Multi-objective intelligent control method and system for the whole process of circulating cooling water system

Abstract

The present invention provides a full-process multi-objective intelligent control method and system for a circulating cooling water system, the method comprising: step S1: extracting characteristic variables of the circulating cooling water system and establishing a characteristic variable set; step S2: collecting real-time relevant data in the circulating water system, and transmitting it to a data processing unit for preprocessing; step S3: clarifying the optimization target and assigning weights to the target; step S4: multi-objective tuning calculation, obtaining a set of excellent non-dominated solution sets, representing different optimization schemes; step S5: for the obtained non-dominated solution set, determining the comprehensive evaluation index of each solution, and selecting the optimal operation scheme; step S6: after selecting the optimal operation scheme, applying it to the circulating cooling water system, and performing real-time dynamic adjustment and optimization during the operation of the system. The full-process multi-objective intelligent control method for a circulating cooling water system of the present invention and the circulating cooling water system using the method can coordinate multiple optimization targets at the same time and provide multiple feasible solutions for users to choose, and can perform real-time and automatic matching and adjustment under dynamic working conditions, thereby improving the efficiency and sustainability of the system; starting from the full process, full cycle, and full elements, it can achieve the purpose of saving water resources, reducing energy consumption, and realizing intelligent control, and provide an overall, comprehensive, and sustainable digital energy-saving solution for energy-consuming units.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a full-process multi-objective intelligent control method for a circulating cooling water system and a circulating cooling water system using the method. Background Art

[0002] The circulating cooling water system is an essential device for industrial production. To ensure normal production and save water resources, the pump system transports cooling water through the pipe and valve system to exchange heat with the heat generated by the materials in the production process. After it becomes hot water, it is cooled by the cooling tower and recycled to achieve the goals of saving water, reducing costs and protecting the environment. The energy consumed by the full-process device of the circulating cooling water system (including electricity and water resources) generally accounts for more than 25% in industrial production, which is one of the main expenditure costs of industrial production. In order to reduce the overall energy consumption of the circulating water system, various production energy-consuming units, design institutes, and energy-saving service units in my country have carried out a lot of optimization and transformation, and have achieved certain results, but they are all equipment optimization or process optimization and upgrading in a local range. In the vast majority of production enterprises, the circulating cooling water system still has low efficiency and high operating costs, and has not been able to solve the problem of excessive energy consumption from an overall and fundamental perspective.

[0003] The equipment transformation of the circulating cooling water system is mainly the transformation of the pump device. By purchasing high-efficiency energy-saving water pumps and high-efficiency motors, the original high-energy consumption pump equipment is replaced to achieve the purpose of energy saving and improving equipment performance. The process optimization transformation is mainly to achieve the purpose of energy saving and consumption reduction by controlling the return water temperature and the opening of the pump outlet valve. These methods only focus on a single goal and cannot combine the various energy consumption-related elements of the whole process for overall design and overall solution. At the same time, when the ambient temperature changes or the working conditions change, traditional equipment transformation and process transformation cannot solve the dynamic adjustment and adaptability problems of the circulating cooling water system.

[0004] Therefore, there is a need for an intelligent control method that takes into account the full process, full cycle, and all-factor operating indicators of the circulating cooling water system, an integrated multi-objective solution, and a solution that can be adjusted in real time under dynamic changes in operating conditions, so as to comprehensively and fundamentally solve problems such as poor system adaptability and high energy consumption. Summary of the invention

[0005] In view of the above, the present invention provides a full-process multi-objective intelligent control method for a circulating cooling water system and a circulating cooling water system using the method, which can simultaneously coordinate multiple optimization objectives and provide multiple feasible solutions for users to choose from, and can perform real-time and automatic matching and adjustment under dynamic working conditions, thereby improving the efficiency and sustainability of the system; starting from the whole process, the whole cycle, and all elements, the purpose of saving water resources, reducing energy consumption, and realizing intelligent control is achieved, providing energy-consuming units with an overall, comprehensive, and sustainable digital energy-saving solution.

[0006] The technical solution of the present invention:

[0007] In a first aspect, the present invention provides a full-process multi-objective intelligent control method for a circulating cooling water system, comprising:

[0008] Step S1: extract characteristic variables of the circulating cooling water system and establish a characteristic variable set;

[0009] Step S2: collect real-time relevant data in the circulating water system and transmit it to the data processing unit for preprocessing;

[0010] Step S3: clarify the optimization goal and assign weights to the goal;

[0011] Step S4: Multi-objective tuning calculation to obtain a set of excellent non-dominated solutions, representing different optimization schemes;

[0012] Step S5: for the obtained non-dominated solution set, determine the comprehensive evaluation index of each solution and select the optimal operation plan;

[0013] Step S6: After the optimal operation plan is selected, it is applied to the circulating cooling water system, and real-time dynamic adjustment and optimization are performed during the operation of the system;

[0014] The S3 step specifically includes:

[0015] S31: Based on the temperature data set, energy consumption data set, and flow data set after data processing, extract the cycle

[0016] The equipment operating status and performance information of the cooling water system are used to determine the objective function and weight distribution;

[0017] S32: Set the system energy consumption objective function of the circulating cooling water system to minimize energy consumption.

[0018] The number is expressed as:

[0019]

[0020] Etotal is the total energy consumed by the entire circulating water system during operation;

[0021] Qheat is the heat of the heat exchanger;

[0022] S33: Considering the system performance requirements, while optimizing energy consumption, it is also necessary to ensure that the system can meet its heat exchange efficiency requirements. Therefore, the system energy consumption objective function needs to be combined with the weight distribution of the heat exchange rate, such as:

[0023] f total =w energy ·fenergy +w performance ·f performance

[0024] Among them, w energy and w performance is the weight coefficient used to balance the relationship between energy minimization and performance requirements, f performance is a function of the heat exchange efficiency;

[0025] S34: The current goal is to minimize the system energy consumption while optimizing without affecting the heat exchange rate. The energy consumption minimization is given a weight of 0.5, and the heat exchange rate is given a weight of 0.5. The system energy consumption objective function is set as follows:

[0026]

[0027] θ current is the heat exchange efficiency, θ target is the target efficiency to be achieved, V fluid It is the volume of cooling fluid. In a circulating cooling water system, it refers to the volume of cooling water flowing in the system.

[0028] In the second aspect, the present invention also provides a full-process multi-objective intelligent control device for a circulating cooling water system, wherein each module included in the device corresponds to each step of the full-process multi-objective intelligent control method for a circulating cooling water system, and is used to implement the full-process multi-objective intelligent control method for a circulating cooling water system.

[0029] In a third aspect, the present invention also provides a circulating cooling water system, using the full-process multi-objective intelligent control method of the circulating cooling water system.

[0030] Compared with the prior art, the full-process multi-objective intelligent control method of the circulating cooling water system of the present invention and the circulating cooling water system using the method have the following beneficial effects:

[0031] First, extract the characteristic variables of the circulating cooling water system equipment and establish a characteristic variable set. Then, minimize the energy consumption (or water saving, drug saving, etc.) of the circulating water cooling water system as the goal (determine the objective function and weight distribution). Secondly, generate a set of different optimization schemes through multi-objective tuning calculations. Through multi-objective tuning decisions, an optimal operation plan is obtained. The content of the optimal plan includes the original single and local transformation patented technology, such as equipment transformation, process transformation, and control technology, which is equivalent to the upgrade of this plan on the existing technology and is more comprehensive. Through control and adjustment, the water pump, cooling tower fan, valve opening, etc. in the circulating water cooling water system are finely controlled and adjusted, and the parameters such as the operating power of the water pump and the operating power of the cooling tower fan are matched to the optimal operation plan for efficient operation. Finally, the unit energy consumption of the circulating water system is minimized (unit energy consumption = total power consumption of the circulating water system ÷ total water supply), achieving the effect of energy saving and consumption reduction.

[0032] After the transformation using the solution of the present invention, no matter what operating conditions it is in, it can automatically identify and match a set of optimal operating modes, so that the circulating water system is always in efficient operation. The user can determine the production load according to the actual production situation without manual intervention. The entire system can be intelligently identified and operated throughout the process, and the new and old control modes can be switched with one button, which can significantly achieve the purpose of energy saving and consumption reduction.

[0033] The multi-objective intelligent control method for the whole process of the circulating cooling water system of the present invention provides a circulating cooling water system optimization method that achieves effective trade-offs between multiple performance indicators. This method not only improves the energy efficiency of the system and reduces operating costs, but also the optimization process is simple to calculate and does not require complex mathematical models or a large amount of experimental data, making the optimization process more efficient and economical.

[0034] The optimization method of the present invention has high practicability and adaptability, and can be applied to different types of circulating water systems. Whether it is the design of a new system or the transformation of an existing system, it can provide an effective optimization solution.

[0035] The preferred embodiments of the present invention and their beneficial effects will be further described in detail in conjunction with specific implementation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present invention, but should not constitute a limitation of the present invention.

[0037] Figure 1 It is a flow chart of the multi-objective intelligent control method for the whole process of the circulating cooling water system of the present invention;

[0038] Figure 2 It is a structural schematic diagram of the circulating cooling water system of the present invention. DETAILED DESCRIPTION

[0039] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0040] See also Figure 1 The present invention provides a multi-objective intelligent control method for the entire process of a circulating cooling water system, including the following

[0041] step:

[0042] Step S1: extract characteristic variables of the circulating cooling water system and establish a characteristic variable set;

[0043] S11: The extracted characteristic variables of the circulating cooling water system include:

[0044] Production materials: medium inlet and outlet temperatures;

[0045] Pump (water pump, fan): model, flow, inlet and outlet pressure, voltage, current, speed;

[0046] Pipes: diameter, length, material;

[0047] Heat exchanger: type, heat transfer area, circulating cooling water inlet and outlet temperatures;

[0048] Cooling tower: fan model, voltage, current, speed;

[0049] Others: opening of each valve, ambient temperature, water replenishment amount, dosage, etc.

[0050] S12: Establishing the characteristic variable set of circulating cooling water system equipment specifically includes:

[0051] S121: The feature variable set includes features that require temperature control and has a calibrated temperature limit identifier.

[0052] ① Circulating cooling water inlet: It controls the characteristics of circulating cooling water flowing into the heat exchanger and has a calibrated temperature limit mark. The high temperature limit is the maximum allowable water temperature of the circulating cooling water, and the low temperature limit is the minimum allowable water temperature of the circulating cooling water.

[0053] ② Circulating cooling water outlet: It controls the characteristics of circulating cooling water flowing into the heat exchanger and has a calibrated temperature limit mark. The high temperature limit is the maximum allowable water temperature of the circulating cooling water, and the low temperature limit is the minimum allowable water temperature of the circulating cooling water.

[0054] ③Temperature sensor: measures the characteristics of ambient temperature.

[0055] S122: The characteristic variable set includes the operating energy consumption characteristics of the water pump and the cooling tower fan, and the operating energy consumption of the water pump and the cooling tower fan are measured respectively by smart meters.

[0056] S123: The characteristic variable set includes water replenishment amount and drug addition amount characteristics, and the water replenishment amount and drug addition amount of the circulating cooling water system are measured respectively by flow sensors.

[0057] Step S2: collect real-time relevant data in the circulating water system and transmit it to the data processing unit for preprocessing;

[0058] S21: Based on the temperature characteristics of the characteristic variable set of the circulating cooling water system, real-time temperature is collected during circulating water regulation to generate a temperature data set with location identification. Temperature sensors are installed on the outer surface of the circulating cooling water pipes at the inlet and outlet of the heat exchanger in the field environment to monitor their temperature. Each temperature sensor has a location identification for recording its corresponding area.

[0059] S22: Based on the energy consumption characteristics of the characteristic variable set of the circulating cooling water system, a smart meter is installed to collect real-time current, voltage, power factor and power when regulating the circulating cooling water, and generate a real-time energy consumption data set.

[0060] S23: Based on the flow characteristics of the characteristic variable set of the circulating cooling water system, flow sensors are installed in the circulating cooling water feed pipe and the circulating cooling water dosing pipe. When the circulating water is adjusted, the real-time flow is collected to generate a real-time flow data set.

[0061] S24: Clean, denoise, and detect outliers on the temperature data set, energy consumption data set, and flow data set to ensure the accuracy and reliability of the data. In addition, the data needs to be converted and sorted, and features extracted. From the preprocessed data, extract the data related to the circulating cooling water system, which includes: equipment operating status, performance, and other information.

[0062] Step S3: clarify the optimization goal and assign weights to the goal;

[0063] S31: Based on the temperature data set, energy consumption data set, and flow data set after data processing, extract the equipment operation status, performance and other information of the circulating cooling water system, and determine the objective function and weight distribution.

[0064] For example, the optimization goal can be to save energy, improve water quality, reduce pollutant emissions, etc.

[0065] S32: Set the system energy consumption objective function of the circulating cooling water system to minimize energy consumption. In order to achieve the purpose of minimizing energy consumption, the system energy consumption minimization of the system energy consumption objective function is taken as an important goal of the circulating cooling water system. The system energy consumption objective function is expressed as:

[0066]

[0067] Etotal is the total energy consumed by the entire circulating water system during operation.

[0068] Qheat is the heat of the heat exchanger.

[0069] S33: Considering the system performance requirements, while optimizing energy consumption, it is also necessary to ensure that the system can meet its heat exchange efficiency requirements. Therefore, the system energy consumption objective function needs to be combined with the weight distribution of the heat exchange rate, such as:

[0070] f total =w energy ·f energy +w performance ·f performance

[0071] Among them, w energy and w performance is the weight coefficient used to balance the relationship between energy minimization and performance requirements, f performance It is a function of the heat exchange efficiency.

[0072] S34: The current goal is to minimize the system energy consumption while optimizing without affecting the heat exchange rate. The energy consumption minimization is given a weight of 0.5, and the heat exchange rate is given a weight of 0.5. The system energy consumption objective function is set as follows:

[0073]

[0074] θ current is the heat exchange efficiency, θ target is the target efficiency to be achieved, V fluid It is the volume of cooling fluid. In a circulating cooling water system, it refers to the volume of cooling water flowing in the system.

[0075] Step S4: Multi-objective tuning calculation is performed to obtain a set of excellent non-dominated solutions, representing different optimization schemes.

[0076] S41: Initialize the population:

[0077] Based on the temperature characteristic variable set, the key design variables affecting the circulating cooling water system are the inlet and outlet temperature difference of the heat exchanger circulating cooling water (℃) and the ambient temperature (℃).

[0078] Based on the energy consumption characteristic variable set, the key design variables affecting the performance of the circulating cooling water system are the operating speed (RPM) of the water pump, the operating speed (RPM) of the cooling tower fan, and the opening (%) of the valve.

[0079] A set of initial solutions is randomly generated, each of which is a specific set of design variable values. For example, we generated 5 initial solutions, each of which contains the following parameters:

[0080] Ambient temperature (℃): [10, 15, 20, 25, 30]

[0081] Heat exchanger circulating cooling water inlet and outlet temperature difference (℃): [2,4,6,8,10]

[0082] Pump speed (RPM): [1485,1485,1485,1485,1485]

[0083] Cooling tower fan speed (RPM): [1485,1485,1485,1485,1485]

[0084] Valve opening (%): [50, 60, 70, 80, 90]

[0085] S42: Calculate the equipment energy consumption objective function value and the heat exchange efficiency objective function value for each solution.

[0086] Energy consumption is mainly determined by the power consumption of water pumps and cooling tower fans. The equipment energy consumption objective function is:

[0087] E=θ p ·P p ·t+θ f ·P f ·t

[0088] Among them, θ p and θ f are the efficiencies of the water pump and cooling tower fan, P p and P f is the power of the water pump and cooling tower fan (in kilowatts), and t is the operating time (in hours).

[0089] Heat exchange efficiency objective function:

[0090]

[0091] Among them, Q in is the heat entering the heat exchanger, Q out is the amount of heat leaving the heat exchanger. The amount of heat can be calculated using the following formula: Q = m·c·△T, where m is the mass flow rate of cooling water (in kg / s), c is the specific heat capacity of cooling water (in joules / kg·degrees Celsius), and △T is the temperature change of cooling water (in degrees Celsius).

[0092] S43: For each solution, its objective vector is calculated using the equipment energy consumption objective function and the heat exchange efficiency objective function.

[0093] Compare the objective vectors of all solutions. If solution A is not worse than solution B in all objectives and is better than solution B in at least one objective, then solution A dominates solution B. Put all undominated solutions into the first layer Front 1. Remove the solutions that have been included in the first layer Front 1, repeat the above process for the remaining solutions, generate the second layer Front 2, and so on.

[0094] S44: Select a reference point, usually a target vector of maximum and minimum values ​​(eg, minimum energy consumption and minimum heat exchange efficiency).

[0095] For each solution in Front, calculate its distance to the reference point.

[0096] Calculate the density estimate of all solutions in Front on each objective function. The crowding distance can be calculated by the following formula:

[0097]

[0098] Where Di is the crowding distance of solution i, n is the total number of solutions in Front, and d ij is the distance between solution i and solution j in the target space.

[0099] S45: According to the non-dominated sorting and crowding distance, excellent solutions are selected from the current population to enter the next generation. The selection process tends to select solutions with higher non-dominated layers and larger crowding distances.

[0100] S46: Genetic operations include:

[0101] Crossover operation: Randomly select two solutions as parents, perform crossover operation with a certain probability, and generate new offspring. For example, single-point crossover can cut and exchange at a random point between the target vectors of two solutions.

[0102] Mutation operation: mutate the target vector of the solution with a certain probability to simulate gene mutation. For example, a small random perturbation can be added to the value of each objective function.

[0103] S47: Iteration operations include:

[0104] Merge new and old solutions: merge the newly generated solution with the current population.

[0105] Recalculate non-dominated sorting and crowding distance: Repeat the non-dominated sorting and crowding distance calculations on the merged population.

[0106] Check termination conditions: Stop iterations if a preset number of iterations is reached or if the quality of the solution no longer improves significantly.

[0107] S48: Termination conditions and results:

[0108] The algorithm terminates when it reaches the maximum number of iterations or the quality of the solution no longer improves.

[0109] The final set of non-dominated solutions represents a trade-off between multiple objectives, i.e., the Pareto optimal solution set. These solutions are used to select the optimal operation plan that best suits a specific situation.

[0110] Step S5: For the obtained non-dominated solution set, determine the comprehensive evaluation index of each solution, so as to select the optimal operation plan.

[0111] S51: Generate a Pareto solution set based on multi-objective optimization, that is, a set of optimal operating plans, and select the optimal operating plan for the current operating conditions through multi-objective optimization decision-making and comprehensive evaluation of each solution.

[0112] S52: Determine the ideal solution and the worst solution:

[0113] The ideal solution (A+) is the set of solutions that are optimal in every objective.

[0114] Ideal solution (A+): energy consumption 700 kWh, heat exchange efficiency 85%.

[0115] The worst solution (A-) is a set of solutions that are not ideal in every objective.

[0116] Worst solution (A-): energy consumption 1500kWh, heat exchange efficiency 70%.

[0117] Now, we have three solutions A, B, and C, and their performance is as follows:

[0118] untie Energy consumption (kwh) Heat exchange efficiency (%) A 1000 80 B 800 75 C 1200 85

[0119] S53: Calculate the distance of each solution:

[0120] The distance to the ideal solution, which takes into account the difference in energy consumption and heat exchange efficiency from the ideal solution:

[0121]

[0122] The distance of the worst solution, which takes into account the difference in energy consumption and heat exchange efficiency from the ideal solution:

[0123]

[0124] The distances for energy consumption and heat exchange efficiency are combined into one overall distance, for example, by summing or taking the maximum value.

[0125] Calculate the distance (d+) of each solution from the ideal solution:

[0126]

[0127] Calculate the distance (d-) between each solution and the worst solution.

[0128]

[0129] Wherein, E represents energy consumption (kWh), P represents heat exchange efficiency (%), j represents the target solution, the subscript ideal represents the ideal solution, and the subscript worst represents the worst solution.

[0130] Compute the distance of each solution from the ideal solution and the worst solution:

[0131] Solution A's distance:

[0132]

[0133] Solution B's distance:

[0134]

[0135] Solution C's distance:

[0136]

[0137] S54: Calculate the relative closeness (Ci) of each solution, which is the ratio of the distance between the solution and the ideal solution to the distance between the solution and the worst solution, using the relative closeness calculation formula:

[0138]

[0139] Relative closeness of solution A:

[0140]

[0141] S55: Select the optimal operation plan:

[0142] According to the relative proximity, the solution with the highest relative proximity is selected as the optimal operation plan. In this example, solution C has the highest relative proximity (0.615), so it is the optimal operation plan. This means that solution C is the closest to the ideal solution in terms of the trade-off between energy consumption and heat exchange efficiency, while being far away from the worst solution, providing the best performance balance.

[0143] Step S6: After selecting the optimal operation plan, apply it to the circulating cooling water system and perform real-time dynamic adjustment and optimization during system operation.

[0144] S61: Based on multi-objective optimization decisions, the optimal operation plan is obtained, the operation parameters are applied to the circulating cooling water system, and real-time dynamic adjustment and optimization are performed during the system process.

[0145] S62: Apply multi-objective optimization decision to determine the best operating parameters to achieve energy-saving optimization goals.

[0146] S63: Dynamic adjustments include:

[0147] Pump speed adjustment: Based on the prediction results, adjust the pump speed to optimize fluid circulation and energy consumption.

[0148] Valve opening adjustment: Adjust the opening of each valve to control the flow direction and flow rate of the fluid and reduce unnecessary energy consumption.

[0149] Cooling tower fan speed adjustment: According to the ambient temperature and humidity, adjust the speed of the cooling tower fan to improve cooling efficiency.

[0150] S64: Feedback Control: After implementing adjustments, continue to monitor system performance and compare it with the predicted results. If the actual performance deviates from the predicted target, the control system will make necessary adjustments based on the feedback.

[0151] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0152] Based on the same inventive concept, an embodiment of the present application also provides a full-process multi-objective intelligent control device for a circulating cooling water system, wherein each module included corresponds to each step of a full-process multi-objective intelligent control method for a circulating cooling water system, and is used to implement a full-process multi-objective intelligent control method for a circulating cooling water system.

[0153] The full-process multi-objective intelligent control device of the circulating cooling water system includes:

[0154] Equipment feature set establishment module: used to extract equipment feature variables of the circulating cooling water system and establish equipment feature variable sets.

[0155] Data acquisition and processing module: used to collect real-time relevant data in the circulating water system and perform preprocessing.

[0156] Weight assignment module: used to clarify optimization objectives and assign weights to objectives.

[0157] Multi-objective tuning calculation module: used to obtain a set of excellent non-dominated solutions, representing different optimization schemes.

[0158] Multi-objective tuning decision module: used to determine the comprehensive evaluation index of each solution based on the obtained non-dominated solution set, so as to select the optimal operation plan.

[0159] Control and regulation module: It is used to select the optimal operation plan, apply it to the circulating cooling water system, and perform real-time dynamic adjustment and optimization during the operation of the system.

[0160] It should be understood that each module of the full-process multi-objective intelligent control device of the circulating cooling water system is used to execute each step in the embodiment of the corresponding method, and each step in the embodiment of the corresponding method has been explained in detail in the above embodiment. Please refer to the relevant description in the embodiment of the corresponding method for details, and no further details will be given here.

[0161] See also Figure 2 , the present invention is necessary to provide a circulating cooling water system that applies the above-mentioned full-process multi-objective intelligent control method, including a cold water pool, a cooling tower fan 8, a pipeline, a heat exchanger 6, a production device 7 and an intelligent control center 9. The cooling tower fan 8 is installed above the cold water pool, and the cold water pool is connected to the water inlet end of the heat exchanger 6 through a pipeline, and the water outlet end of the heat exchanger 6 is connected to the cold water pool through a pipeline. A water pump 1, a flow sensor 2, a first valve 3 and a second valve 4 are installed on the pipeline between the cold water pool and the heat exchanger 6. The production device 7 is connected to the heat exchanger 6 through a pipeline to exchange the hot material produced by the production device 7 with the heat exchanger 6 to become a cold material. A temperature sensor 5 is installed on the pipeline between the heat exchanger 6 and the production device 7. The water pump 1, the flow sensor 2, the first valve 3, the second valve 4, the temperature sensor 5 and the cooling tower fan 8 are electrically connected to the intelligent control center 9 respectively.

[0162] The full-process multi-objective intelligent control method, device and system of the circulating cooling water system of the present invention have the following beneficial effects:

[0163] First, extract the characteristic variables of the circulating cooling water system equipment and establish a characteristic variable set. Then, minimize the energy consumption (or water saving, drug saving, etc.) of the circulating water cooling water system as the goal (determine the objective function and weight distribution). Secondly, generate a set of different optimization schemes through multi-objective tuning calculations. Through multi-objective tuning decisions, an optimal operation plan is obtained. The content of the optimal plan includes the original single and local transformation patented technology, such as equipment transformation, process transformation, and control technology, which is equivalent to the upgrade of this plan on the existing technology and is more comprehensive. Through control and adjustment, the water pump, cooling tower fan, valve opening, etc. in the circulating water cooling water system are finely controlled and adjusted, and the parameters such as the operating power of the water pump and the operating power of the cooling tower fan are matched to the optimal operation plan for efficient operation. Finally, the unit energy consumption of the circulating water system is minimized (unit energy consumption = total power consumption of the circulating water system ÷ total water supply), achieving the effect of energy saving and consumption reduction.

[0164] After the transformation using the solution of the present invention, no matter what operating conditions it is in, it can automatically identify and match a set of optimal operating modes, so that the circulating water system is always in efficient operation. The user can determine the production load according to the actual production situation without manual intervention. The entire system can be intelligently identified and operated throughout the process, and the new and old control modes can be switched with one button, which can significantly achieve the purpose of energy saving and consumption reduction.

[0165] The multi-objective intelligent control method for the whole process of the circulating cooling water system of the present invention provides a circulating cooling water system optimization method that achieves effective trade-offs between multiple performance indicators. This method not only improves the energy efficiency of the system and reduces operating costs, but also the optimization process is simple to calculate and does not require complex mathematical models or a large amount of experimental data, making the optimization process more efficient and economical.

[0166] The optimization method of the present invention has high practicability and adaptability, and can be applied to different types of circulating water systems. Whether it is the design of a new system or the transformation of an existing system, it can provide an effective optimization solution.

[0167] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A multi-objective intelligent control method for the entire process of a circulating cooling water system, characterized in that: include: Step S1: extract characteristic variables of the circulating cooling water system and establish a characteristic variable set; Step S2: collect relevant real-time data in the circulating water system and transmit it to the data processing unit for preprocessing; Step S3: clarify the optimization target and assign weights to the target; Step S4: multi-objective tuning calculation, obtain a set of excellent non-dominated solution sets, representing different optimization schemes; Step S5: for the obtained non-dominated solution set, determine the comprehensive evaluation index of each solution and select the optimal operation scheme; Step S6: after selecting the optimal operation scheme, apply it to the circulating cooling water system, and perform real-time dynamic adjustment and optimization during the operation of the system; The S3 step specifically includes: S31: Based on the temperature data set, energy consumption data set, and flow data set after data processing, extract the equipment operation status and performance information of the circulating cooling water system, and determine the objective function and weight distribution; S32: The system energy consumption objective function of the circulating cooling water system is set to minimize energy consumption. The system energy consumption objective function is expressed as: Etotal is the total energy consumed by the entire circulating water system during operation; Qheat is the heat of the heat exchanger; S33: Considering the system performance requirements, while optimizing energy consumption, it is also necessary to ensure that the system can meet its heat exchange efficiency requirements. Therefore, the system energy consumption objective function needs to be combined with the weight distribution of the heat exchange rate, such as: f total =w energy ·f energy +w performance ·f performance Among them, w energy and w performance is the weight coefficient used to balance the relationship between energy minimization and performance requirements, f performance is a function of the heat exchange efficiency; S34: The current goal is to minimize the system energy consumption while optimizing without affecting the heat exchange rate. The energy consumption minimization is given a weight of 0.5, and the heat exchange rate is given a weight of 0.

5. The system energy consumption objective function is set as follows: θ current is the heat exchange efficiency, θ target is the target efficiency to be achieved, V fluid It is the volume of cooling fluid. In a circulating cooling water system, it refers to the volume of cooling water flowing in the system.

2. The full-process multi-objective intelligent control method for a circulating cooling water system according to claim 1 is characterized in that: The S1 step specifically includes: S11: The extracted characteristic variables of the circulating cooling water system include: Production materials: medium inlet and outlet temperatures; Pump: model, flow, inlet and outlet pressure, voltage, current, speed; Pipes: diameter, length, material; Heat exchanger: type, heat transfer area, circulating cooling water inlet and outlet temperatures; Cooling tower: fan model, voltage, current, speed; Others: opening of each valve, ambient temperature, water replenishment amount, dosage; S12: Establish the characteristic variable set of circulating cooling water system equipment: S121: The feature variable set includes features that require temperature control and has a calibration temperature limit identifier; S122: the characteristic variable set includes the operating energy consumption characteristics of the water pump and the cooling tower fan, and the operating energy consumption of the water pump and the cooling tower fan are measured respectively by the smart meter; S123: The characteristic variable set includes water replenishment amount and drug addition amount characteristics, and the water replenishment amount and drug addition amount of the circulating cooling water system are measured respectively by flow sensors.

3. The full-process multi-objective intelligent control method for a circulating cooling water system according to claim 1 is characterized in that: The S2 step specifically includes: S21: Based on the temperature characteristics of the characteristic variable set of the circulating cooling water system, when adjusting the circulating water, collect the real-time temperature and generate a temperature data set with a location identifier; S22: Based on the energy consumption characteristics of the characteristic variable set of the circulating cooling water system, a smart meter is installed to collect real-time current, voltage, power factor and power when regulating the circulating cooling water, and generate a real-time energy consumption data set; S23: Based on the flow characteristics of the characteristic variable set of the circulating cooling water system, flow sensors are installed in the circulating cooling water feed pipe and the circulating cooling water dosing pipe, and real-time flow is collected when circulating water is regulated to generate a real-time flow data set; S24: Clean, denoise and detect outliers on the temperature data set, energy consumption data set and flow data set to ensure the accuracy and reliability of the data; in addition, the data needs to be converted and sorted, and features extracted to extract data related to the circulating cooling water system from the preprocessed data.

4. The full-process multi-objective intelligent control method for a circulating cooling water system according to claim 1 is characterized in that: The S4 step specifically includes: S41: Initialize the population: Based on the temperature characteristic variable set, the key design variables affecting the circulating cooling water system are the inlet and outlet temperature difference of the circulating cooling water in the heat exchanger and the ambient temperature; Based on the energy consumption characteristic variable set, the key design variables that affect the performance of the circulating cooling water system are the operating speed of the water pump, the operating speed of the cooling tower fan and the opening of the valve; A set of initial solutions is randomly generated, each of which is a specific set of design variable values; S42: Calculating the equipment energy consumption objective function value and the heat exchange efficiency objective function value for each solution; Energy consumption is mainly determined by the power consumption of water pumps and cooling tower fans. The equipment energy consumption objective function is: E=θ p ·P p ·t+θ f ·P f ·t Among them, θ p and θ f are the efficiencies of the water pump and cooling tower fan, P p and P f is the power of the water pump and cooling tower fan, and t is the operating time; Heat exchange efficiency objective function: Among them, Q in is the heat entering the heat exchanger, Q out is the amount of heat leaving the heat exchanger; the amount of heat is calculated using the following formula: Q = m·c·△T, where m is the mass flow rate of cooling water, c is the specific heat capacity of cooling water, and △T is the temperature change of cooling water; S43: For each solution, calculate its target vector using the equipment energy consumption target function and the heat exchange efficiency target function; Compare the objective vectors of all solutions. If solution A is not worse than solution B in all objectives and is better than solution B in at least one objective, then solution A dominates solution B. Put all undominated solutions into the first layer Front 1. Remove the solutions that have been included in the first layer Front 1, repeat the above process for the remaining solutions, generate the second layer Front 2, and so on. S44: Select a reference point, usually the target vector of the maximum and minimum values; For each solution in Front, calculate its distance to the reference point; Calculate the density estimate of all solutions in Front on each objective function, and the crowding distance is calculated by the following formula: Where Di is the crowding distance of solution i, n is the total number of solutions in Front, and d ij is the distance between solution i and solution j in the target space; S45: According to the non-dominated sorting and crowding distance, excellent solutions are selected from the current population to enter the next generation. The selection process tends to select solutions with higher non-dominated layers and larger crowding distances. S46: Genetic operations include: Crossover operation: Randomly select two solutions as parents, perform crossover operation with a certain probability, and generate new offspring; Mutation operation: mutate the target vector of the solution with a certain probability to simulate gene mutation; S47: Iteration operation includes: Merge new and old solutions: merge the newly generated solution with the current population; Recalculate the non-dominated sort and crowding distance: Repeat the non-dominated sort and crowding distance calculations on the merged population; Check termination conditions: If the preset number of iterations is reached or the quality of the solution no longer improves significantly, the iteration is stopped; S48: Termination conditions and results: The algorithm terminates when it reaches the maximum number of iterations or the quality of the solution no longer improves; The final non-dominated solution set represents a trade-off between multiple objectives, namely the Pareto optimal solution set, which is used to select the optimal operation plan that best suits a specific situation.

5. The full-process multi-objective intelligent control method for a circulating cooling water system according to claim 4 is characterized in that: The S5 step specifically includes: S51: Generate a Pareto solution set based on multi-objective optimization, i.e., a set of optimal operation plans, and select the optimal operation plan for the current working condition through multi-objective optimization decision making and comprehensive evaluation of each solution; S52: Determine the ideal solution and the worst solution: The ideal solution (A+) is the set of solutions that are optimal in every objective; The worst solution (A-) is a set of solutions that are not ideal in every objective; S53: Calculate the distance of each solution: The distance to the ideal solution, which takes into account the difference in energy consumption and heat exchange efficiency from the ideal solution: The distance of the worst solution, which takes into account the difference in energy consumption and heat exchange efficiency from the ideal solution: Combine the distances of energy consumption and heat exchange efficiency into a total distance and calculate the distance (d+) between each solution and the ideal solution: Calculate the distance (d-) between each solution and the worst solution: Where, E represents energy consumption (kWh), P represents heat exchange efficiency (%), j represents the target solution, the subscript ideal represents the ideal solution, and the subscript worst represents the worst solution; Calculate the distance between each solution and the ideal solution and the worst solution; S54: Calculate the relative closeness (Ci) of each solution, which is the ratio of the distance between the solution and the ideal solution to the distance between the solution and the worst solution, using the relative closeness calculation formula: S55: Select the optimal operation plan: According to the relative proximity, select the solution with the highest relative proximity as the optimal operation plan.

6. The full-process multi-objective intelligent control method for a circulating cooling water system according to claim 4 is characterized in that: The S6 step specifically includes: S61: Based on multi-objective optimization decision, the optimal operation plan is obtained, the operation parameters are applied to the circulating cooling water system, and real-time dynamic adjustment and optimization are performed during the system process; S62: Apply multi-objective optimization decision to determine the best operating parameters to achieve energy-saving optimization goals; S63: Dynamic adjustments include: Pump speed adjustment: According to the prediction results, adjust the pump speed to optimize fluid circulation and energy consumption; Valve opening adjustment: adjust the opening of each valve to control the flow direction and flow rate of the fluid and reduce unnecessary energy consumption; Cooling tower fan speed adjustment: According to the ambient temperature and humidity, adjust the speed of the cooling tower fan to improve cooling efficiency; S64: Feedback control: After implementing adjustments, continue to monitor system performance and compare it with the predicted results. If the actual performance deviates from the predicted target, the control system will make necessary adjustments based on the feedback.

7. A multi-objective intelligent control device for the entire process of a circulating cooling water system, characterized in that: The modules it includes correspond to the steps of the full-process multi-objective intelligent control method for a circulating cooling water system as described in any one of claims 1-6, and are used to implement the full-process multi-objective intelligent control method for a circulating cooling water system as described in any one of claims 1-6.

8. A circulating cooling water system, characterized in that: Use the full-process multi-objective intelligent control method for a circulating cooling water system as described in any one of claims 1-6.

9. The circulating cooling water system according to claim 8, characterized in that: The invention comprises a cold water pool, a cooling tower fan (8), a pipeline, a heat exchanger (6), a production device (7) and an intelligent control center (9). The cooling tower fan (8) is installed above the cold water pool. The cold water pool is connected to the water inlet of the heat exchanger (6) through a pipeline. The water outlet of the heat exchanger (6) is connected to the cold water pool through a pipeline. A water pump (1), a flow sensor (2), a first valve (3) and a second valve (4) are installed on the pipeline between the cold water pool and the heat exchanger (6). The production device (7) is connected to the heat exchanger (6) through a pipeline so that hot materials produced by the production device (7) are exchanged with the heat exchanger (6) to become cold materials. A temperature sensor (5) is installed on the pipeline between the heat exchanger (6) and the production device (7). The water pump (1), the flow sensor (2), the first valve (3), the second valve (4), the temperature sensor (5) and the cooling tower fan (8) are respectively electrically connected to the intelligent control center (9).

Images