A pump stopping water hammer protection optimization method based on multi-objective sparrow search algorithm

Abstract

The application discloses a pump stopping water hammer protection optimization method based on a multi-objective sparrow search algorithm, and specifically comprises the following steps: a water transient simulation model conforming to actual water transfer project operation is established, input parameter groups of the model are obtained through a Latin hypercube sampling method, are substituted into the model for simulation, and an expected sample set is constructed; a pump stopping water hammer protection prediction model is established based on a random forest algorithm, and is taken as a target function of a multi-objective optimization model; a multi-objective optimization mathematical model for a pump stopping water hammer protection measure optimization problem is established by using MOSSA; the theoretical optimal pump stopping water hammer protection design parameters obtained are substituted into the water transient simulation model, and the optimization effect is determined; and it is judged whether the optimization effect meets an expected effect, and secondary optimization can be performed if necessary. The application solves the multi-objective optimization problem of the pump stopping water hammer protection measures, guarantees the safety and reliability of the water transfer project operation, and has economic cost benefits simultaneously.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of water conservancy project hydraulic facilities regulation and control, and particularly relates to a pump stopping water hammer protection optimization method based on a multi-objective sparrow search algorithm. BACKGROUND

[0002] Water hammer effect has always been a key challenge faced by water transfer projects. Unexpected pump stopping events can cause severe pressure fluctuations, leading to extreme water hammer pressure on the pipeline and vaporization, and in extreme cases, may even cause pipeline rupture and equipment damage, thereby endangering the safe operation of the water transfer project. In order to maintain its safety, appropriate water hammer protection measures are usually taken, but this will increase the project budget. Therefore, it is particularly important to find a balance between safety and cost-effectiveness by using optimization algorithms to solve this contradiction.

[0003] Current research mainly focuses on optimization based on pump valve closing rules or single water hammer protection measures. This method often ignores the interaction between different factors, limiting its application in practice. In addition, relying solely on optimization of a single protection measure cannot fully meet the complex needs of engineering practice. Secondly, when dealing with pump stopping water hammer problems, there are relatively few studies on multi-objective optimization using intelligent algorithms, and the results obtained by existing methods are not accurate enough. Considering that there is no direct linear relationship between water hammer protection device parameters and protection effect, studying the interaction between these parameters and building a more accurate comprehensive multi-objective optimization mathematical model will provide strong theoretical support for the optimization design of water transfer projects. SUMMARY

[0004] The present application aims to provide a pump stopping water hammer protection optimization method based on a multi-objective sparrow search algorithm, thereby solving the aforementioned problems in the prior art.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present application is as follows:

[0006] A pump stopping water hammer protection optimization method based on a multi-objective sparrow search algorithm, comprising the following steps:

[0007] S1, a water hammer transient simulation model conforming to the actual operation of a water transfer project is established, and then the Latin hypercube sampling method is used to obtain the input parameter set of the model, which is substituted into the model for simulation to construct an expected sample set;

[0008] S2, a pump stopping water hammer protection prediction model is established based on a random forest algorithm, which is used as the objective function of the multi-objective optimization model;

[0009] S3, a multi-objective optimization mathematical model for the pump stopping water hammer protection measure optimization problem is established using MOSSA to obtain the optimal pump stopping water hammer protection design parameter solution set.

[0010] S4, applying ideal point method to obtain optimal pump shutdown water hammer protection design parameters under different deflections;

[0011] S5, substituting the obtained theoretical optimal pump shutdown water hammer protection design parameters into the hydraulic transient simulation model to determine the optimization effect;

[0012] S6, judging whether the optimization effect meets the expected effect, and if necessary, secondary optimization can be performed.

[0013] Further, the specific method of step S1 comprises:

[0014] S11, combining the water transfer project topological structure diagram, and establishing a hydraulic transient simulation model based on the characteristics line method, wherein the boundary conditions include: upstream boundary, downstream boundary, post-pump valve boundary, air valve boundary, one-way surge tower boundary, and pump station boundary;

[0015] S12, collecting and sorting the monitoring data of the pipeline along the flow, pressure, water level, and the operating state of the water pump, post-pump valve, one-way surge tower, etc., selecting two groups of monitoring data containing actual working condition changes for 10 minutes with a step of 0.01 seconds, respectively using them to calibrate and verify the model, controlling the verification error within 10%, and obtaining a hydraulic transient simulation model that meets the actual water transfer project operation;

[0016] S13, selecting the parameters of the post-pump valve closing law and the parameters of the one-way surge tower as the target optimization variables; then obtaining the input parameter group of the hydraulic transient simulation model, i.e. the target optimization variable group, by Latin hypercube sampling method, substituting it into the model for simulation, and outputting the obtained maximum water hammer pressure value H max , minimum negative pressure value H min , and maximum reverse speed of water pump V max , and constructing the expected sample set.

[0017] Further, the parameters of the post-pump valve closing law include: fast closing time T1, fast closing angle θ1, slow closing time T2, and slow closing angle θ2;

[0018] The parameters of the one-way surge tower include: tower diameter D t , initial effective water head H t , and water supply pipe diameter D b .

[0019] Further, the specific method of step S2 comprises:

[0020] Randomly extract 80% of the desired sample set as the training set, and the rest as the test set, use the training set to construct a water hammer protection prediction model based on the random forest algorithm, and use the test set to test the trained prediction model; if the error is large, increase the data volume and retrain the model; if it meets the requirements, it is used as the objective function of the multi-objective optimization model; the algorithm expression is as follows:

[0021] f = RF (T1, θ1, T2, θ2, D t ,H t ,D b ,mtry, ntree)

[0022] mtry is the number of variables randomly sampled when constructing a decision tree branch, generally 1 / 3 of the total number of input variables; ntree is the number of random forest decision trees.

[0023] Further, the specific method of step S3 comprises:

[0024] Introducing the pump shutdown water hammer protection prediction model as the objective function in the multi-objective optimization algorithm, taking H max minimization, H min maximization, V max minimization and water hammer protection cost minimization as optimization objectives, using MOSSA as the main algorithm, establishing a multi-objective optimization mathematical model for the pump shutdown water hammer protection measure optimization problem, and iteratively searching for the optimal pump shutdown water hammer protection design parameter solution set.

[0025] Further, the specific steps for obtaining the optimal pump shutdown water hammer protection design parameter solution set are:

[0026] S31, input the initial parameters, generate the initial sparrow population, and set the iteration number to 1; the initialization parameters of MOSSA are the total number of sparrows n, the number of discoverers F, the number of alarmers S, the dimension d of the optimization variable, the maximum iteration number t max , alarm value and input variable constraint condition;

[0027] S32, calculate the fitness function value of each sparrow according to the parameters corresponding to its position, and then perform non-dominated sorting on the solved function value and calculate its crowding degree;

[0028] While fully considering the reliability and economy of the water transfer project, the minimum water hammer pressure value minimization, the minimum negative pressure value maximization, the maximum pump reverse rotation speed minimization and the water hammer protection cost minimization are taken as the optimization objectives, and the fitness function value is used to represent the advantages and disadvantages, and the objective function is as follows:

[0029]

[0030]

[0031] In the formula, is the maximum water hammer pressure value; is the minimum negative pressure value; is the maximum reverse rotation speed of the water pump; V d is the volume of the one-way pressure regulating tower;

[0032] S33, select the first F sparrows with optimal fitness function values as discoverers, and update their positions through the formula;

[0033] S34, the sparrows remaining after removing the discoverers are regarded as followers, and move to the sparrows with optimal fitness function values, and update their positions through the formula;

[0034] S35, randomly select S sparrows from the total number of sparrows as sentinels, and update their positions through the formula;

[0035] S36, obtain the new positions of each sparrow after updating, perform constraint condition screening, and then calculate the fitness function values, and replace the new and old positions according to the advantages and disadvantages of the fitness function values;

[0036] S37, check whether the termination condition is met: the number of iterations reaches the maximum number of iterations, if yes, proceed to step S38, otherwise jump to step S32, and increase the number of iterations by 1;

[0037] S38, output the optimal pump stop water hammer protection design parameter solution set.

[0038] Further, in step S31, under the premise of ensuring the safe operation of the water transfer project, based on the characteristics of each water hammer protection device, the following constraint conditions need to be met:

[0039] (1) Pump valve closing constraint:

[0040]

[0041] In the formula, T1 is the fast closing time; θ1 is the fast closing angle; T2 is the slow closing time; and θ2 is the slow closing angle;

[0042] (2) Pipeline system extreme value constraint:

[0043] H max ≤1.3H w_max

[0044] H min >-5m

[0045] V max <1.2V r

[0046] In the formula, H max is the maximum water hammer pressure value; and H w_maxis the steady maximum pressure value along the line; H min is the minimum negative pressure value; V max is the maximum reverse rotation speed of the water pump; V r is the rated rotation speed of the water pump;

[0047] (3) the upper and lower bounds of other input variables must be within the specified value range, i.e. the constraints are:

[0048]

[0049] In the formula, D t is the diameter of the tower body; Ht is the initial effective water head; D b is the diameter of the water supplement pipe.

[0050] Further, the specific method of step S4 comprises:

[0051] According to the technical specifications and actual requirements, under the premise of ensuring the safe operation of the water transfer project, the water hammer protection cost is reduced, the weight vector is determined according to the importance of each optimization target, the ideal point method is used to compare and select the Pareto optimal solution set, and the optimal pump stopping water hammer protection design parameters of different bias are obtained; the calculation formula is as follows:

[0052]

[0053] In the formula, x pareto , y pareto and z pareto are ideal point coordinates; x point , y point and z point are the coordinates of each Pareto front scatter point; W n is the distance between each optimal solution and the ideal point, in addition, the optimal solution of different bias is the nearest point to the ideal point, i.e. min W n .

[0054] Further, the weight is determined according to different bias optimization targets, and the optimization targets are divided into three kinds: safety reliability priority, cost economy priority and unbiased optimization.

[0055] The beneficial effects of the present application are:

[0056] The application discloses a pump stopping water hammer protection optimization method based on a multi-objective sparrow search algorithm, and comprises the following steps: a water transient simulation model conforming to actual water transfer project operation is established, input parameter groups of the model are obtained through a Latin hypercube sampling method, are substituted into the model for simulation, and an expected sample set is constructed; a pump stopping water hammer protection prediction model is established based on a random forest algorithm, and is taken as an objective function of a multi-objective optimization model; a multi-objective optimization mathematical model for a pump stopping water hammer protection measure optimization problem is established by using the MOSSA, so that an optimal pump stopping water hammer protection design parameter solution set is obtained; an ideal point method is applied to obtain optimal pump stopping water hammer protection design parameters under different biases; the obtained theoretical optimal pump stopping water hammer protection design parameters are substituted into the water transient simulation model, and the optimization effect is determined; and it is determined whether the optimization effect meets an expected effect, and secondary optimization can be performed if necessary. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 It is a flow chart of the pump stopping water hammer protection optimization method based on the multi-objective sparrow search algorithm of the application.

[0058] Figure 2 It is another embodiment flow chart of the pump stopping water hammer protection optimization method based on the multi-objective sparrow search algorithm of the application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical scheme and advantages of the application more clear, the application is further described in detail below with reference to the drawings. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0060] Referring to Figure 1 and Figure 2 The pump stopping water hammer protection optimization method based on the multi-objective sparrow search algorithm comprises the following steps:

[0061] S1, a water transient simulation model conforming to actual water transfer project operation is established, input parameter groups of the model are obtained through a Latin hypercube sampling method, are substituted into the model for simulation, and an expected sample set is constructed.

[0062] S2, a pump stopping water hammer protection prediction model is established based on a random forest algorithm, and is taken as an objective function of a multi-objective optimization model.

[0063] S3, a multi-objective optimization mathematical model for a pump stopping water hammer protection measure optimization problem is established by using the MOSSA, so that an optimal pump stopping water hammer protection design parameter solution set is obtained.

[0064] S4, obtaining optimal pump shutdown water hammer protection design parameters under different deflections by using ideal point method.

[0065] S5, substituting the obtained theoretical optimal pump shutdown water hammer protection design parameters into the hydraulic transient simulation model to determine the optimization effect.

[0066] S6, judging whether the optimization effect meets the expected effect, and performing secondary optimization if necessary.

[0067] Further, the specific method of step S1 includes:

[0068] S11, combining the water transfer project topology structure diagram, and establishing a hydraulic transient simulation model based on the characteristics line method, wherein the boundary conditions include: upstream boundary, downstream boundary, post-pump valve boundary, air valve boundary, one-way surge tower boundary, and pump station boundary, etc.

[0069] S12, collecting and sorting the monitoring data of the pipeline along the flow, pressure, water level, and the operation state of the water pump, post-pump valve, one-way surge tower, etc., selecting two groups of monitoring data containing actual working condition changes for 10 minutes with a step of 0.01 seconds, respectively using them to calibrate and verify the model, controlling the verification error within 10%, and obtaining the hydraulic transient simulation model that meets the actual operation of the water transfer project.

[0070] S13, selecting the parameters of the post-pump valve closing law (fast closing time T1, fast closing angle θ1, slow closing time T2, slow closing angle θ2) and the parameters of the one-way surge tower (tower diameter D t , initial effective head H t , and water supply pipe diameter D b ) as the target optimization variables; then obtaining the input parameter group of the hydraulic transient simulation model, i.e. the target optimization variable group, by using the Latin hypercube sampling method, substituting it into the model for simulation, and outputting the obtained maximum water hammer pressure value H max , minimum negative pressure value H min , and maximum reverse speed of the water pump V max to construct the expected sample set.

[0071] Further, the parameters of the post-pump valve closing law include: fast closing time T1, fast closing angle θ1, slow closing time T2, and slow closing angle θ2.

[0072] The parameters of the one-way surge tower include: tower diameter D t , initial effective head H t , and water supply pipe diameter D b .

[0073] Further, the specific method of step S2 includes:

[0074] Randomly extract 80% of the desired sample set as the training set, and the rest as the test set, use the training set to construct a water hammer protection prediction model based on the random forest algorithm, and use the test set to test the trained prediction model; if the error is large, increase the data volume and retrain the model; if it meets the requirements, it is used as the objective function of the multi-objective optimization model; the algorithm expression is as follows:

[0075] f=RF(T1, θ1, T2, θ2, D t , H t , D b , mtry, ntree)

[0076] mtry is the number of variables randomly sampled when constructing a decision tree branch, generally 1 / 3 of the total number of input variables; ntree is the number of random forest decision trees.

[0077] Further, the specific method of step S3 comprises:

[0078] Introduce the pump-off water hammer protection prediction model as the objective function in the multi-objective optimization algorithm, minimize H max , maximize H min , minimize V max , and minimize the water hammer protection cost as the optimization goal, use MOSSA as the main algorithm, establish a multi-objective optimization mathematical model for the pump-off water hammer protection measure optimization problem, and iteratively search for the optimal pump-off water hammer protection design parameter solution set.

[0079] Further, the specific steps for obtaining the optimal pump-off water hammer protection design parameter solution set are:

[0080] S31, input the initial parameters, generate the initial sparrow population, and set the iteration number to 1. The initialization parameters of MOSSA are the total number of sparrows n, the number of discoverers F, the number of alarmers S, the dimension d of the optimization variable, the maximum iteration number t max , the alarm value and the input variable constraint condition.

[0081] A sparrow population consisting of n sparrows can be represented as:

[0082]

[0083] In the formula, xi is the position of the ith sparrow; xi,j is the position of the ith sparrow in the jth dimension.

[0084] S32, calculate the fitness function value of each sparrow combined with the corresponding parameters of its position, and then perform non-dominated sorting on the function value of the solution and calculate its crowding degree.

[0085] In full consideration of the reliability and economy of water diversion project, the minimum maximum water hammer pressure value, the maximum minimum negative pressure value, the minimum maximum reverse rotation speed of water pump and the minimum water hammer protection cost are taken as the optimization objectives to represent the advantages and disadvantages of fitness function value, and the objective function is as follows:

[0086]

[0087] In the formula, is the maximum water hammer pressure value; is the minimum negative pressure value; is the maximum reverse rotation speed of water pump; V d is the volume of one-way pressure regulating tower.

[0088] S33, select the first F sparrows with better fitness function value as discoverers, and update their positions by the formula.

[0089] The formula is as follows:

[0090]

[0091] Wherein, t is the current iteration number; t max is the maximum iteration number; represents the position of the ith sparrow at the tth iteration; α ∈ (0, 1) is a random number; R2 ∈ [0, 1] represents the alert value; ST ∈ [0.5, 1] represents the safety threshold; Q is a random number subject to normal distribution; L is a 1 × d matrix with all elements being 1. When R2 < ST, it means that no predators are found around the foraging environment, and the discoverers can perform extensive search operations; if R2 ≥ ST, it means that the sparrows in the population have found predators, and the discoverers need to lead the sparrow population to other safe places to forage.

[0092] S34, the sparrows left after removing the discoverers are regarded as followers, and move to the sparrow individuals with better fitness function value, and update their positions by the formula.

[0093] The position updating formula is as follows:

[0094]

[0095] Wherein, X p represents the best position occupied by the discoverer; X w represents the current global worst position; A is a 1 × d matrix with elements being 1 or -1, A + = A T (AA T ) -1 ; when , it means that the ith sparrow with poor fitness function value does not obtain food and needs to fly to other places to forage to obtain more energy.

[0096] S35, randomly select S sparrows from the total number of sparrows as sentinels, and update their positions by the formula.

[0097] The formula is as follows:

[0098]

[0099] wherein, represents the current global optimal position; β is a step control parameter; K ∈ [-1, 1] is a random number, which represents the direction of movement of the sparrow and is also a step control parameter. i is the fitness function value of the current sparrow; f g and f w are the optimal fitness function value and the worst fitness function value of the current global, respectively; ε represents a constant, mainly used to avoid zero denominator; when f i ≠ f g , the sparrow is at the edge of the population and is extremely vulnerable to predators; when f i = f g , the sparrow realizes the danger and needs to approach other sparrows to reduce the risk of being preyed upon.

[0100] S36, obtain the new position of each sparrow after updating, perform constraint condition screening, and then calculate the fitness function value, and replace the new and old positions according to the advantages and disadvantages of the fitness function value.

[0101] S37, check whether the termination condition is met: the number of iterations reaches the maximum number of iterations, if yes, proceed to step S38, otherwise jump to step S32, and increase the number of iterations by 1.

[0102] S38, output the optimal pump shutdown water hammer protection design parameter solution set.

[0103] Further, in step S31, under the premise of ensuring the safe operation of the water transfer project, based on the characteristics of each water hammer protection device, the following constraint conditions need to be met:

[0104] (1) Pump post valve closing constraint:

[0105]

[0106] In the formula, T1 is the fast closing time; θ1 is the fast closing angle; T2 is the slow closing time; θ2 is the slow closing angle;

[0107] (2) Pipeline system extreme value constraint:

[0108] H max ≤ 1.3H w_max

[0109] H min >-5m

[0110] V max <1.2V r

[0111] In the formula, H max is the maximum water hammer pressure value; H w_max is the maximum steady pressure value along the line; H min is the minimum negative pressure value; V max is the maximum reverse rotation speed of the water pump; V r is the rated speed of the water pump;

[0112] (3) the upper and lower bounds of other input variables must be within the specified value range, i.e. the constraints are:

[0113]

[0114] In the formula, D t is the tower diameter; H t is the initial effective water head; D b is the diameter of the water replenishing pipe.

[0115] Further, the specific method of step S4 comprises:

[0116] According to the technical specifications and actual requirements, under the premise of ensuring the safe operation of the water diversion project, the water hammer protection cost is reduced, the weight vector is determined according to the importance of each optimization target, the ideal point method is used to compare and select the Pareto optimal solution set, and the optimal pump stopping water hammer protection design parameters with different biases are obtained; the calculation formula is as follows:

[0117]

[0118] In the formula, x pareto , y pareto and z pareto are ideal point coordinates; x point , y point and z point are the coordinates of each Pareto front scatter point; W n is the distance between each optimal solution and the ideal point, in addition, the optimal solution with different biases is the point closest to the ideal point, i.e. min W n .

[0119] Further, the weight is determined according to different biased optimization targets, and the optimization targets are divided into three kinds: safety reliability priority, cost economy priority and unbiased optimization.

[0120] The beneficial effects of the present application are:

[0121] The application discloses a pump stopping water hammer protection optimization method based on a multi-objective sparrow search algorithm, which comprises the following steps: a water transient simulation model conforming to actual water transfer project operation is established, input parameter groups of the model are obtained through a Latin hypercube sampling method, are substituted into the model for simulation, and an expected sample set is constructed; a pump stopping water hammer protection prediction model is established based on a random forest algorithm, and is taken as an objective function of a multi-objective optimization model; a multi-objective optimization mathematical model for the pump stopping water hammer protection measure optimization problem is established by using the MOSSA, so that an optimal pump stopping water hammer protection design parameter solution set is obtained; an ideal point method is applied to obtain optimal pump stopping water hammer protection design parameters under different biases; the obtained theoretical optimal pump stopping water hammer protection design parameters are substituted into the water transient simulation model, and the optimization effect is determined; and it is judged whether the optimization effect meets the expected effect, and secondary optimization can be performed if necessary. Compared with the prior art, the application can be adjusted according to optimization targets under different biases when performing multi-objective optimization, and economic cost benefits are ensured while safety and reliability are ensured.

[0122] The above only describes the preferred embodiments of the present application and is not used to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An optimization method for pump shutdown water hammer protection based on a multi-objective sparrow search algorithm, characterized in that, Includes the following steps: S1. Establish a hydraulic transient simulation model that conforms to the actual operation of the water diversion project, and then obtain the input parameter set of the model through the Latin hypercube sampling method. Substitute it into the model for simulation and construct the desired sample set. S2. A prediction model for pump stoppage water hammer protection is established based on the random forest algorithm, and it is used as the objective function of the multi-objective optimization model. S3. Use MOSSA to establish a multi-objective optimization mathematical model for the optimization problem of pump shutdown water hammer protection measures, so as to obtain the optimal solution set of pump shutdown water hammer protection design parameters; S4. Apply the ideal point method to obtain the optimal design parameters for pump shutdown water hammer protection under different deflection directions; S5. Substitute the theoretically optimal pump shutdown water hammer protection design parameters into the hydraulic transient simulation model to determine the optimization effect; S6. Determine whether the optimization effect meets the expected effect, and perform secondary optimization if necessary; The specific method of step S1 includes: S11. Based on the topology diagram of the water diversion project, establish a hydraulic transient simulation model using the method of characteristics. The boundary conditions include: upstream boundary, downstream boundary, downstream valve boundary, air valve boundary, unidirectional pressure regulating tower boundary, and pump station boundary. S12. Collect and organize monitoring data on flow rate, pressure, water level, and operating status of pumps, downstream valves, and one-way pressure regulating towers along the pipeline. Select two sets of monitoring data containing 10 minutes of continuous monitoring data with a step size of 0.01 seconds under actual operating conditions. Use these data to calibrate and verify the model, controlling the verification error to within 10%, and obtain a hydraulic transient simulation model that conforms to the actual operation of the water diversion project. S13. Select the parameters of the pump downstream valve closing behavior and the parameters of the unidirectional pressure regulating tower as the target optimization variables; then obtain the input parameter set of the hydraulic transient simulation model, i.e., the target optimization variable set, through the Latin hypercube sampling method, and substitute them into the model for simulation, outputting the obtained maximum water hammer pressure value H. max Minimum negative pressure value H min and the maximum reverse rotation speed V of the water pump max Construct the desired sample set.

2. The optimization method for pump shutdown water hammer protection based on multi-objective sparrow search algorithm according to claim 1, characterized in that, The parameters for selecting the valve closing pattern after the pump include: fast closing time T1, fast closing angle θ1, slow closing time T2, and slow closing angle θ2. The parameters of the unidirectional pressure regulating tower include: tower body diameter D. t Initial effective head H t Water supply pipe diameter D b .

3. The optimization method for pump shutdown water hammer protection based on multi-objective sparrow search algorithm according to claim 2, characterized in that, The specific method of step S2 includes: 80% of the desired sample set is randomly selected as the training set, and the remainder is used as the test set. A water hammer protection prediction model based on the random forest algorithm is constructed using the training set, and the trained prediction model is tested using the test set. If the error is large, the amount of data is increased, and the model is retrained. If the model meets the requirements, it is used as the objective function of the multi-objective optimization model. The algorithm expression is as follows: f=RF(T1,θ1,T2,θ2,D t ,H t ,D b ,mtry,ntree) `mtry` is the number of variables randomly sampled when building the decision tree branches, typically one-third of the total number of input variables; `ntree` is the number of random forest decision trees.

4. The optimization method for pump shutdown water hammer protection based on multi-objective sparrow search algorithm according to claim 3, characterized in that, The specific method of step S3 includes: The aforementioned pump shutdown water hammer protection prediction model is introduced as the objective function in the multi-objective optimization algorithm, with H... max Minimize, H min Maximize, V max Minimizing the cost of water hammer protection is the optimization objective. MOSSA is used as the main algorithm to establish a multi-objective optimization mathematical model for optimizing water hammer protection measures during pump shutdown, and the optimal set of design parameters for water hammer protection during pump shutdown is iteratively searched.

5. The optimization method for pump shutdown water hammer protection based on multi-objective sparrow search algorithm according to claim 4, characterized in that, The specific steps to obtain the optimal solution set of pump shutdown water hammer protection design parameters are as follows: S31. Input initialization parameters to generate an initial sparrow population. Set the number of iterations to 1. The initialization parameters for MOSSA are: total number of sparrows n, number of discoverers F, number of watchers S, dimension of optimization variables d, and maximum number of iterations t. max Alarm values ​​and input variable constraints; S32. Combine the parameters corresponding to the location of each sparrow to calculate their respective fitness function values, then perform non-dominated sorting on the solved function values ​​and calculate their crowding degree. While fully considering the reliability and economy of the water diversion project, the optimization objectives are to minimize the maximum water hammer pressure, maximize the minimum negative pressure, minimize the maximum reverse speed of the water pump, and minimize the water hammer protection cost. The applicability function value is used to represent the merits of the applicability function, which is as follows: In the formula, This represents the maximum water hammer pressure value. This is the minimum negative pressure value; V is the maximum reverse rotation speed of the water pump. d This refers to the volume of a unidirectional pressure regulating tower. S33. Select the top F sparrows with the best fitness function values ​​as discoverers, and update their positions using a formula; S34. The remaining sparrows, excluding the discoverer, act as followers and move towards the sparrow with the best fitness function value, updating their positions using a formula. S35. Randomly select S sparrows from the total number of sparrows as watchmen, and update their positions using a formula; S36. Obtain the new position of each sparrow after the update, filter the constraints, calculate its fitness function value, and replace the old and new positions according to the quality of the fitness function value. S37. Check if the termination condition is met: If the number of iterations reaches the maximum number of iterations, proceed to step S38; otherwise, jump to step S32 and increment the number of iterations by 1. S38. Output the optimal solution set of design parameters for pump shutdown water hammer protection.

6. The optimization method for pump shutdown water hammer protection based on multi-objective sparrow search algorithm according to claim 5, characterized in that, In step S31, under the premise of ensuring the safe operation of the water diversion project, the following constraints need to be met based on the characteristics of each water hammer protection device: (1) Valve closing constraint after pump: In the formula, T1 is the fast closing time; θ1 is the fast closing angle; T2 is the slow closing time; θ2 is the slow closing angle. (2) Extreme value constraints of the pipeline system: H max ≤1.3H w_max H min >-5m V max <1.2V r In the formula, H max H represents the maximum water hammer pressure value. w_max H represents the maximum steady-state pressure along the line. min This is the minimum negative pressure value; V max V is the maximum reverse rotation speed of the water pump. r This refers to the rated speed of the water pump; (3) The upper and lower bounds of other input variables must be within the specified range, i.e., the constraint is: In the formula, D t H is the diameter of the tower body; t D is the initial effective head. b This refers to the diameter of the water supply pipe.

7. The optimization method for pump shutdown water hammer protection based on multi-objective sparrow search algorithm according to claim 6, characterized in that, The specific method of step S4 includes: Based on technical specifications and actual needs, and under the premise of ensuring the safe operation of the water transfer project, the cost of water hammer protection is reduced. Weight vectors are determined according to the importance of each optimization objective. The ideal point method is used to compare and select the Pareto optimal solution set to obtain the optimal pump shutdown water hammer protection design parameters with different biases. The calculation formula is as follows: In the formula, x pareto y pareto and z pareto x represents the coordinates of the ideal point; point y point and z point W represents the coordinates of each Pareto front scatter point; n W represents the distance from each optimal solution to the ideal point. Furthermore, the optimal solutions with different biases are the points closest to the ideal point, i.e., min W. n .

8. The optimization method for pump shutdown water hammer protection based on multi-objective sparrow search algorithm according to claim 7, characterized in that, Weights are determined based on different biased optimization objectives. There are three types of optimization objectives: safety and reliability priority, cost and economy priority, and unbiased optimization.

Images