Shield tunneling machine slurry station energy-saving management and control method based on multi-objective particle swarm optimization

Abstract

The invention provides a shield tunneling machine slurry station energy-saving management and control method based on multi-objective particle swarm optimization, and relates to the technical field of slurry station energy-saving management and control, and the method comprises the steps: arranging a data collection system at a shield tunneling machine slurry station, and enabling the data collection system to obtain a power calculation parameter, an optimization calculation parameter and an equipment parameter; and optimizing equipment parameters through a multi-target particle swarm optimization energy-saving algorithm. Through the multi-target particle swarm optimization energy-saving algorithm, optimization adjustment of equipment parameters is achieved, actual working condition requirements are matched, unnecessary energy consumption is reduced, and therefore the purposes of saving energy and reducing consumption are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving management and control of slurry stations, and specifically to an energy-saving management and control method for a slurry station of a shield machine based on multi-objective particle swarm optimization. Background Art

[0002] With the booming development of urban subway construction, as a key link in subway construction, the energy consumption management and control of slurry stations is of great significance for project costs, environmental protection, and sustainable operation.

[0003] The traditional management mode of slurry stations is extensive, and the means of energy consumption monitoring and control of various equipment are limited, resulting in frequent energy waste phenomena. This not only increases the construction cost but also may affect the construction progress due to unstable power supply. Therefore, the present invention provides an energy-saving management and control method for a slurry station of a shield machine based on multi-objective particle swarm optimization. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides an energy-saving management and control method for a slurry station of a shield machine based on multi-objective particle swarm optimization, which solves the problems that the current means of energy consumption monitoring and control of various equipment in slurry station management are limited, resulting in frequent energy waste phenomena, not only increasing the construction cost but also possibly affecting the construction progress due to unstable power supply.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions:

[0006] An energy-saving management and control method for a slurry station of a shield machine based on multi-objective particle swarm optimization, comprising the following steps:

[0007] S1. Arrange a data acquisition system in the slurry station of the shield machine, and the data acquisition system is used to obtain power calculation parameters, optimization calculation parameters, and equipment parameters;

[0008] S2. Optimize the equipment parameters through a multi-objective particle swarm optimization energy-saving algorithm;

[0009] Among them, the fitness comprehensive function of the multi-objective particle swarm optimization energy-saving algorithm is:

[0010] F(x) = w1f(x) + w2h(x) ①

[0011] In formula ①, F(x) is the fitness comprehensive function, f(x) is the energy consumption objective function, h(x) is the optimization objective function, and w1, w2 are weight coefficients;

[0012] Calculate the energy consumption objective function f(x) based on the power calculation parameters, and calculate the optimization objective function h(x) based on the optimization calculation parameters.

[0013] Preferably, the multi-objective particle swarm optimization energy-saving algorithm includes:

[0014] Initialization

[0015] Particle swarm size: The particle swarm size is N, and the position x of each particle i and velocity v i are randomly initialized;

[0016] Position range: Set according to the physical limitations of the device parameters;

[0017] Individual optimal position p: Initialized as the initial position of the particle;

[0018] Global optimal position g: Initialized as the position of the particle with the optimal fitness value;

[0019] Fitness calculation

[0020] Calculate the power and optimized parameters for each particle i;

[0021] Update the individual and global optima

[0022] Update the individual optimum p i : If the current fitness F(i) is better than the individual historical optimal fitness, then update p i = i;

[0023] Update the individual optimum gi: If the fitness F(i) of the current particle i is better than the global optimal fitness, then update g = i;

[0024] Update the velocity and position

[0025] For each particle i and each dimension j:

[0026] v ij (t + 1) = wv ij (t) + c1r1(p ij - x ij (t)) + c2r2(g j - x ij (t)) ②

[0027] In Equation ②, w is the inertia weight, c1 and c2 are the learning factors, r1 and r2 are both random numbers in [0, 1], and v ij (t + 1) is the value of the velocity of the i-th particle in the j-th dimension at time t + 1, v ij (t) is the value of the velocity of the i-th particle in the j-th dimension at time t, x ij (t) is the value of the position of the i-th particle in the j-th dimension at time t, p ij is the individual extreme value of the i-th particle in the j-th dimension, g j is the global extreme value of the entire population in the j-th dimension;

[0028] Position update formula

[0029] x ij (t + 1) = x ij (t) + v ij (t + 1) ③

[0030] In formula ③, x ij (t) is the value of the position of the i-th particle in the j-th dimension at time t;

[0031] If the updated position is within the parameter range, otherwise perform boundary processing;

[0032] Termination condition

[0033] Maximum number of iterations: Tmax = 100;

[0034] Fitness convergence: If the global optimal fitness changes less than the threshold ∈ in several consecutive iterations, then terminate.

[0035] Preferably, in the mud separation system of the shield machine mud station:

[0036] The equipment parameters obtained by the data acquisition system include: separation motor speed x1, separation motor frequency x2, separation motor starting current x3, separation motor starting torque x4, water pump flow x5, water pump speed x6;

[0037] Define the particle position vector x1 = [x1, x2, x3, x4, x5, x6] based on the equipment parameters obtained by the data acquisition system;

[0038] The optimization objective function h(x1) includes: separation efficiency objective function h1(x1), muck water content objective function h2(x1);

[0039]

[0040] In formula ④, m 分离后干物质 and m 分离前泥水和混合物中干物质 Obtained through material balance calculation or data acquisition system;

[0041]

[0042] In formula ⑤, m 分离后渣土中水分 and m 分离后渣土总质量 Obtained through the data acquisition system;

[0043] w2h(x1) = w 21 h1(x1) + w 22 h2(x1) ⑥

[0044] In formula ⑥, w 21 、w 22is the first weight coefficient.

[0045] Preferably, in the pressure filtration system of the shield machine mud station:

[0046] The equipment parameters obtained by the data acquisition system include: the pressure x7 and filtration time x8 of the pressure filtration device;

[0047] Define the particle position vector x2 = [x7, x8] based on the equipment parameters obtained by the data acquisition system;

[0048] The optimization objective function h(x2) includes: the pressure filtration time objective function h3(x2);

[0049] h3(x2) = x8 ⑦

[0050] w2h(x2) = w 23 h3(x2) ⑧

[0051] In Equation ⑧, w 23 is the second weight coefficient.

[0052] Preferably, in the slurry preparation and adjustment system of the shield machine mud station:

[0053] The equipment parameters obtained by the data acquisition system include: the motor power x9 of the mixer, the rotation speed x 10 , and the temperature x of the slurry 11 ;

[0054] Define the particle position vector x3 = [x9, x 10 , x 11 ;

[0055] The optimization objective function h(x3) includes: the slurry quality objective function h4(x3);

[0056]

[0057] In Equation ⑤, m 干物质 and m 总质量 are obtained through the data acquisition system or material balance calculation;

[0058] w2h(x3) = w 24 h4(x3) ⑩

[0059] In Equation ⑥, w 24 is the third weight coefficient.

[0060] Preferably, during the tunneling of the shield machine in the shield machine mud station:

[0061] The equipment parameters obtained by the data acquisition system include: the grouting volume x 12 , the earth excavation volume x13 ;

[0062] Define the particle position vector x4 = [x 12 , x 13 based on the equipment parameters obtained by the data acquisition system;

[0063] The optimization objective function h(x4) includes: the tunneling speed objective function h5(x4);

[0064] w2h(x2) = w 25 h5(x2)

[0065] In the formula , w 25 is the fourth weight coefficient.

[0066] Preferably, it further includes:

[0067] Parameter adjustment: Real-time feedback the optimized equipment parameters to the control system of the shield machine mud station to adjust the equipment operation state.

[0068] The present invention provides an energy-saving control method for a shield machine mud station based on multi-objective particle swarm optimization.

[0069] It has the following beneficial effects:

[0070] 1. In the present invention, through the multi-objective particle swarm optimization energy-saving algorithm, the optimized adjustment of equipment parameters is realized, matching the actual working condition requirements, reducing unnecessary energy consumption, and thus achieving the purpose of energy conservation and consumption reduction.

[0071] 2. In the present invention, the equipment parameters of the tunneling system of the shield machine and its subsystems (mud separation, pressure filtration, and slurry preparation and adjustment systems) are optimized based on the multi-objective optimization framework of the PSO (multi-objective particle swarm optimization energy-saving algorithm) algorithm; specifically, by defining the particle position vector and the fitness function, integrating objectives such as comprehensive energy consumption, efficiency, stability, and construction quality, and using the PSO algorithm to iteratively optimize the equipment parameters, finally achieving the unified goal of minimizing energy consumption, maximizing efficiency, and ensuring construction quality. Description of the Drawings

[0072] Figure 1 It is the equipment parameter optimization flowchart of the mud separation system in the energy-saving control method for a shield machine mud station based on multi-objective particle swarm optimization proposed by the present invention; Detailed Embodiment

[0073] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0074] Embodiment 1:

[0075] A shield machine slurry station energy-saving control method based on multi-objective particle swarm optimization provided by an embodiment of the present invention specifically includes the following steps:

[0076] S1. Arrange a data acquisition system in the shield machine slurry station. The data acquisition system includes: a power quality meter, a flow meter, a density meter, a weight measurement module, etc. The power quality meter can obtain data such as voltage, current, frequency, power, rotation speed, and water pump rotation speed of motors and water pumps. The flow meter and density meter can measure the flow of materials in each link and the density distribution of intermediate materials, etc. The weight measurement module can measure the medium of each substance; the data collected by the above data acquisition system is used on the one hand in the shield machine slurry station energy-saving control method based on multi-objective particle swarm optimization, and on the other hand is also fed back to other systems (such as a quality monitoring system, an efficiency control system, etc.); the data collected by the data acquisition system at least includes: power calculation parameters, optimization calculation parameters, and equipment parameters.

[0077] S2. Optimize the equipment parameters through a multi-objective particle swarm optimization energy-saving algorithm. In the multi-objective particle swarm optimization energy-saving algorithm, the equipment parameters are used to define the particle position vector, and the fitness comprehensive function of the multi-objective particle swarm optimization energy-saving algorithm is calculated by using the energy consumption objective function and the optimization objective function.

[0078] The fitness comprehensive function of the multi-objective particle swarm optimization energy-saving algorithm is:

[0079] F(x) = w1f(x) + w2h(x) ①

[0080] In formula ①, F(x) is the fitness comprehensive function, f(x) is the energy consumption objective function, h(x) is the optimization objective function, w1 and w2 are weight coefficients, and w1 and w2 are adjusted according to the actual working conditions to comprehensively consider the importance of the corresponding objective functions in the multi-objective particle swarm optimization energy-saving algorithm.

[0081] Calculate the energy consumption objective function f(x) based on the power calculation parameters, and calculate the optimization objective function h(x) based on the optimization calculation parameters. The optimization objective function h(x) can be one or more in a specific system.

[0082] The optimized equipment parameters of the above process need to be put into use in the shield machine mud station. Specifically, the optimized equipment parameters are fed back to the control system of the shield machine mud station in real time to adjust the equipment operation status to meet the goals of comprehensive energy consumption, efficiency, stability, and construction quality.

[0083] In one embodiment, the multi-objective particle swarm optimization energy-saving algorithm includes:

[0084] Initialization

[0085] Particle swarm size: Assume the particle swarm size is N, and the position x of each particle i and velocity v i are randomly initialized. Position range: Set according to the physical limitations of the equipment parameters; for example: x1[100,300]rpm. The individual optimal position p i： is initialized to the initial position of the particle. The global optimal position g: is initialized to the particle position with the optimal fitness value.

[0086] Fitness calculation

[0087] For each particle i, calculate the power and optimized parameters.

[0088] Update the individual and global optima

[0089] Update the individual optimum p i : If the current fitness F(i) is better than the individual historical optimal fitness, then update p i = i.

[0090] Update the individual optimum gi: If the fitness F(i) of the current particle i is better than the global optimal fitness, then update g = i.

[0091] Update the velocity and position

[0092] For each particle i and each dimension j.

[0093] v ij (t + 1) = wv ij (t) + c1r1(p ij - x ij (t)) + c2r2(g j - x ij (t)) ②

[0094] In equation ②, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are both random numbers in [0,1], v ij (t + 1) is the value of the velocity of the i-th particle in the j-th dimension at time t + 1, v ij (t) is the value of the velocity of the i-th particle in the j-th dimension at time t, x ij(t) is the value of the position of the i-th particle in the j-th dimension at time t, p ij is the individual extreme value of the i-th particle in the j-th dimension, g j is the global extreme value of the entire population in the j-th dimension.

[0095] Position update formula

[0096] x ij (t + 1) = x ij (t) + v ij (t + 1) ③

[0097] In formula ③, x ij (t) is the value of the position of the i-th particle in the j-th dimension at time t.

[0098] The updated position is within the parameter range; otherwise, boundary processing is performed.

[0099] Termination condition

[0100] Maximum number of iterations: Tmax = 100.

[0101] Fitness convergence: If the global optimal fitness changes less than the threshold ∈ in several consecutive iterations, then terminate.

[0102] The shield machine mud station includes a tunneling system and its subsystems (mud separation, pressure filtration, slurry preparation and adjustment system).

[0103] In the mud separation system of the shield machine mud station:

[0104] The equipment parameters obtained by the data acquisition system include: separation motor speed x1, separation motor frequency x2, separation motor starting current x3, separation motor starting torque x4, water pump flow x5, water pump speed x6.

[0105] Define the particle position vector x1 = [x1, x2, x3, x4, x5, x6 based on the equipment parameters obtained by the data acquisition system.

[0106] The optimization objective function h(x1) includes: separation efficiency objective function h1(x1), muck water content objective function h2(x1);

[0107]

[0108] In formula ④, m 分离后干物质 and m 分离前泥水和混合物中干物质 are obtained through material balance calculation or the data acquisition system.

[0109]

[0110] In formula ⑤, m 分离后渣土中水分 and m分离后渣土总质量 Obtained through the data acquisition system.

[0111] w2h(x1) = w 21 h1(x1) + w 22 h2(x1) ⑥

[0112] In Equation ⑥, w 21 , w 22 is the first weight coefficient.

[0113] In the pressure filtration system of the shield machine mud station:

[0114] The equipment parameters obtained by the data acquisition system include: the pressure x7 and filtration time x8 of the pressure filtration device;

[0115] Define the particle position vector x2 = [x7, x8] based on the equipment parameters obtained by the data acquisition system.

[0116] The optimization objective function h(x2) includes: the pressure filtration time objective function h3(x2);

[0117] h3(x2) = x8 ⑦

[0118] w2h(x2) = w 23 h3(x2) ⑧

[0119] In Equation ⑧, w 23 is the second weight coefficient.

[0120] In the slurry preparation and adjustment system of the shield machine mud station:

[0121] The equipment parameters obtained by the data acquisition system include: the motor power x9 of the mixer, the rotation speed x 10 , the temperature x of the slurry 11 .

[0122] Define the particle position vector x3 = [x9, x 10 , x 11 .

[0123] The optimization objective function h(x3) includes: the slurry quality objective function h4(x3);

[0124]

[0125] In Equation ⑤, m 干物质 and m 总质量 Are obtained through the data acquisition system or calculated by material balance;

[0126] w2h(x3) = w 24 h4(x3) ⑩

[0127] In Equation ⑥, w 24 is the third weight coefficient.

[0128] During the tunneling of the shield machine at the shield machine mud station:

[0129] The equipment parameters obtained by the data acquisition system include: the grouting volume x 12 , and the soil output x 13 .

[0130] Define the particle position vector x4 = [x 12 , x 13 based on the equipment parameters obtained by the data acquisition system.

[0131] The optimization objective function h(x4) includes: the tunneling speed objective function h5(x4);

[0132] w2h(x2) = w 25 h5(x2)

[0133] In Equation , w 25 is the fourth weight coefficient.

[0134] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An energy-saving control method for the slurry station of a shield machine based on multi-objective particle swarm optimization, characterized in that, It includes the following steps: S1. Arrange a data acquisition system at the shield machine mud station, and the data acquisition system is used to obtain power calculation parameters, optimization calculation parameters, and equipment parameters; S2. Optimize the equipment parameters through the multi-objective particle swarm optimization energy-saving algorithm; Among them, the fitness comprehensive function of the multi-objective particle swarm optimization energy-saving algorithm is: F(x) = w1f(x) + w2h(x) ① In formula ①, F(x) is the fitness comprehensive function, f(x) is the energy consumption objective function, h(x) is the optimization objective function, and w1, w2 are weight coefficients; Calculate the energy consumption objective function f(x) based on the power calculation parameters, and calculate the optimization objective function h(x) based on the optimization calculation parameters.

2. The energy-saving control method for the slurry station of a shield machine based on multi-objective particle swarm optimization according to claim 1, characterized in that The multi-objective particle swarm optimization energy-saving algorithm includes: Initialization Particle swarm size: The particle swarm size is N, and the position x of each particle i and velocity v i are randomly initialized; Position range: Set according to the physical limitations of the equipment parameters; Individual optimal position p: Initialized as the initial position of the particle; Global optimal position g: Initialized as the particle position with the optimal fitness value; Fitness calculation Calculate the power and optimized parameters for each particle i; Update individual and global optima Update the individual optimal p i : If the current fitness F(i) is better than the individual's historical optimal fitness, then update p i = i; Update the individual optimum gi: If the fitness F(i) of the current particle i is better than the global optimal fitness, then update g = i; Update speed and position For each particle i and each dimension j: v ij (t + 1) = wv ij (t) + c1r1(p ij -x ij (t)) + c2r2(g j -x ij (t)) ② In formula ②, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are both random numbers in [0, 1], and v ij (t + 1) is the value of the velocity of the i-th particle in the j-th dimension at time t + 1, and v ij (t) is the value of the velocity of the i-th particle in the j-th dimension at time t, and x ij (t) is the value of the position of the i-th particle in the j-th dimension at time t, and p ij is the personal best value of the i-th particle in the j-th dimension, and g j is the global best value of the entire population in the j-th dimension; Position update formula x ij (t + 1)=x ij (t)+v ij (t + 1) ③ In Equation ③, x ij (t) is the value of the position of the i-th particle in the j-th dimension at time t; The updated position is within the parameter range, otherwise boundary processing is performed; Termination condition Maximum number of iterations: Tmax = 100; Fitness convergence: If the global optimal fitness changes less than the threshold ∈ in several consecutive iterations, then terminate.

3. A method for energy-saving control and management of a slurry station of a shield machine based on multi-objective particle swarm optimization according to claim 1 or 2, characterized in that: In the mud separation system of the shield machine mud station: The equipment parameters obtained by the data acquisition system include: separation motor speed x1, separation motor frequency x2, separation motor starting current x3, separation motor starting torque x4, water pump flow x5, water pump speed x6; Define the particle position vector x1 = [x1, x2, x3, x4, x5, x6] based on the equipment parameters obtained by the data acquisition system; The optimization objective function h(x1) includes: separation efficiency objective function h1(x1), muck water content objective function h2(x1); In formula ④, m 分离后干物质 and m 分离前泥水和混合物中干物质 are obtained through material balance calculation or data acquisition system; In Equation ⑤, m 分离后渣土中水分 and m 分离后渣土总质量 are obtained through the data acquisition system; w2h(x1) = w 21 h1(x1) + w 22 h2(x1) ⑥ In formula ⑥, w 21 and w 22 are the first weight coefficients.

4. A method for energy-saving control of a slurry station of a shield machine based on multi-objective particle swarm optimization according to claim 1 or 2, characterized in that In the filter press system of the shield machine mud station: The equipment parameters obtained by the data acquisition system include: pressure x7 and filtration time x8 of the filter press device; Define the particle position vector x2 = [x7, x8] based on the equipment parameters obtained by the data acquisition system; The optimization objective function h(x2) includes: filtration time objective function h3(x2); h3(x2) = x8 ⑦ w2h(x2) = w 23 h3(x2) ⑧ In Equation ⑧, w 23 is the second weight coefficient.

5. A method for energy-saving control of a slurry station of a shield machine based on multi-objective particle swarm optimization according to claim 1 or 2, characterized in that In the slurry preparation and adjustment system of the shield machine mud station: The equipment parameters obtained by the said data acquisition system include: the motor power x9 of the mixer, the rotation speed x of the mixer 10 , the temperature x of the slurry 11 ; Define the particle position vector x3 = [x9, x 10 , x 11 based on the device parameters obtained by the data acquisition system; The optimization objective function h(x3) includes: slurry quality objective function h4(x3); In Equation ⑤, m 干物质 and m 总质量 are obtained through a data acquisition system or calculated by material balance calculation; w2h(x3) = w 24 h4(x3) ⑩ In Equation ⑥, w 24 is the third weight coefficient.

6. A method for energy-saving control of a slurry station of a shield machine based on multi-objective particle swarm optimization according to claim 1 or 2, characterized in that During the tunneling of the shield machine in the shield machine mud station: The equipment parameters obtained by the said data acquisition system include: grouting volume x 12 , excavation volume x 13 ; Define the particle position vector x4 = [x 12 , x 13 based on the device parameters obtained by the data acquisition system; The optimization objective function h(x4) includes: tunneling speed objective function h5(x4); In the formula , w 25 is the fourth weight coefficient.

7. A method for energy-saving control and management of a slurry station of a shield machine based on multi-objective particle swarm optimization according to claim 1, characterized in that, It also includes: Parameter adjustment: Real-time feedback the optimized equipment parameters to the control system of the shield machine mud station to adjust the equipment operation state.

Images