An autonomous emergency scheduling method and system for a heat supply system under accident conditions

Abstract

The application discloses a kind of self-aid emergency scheduling methods under the accident condition of heating system, comprising: establishing heating system heat network hydraulic condition model, simulating each pipe section accident and heat source accident of heat network, analyze heat network hydraulic condition change, with station flow guarantee rate under the accident condition, station pressure guarantee rate, user heating quality and heat network stability as objective function, establish heat network reconstruction optimization model;The optimal heat network solution scheme or networking scheme is obtained by solving heat network reconstruction optimization model;According to the topology structure of reconstructed heat network, with the maximum total heating capacity under the accident condition, the maximum limit heating coefficient, the maximum flow guarantee coefficient of key user, the minimum normal heat source load increase amplitude, the minimum pump energy consumption as objective function, establish heat source scheduling optimization model;The optimal strategy of heat source output is obtained by solving heat source scheduling optimization model;Establish heat station pump valve control model, obtain optimal heat station pump valve control parameter.

Description

Technical Field

[0001] This invention belongs to the field of smart heating technology, specifically relating to an autonomous emergency dispatching method for heating system accidents. Background Technology

[0002] As heating network pipelines continue to grow and the scale of the network expands, the accident rate is also rising. In other words, heating systems are becoming increasingly complex, and the demands for reliability are also increasing. The task of a heating system is to ensure that the parameters required for residents' comfortable living are met at the user end. Once an accident occurs during the operation of the heating network, it will cause some or even all heat users to stop receiving heat. This will damage the thermal environment of buildings, thereby worsening living and working conditions, failing to meet human comfort standards, and in severe cases, even threatening human life, leading to incalculable social consequences.

[0003] In order to minimize losses for businesses and residents, in addition to monitoring and diagnosing the operating status of the heating system during operation and promptly identifying and handling any abnormalities that occur, it is also necessary to adopt scientific, reasonable, and highly reliable emergency dispatch methods after an accident occurs. This includes rationally decoupling the heating network and accurately controlling the heat source load and pump valves of the heating station to minimize the impact of the accident. Therefore, the analysis of the heating network and the research on emergency dispatch strategies under accident conditions are particularly urgent and important.

[0004] However, this is difficult to achieve through manual analysis and calculation alone. Currently, most systems lack scientific, reasonable, and reliable calculation and analysis for emergency dispatching under accident conditions. How to systematically, intelligently, and comprehensively consider multiple issues under system accident conditions and achieve autonomous emergency dispatching of heating systems under accident conditions with high quality, high efficiency, and high reliability is an urgent problem to be solved.

[0005] Based on the above technical problems, it is necessary to design an autonomous emergency dispatch method for heating system accidents. Summary of the Invention

[0006] The technical problem to be solved by this invention is to overcome the shortcomings of the prior art and provide an autonomous emergency dispatching method for heating system accidents. This method can quickly analyze the hydraulic conditions of the heating network in response to accidents, and propose rational valve disconnection, heat source load increase, and heating station pump and valve control parameter combinations to quickly reconstruct the hydraulic balance of the heating network. This enables accurate location and rapid response to emergency fault conditions. The method can conduct comprehensive, scientific, rational, and highly reliable design and analysis from the aspects of heating network hydraulic condition analysis, heating network reconstruction, heat source dispatching, and heating station pump and valve control.

[0007] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0008] This invention provides an autonomous emergency dispatching method for heating systems under accident conditions, the autonomous emergency dispatching method comprising:

[0009] A hydraulic operating condition model of the heating network of the heating system is established using mechanistic modeling and data identification methods;

[0010] The heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat sources of the heating network, analyze the changes in the hydraulic operating condition of the heating network, and establish a heating network reconstruction optimization model with the station flow guarantee rate, station pressure guarantee rate, user heating quality and heating network stability under accident conditions as objective functions.

[0011] An improved butterfly optimization algorithm is used to solve the heat network reconstruction optimization model to obtain the optimal heat network disconnection or interconnection scheme for heat network topology reconstruction.

[0012] Based on the reconstructed heating network topology, a heating source scheduling optimization model is established with the objective functions of maximizing total heat supply, maximizing the quota flow coefficient, maximizing the flow guarantee coefficient for key users, minimizing the increase in normal heat source load, and minimizing pump energy consumption under accident conditions.

[0013] An improved spider-monkey optimization algorithm is used to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output;

[0014] Based on the optimal strategy for heat source output and historical operating data of the heating station, a pump and valve control model for the heating station is established to obtain the optimal pump and valve control parameters for the heating station.

[0015] Furthermore, the method of establishing a hydraulic operating condition model of the heating system network using mechanistic modeling and data identification includes:

[0016] Construct a physical entity model and a simulation calculation model for the heating system network; among which,

[0017] The establishment of the physical entity model of the heating network includes: based on graph theory, the heat source, heating station, and pipeline branch connections are abstracted as connection nodes, and the supply and return water pipe sections between nodes are abstracted as edges. The heating network structure, comprising N points and B edges, is described through a relationship matrix between nodes and edges, represented as:

[0018] ;

[0019] This is the basic correlation matrix of the heating network; The flow rate is listed as the flow rate for the pipe section; The column vector of outflow from the node; This represents the basic loop matrix of the heating network. This is the column vector of pressure drop in the pipe section; The pressure drop across pipe segment i; The friction coefficient of the pipe section; Let be the inner diameter of pipe segment i; Let i be the length of pipe segment i; This represents the total local resistance coefficient of the pipe section; Density of the heat transfer medium; The velocity of the heat transfer medium in the pipe section;

[0020] The establishment of the simulation calculation model includes: structural modeling based on the physical entity of the heating network; setting boundary conditions; using the heat source supply temperature, supply and return water pressure, heating station load, heating station flow rate and heating network structure as input data for the heating network hydraulic condition simulation model to calculate the heating network hydraulic condition, and obtaining the pressure, flow rate, temperature, flow velocity and specific friction resistance distribution information of the heating network under each condition.

[0021] The model rationality verification includes: inputting the real-time operation data of the heating network under multiple operating conditions into the hydraulic operating condition model of the heating system, and using the reverse identification method to adaptively identify and correct the hydraulic operating condition model of the heating system based on the obtained ideal and measured values ​​of the parameters, so as to obtain the identified and corrected hydraulic operating condition model of the heating system.

[0022] Furthermore, the heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat source areas of the heating network, analyze changes in the heating network's hydraulic operating conditions, and establish a heating network reconfiguration optimization model with the station flow guarantee rate, station pressure distribution guarantee rate, user heating quality, and heating network stability under accident conditions as objective functions. This model includes:

[0023] The heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat source areas of the heating network, and to analyze changes in the hydraulic operating conditions of the heating network. Under normal operating conditions, the heat source is abstracted as an equivalent pipe section, the connection node between the heat user and the water supply is abstracted as the outflow rate, and the connection node between the heat user and the return water is abstracted as the inflow rate. The outflow rate of each heat user is the design flow rate multiplied by the limit flow rate coefficient. Under accident conditions, heat source accidents and accidents in various pipe sections of the heating network are simulated. Based on the fault point, a valve shut-off scheme is set to isolate the accident pipe section from the network. By opening and closing multiple valves in the heating network, the network can be connected or disconnected, obtaining various network topology disconnection or connection schemes. The heating network topology is reconstructed, and the basic loop matrix of the basic correlation matrix of the heating network is regenerated. The hydraulic operating condition model of the heating network is solved to obtain the flow rate of each pipe section and the inlet pressure of each node after the accident. The changes in the hydraulic operating conditions of the heating network are monitored in real time, simulating the flow distribution and pressure changes of the heating network.

[0024] The flow guarantee rate and pressure distribution guarantee rate of each station are used as objective functions to characterize the degree of impact on heating supply at each station under accident conditions; the flow guarantee rate is expressed as: ; The actual heat supply to station i; Provide heat for the design of site i; For the number of sites; For traffic guarantee rate;

[0025] The pressure distribution guarantee rate is expressed as:

[0026] ;

[0027] For pressure distribution guarantee rate; The actual pressure distribution at site i; The design pressure distribution for station i is the pressure corresponding to the heat supply required by the station. The minimum pressure required for site i; when When, it indicates that the required heat for the site can still be guaranteed; when When, it indicates that heating has been interrupted; when When the heating supply is sufficient, it indicates that the heating supply is adequate.

[0028] Taking the temperature and flow rate compliance status of key load users before and after changing their operating mode as the heating quality objective function, it is expressed as:

[0029] ;

[0030] The actual temperature of user j, a key load on the heating network; , These are the minimum and maximum design temperatures for important load user j on the heating network, respectively. The actual flow rate of important load user j on the heating network; , These are the minimum and maximum design flow rates for important load user j on the heating network, respectively.

[0031] The objective function for the stability of the heating network, characterized by the temperature and pressure variances of key load users, is expressed as:

[0032] ;

[0033] The average temperature of J key load users on the heating network; Let J be the average flow rate of J critical load users on the heating network; J is the number of critical load users.

[0034] Set constraints, including heat load balance constraints, heat source load range constraints, heat source flow range constraints, and heat network transmission and distribution capacity constraints.

[0035] Furthermore, the method of setting up valve closure based on the fault point isolates the faulty pipe section from the pipe network. By switching multiple valves in the heating network, the network can be connected or disconnected, resulting in various heating network topology disconnection schemes, including:

[0036] If valves are installed on both sides of the pipe segment where the fault point is located, then the valves on both sides closest to the fault point are shut off. If valves are installed on only one side of the pipe segment where the fault point is located, then the valve closest to the fault point on the side with the valve is shut off. On the side without the valve, the heating network is traversed and searched preferentially starting from the node of the pipe segment on that side until a valve is found and shut off. If no valves are installed on either side of the pipe segment where the fault point is located, the heating network is traversed and searched preferentially starting from the nodes on both sides of the pipe segment where the fault point is located until a valve is found and shut off.

[0037] By switching multiple valves in the heating network, different combinations of valve opening and closing result in different heating zones supplied by the heat source, forming different network operation modes or disconnection operation modes; different disconnection methods of the heating network improve the flexibility of heat transmission in the heating system; in the event of a heat source accident, the heat supply and hot water flow of the heat source are reasonably allocated through the connecting pipe, and the heat supply between multiple heat sources is coordinated.

[0038] Furthermore, the step of using an improved butterfly optimization algorithm to solve the heat network reconfiguration optimization model to obtain the optimal heat network disengagement or reconnection scheme for heat network topology reconfiguration includes:

[0039] The analytic hierarchy process (AHP) is used to subjectively assign weights to the objective functions of the heat network reconfiguration optimization model, determine the weights of the sub-objectives, and then unify the multiple sub-objective functions into a single objective function.

[0040] Improvements were made to the butterfly optimization algorithm, including:

[0041] The positions of individual butterflies are initialized using chaotic mapping, and then the initial positions of the butterfly population are inversely mapped to the chaotic sequence values, as shown below:

[0042] ;

[0043] ;

[0044] The initial population location; , [ ] represents the search range for individual i; The values ​​are chaotic sequences between [0,1].

[0045] When updating the position of the population during iteration, individuals are ranked according to their fitness values, and are divided into at least three categories: inferior, average, and superior. A golden sinusoidal mutation perturbation mechanism is used to update the position of inferior individuals, an inertial weighted position update mechanism is used for average individuals, and an elite-guided mechanism is used for superior individuals. These are represented as follows:

[0046] ;

[0047] Original position; The updated position; It is the best individual in the current inferior population; , All are random numbers. Determines the distance traveled during individual iterations. Determines the direction of movement during individual iterations; and It is based on the golden ratio. The obtained coefficients, , ;

[0048] ;

[0049] ;

[0050] , and A random number in the range [0,1]. This is the inertia weighting coefficient; The fragrance concentration of butterfly i; , These represent the positions of two butterflies randomly selected from the population. The probability of switching between global search and local exploitation of the population; This represents the maximum value of the initial inertia weight. This represents the minimum inertia weight at the end of the iteration. This represents the maximum number of iterations.

[0051] ;

[0052] The probability of switching between elite-guided and primitive population renewal methods. ; A random number in the range [0,1].

[0053] The improved butterfly optimization algorithm is used to solve the heat network reconstruction optimization model to obtain the optimal heat network disengagement or reconnection scheme for heat network topology reconstruction. This includes: initializing the butterfly optimization algorithm and the chaotic mapping population; calculating the population fitness, determining the current global optimum, and calculating the fragrance concentration of individual butterflies; sorting the population individuals according to their fitness values, dividing them into at least inferior, average, and superior populations; using a golden sine mutation perturbation mechanism to update the positions of inferior populations, an inertial weight position update mechanism to update the positions of average populations, and an elite-guided mechanism to update the positions of superior populations; recalculating the population fitness and updating the global optimum; and iterating until the maximum number of iterations is reached, outputting the global optimum, which is the optimal heat network disengagement or reconnection scheme.

[0054] Furthermore, based on the reconstructed heating network topology, a heat source scheduling optimization model is established with the objective functions of maximizing total heat supply, maximizing the quota flow coefficient, maximizing the flow guarantee coefficient for key users, minimizing the increase in normal heat source load, and minimizing pump energy consumption under accident conditions. This model includes:

[0055] Based on the reconstructed heating network topology, a heating network simulation analysis was conducted. A heating source scheduling optimization model was established with the objective functions of maximizing total heat supply, maximizing the quota heating coefficient, maximizing the flow guarantee coefficient of key users, minimizing the increase in normal heat source load, and minimizing water pump energy consumption under accident conditions. The model was constrained by the basic equations of the heating network hydraulic condition model, and by not exceeding the maximum output of water pumps, not exceeding the maximum pressure bearing capacity of pipelines, and not exceeding the design heating capacity of each heat source.

[0056] The maximum total heat supply is expressed as follows: ; The heat supplied to heat source s;

[0057] The maximum value of the limit flow coefficient is: ; The limited flow rate of the heating network under accident conditions; This refers to the design flow rate of the pipeline network under accident conditions. This refers to the heating quota coefficient. ; , These are the indoor and outdoor temperatures during the limited heating season; , These are the indoor and outdoor design temperatures, respectively. , These are the design supply and return water temperatures under accident conditions, respectively. , These refer to the limited supply and return water temperatures for heating under accident conditions.

[0058] The maximum heating guarantee coefficient for key users is expressed as follows: ; The actual heat supply for key user i; Provide the required heat for key user i;

[0059] The minimum increase in normal heat source load is defined as the amount of heat and hot water supplied by other normal heat sources through the interconnection pipe distribution system during a heat source failure, thus achieving inter-source complementarity. This is expressed as: ; This represents the new load on the k-th heat source under accident conditions. Let be the original load of the k-th heat source;

[0060] The minimum energy consumption of the water pump is expressed as follows: ; For the first Water pump energy consumption of a heat source scheduling scheme.

[0061] Furthermore, the step of using an improved spider-monkey optimization algorithm to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output includes:

[0062] The analytic hierarchy process (AHP) is used to subjectively assign weights to the objective functions of the heat source scheduling optimization model, determine the weights of the sub-objectives, and then unify the multiple sub-objective functions into a single objective function.

[0063] Improvements were made to the Spider-Monkey optimization algorithm, including:

[0064] An improvement to the local leadership phase is made: a phase factor based on the number of iterations is used instead of the random numbers generated by the uniform distribution for spider monkey position updates, expressed as:

[0065] ;

[0066] ;

[0067] For phase factor; This represents the current iteration number; This represents the maximum number of iterations. ; Let be the component of the i-th spider monkey in the j-th dimension; Let be the component of the k-th local group guide in the j-th dimension; Let be the j-th dimension component of the r-th spider monkey randomly selected from the k-th group;

[0068] Improvements to the global leadership phase: Introduce a non-linearly dynamically transformed guidance factor for spider-monkey position updates, expressed as:

[0069] ;

[0070] ;

[0071] , These are the minimum and maximum values ​​of the guiding factor, respectively; This represents the current fitness value of the spider monkey. , These are the minimum and average fitness values, respectively. A random number uniformly distributed on [0,1]. is a random number uniformly distributed on [-1, 1]. Let be the component of the global guide in the j-th dimension;

[0072] Improvements to the local leadership decision-making stage: Employ the Cauchy mutation strategy to help spider monkey individuals escape local optima, represented as:

[0073] ;

[0074] A scaling factor that decreases linearly from 2 to 0; The mutation probability; A random number uniformly distributed on [0,1]. A random number in the range [0,1].

[0075] An improved spider-monkey optimization algorithm is used to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output. This includes: setting the parameters of the spider-monkey optimization algorithm and initializing the initial positions of all spider monkeys in the group; calculating and sorting the fitness values ​​of each spider monkey; selecting local and global leaders; generating new positions during the local leadership phase and selecting suitable positions based on the fitness of each spider monkey; obtaining the probability of individuals being selected in the entire group during the global leadership phase and updating the positions of the selected spider monkeys; and selecting spider monkeys from all groups during the global leadership learning phase and the local leadership learning phase. Select the positions of local and global leaders; if any local leader fails to update its position within a specified number of times, the local leader will lead all the spider monkeys under its responsibility to find food again; in the local leadership decision phase, perform the Cauchy mutation operation to update the positions of the spider monkeys and select a better position; in the global leadership decision phase, if the global leader fails to update its position within a specified number of times and the maximum number of groups has not been reached, the optimal leader will group the group; otherwise, the optimal leader will merge all groups into one; continue iterating until the termination condition is met, and output the optimal solution, which is the optimal strategy for heat source output.

[0076] Furthermore, the step of establishing a pump and valve control model for the heating station based on the optimal heat source output strategy and historical heating station operation data to obtain optimal pump and valve control parameters includes:

[0077] Based on the optimal heat source output strategy, the historical supply and return water temperatures, flow rates, supply and return water pressures, and pump and valve parameters of the heating stations are used as model sample data.

[0078] After optimizing the penalty factor and kernel parameters of the support vector machine using the improved tern optimization algorithm, the model sample data is input into the optimized support vector machine for learning and training to establish a pump valve control model for a heating station.

[0079] The real-time collected system operation data is input into the heating station pump and valve control model to obtain the optimal heating station pump and valve control parameters;

[0080] The improved tern optimization algorithm includes: optimizing the random variables in the tern algorithm. The improvement is represented as:

[0081] ;

[0082] ;

[0083] To adjust variables Control parameters; This represents the current iteration number; This represents the maximum number of iterations. These are adaptive weighting coefficients;

[0084] A dynamic weighted position update mechanism is introduced to update the position of the black tern, represented as:

[0085] ;

[0086] ;

[0087] ;

[0088] ;

[0089] ;

[0090] The trajectory of the black tern moving towards the optimal position; , , They are respectively , , The corresponding weighting coefficients; This indicates the attack position for the Black-crowned Tern; This is the best location for the black tern; , , and Used to define the circling behavior of the black tern in the air; Variables between [0, 2π]; , For the spiral shape, there are relevant constants.

[0091] Furthermore, the autonomous emergency dispatch method also includes: simulating and extrapolating the optimal heat network disconnection or interconnection scheme, the optimal heat source output strategy, and the optimal heat station pump and valve control parameters through the established digital twin model of the heating system; analyzing the hydraulic conditions of the heat network; if the system design requirements are not met, then the autonomous emergency dispatch scheme is modified; otherwise, the autonomous emergency dispatch scheme is issued and executed.

[0092] This invention also provides an autonomous emergency dispatch system for heating system accidents, the autonomous emergency dispatch system comprising:

[0093] The hydraulic condition model establishment unit is used to establish a hydraulic condition model of the heating system network using mechanistic modeling and data identification methods.

[0094] The heating network reconfiguration optimization model establishment unit is used to simulate accidents and heat source accidents in each pipe section of the heating network through the heating system heating network hydraulic condition model, analyze the changes in heating network hydraulic condition, and establish a heating network reconfiguration optimization model with the station flow guarantee rate, station pressure guarantee rate, user heating quality and heating network stability under accident conditions as objective functions.

[0095] The heating network reconfiguration model solving unit is used to solve the heating network reconfiguration optimization model using an improved butterfly optimization algorithm to obtain the optimal heating network disengagement scheme or interconnection scheme for heating network topology reconfiguration.

[0096] The heat source scheduling optimization model establishment unit is used to establish a heat source scheduling optimization model based on the reconstructed heat network topology, with the objective functions being the maximum total heat supply under accident conditions, the maximum quota flow coefficient, the maximum flow guarantee coefficient for key users, the minimum increase in normal heat source load, and the minimum water pump energy consumption.

[0097] The heat source scheduling model solving unit is used to solve the heat source scheduling optimization model using an improved spider monkey optimization algorithm to obtain the optimal strategy for heat source output.

[0098] The heating station pump and valve control model establishment unit is used to establish a heating station pump and valve control model based on the optimal strategy for heat source output and historical heating station operation data, and to obtain the optimal heating station pump and valve control parameters.

[0099] The beneficial effects of this invention are:

[0100] This invention establishes a hydraulic operating condition model of the heating system network using mechanistic modeling and data identification methods. The model is used to simulate accidents in various pipe sections and heat source accidents, analyzing changes in the network's hydraulic conditions. A network reconfiguration optimization model is established with the station flow guarantee rate, station pressure guarantee rate, user heating quality, and network stability under accident conditions as objective functions. An improved butterfly optimization algorithm is used to solve the model to obtain the optimal network disconnection or reconnection scheme for network topology reconfiguration. Based on the reconfigured network topology, the following parameters are considered: maximum total heat supply under accident conditions, maximum quota flow coefficient, maximum flow guarantee coefficient for key users, minimum increase in normal heat source load, and minimum pump energy consumption. A heat source scheduling optimization model is established with the minimum objective function. An improved spider monkey optimization algorithm is used to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output. Based on the optimal strategy for heat source output and historical heat station operation data, a heat station pump and valve control model is established to obtain the optimal heat station pump and valve control parameters. It can quickly analyze the hydraulic conditions of the heating network when accidents occur in the heating system, and propose reasonable valve disconnection, heat source load increase, and heat station pump and valve control parameter combinations to quickly reconstruct the hydraulic balance condition of the heating network. It can achieve accurate location and rapid response to emergency fault conditions, and can conduct comprehensive, scientific, reasonable, and highly reliable design and analysis from the aspects of heating network hydraulic condition analysis, heating network reconstruction, heat source scheduling, and heat station pump and valve control.

[0101] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0102] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0103] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0104] Figure 1 This is a schematic diagram of the autonomous emergency dispatching method for a heating system under accident conditions according to the present invention;

[0105] Figure 2This is a schematic diagram of the structure of an autonomous emergency dispatch system for a heating system under accident conditions according to the present invention. Detailed Implementation

[0106] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0107] Example 1

[0108] Figure 1 This is a schematic diagram of the autonomous emergency dispatching method for a heating system under accident conditions, as described in this invention.

[0109] like Figure 1 As shown in Embodiment 1, this embodiment provides an autonomous emergency dispatching method for heating system accident conditions. The autonomous emergency dispatching method includes:

[0110] A hydraulic operating condition model of the heating network of the heating system is established using mechanistic modeling and data identification methods;

[0111] The heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat sources of the heating network, analyze the changes in the hydraulic operating condition of the heating network, and establish a heating network reconstruction optimization model with the station flow guarantee rate, station pressure guarantee rate, user heating quality and heating network stability under accident conditions as objective functions.

[0112] An improved butterfly optimization algorithm is used to solve the heat network reconstruction optimization model to obtain the optimal heat network disconnection or interconnection scheme for heat network topology reconstruction.

[0113] Based on the reconstructed heating network topology, a heating source scheduling optimization model is established with the objective functions of maximizing total heat supply, maximizing the quota flow coefficient, maximizing the flow guarantee coefficient for key users, minimizing the increase in normal heat source load, and minimizing pump energy consumption under accident conditions.

[0114] An improved spider-monkey optimization algorithm is used to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output;

[0115] Based on the optimal strategy for heat source output and historical operating data of the heating station, a pump and valve control model for the heating station is established to obtain the optimal pump and valve control parameters for the heating station.

[0116] In this embodiment, the method of establishing a hydraulic operating condition model of the heating system network using mechanism modeling and data identification includes:

[0117] Construct a physical entity model and a simulation calculation model for the heating system network; among which,

[0118] The establishment of the physical entity model of the heating network includes: based on graph theory, the heat source, heating station, and pipeline branch connections are abstracted as connection nodes, and the supply and return water pipe sections between nodes are abstracted as edges. The heating network structure, comprising N points and B edges, is described through a relationship matrix between nodes and edges, represented as:

[0119] ;

[0120] This is the basic correlation matrix of the heating network; The flow rate is listed as the flow rate for the pipe section; The column vector of outflow from the node; This represents the basic loop matrix of the heating network. This is the column vector of pressure drop in the pipe section; The pressure drop across pipe segment i; The friction coefficient of the pipe section; Let be the inner diameter of pipe segment i; Let i be the length of pipe segment i; This represents the total local resistance coefficient of the pipe section; Density of the heat transfer medium; The velocity of the heat transfer medium in the pipe section;

[0121] The establishment of the simulation calculation model includes: structural modeling based on the physical entity of the heating network; setting boundary conditions; using the heat source supply temperature, supply and return water pressure, heating station load, heating station flow rate and heating network structure as input data for the heating network hydraulic condition simulation model to calculate the heating network hydraulic condition, and obtaining the pressure, flow rate, temperature, flow velocity and specific friction resistance distribution information of the heating network under each condition.

[0122] The model rationality verification includes: inputting the real-time operation data of the heating network under multiple operating conditions into the hydraulic operating condition model of the heating system, and using the reverse identification method to adaptively identify and correct the hydraulic operating condition model of the heating system based on the obtained ideal and measured values ​​of the parameters, so as to obtain the identified and corrected hydraulic operating condition model of the heating system.

[0123] In this embodiment, the heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat source accidents within the heating network, analyze changes in the heating network's hydraulic operating conditions, and establish a heating network reconfiguration optimization model with the station flow guarantee rate, station pressure distribution guarantee rate, user heating quality, and heating network stability under accident conditions as objective functions. This model includes:

[0124] The heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat source areas of the heating network, and to analyze changes in the hydraulic operating conditions of the heating network. Under normal operating conditions, the heat source is abstracted as an equivalent pipe section, the connection node between the heat user and the water supply is abstracted as the outflow rate, and the connection node between the heat user and the return water is abstracted as the inflow rate. The outflow rate of each heat user is the design flow rate multiplied by the limit flow rate coefficient. Under accident conditions, heat source accidents and accidents in various pipe sections of the heating network are simulated. Based on the fault point, a valve shut-off scheme is set to isolate the accident pipe section from the network. By opening and closing multiple valves in the heating network, the network can be connected or disconnected, obtaining various network topology disconnection or connection schemes. The heating network topology is reconstructed, and the basic loop matrix of the basic correlation matrix of the heating network is regenerated. The hydraulic operating condition model of the heating network is solved to obtain the flow rate of each pipe section and the inlet pressure of each node after the accident. The changes in the hydraulic operating conditions of the heating network are monitored in real time, simulating the flow distribution and pressure changes of the heating network.

[0125] The flow guarantee rate and pressure distribution guarantee rate of each station are used as objective functions to characterize the degree of impact on heating supply at each station under accident conditions; the flow guarantee rate is expressed as: ; The actual heat supply to station i; Provide heat for the design of site i; For the number of sites; For traffic guarantee rate;

[0126] The pressure distribution guarantee rate is expressed as:

[0127] ;

[0128] For pressure distribution guarantee rate; The actual pressure distribution at site i; The design pressure distribution for station i is the pressure corresponding to the heat supply required by the station. The minimum pressure required for site i; when When, it indicates that the required heat for the site can still be guaranteed; when When, it indicates that heating has been interrupted; when When this time, it indicates that the heating supply is sufficient;

[0129] Taking the temperature and flow rate compliance status of key load users before and after changing their operating mode as the heating quality objective function, it is expressed as:

[0130] ;

[0131] The actual temperature of user j, a key load on the heating network; , These are the minimum and maximum design temperatures for important load user j on the heating network, respectively. The actual flow rate of important load user j on the heating network; , These are the minimum and maximum design flow rates for important load user j on the heating network, respectively.

[0132] The objective function for the stability of the heating network, characterized by the temperature and pressure variances of key load users, is expressed as:

[0133] ;

[0134] The average temperature of J key load users on the heating network; Let J be the average flow rate of J critical load users on the heating network; J is the number of critical load users.

[0135] Set constraints, including heat load balance constraints, heat source load range constraints, heat source flow range constraints, and heat network transmission and distribution capacity constraints.

[0136] In this embodiment, the valve shut-off scheme based on the fault point isolates the faulty pipe section from the pipe network. By switching multiple valves in the heating network, the heating network can be connected or disconnected for operation, resulting in various heating network topology disconnection schemes, including:

[0137] If valves are installed on both sides of the pipe segment where the fault point is located, then the valves on both sides closest to the fault point are shut off. If valves are installed on only one side of the pipe segment where the fault point is located, then the valve closest to the fault point on the side with the valve is shut off. On the side without the valve, the heating network is traversed and searched preferentially starting from the node of the pipe segment on that side until a valve is found and shut off. If no valves are installed on either side of the pipe segment where the fault point is located, the heating network is traversed and searched preferentially starting from the nodes on both sides of the pipe segment where the fault point is located until a valve is found and shut off.

[0138] By switching multiple valves in the heating network, different combinations of valve opening and closing result in different heating zones supplied by the heat source, forming different network operation modes or disconnection operation modes; different disconnection methods of the heating network improve the flexibility of heat transmission in the heating system; in the event of a heat source accident, the heat supply and hot water flow of the heat source are reasonably allocated through the connecting pipe, and the heat supply between multiple heat sources is coordinated.

[0139] In this embodiment, the step of using an improved butterfly optimization algorithm to solve the heat network reconfiguration optimization model to obtain the optimal heat network disengagement or reconnection scheme for heat network topology reconfiguration includes:

[0140] The analytic hierarchy process (AHP) is used to subjectively assign weights to the objective functions of the heat network reconfiguration optimization model, determine the weights of the sub-objectives, and then unify the multiple sub-objective functions into a single objective function.

[0141] Improvements were made to the butterfly optimization algorithm, including:

[0142] The positions of individual butterflies are initialized using chaotic mapping, and then the initial positions of the butterfly population are inversely mapped to the chaotic sequence values, as shown below:

[0143] ;

[0144] ;

[0145] The initial population location; , [ ] represents the search range for individual i; The values ​​are chaotic sequences between [0,1].

[0146] When updating the position of the population during iteration, individuals are ranked according to their fitness values, and are divided into at least three categories: inferior, average, and superior. A golden sinusoidal mutation perturbation mechanism is used to update the position of inferior individuals, an inertial weighted position update mechanism is used for average individuals, and an elite-guided mechanism is used for superior individuals. These are represented as follows:

[0147] ;

[0148] Original position; The updated position; It is the best individual in the current inferior population; , All are random numbers. Determines the distance traveled during individual iterations. Determines the direction of movement during individual iterations; and It is based on the golden ratio. The obtained coefficients, , ;

[0149] ;

[0150] ;

[0151] , and A random number in the range [0,1]. This is the inertia weighting coefficient; The fragrance concentration of butterfly i; , These represent the positions of two butterflies randomly selected from the population. The probability of switching between global search and local exploitation of the population; This represents the maximum value of the initial inertia weight. This represents the minimum inertia weight at the end of the iteration. This represents the maximum number of iterations.

[0152] ;

[0153] The probability of switching between elite-guided and primitive population renewal methods. ; A random number in the range [0,1].

[0154] The improved butterfly optimization algorithm is used to solve the heat network reconstruction optimization model to obtain the optimal heat network disengagement or reconnection scheme for heat network topology reconstruction. This includes: initializing the butterfly optimization algorithm and the chaotic mapping population; calculating the population fitness, determining the current global optimum, and calculating the fragrance concentration of individual butterflies; sorting the population individuals according to their fitness values, dividing them into at least inferior, average, and superior populations; using a golden sine mutation perturbation mechanism to update the positions of inferior populations, an inertial weight position update mechanism to update the positions of average populations, and an elite-guided mechanism to update the positions of superior populations; recalculating the population fitness and updating the global optimum; and iterating until the maximum number of iterations is reached, outputting the global optimum, which is the optimal heat network disengagement or reconnection scheme.

[0155] It should be noted that chaotic sequences, compared to random search, possess ergodicity, randomness, and regularity, allowing for a higher probability of global search of the solution space and ensuring population diversity. For the basic butterfly optimization algorithm, the fitness of individuals in the population varies with each iteration. Individuals near the optimal solution have better fitness, while those far from the optimal solution have worse fitness. To balance global search and local development capabilities, the population needs to possess this diversity characteristic. However, if all individuals use the same position update method, it will inevitably affect the algorithm's optimization efficiency. Therefore, a hierarchical method is introduced, dynamically dividing the population into individuals of different qualities based on the ascending order of their fitness values ​​in each iteration, and using different strategies to update the positions of these individuals. Inferior individuals have poor position fitness, indicating they are far from the optimal solution region. Therefore, to avoid local optima, a mutation mechanism is introduced to perturb inferior individuals, thereby improving population diversity. For general populations, their fitness is in the middle range; they are not far from the optimal solution, but their evolution speed is slower. To accelerate algorithm convergence, the population position update generally maintains the original butterfly optimization algorithm's position update method while introducing the concept of inertia weight. This inertia weight controls the social and cognitive learning abilities of individual butterflies. The idea behind inertia weight is: in the early iterations, a larger inertia weight enhances the global search ability; in the later iterations, a smaller inertia weight enhances the local exploration ability, thus accelerating algorithm convergence. For high-quality populations, since they are already close to the optimal solution, it is necessary to accelerate the individuals' approach to the optimal solution. Therefore, an elite guidance strategy is introduced for high-quality populations, incorporating the individual's optimality into the position update, thereby accelerating algorithm convergence through elite guidance.

[0156] In this embodiment, based on the reconstructed heating network topology, and with the objective functions of maximizing total heat supply, maximizing the quota flow coefficient, maximizing the flow guarantee coefficient for key users, minimizing the increase in normal heat source load, and minimizing pump energy consumption under accident conditions, a heat source scheduling optimization model is established, including:

[0157] Based on the reconstructed heating network topology, a heating network simulation analysis was conducted. A heating source scheduling optimization model was established with the objective functions of maximizing total heat supply, maximizing the quota heating coefficient, maximizing the flow guarantee coefficient of key users, minimizing the increase in normal heat source load, and minimizing water pump energy consumption under accident conditions. The model was constrained by the basic equations of the heating network hydraulic condition model, and by not exceeding the maximum output of water pumps, not exceeding the maximum pressure bearing capacity of pipelines, and not exceeding the design heating capacity of each heat source.

[0158] The maximum total heat supply is expressed as follows: ; The heat supplied to heat source s;

[0159] The maximum value of the limit flow coefficient is: ; The limited flow rate of the heating network under accident conditions; This refers to the design flow rate of the pipeline network under accident conditions. This refers to the heating quota coefficient. ; , These are the indoor and outdoor temperatures during the limited heating season; , These are the indoor and outdoor design temperatures, respectively. , These are the design supply and return water temperatures under accident conditions, respectively. , These refer to the limited supply and return water temperatures for heating under accident conditions.

[0160] The maximum heating guarantee coefficient for key users is expressed as follows: ; The actual heat supply for key user i; Provide the required heat for key user i;

[0161] The minimum increase in normal heat source load is defined as the amount of heat and hot water supplied by other normal heat sources through the interconnection pipe distribution system during a heat source failure, thus achieving inter-source complementarity. This is expressed as: ; This represents the new load on the k-th heat source under accident conditions. Let be the original load of the k-th heat source;

[0162] The minimum energy consumption of the water pump is expressed as follows: ; For the first Water pump energy consumption of a heat source scheduling scheme.

[0163] In this embodiment, the step of using an improved spider-monkey optimization algorithm to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output includes:

[0164] The analytic hierarchy process (AHP) is used to subjectively assign weights to the objective functions of the heat source scheduling optimization model, determine the weights of the sub-objectives, and then unify the multiple sub-objective functions into a single objective function.

[0165] Improvements were made to the Spider-Monkey optimization algorithm, including:

[0166] An improvement to the local leadership phase is made: a phase factor based on the number of iterations is used instead of the random numbers generated by the uniform distribution for spider monkey position updates, expressed as:

[0167] ;

[0168] ;

[0169] For phase factor; This represents the current iteration number; This represents the maximum number of iterations. ; Let be the component of the i-th spider monkey in the j-th dimension; Let be the component of the k-th local group guide in the j-th dimension; Let be the j-th dimension component of the r-th spider monkey randomly selected from the k-th group;

[0170] Improvements to the global leadership phase: Introduce a non-linearly dynamically transformed guidance factor for spider-monkey position updates, expressed as:

[0171] ;

[0172] ;

[0173] , These are the minimum and maximum values ​​of the guiding factor, respectively; This represents the current fitness value of the spider monkey. , These are the minimum and average fitness values, respectively. A random number uniformly distributed on [0,1]. is a random number uniformly distributed on [-1, 1]. Let be the component of the global guide in the j-th dimension;

[0174] Improvements to the local leadership decision-making stage: Employ the Cauchy mutation strategy to help spider monkey individuals escape local optima, represented as:

[0175] ;

[0176] A scaling factor that decreases linearly from 2 to 0; The mutation probability; A random number uniformly distributed on [0,1]. A random number in the range [0,1].

[0177] An improved spider-monkey optimization algorithm is used to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output. This includes: setting the parameters of the spider-monkey optimization algorithm and initializing the initial positions of all spider monkeys in the group; calculating and sorting the fitness values ​​of each spider monkey; selecting local and global leaders; generating new positions during the local leadership phase and selecting suitable positions based on the fitness of each spider monkey; obtaining the probability of individuals being selected in the entire group during the global leadership phase and updating the positions of the selected spider monkeys; and selecting spider monkeys from all groups during the global leadership learning phase and the local leadership learning phase. Select the positions of local and global leaders; if any local leader fails to update its position within a specified number of times, the local leader will lead all the spider monkeys under its responsibility to find food again; in the local leadership decision phase, perform the Cauchy mutation operation to update the positions of the spider monkeys and select a better position; in the global leadership decision phase, if the global leader fails to update its position within a specified number of times and the maximum number of groups has not been reached, the optimal leader will group the group; otherwise, the optimal leader will merge all groups into one; continue iterating until the termination condition is met, and output the optimal solution, which is the optimal strategy for heat source output.

[0178] It should be noted that a phase factor was introduced in the local leadership phase, and a nonlinear dynamically transformed learning factor was used in the global leadership phase. A Cauchy mutation operator was added in the local leadership decision phase to apply a perturbation to the spider monkeys, preventing the algorithm from getting trapped in local optima. These improvements to the spider monkey algorithm enhance its superiority and provide an effective method for multi-objective heat source scheduling optimization problems. Improvements in the local leadership decision phase: In the later stages of the algorithm's iteration, more and more spider monkeys will move towards the optimal position to forage, which slows down the optimization efficiency and makes it easy to fall into local optima, hindering the improvement of the algorithm's optimization accuracy. Therefore, after executing the local leadership decision phase, a Cauchy mutation strategy is used to allow individual spider monkeys to escape local optima, thereby further enhancing the search ability and helping to find potential solutions in the local region of the current solution, balancing the algorithm's exploration speed and optimization accuracy. In the global leadership phase, an adaptive guidance factor is added to reduce the uncertainty of random step size search, making the spider monkey's position update adaptive and better maintaining the region search and local exploration capabilities. In the local leadership phase, the spider monkey adopts a greedy foraging strategy, that is, it always forages for food in a position that is better than the current one. This can easily cause the spider monkey to get trapped in a local optimum due to excessive greed, and the position update of the spider monkey has a lot of randomness. Here, a phase factor based on the number of iterations is introduced to replace the random numbers generated by uniform distribution, which improves the flexibility, randomness and traversal of the spider monkey search, and improves the global foraging ability of the algorithm.

[0179] In this embodiment, the step of establishing a pump and valve control model for the heating station based on the optimal heat source output strategy and historical heating station operation data to obtain optimal pump and valve control parameters includes:

[0180] Based on the optimal heat source output strategy, the historical supply and return water temperatures, flow rates, supply and return water pressures, and pump and valve parameters of the heating stations are used as model sample data.

[0181] After optimizing the penalty factor and kernel parameters of the support vector machine using the improved tern optimization algorithm, the model sample data is input into the optimized support vector machine for learning and training to establish a pump valve control model for a heating station.

[0182] The real-time collected system operation data is input into the heating station pump and valve control model to obtain the optimal heating station pump and valve control parameters;

[0183] The improved tern optimization algorithm includes: optimizing the random variables in the tern algorithm. The improvement is represented as:

[0184] ;

[0185] ;

[0186] To adjust variables Control parameters; This represents the current iteration number; This represents the maximum number of iterations. These are adaptive weighting coefficients;

[0187] A dynamic weighted position update mechanism is introduced to update the position of the black tern, represented as:

[0188] ;

[0189] ;

[0190] ;

[0191] ;

[0192] ;

[0193] The trajectory of the black tern moving towards the optimal position; , , They are respectively , , The corresponding weighting coefficients; This indicates the attack position for the Black-crowned Tern; This is the best location for the black tern; , , and Used to define the circling behavior of the black tern in the air; Variables between [0, 2π]; , For the spiral shape, there are relevant constants.

[0194] It should be noted that variables In the optimization process, the weights act as adaptive inertia weights. Larger weights provide excellent global search capabilities and accelerate convergence, but may not yield the optimal solution. To enhance local search capabilities, the weight values ​​are appropriately reduced as the number of iterations increases, affecting the variables... Improvements will be made.

[0195] In this embodiment, the autonomous emergency dispatch method further includes: simulating and extrapolating the optimal heat network disconnection or interconnection scheme, the optimal heat source output strategy, and the optimal heat station pump and valve control parameters through the established digital twin model of the heating system; analyzing the hydraulic conditions of the heat network; and if the system design requirements are not met, then modifying the autonomous emergency dispatch scheme; otherwise, issuing and executing the autonomous emergency dispatch scheme.

[0196] Example 2

[0197] Figure 2 This is a schematic diagram of the structure of an autonomous emergency dispatch system for a heating system under accident conditions, as described in this invention.

[0198] like Figure 2 As shown in Embodiment 2, this embodiment provides an autonomous emergency dispatch system for heating system accidents. The autonomous emergency dispatch system includes:

[0199] The hydraulic condition model establishment unit is used to establish a hydraulic condition model of the heating system network using mechanistic modeling and data identification methods.

[0200] The heating network reconfiguration optimization model establishment unit is used to simulate accidents and heat source accidents in each pipe section of the heating network through the heating system heating network hydraulic condition model, analyze the changes in heating network hydraulic condition, and establish a heating network reconfiguration optimization model with the station flow guarantee rate, station pressure guarantee rate, user heating quality and heating network stability under accident conditions as objective functions.

[0201] The heating network reconfiguration model solving unit is used to solve the heating network reconfiguration optimization model using an improved butterfly optimization algorithm to obtain the optimal heating network disengagement scheme or interconnection scheme for heating network topology reconfiguration.

[0202] The heat source scheduling optimization model establishment unit is used to establish a heat source scheduling optimization model based on the reconstructed heat network topology, with the objective functions being the maximum total heat supply under accident conditions, the maximum quota flow coefficient, the maximum flow guarantee coefficient for key users, the minimum increase in normal heat source load, and the minimum water pump energy consumption.

[0203] The heat source scheduling model solving unit is used to solve the heat source scheduling optimization model using an improved spider monkey optimization algorithm to obtain the optimal strategy for heat source output.

[0204] The heating station pump and valve control model establishment unit is used to establish a heating station pump and valve control model based on the optimal strategy for heat source output and historical heating station operation data, and to obtain the optimal heating station pump and valve control parameters.

[0205] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0206] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0207] If the functionality is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0208] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A method for autonomous emergency dispatching under accident conditions in a heating system, characterized in that, The autonomous emergency dispatch method includes: A hydraulic operating condition model of the heating network of the heating system is established using mechanistic modeling and data identification methods; The heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat sources of the heating network, analyze the changes in the hydraulic operating condition of the heating network, and establish a heating network reconstruction optimization model with the station flow guarantee rate, station pressure guarantee rate, user heating quality and heating network stability under accident conditions as objective functions. An improved butterfly optimization algorithm is used to solve the heat network reconstruction optimization model to obtain the optimal heat network disconnection or interconnection scheme for heat network topology reconstruction. Based on the reconstructed heating network topology, a heating source scheduling optimization model is established with the objective functions of maximizing total heat supply, maximizing the quota flow coefficient, maximizing the flow guarantee coefficient for key users, minimizing the increase in normal heat source load, and minimizing pump energy consumption under accident conditions. An improved spider-monkey optimization algorithm is used to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output; Based on the optimal strategy for heat source output and historical operating data of the heating station, a pump and valve control model for the heating station is established to obtain the optimal pump and valve control parameters for the heating station.

2. The autonomous emergency dispatch method according to claim 1, characterized in that, The method of establishing a hydraulic operating condition model of the heating system network using mechanism modeling and data identification includes: Construct a physical entity model and a simulation calculation model for the heating system network; among which, The establishment of the physical entity model of the heating network includes: based on graph theory, the heat source, heating station, and pipeline branch connections are abstracted as connection nodes, and the supply and return water pipe sections between nodes are abstracted as edges. The heating network structure, comprising N points and B edges, is described through a relationship matrix between nodes and edges, represented as: ； This is the basic correlation matrix of the heating network; The flow rate is listed as the flow rate for the pipe section; The column vector of outflow from the node; This represents the basic loop matrix of the heating network. This is the column vector of pressure drop in the pipe section; The pressure drop across pipe segment i; The friction coefficient of the pipe section; Let be the inner diameter of pipe segment i; Let i be the length of pipe segment i; This represents the total local resistance coefficient of the pipe section; Density of the heat transfer medium; The velocity of the heat transfer medium in the pipe section; The establishment of the simulation calculation model includes: structural modeling based on the physical entity of the heating network; setting boundary conditions; using the heat source supply temperature, supply and return water pressure, heating station load, heating station flow rate and heating network structure as input data for the heating network hydraulic condition simulation model to calculate the heating network hydraulic condition, and obtaining the pressure, flow rate, temperature, flow velocity and specific friction resistance distribution information of the heating network under each condition. The model rationality verification includes: inputting the real-time operation data of the heating network under multiple operating conditions into the hydraulic operating condition model of the heating system, and using the reverse identification method to adaptively identify and correct the hydraulic operating condition model of the heating system based on the obtained ideal and measured values ​​of the parameters, so as to obtain the identified and corrected hydraulic operating condition model of the heating system.

3. The autonomous emergency dispatch method according to claim 1, characterized in that, The heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat source areas of the heating network, analyze changes in the heating network's hydraulic operating conditions, and establish a heating network reconfiguration optimization model with the station flow guarantee rate, station pressure distribution guarantee rate, user heating quality, and heating network stability under accident conditions as objective functions. This model includes: The heating system's hydraulic operating condition model is used to simulate accidents in various pipe sections and heat source areas of the heating network, and to analyze changes in the hydraulic operating conditions of the heating network. Under normal operating conditions, the heat source is abstracted as an equivalent pipe section, the connection node between the heat user and the water supply is abstracted as the outflow rate, and the connection node between the heat user and the return water is abstracted as the inflow rate. The outflow rate of each heat user is the design flow rate multiplied by the limit flow rate coefficient. Under accident conditions, heat source accidents and accidents in various pipe sections of the heating network are simulated. Based on the fault point, a valve shut-off scheme is set to isolate the accident pipe section from the network. By opening and closing multiple valves in the heating network, the network can be connected or disconnected, obtaining various network topology disconnection or connection schemes. The heating network topology is reconstructed, and the basic loop matrix of the basic correlation matrix of the heating network is regenerated. The hydraulic operating condition model of the heating network is solved to obtain the flow rate of each pipe section and the inlet pressure of each node after the accident. The changes in the hydraulic operating conditions of the heating network are monitored in real time, simulating the flow distribution and pressure changes of the heating network. The flow guarantee rate and pressure distribution guarantee rate of each station are used as objective functions to characterize the degree of impact on heating supply at each station under accident conditions; the flow guarantee rate is expressed as: ; The actual heat supply to station i; Provide heat for the design of site i; For the number of sites; For traffic guarantee rate; The pressure distribution guarantee rate is expressed as: ； For pressure distribution guarantee rate; The actual pressure distribution at site i; The design pressure distribution for station i is the pressure corresponding to the heat supply required by the station. The minimum pressure required for site i; when When, it indicates that the required heat for the site can still be guaranteed; when When, it indicates that heating has been interrupted; when When this time, it indicates that the heating supply is sufficient; Taking the temperature and flow rate compliance status of key load users before and after changing their operating mode as the heating quality objective function, it is expressed as: ； The actual temperature of user j, a key load on the heating network; , These are the minimum and maximum design temperatures for important load user j on the heating network, respectively. The actual flow rate of important load user j on the heating network; , These are the minimum and maximum design flow rates for important load user j on the heating network, respectively. The objective function for the stability of the heating network, characterized by the temperature and pressure variances of key load users, is expressed as: ； The average temperature of J key load users on the heating network; Let J be the average flow rate of J critical load users on the heating network; J is the number of critical load users. Set constraints, including heat load balance constraints, heat source load range constraints, heat source flow range constraints, and heat network transmission and distribution capacity constraints.

4. The autonomous emergency dispatch method according to claim 3, characterized in that, The method of setting up valve closure based on the fault point isolates the faulty pipe section from the pipe network. By switching multiple valves in the heating network, the network can be connected or disconnected for operation, resulting in various heating network topology disconnection schemes, including: If valves are installed on both sides of the pipe segment where the fault point is located, then the valves on both sides closest to the fault point are shut off. If valves are installed on only one side of the pipe segment where the fault point is located, then the valve closest to the fault point on the side with the valve is shut off. On the side without the valve, the heating network is traversed and searched preferentially starting from the node of the pipe segment on that side until a valve is found and shut off. If no valves are installed on either side of the pipe segment where the fault point is located, the heating network is traversed and searched preferentially starting from the nodes on both sides of the pipe segment where the fault point is located until a valve is found and shut off. By switching multiple valves in the heating network, different combinations of valve opening and closing result in different heating zones supplied by the heat source, forming different network operation modes or disconnection operation modes; different disconnection methods of the heating network improve the flexibility of heat transmission in the heating system; in the event of a heat source accident, the heat supply and hot water flow of the heat source are reasonably allocated through the connecting pipe, and the heat supply between multiple heat sources is coordinated.

5. The autonomous emergency dispatch method according to claim 1, characterized in that, The process of using an improved butterfly optimization algorithm to solve the heating network reconfiguration optimization model to obtain the optimal heating network disengagement or reconnection scheme for heating network topology reconfiguration includes: The analytic hierarchy process (AHP) is used to subjectively assign weights to the objective functions of the heat network reconfiguration optimization model, determine the weights of the sub-objectives, and then unify the multiple sub-objective functions into a single objective function. Improvements were made to the butterfly optimization algorithm, including: The positions of individual butterflies are initialized using chaotic mapping, and then the initial positions of the butterfly population are inversely mapped to the chaotic sequence values, as shown below: ； ； The initial population location; , [ ] represents the search range for individual i; The values ​​are chaotic sequences between [0,1]. When updating the position of individuals in the population during iteration, individuals are sorted according to their fitness values ​​and divided into at least three categories: inferior, average, and superior. A golden sinusoidal mutation perturbation mechanism is used to update the position of inferior individuals, an inertial weighted position update mechanism is used for average individuals, and an elite-guided mechanism is used for superior individuals. These are represented as follows: ； Original position; The updated position; It is the best individual in the current inferior population; , All are random numbers. Determines the distance traveled during individual iterations. Determines the direction of movement during individual iterations; and It is based on the golden ratio. The obtained coefficients, , ; ； ； , and A random number in the range [0,1]. This is the inertia weighting coefficient; The fragrance concentration of butterfly i; , These represent the positions of two butterflies randomly selected from the population. The probability of switching between global search and local exploitation of the population; This represents the maximum value of the initial inertia weight. This represents the minimum inertia weight at the end of the iteration. This represents the maximum number of iterations. ； The probability of switching between elite-guided and primitive population renewal methods. ; A random number in the range [0,1]. The improved butterfly optimization algorithm is used to solve the heat network reconstruction optimization model to obtain the optimal heat network disengagement or reconnection scheme for heat network topology reconstruction. This includes: initializing the butterfly optimization algorithm and the chaotic mapping population; calculating the population fitness, determining the current global optimum, and calculating the fragrance concentration of individual butterflies; sorting the population individuals according to their fitness values, dividing them into at least inferior, average, and superior populations; using a golden sine mutation perturbation mechanism to update the positions of inferior populations, an inertial weight position update mechanism to update the positions of average populations, and an elite-guided mechanism to update the positions of superior populations; recalculating the population fitness and updating the global optimum; and iterating until the maximum number of iterations is reached, outputting the global optimum, which is the optimal heat network disengagement or reconnection scheme.

6. The autonomous emergency dispatch method according to claim 1, characterized in that, Based on the reconstructed heating network topology, a heat source scheduling optimization model is established with the objective functions of maximizing total heat supply, maximizing the quota flow coefficient, maximizing the flow guarantee coefficient for key users, minimizing the increase in normal heat source load, and minimizing pump energy consumption under accident conditions. This model includes: Based on the reconstructed heating network topology, a heating network simulation analysis was conducted. A heating source scheduling optimization model was established with the objective functions of maximizing total heat supply, maximizing the quota heating coefficient, maximizing the flow guarantee coefficient of key users, minimizing the increase in normal heat source load, and minimizing water pump energy consumption under accident conditions. The model was constrained by the basic equations of the heating network hydraulic condition model, and by not exceeding the maximum output of water pumps, not exceeding the maximum pressure bearing capacity of pipelines, and not exceeding the design heating capacity of each heat source. The maximum total heat supply is expressed as follows: ; The heat supplied to heat source s; The maximum value of the limit flow coefficient is: ; The limited flow rate of the heating network under accident conditions; This refers to the design flow rate of the pipeline network under accident conditions. This is the heating quota coefficient. ; , These are the indoor and outdoor temperatures during the limited heating season; , These are the indoor and outdoor design temperatures, respectively. , These are the design supply and return water temperatures under accident conditions, respectively. , These refer to the limited supply and return water temperatures for heating under accident conditions. The maximum heating guarantee coefficient for key users is expressed as follows: ; The actual heat supply for key user i; Provide the required heat for key user i; The minimum increase in normal heat source load is defined as the amount of heat and hot water supplied by other normal heat sources through the interconnection pipe distribution system during a heat source failure, thus achieving inter-source complementarity. This is expressed as: ; This represents the new load on the k-th heat source under accident conditions. Let be the original load of the k-th heat source; The minimum energy consumption of the water pump is expressed as follows: ; For the first Water pump energy consumption of a heat source scheduling scheme.

7. The autonomous emergency dispatch method according to claim 1, characterized in that, The step of using an improved spider-monkey optimization algorithm to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output includes: The analytic hierarchy process (AHP) is used to subjectively assign weights to the objective functions of the heat source scheduling optimization model, determine the weights of the sub-objectives, and then unify the multiple sub-objective functions into a single objective function. Improvements were made to the Spider-Monkey optimization algorithm, including: An improvement to the local leadership phase is made: a phase factor based on the number of iterations is used instead of the random numbers generated by the uniform distribution for spider monkey position updates, expressed as: ； ； For phase factor; This represents the current iteration number; This represents the maximum number of iterations. ; Let be the component of the i-th spider monkey in the j-th dimension; Let be the component of the k-th local group guide in the j-th dimension; Let be the j-th dimension component of the r-th spider monkey randomly selected from the k-th group; Improvements to the global leadership phase: Introduce a non-linearly dynamically transformed guidance factor for spider-monkey position updates, expressed as: ； ； , These are the minimum and maximum values ​​of the guiding factor, respectively; This represents the current fitness value of the spider monkey. , These are the minimum and average fitness values, respectively. A random number uniformly distributed on [0,1]. A random number uniformly distributed on [-1, 1]. Let be the component of the global guide in the j-th dimension; Improvements to the local leadership decision-making stage: Employ the Cauchy mutation strategy to help spider monkey individuals escape local optima, represented as: ； A scaling factor that decreases linearly from 2 to 0; The mutation probability; A random number uniformly distributed on [0,1]. A random number in the range [0,1]. An improved spider-monkey optimization algorithm is used to solve the heat source scheduling optimization model to obtain the optimal strategy for heat source output. This includes: setting the parameters of the spider-monkey optimization algorithm and initializing the initial positions of all spider monkeys in the group; calculating and sorting the fitness values ​​of each spider monkey; selecting local and global leaders; generating new positions during the local leadership phase and selecting suitable positions based on the fitness of each spider monkey; obtaining the probability of individuals being selected in the entire group during the global leadership phase and updating the positions of the selected spider monkeys; and selecting spider monkeys from all groups during the global leadership learning phase and the local leadership learning phase. Select the positions of local and global leaders; if any local leader fails to update its position within a specified number of times, the local leader will lead all the spider monkeys under its responsibility to find food again; in the local leadership decision phase, perform the Cauchy mutation operation to update the positions of the spider monkeys and select a better position; in the global leadership decision phase, if the global leader fails to update its position within a specified number of times and the maximum number of groups has not been reached, the optimal leader will group the group; otherwise, the optimal leader will merge all groups into one; continue iterating until the termination condition is met, and output the optimal solution, which is the optimal strategy for heat source output.

8. The autonomous emergency dispatch method according to claim 1, characterized in that, The step of establishing a pump and valve control model for the heating station based on the optimal heat source output strategy and historical heating station operation data to obtain optimal pump and valve control parameters includes: Based on the optimal heat source output strategy, the historical supply and return water temperatures, flow rates, supply and return water pressures, and pump and valve parameters of the heating stations are used as model sample data. After optimizing the penalty factor and kernel parameters of the support vector machine using the improved tern optimization algorithm, the model sample data is input into the optimized support vector machine for learning and training to establish a pump valve control model for a heating station. The real-time collected system operation data is input into the heating station pump and valve control model to obtain the optimal heating station pump and valve control parameters; The improved tern optimization algorithm includes: optimizing the random variables in the tern algorithm. The improvement is represented as: ； ； To adjust variables Control parameters; This represents the current iteration number; This represents the maximum number of iterations. These are adaptive weighting coefficients; A dynamic weighted position update mechanism is introduced to update the position of the black tern, represented as: ； ； ； ； ； The trajectory of the black tern moving towards the optimal position; , , They are respectively , , The corresponding weighting coefficients; This indicates the attack position for the Black-crowned Tern; This is the best location for the black tern; , , and Used to define the circling behavior of the black tern in the air; Variables between [0, 2π]; , For the spiral shape, there are relevant constants.

9. The autonomous emergency dispatch method according to claim 1, characterized in that, The autonomous emergency dispatch method further includes: simulating and extrapolating the optimal heat network disconnection or interconnection scheme, the optimal heat source output strategy, and the optimal heat station pump and valve control parameters through the established digital twin model of the heating system; analyzing the hydraulic conditions of the heat network; and if the system design requirements are not met, then the autonomous emergency dispatch scheme is modified; otherwise, the autonomous emergency dispatch scheme is issued and executed.

10. An autonomous emergency dispatch system for heating system accidents, characterized in that, The autonomous emergency dispatch system includes: The hydraulic condition model establishment unit is used to establish a hydraulic condition model of the heating system network using mechanistic modeling and data identification methods. The heating network reconfiguration optimization model establishment unit is used to simulate accidents and heat source accidents in each pipe section of the heating network through the heating system heating network hydraulic condition model, analyze the changes in heating network hydraulic condition, and establish a heating network reconfiguration optimization model with the station flow guarantee rate, station pressure guarantee rate, user heating quality and heating network stability under accident conditions as objective functions. The heating network reconfiguration model solving unit is used to solve the heating network reconfiguration optimization model using an improved butterfly optimization algorithm to obtain the optimal heating network disengagement scheme or interconnection scheme for heating network topology reconfiguration. The heat source scheduling optimization model establishment unit is used to establish a heat source scheduling optimization model based on the reconstructed heat network topology, with the objective functions being the maximum total heat supply under accident conditions, the maximum quota flow coefficient, the maximum flow guarantee coefficient for key users, the minimum increase in normal heat source load, and the minimum water pump energy consumption. The heat source scheduling model solving unit is used to solve the heat source scheduling optimization model using an improved spider monkey optimization algorithm to obtain the optimal strategy for heat source output. The heating station pump and valve control model establishment unit is used to establish a heating station pump and valve control model based on the optimal strategy for heat source output and historical heating station operation data, and to obtain the optimal heating station pump and valve control parameters.

Images