition-equipment coupling prediction results. The water level control deviation calculation obtains the deviation value by calculating the difference between the target water level and the predicted water level. The deviation reflects the gap between the current scheduling strategy and the expected control target. The equipment health grading calculation classifies the health value of each gate according to the preset grading standard. The grading standard includes four levels: excellent, good, general, and poor. The grading calculation determines the corresponding level according to the interval in which the health value is located. Then, the weight distribution calculation is performed based on the urgency of the water level control deviation and the equipment health grading results. The water level control demand with a high degree of urgency is assigned a higher weight, and the gate with a lower equipment health is assigned a lower adjustment weight. Finally, the initial value of the multi-objective optimization weight including the water level control weight and the equipment protection weight is obtained.

[0044] Based on the water condition-equipment coupling prediction results, the health of each gate is judged by threshold. The threshold judgment process first sets a safety threshold as the health judgment standard. The safety threshold is usually set as the median of the health value or the critical value determined based on equipment maintenance experience. The judgment process compares the health value of each gate with the safety threshold. When the gate health value is greater than the safety threshold, the classification operation is performed to classify the gate into the healthy gate group. When the gate health value is less than or equal to the safety threshold, the classification operation is performed to classify the gate into the aging gate group. The healthy gate group represents a collection of equipment with good adjustment capabilities, and the aging gate group represents a collection of equipment that needs protective use.

[0045] The load distribution calculation is performed based on the healthy gate group and the aging gate group. The load distribution calculation first counts the number of equipment in the healthy gate group and the aging gate group, and then calculates the proportion of the regulation load that each group should bear based on the overall regulation demand. The healthy gate group undertakes the main regulation task, and the aging gate group undertakes the auxiliary regulation task. The load distribution calculation determines the healthy gate regulation weight coefficient by the ratio of the number of healthy gates to the total number of gates. This coefficient reflects the contribution ratio of the healthy gate in the overall regulation. At the same time, the aging gate protection weight coefficient is calculated by the health level of the aging gate. This coefficient is used to limit the usage intensity of the aging gate, and the protection weight coefficient is inversely proportional to the health level.

[0046] The initial values ​​of the multi-objective optimization weights and the adjustment weight coefficients are adaptively adjusted. The adaptive adjustment operation is a dynamic weight optimization method. The operation first uses the initial values ​​of the multi-objective optimization weights as the basic weights, and then dynamically corrects the weights according to the current urgency of the water situation. When the water level control demand is urgent, the water level control weight ratio is increased. When the health status of the equipment deteriorates, the equipment protection weight ratio is increased. The adjustment operation incorporates the healthy gate adjustment weight coefficient and the aging gate protection weight coefficient into the weight correction process. The dynamic weight distribution matrix that takes into account the differences in equipment status is obtained through weighted average calculation. This matrix contains the personalized weight distribution plan for each gate.

[0047] The scheduling objectives of the healthy gates are optimized and solved based on the dynamic weight allocation matrix. The optimization solution uses a multi-objective optimization algorithm to calculate the scheduling plan of the healthy gates. The optimization objectives include maximizing the water level control accuracy and minimizing the regulation energy consumption. The solution uses the healthy gate weights in the dynamic weight allocation matrix as the weight coefficients of the objective function, and searches for the optimal solution that meets the constraints through iterative calculation. The constraints include the physical limitation of the gate opening, the regulation rate limitation and the water level safety range limitation. The optimization algorithm searches for the scheduling plan that minimizes the objective function value in the feasible solution space, and finally obtains the first scheduling strategy that includes the opening adjustment sequence and time arrangement of each healthy gate.

[0048] The scheduling constraints of aging gates are subject to restrictive optimization processing based on the protection weight coefficient. Restrictive optimization processing is a protective scheduling method specifically for aging equipment. The processing process converts the protection weight coefficient of the aging gate into a scheduling constraint condition. The constraints include restrictions such as the single adjustment amplitude not exceeding a specific proportion of the design value, the adjustment frequency not exceeding a specific multiple of the healthy gate, and the continuous operation time not exceeding the safe time. The optimization processing searches for the optimal use plan of the aging gate under these strict constraints, giving priority to the scheduling mode with a small adjustment amplitude and low frequency, while ensuring that the aging gate can still play an auxiliary adjustment role when necessary, and finally obtaining a second scheduling strategy that takes into account both equipment protection and adjustment needs.

[0049] In a specific embodiment, the process of performing the step of optimizing and solving the health gate scheduling target based on the dynamic weight allocation matrix may specifically include the following steps: The weight coefficients of the healthy gates in the dynamic weight distribution matrix are processed by objective function construction to obtain a multi-objective optimization function including a water level control deviation term, an adjustment stability constraint term, and an inter-gate coordination penalty term; Perform multi-level constraint condition setting processing on the optimization function based on the physical opening limit and adjustment rate constraint of the healthy gate group to obtain a healthy gate scheduling constraint set including upper and lower limits of opening, adjustment range limit and response time constraint; The current water level deviation, flow demand parameters and predicted water regime change trends are input into the improved particle swarm algorithm for global optimization iterative processing to obtain the optimal opening adjustment sequence of the healthy gate that meets the constraints. According to the optimal opening adjustment sequence of the healthy gate, load balancing and response delay compensation are performed on the opening and closing timing of each gate to obtain a healthy gate time allocation scheme that takes into account the response characteristics of the equipment; Based on the healthy gate time allocation scheme, hierarchical control instruction encoding and execution priority sorting are performed to obtain a first scheduling strategy including an opening target value, an adjustment rate and an execution time.

[0050] Specifically, the weight coefficients of the healthy gates in the dynamic weight distribution matrix are processed by objective function construction. Objective function construction is the process of converting practical problems into mathematical expressions in mathematical optimization. The construction process first extracts the weight coefficients of the healthy gates as the importance indicators of each optimization target, and then constructs the water level control deviation term, which expresses the water level control accuracy requirement in the form of the square of the difference between the target water level and the actual water level. Then, the adjustment smoothness constraint term is constructed, which constrains the smoothness of the adjustment process in the form of the sum of the squares of the gate opening changes at adjacent moments, and then constructs the inter-gate coordination penalty term, which punishes uncoordinated adjustment behavior in the form of the variance of the gate opening differences. Finally, the three terms are linearly combined according to the weight coefficients to obtain a multi-objective optimization function that comprehensively considers control accuracy, adjustment smoothness and gate coordination.

[0051] Multi-level constraint setting is performed based on the physical characteristics of the healthy gate group. Constraint setting is a key link in limiting the range of feasible solutions in the optimization problem. The setting process first determines the upper and lower limit constraints of the opening according to the mechanical structure of the gate. The upper limit of the opening corresponds to the fully open state of the gate, and the lower limit of the opening corresponds to the fully closed state of the gate. Then, the adjustment amplitude limit is set according to the mechanical performance of the gate opening and closing. This limit prevents the single adjustment amplitude from being too large and causing equipment impact. Then, the response time constraint is set according to the gate response characteristics. This constraint ensures that the execution time of the gate adjustment instruction is within the equipment capacity. The multi-level constraint conditions include hard constraints and soft constraints. Hard constraints must be strictly met, and soft constraints allow a certain degree of violation but will be punished. Finally, a healthy gate scheduling constraint set containing physical constraints, performance constraints and time constraints is formed.

[0052] The water condition parameters are input into the improved particle swarm algorithm for global optimization iterative processing. The improved particle swarm algorithm is a heuristic optimization algorithm based on swarm intelligence. The algorithm finds the optimal solution by simulating the foraging behavior of bird flocks. The iterative process first initializes the particle swarm. Each particle represents a candidate gate scheduling plan. The position of the particle corresponds to the opening adjustment sequence of each gate. Then the current water level deviation, flow demand parameters and predicted water condition change trend are used as input data of the algorithm. The algorithm evaluates the fitness of each particle according to the objective function value. Particles with high fitness represent better scheduling plans. Then the particle position is adjusted through the speed update and position update formulas. The speed update takes into account the guiding role of the particle's historical best position and the group's best position. After multiple rounds of iterative calculation until the convergence conditions are met, the optimal opening adjustment sequence of healthy gates that meets all constraints is finally obtained.

[0053] Load balancing and response delay compensation are performed according to the optimal opening adjustment sequence. Load balancing is a technical means to ensure the reasonable distribution of adjustment tasks of each gate. The processing process first analyzes the adjustment load distribution of each healthy gate. When the adjustment tasks of some gates are too heavy, some tasks are transferred to gates with lighter loads. Load balancing achieves a balance of workload for each gate through the adjustment sequence redistribution algorithm. Response delay compensation is a corrective measure for the differences in response characteristics of different gates. The compensation process calculates the response delay coefficient based on the historical response time data of each gate, issues control instructions in advance to the gate with slower response, and issues control instructions later to the gate with faster response. The synchronization of the actual action time of each gate is ensured through time offset adjustment, and finally a healthy gate time distribution plan that takes into account individual differences in equipment is obtained.

[0054] Hierarchical control instruction encoding and execution priority sorting are performed based on the time allocation scheme. Hierarchical control instruction encoding is a data conversion process that converts optimization results into executable instructions for the device. The encoding process converts the opening target value in the time allocation scheme into a digital signal recognized by the gate controller, and at the same time encodes the adjustment rate information into the speed parameter of the controller, and the execution time information is encoded into a timestamp format. Execution priority sorting is a scheduling mechanism that determines the order of instruction execution. The sorting process calculates the priority value of each instruction based on factors such as the urgency of water level control, the health status of the gate and the adjustment effect. Instructions with high priority are executed first, and instructions with low priority are executed later. The sorting algorithm ensures that important adjustment tasks are completed first under limited execution resources, and finally a complete first scheduling strategy including the opening target value, adjustment rate and execution time is obtained.

[0055] For example, a water conservancy project needed to cope with a sudden surge in upstream water inflow. The dynamic weight allocation matrix showed that the weights of the three gates in the healthy gate group corresponded to different emphases on water level control, regulation stability, and coordination. The objective function construction used the water level deviation term as the dominant objective, with the stability constraint term and the coordination penalty term as auxiliary objectives. Constraints were set based on limiting the opening range of the three healthy gates to between 0% and 100%, limiting the adjustment amplitude to no more than 15% per time, and constraining the response time to complete the adjustment within 10 minutes. The particle swarm algorithm was fed with information indicating that the current water level exceeded the target value and a forecast of a continued increase in flow over the next two hours. After 50 rounds of iterative optimization, the optimal opening adjustment sequence for the three gates was obtained. Load balancing identified that the first gate had an excessively heavy regulation load and allocated some of the load to the second gate. Response delay compensation, based on the slower response of the third gate, issued a command three minutes in advance. Hierarchical coding converted the optimization results into specific control commands. Priority sorting ensured that the command for the first gate was executed first, ultimately forming a coordinated and consistent first scheduling strategy.

[0056] In a specific embodiment, the process of executing step S105 may specifically include the following steps: Performing instruction parsing on the target value of the healthy gate opening in the first scheduling strategy to obtain a healthy gate opening control instruction and an adjustment timing arrangement; Based on the second scheduling strategy, a progressive correction process is performed on the aging gate opening control instruction to obtain an aging gate protective control instruction that limits the adjustment range and extends the adjustment time; Perform time conflict detection and processing based on the healthy gate adjustment timing arrangement and the aging gate protective control instruction to obtain a collaborative scheduling time window allocation plan; The collaborative scheduling time window allocation scheme is input into the control instruction arrangement algorithm for serialization generation processing to obtain a collaborative control instruction sequence.

[0057] Specifically, the target opening value of the healthy gate in the first scheduling strategy is subjected to instruction parsing processing. Instruction parsing is a data conversion process that converts high-level scheduling decisions into executable instructions for the device. The parsing process first extracts the opening target value of each healthy gate from the first scheduling strategy. These target values ​​represent the expected opening degree of the gate in the form of a percentage. The opening target value is then converted into a standardized digital signal recognized by the gate controller. The conversion process includes numerical format adjustment and unit conversion. The adjustment rate information is then parsed, and the rate parameters in the strategy are converted into motion speed control parameters of the gate opening and closing mechanism. Finally, the execution time information is parsed, and the time schedule in the strategy is converted into an accurate timestamp format to form a healthy gate opening control instruction and an adjustment timing schedule. The adjustment timing schedule specifies in detail the time when each gate starts adjustment, the duration of adjustment, and the target time when the adjustment is completed.

[0058] Based on the second scheduling strategy, the opening control instruction of the aging gate is gradually corrected. The gradual correction is a protective adjustment method specifically for aging equipment. The correction process first analyzes the scheduling requirements of the aging gate in the second scheduling strategy, identifies the opening amplitude and adjustment time schedule that need to be adjusted, and then applies the gradual correction algorithm to perform protective transformation on the original scheduling instruction. The correction algorithm decomposes the large-amplitude adjustment into multiple small-amplitude adjustment steps. The adjustment amplitude of each step does not exceed the safety threshold of the aging gate. At the same time, it extends the execution time of a single adjustment and slows down the adjustment speed to reduce the mechanical impact on the aging equipment. The correction process also inserts rest intervals between continuous adjustment operations to ensure that the aging equipment has sufficient recovery time. Finally, a protective control instruction for the aging gate with limited adjustment amplitude and extended adjustment time is obtained. The protective control instruction takes into account the dual requirements of adjustment needs and equipment protection.

[0059] Time conflict detection and processing are performed based on the adjustment timing schedule of healthy gates and the protective control instructions of aging gates. Time conflict detection is a key technical link to ensure the time coordination of collaborative operations of multiple gates. The detection and processing first establishes a time axis model and maps the adjustment timing schedule of all gates to a unified time coordinate system. Then, the time periods of the adjustment operations of each gate are compared one by one to identify the time intervals with overlap or conflict. The conflict detection algorithm analyzes the number of gates adjusted at the same time and the adjustment intensity. When there are too many gates adjusted at the same time or the adjustment intensity is too large, it is determined to be a time conflict. After the conflict is detected, the time reallocation algorithm is started. The reallocation algorithm adjusts the time of the conflicting operations according to the adjustment priority and urgency. Operations with high priority maintain the original time, and operations with low priority are delayed. Finally, a collaborative scheduling time window allocation scheme without time conflict is obtained. This scheme ensures the orderly coordination of the adjustment operations of each gate in time.

[0060] The collaborative scheduling time window allocation plan is input into the control instruction scheduling algorithm for serialization generation processing. The control instruction scheduling algorithm is a data organization method that integrates scattered scheduling plans into a unified execution sequence. The serialization generation process first sorts all the adjustment operations in the time window allocation plan according to the execution time to form a time-ordered operation queue, and then assigns a unique execution identifier and priority tag to each operation. Then, the operation parameters are standardized and encoded, including gate identification, opening target value, adjustment rate and execution time. The encoding process adopts a unified data format and communication protocol to ensure the accuracy of the instructions during transmission and execution. Finally, the encoded instructions are organized into a continuous instruction sequence in chronological order to form a collaborative control instruction sequence containing execution time, opening increment and adjustment rate. This sequence is the direct execution basis of the gate automation control system.

[0061] The gate control method based on dynamic collaborative scheduling in the embodiment of the present application is described above. The gate control system based on dynamic collaborative scheduling in the embodiment of the present application is described below. Figure 2 In the embodiments of the present application, an embodiment of a gate control system based on dynamic collaborative scheduling includes: The quantification module is used to perform fatigue quantification on the gate opening and closing torque changes and the accumulated adjustment times through the strain sensor array to obtain the gate comprehensive health index; A correlation module is used to perform correlation modeling processing on the gate adjustment frequency and the equipment degradation rate according to the gate comprehensive health index to obtain equipment health degradation prediction data; A fusion module is used to couple and fuse the upstream and downstream water level flow data with the equipment health degradation prediction data to obtain a water condition-equipment coupling prediction result; a collaborative module, configured to perform multi-gate collaborative optimization processing on the water regime-equipment coupling prediction result by using an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy; The correction module is used to process the healthy gate opening control according to the first scheduling strategy and to correct the aging gate opening control according to the second scheduling strategy to obtain a coordinated control instruction sequence.

[0062] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the gate control method based on dynamic collaborative scheduling.

[0063] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A gate control method based on dynamic collaborative scheduling, characterized in that: The method comprises: The strain sensor array is used to quantify the gate opening and closing torque changes and the accumulated adjustment times to obtain the gate comprehensive health index. Conducting correlation modeling on the gate adjustment frequency and the equipment degradation rate based on the gate comprehensive health index to obtain equipment health degradation prediction data; The upstream and downstream water level flow data are coupled and integrated with the equipment health degradation prediction data to obtain a water regime-equipment coupling prediction result; Performing multi-gate collaborative optimization processing on the water regime-equipment coupling prediction results through an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy; The healthy gate opening control is processed according to the first scheduling strategy, and the aging gate opening control is corrected according to the second scheduling strategy to obtain a coordinated control instruction sequence.

2. The gate control method based on dynamic collaborative scheduling according to claim 1 is characterized in that: The strain sensor array is used to perform fatigue quantification on the gate opening and closing torque changes and the cumulative number of adjustments to obtain a comprehensive gate health index, including: The torque sensor signal of the gate opening and closing mechanism is collected and processed in real time to obtain the current opening and closing torque value and the initial design torque value; Performing a difference calculation based on the current opening and closing torque value and the initial design torque value to obtain a torque change rate and a wear degree coefficient; Input the gate adjustment operation history records into the cumulative counter for statistical analysis and processing to obtain the cumulative adjustment times and fatigue index; A weighted fusion calculation is performed based on the wear degree coefficient and fatigue index to obtain a comprehensive gate health index.

3. The gate control method based on dynamic collaborative scheduling according to claim 1 is characterized in that: The gate adjustment frequency and the equipment degradation rate are correlated and modeled according to the gate comprehensive health index to obtain equipment health degradation prediction data, including: Inputting the gate comprehensive health index into a nonlinear regression algorithm to calculate the adjustment frequency impact factor to obtain the frequency-degradation correlation coefficient; Performing fitting analysis on historical adjustment amplitude data based on the frequency-degradation correlation coefficient to obtain a degradation rate calculation model; Input the current gate adjustment frequency and adjustment amplitude parameters into the degradation rate calculation model for prediction and calculation processing to obtain equipment degradation trend data for future time periods; The remaining life of the gate is evaluated and calculated based on the equipment degradation trend data in the future period to obtain equipment health degradation prediction data.

4. The gate control method based on dynamic coordinated scheduling according to claim 1 is characterized in that: The coupling and fusing of upstream and downstream water level flow data with the equipment health degradation prediction data to obtain a water regime-equipment coupling prediction result includes: Perform time series difference calculation on the water level data collected by upstream and downstream water level sensors to obtain water level change trend parameters and flow rate change rate parameters; Performing matrix combination and permutation processing on the equipment health degradation prediction data and the water level and flow data to obtain a coupled state vector containing the equipment state; Performing partial derivative calculation processing on the coupling state vector based on the water level change trend parameter to obtain a water regime-equipment interaction coefficient; Inputting the flow rate change parameter into the extended Kalman filter algorithm for recursive estimation processing to obtain a predicted state value of the coupling system; A covariance matrix updating process is performed on the predicted state value of the coupling system according to the interaction influence coefficient to obtain a water regime-equipment coupling prediction result.

5. The gate control method based on dynamic coordinated scheduling according to claim 1 is characterized in that: The multi-gate collaborative optimization process is performed on the water regime-equipment coupling prediction result by using an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy, including: Performing water level control deviation and equipment health classification calculation on the water regime-equipment coupling prediction result to obtain initial values ​​of multi-objective optimization weights; Based on the water regime-equipment coupling prediction result, threshold judgment processing is performed on the health of each gate, and gates with health higher than the safety threshold are classified into a healthy gate group, and gates with health lower than the safety threshold are classified into an aging gate group; Perform load distribution calculation based on the healthy gate group and the aged gate group to obtain a healthy gate adjustment weight coefficient and an aged gate protection weight coefficient; Performing adaptive adjustment operation on the multi-objective optimization weight initial value and the adjustment weight coefficient to obtain a dynamic weight allocation matrix; Optimizing and solving the health gate scheduling target based on the dynamic weight allocation matrix to obtain a first scheduling strategy; The aging gate scheduling constraint is subjected to restrictive optimization processing according to the protection weight coefficient to obtain a second scheduling strategy.

6. The gate control method based on dynamic coordinated scheduling according to claim 5 is characterized in that: The optimizing and solving the health gate scheduling target based on the dynamic weight allocation matrix to obtain a first scheduling strategy includes: The weight coefficients of the healthy gates in the dynamic weight distribution matrix are processed by objective function construction to obtain a multi-objective optimization function including a water level control deviation term, an adjustment stability constraint term, and an inter-gate coordination penalty term; Based on the physical opening limit and adjustment rate constraint of the healthy gate group, a multi-level constraint condition setting process is performed on the optimization function to obtain a healthy gate scheduling constraint set including upper and lower limits of opening, adjustment range limit and response time constraint; The current water level deviation, flow demand parameters and predicted water regime change trends are input into the improved particle swarm algorithm for global optimization iterative processing to obtain the optimal opening adjustment sequence of the healthy gate that meets the constraints. According to the optimal opening adjustment sequence of the healthy gate, load balancing and response delay compensation are performed on the opening and closing timing of each gate to obtain a healthy gate time allocation scheme that takes into account the response characteristics of the equipment; Based on the healthy gate time allocation scheme, hierarchical control instruction encoding and execution priority sorting are performed to obtain a first scheduling strategy including an opening target value, an adjustment rate and an execution time.

7. The gate control method based on dynamic coordinated scheduling according to claim 1 is characterized in that: The healthy gate opening control is processed according to the first scheduling strategy, and the aged gate opening control is corrected according to the second scheduling strategy to obtain a coordinated control instruction sequence, including: Performing instruction parsing on the target value of the healthy gate opening in the first scheduling strategy to obtain a healthy gate opening control instruction and an adjustment timing arrangement; Based on the second scheduling strategy, a progressive correction process is performed on the aging gate opening control instruction to obtain an aging gate protective control instruction that limits the adjustment range and extends the adjustment time; Perform time conflict detection and processing based on the healthy gate adjustment timing arrangement and the aging gate protective control instruction to obtain a collaborative scheduling time window allocation plan; The collaborative scheduling time window allocation scheme is input into the control instruction arrangement algorithm for serialization generation processing to obtain a collaborative control instruction sequence.

8. A gate control system based on dynamic collaborative scheduling, characterized in that: For implementing the gate control method based on dynamic collaborative scheduling according to any one of claims 1 to 7, the gate control system based on dynamic collaborative scheduling includes: The quantification module is used to perform fatigue quantification on the gate opening and closing torque changes and the accumulated adjustment times through the strain sensor array to obtain the gate comprehensive health index; A correlation module is used to perform correlation modeling processing on the gate adjustment frequency and the equipment degradation rate according to the gate comprehensive health index to obtain equipment health degradation prediction data; A fusion module is used to couple and fuse the upstream and downstream water level flow data with the equipment health degradation prediction data to obtain a water condition-equipment coupling prediction result; a collaborative module, configured to perform multi-gate collaborative optimization processing on the water regime-equipment coupling prediction result by using an adaptive weight adjustment algorithm to obtain a first scheduling strategy and a second scheduling strategy; The correction module is used to process the healthy gate opening control according to the first scheduling strategy and to correct the aging gate opening control according to the second scheduling strategy to obtain a coordinated control instruction sequence.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor is enabled to perform the gate control method based on dynamic cooperative scheduling according to any one of claims 1 to 7.

Images