An energy-saving optimization control method and system for evaporative cooling air conditioning based on mechanism model

Abstract

The present invention discloses an energy-saving optimization control method and system for evaporative cooling air conditioners based on a mechanism model, and relates to the technical field of evaporative cooling air conditioner control. The steps of the method include: preliminary zoning by the distribution of evaporative cooling air conditioners in the warehouse to obtain cold supply zones; real-time monitoring of the equipment operation status, personnel activities and lighting system in the warehouse to obtain the heat source distribution values ​​of all zones in the cold supply zones; setting a regional heat source prediction algorithm, combining the predicted value of the heat source distribution in the zone with the cargo density prediction; setting an adaptive evaporative cooling air conditioner parameter adjustment strategy, and dynamically adjusting the cooling water temperature, air intake volume, air supply temperature and direction according to the predicted value of the heat source distribution and the monitored humidity level. The present invention solves the problems of insufficient robustness and high energy consumption of the air conditioning system under high humidity and high cargo density, and ensures that it can still operate efficiently and stably when the load changes.

Description

Technical Field

[0001] The present invention relates to the technical field of evaporative cooling air conditioner control, and in particular to an evaporative cooling air conditioner energy-saving optimization control method and system based on a mechanism model. Background Art

[0002] The application of evaporative cooling air conditioning in places such as logistics warehouse centers and large production workshops faces many challenges. Traditional evaporative cooling air conditioning control methods mainly rely on a single control strategy, such as temperature-based PID control or set point adjustment. Although this method is simple and easy to use, it cannot achieve efficient energy-saving control when facing dynamically changing heat loads. In addition, fluctuations in environmental conditions such as humidity and air quality have a significant impact on air conditioning energy consumption. How to optimize the air conditioning system through more precise control methods has become an important issue in current air conditioning energy conservation research.

[0003] In order to improve the energy efficiency of evaporative cooling air conditioners, combining mechanism models, dynamic prediction and optimization control technology has become a new research trend. By considering multiple influencing factors, the air conditioning system based on the mechanism model can dynamically adjust the working parameters to respond to changes in the environment and load in real time, thereby achieving a balance between energy saving and comfort.

[0004] For example, the existing patent with publication number CN119222765A discloses an energy-saving control method and system for centralized cooling with a combined wind cabinet, which is suitable for central air-conditioning systems in large buildings. First, the outdoor temperature and humidity data are collected using the equal time interval division method, and the time series features are formed through the sliding window technology to train the ARIMA model. After the model training is completed, the future outdoor environment is predicted, and the indoor temperature set value, air supply volume and humidity control threshold are dynamically adjusted accordingly. At the same time, the system adopts a closed-loop control strategy to monitor indoor temperature changes in real time, and automatically adjusts the air volume by calculating the error between the current environmental state and the target state to ensure that the indoor temperature is constant. In order to prevent equipment overload or underload, the system also sets an air volume adjustment mapping and limiting processing mechanism.

[0005] However, the ARIMA model is mainly based on time series data for prediction, and there may be certain prediction errors for external environmental changes (such as sudden weather, extreme climate change, etc.). Although the sliding window technology can improve the adaptability of the model to a certain extent, over-reliance on historical data during the prediction process may lead to inaccurate predictions of future trends, especially when environmental conditions fluctuate violently, the system may not be able to respond in time. To this end, the present invention provides an evaporative cooling air conditioning energy-saving optimization control method and system based on a mechanism model. Summary of the invention

[0006] The object of the present invention is to provide an energy-saving optimization control method and system for an evaporative cooling air conditioner based on a mechanism model, so as to solve the existing problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: an evaporative cooling air conditioning energy-saving optimization control method based on a mechanism model, comprising the following steps:

[0008] S1. Perform preliminary zoning based on the distribution of evaporative cooling air conditioners in the warehouse to obtain cold supply zones;

[0009] S2. Real-time monitoring of the equipment operation status, personnel activities and lighting system in the warehouse to obtain the heat source distribution values ​​of all partitions in the cold supply partition;

[0010] S3. According to the heat source distribution value, a regional heat source prediction algorithm is set, and the heat source distribution prediction value in the partition is predicted in combination with the density of goods;

[0011] S4. Setting an adaptive evaporative cooling air conditioning parameter adjustment strategy to dynamically adjust the cooling water temperature, air intake volume, air supply temperature and direction according to the predicted value of the heat source distribution and the monitored humidity level.

[0012] The present invention is further improved in that the regional heat source prediction algorithm is based on the LSTM model, takes the heat source distribution value of any partition as input data, and dynamically adjusts the forget gate of the LSTM model according to the heat source volatility dynamic adjustment parameter. The heat source volatility dynamic adjustment parameter calculation formula is: ,in, is a bias term, represents the sigmoid activation function, represents the heat source distribution value of the partition at time i, t represents the number of timestamps, represents the sensitivity coefficient of the adjustment factor of the partition; then the forget gate is expressed as ,in, represents the weight matrix of the forget gate, Represents the hidden state of the previous time step; the output of the forget gate is used to update the memory unit to obtain the output content of the output gate, which is the predicted value of the heat source distribution. .

[0013] The present invention is further improved in that the sensitivity coefficient of the adjustment factor is determined by the current actual cooling water temperature, the heat source distribution value and the density of the goods, and the current actual cooling water temperature Tem and the density of the goods corresponding to the evaporative cooling air conditioner in the current partition are extracted. , the current actual cooling water temperature Tem, the density of the goods The heat source distribution value is normalized and weighted summed to obtain the thermal sensitivity impact value Hse of the current partition. The thermal sensitivity impact benchmark value SHse is set, and the sensitivity coefficient of the adjustment factor is , Represents the initial adjustment factor sensitivity coefficient.

[0014] The present invention is further improved in that the adaptive evaporative cooling air conditioning parameter adjustment strategy specifically comprises the following steps:

[0015] S41. Define control targets, including cooling water temperature, air intake volume, air supply temperature and air supply direction;

[0016] S42, randomly generating a PID parameter combination and a corresponding control target output combination for each particle;

[0017] S43, setting the PID controller fitness function FF;

[0018] S44, setting a PID controller fitness threshold TFF, and extracting a PID parameter combination whose FF is less than the PID controller fitness threshold TFF;

[0019] S45, setting an energy consumption adaptation particle mutation strategy, performing particle mutation on all extracted PID parameter combinations, and calculating the fitness of the mutated PID controller to generate a mutation fitness sequence;

[0020] S46, selecting a PID parameter combination corresponding to the minimum fitness value in the variant fitness sequence, and using the corresponding control target.

[0021] A further improvement of the present invention is that the fitness function calculation formula of the PID controller is:

[0022] ;

[0023] in, Indicates room temperature, Indicates the cooling water temperature of the control target output combination, represents the target room temperature, Indicates the air intake volume. Indicates the actual cooling water temperature Tem and room temperature under the current air humidity The ideal air intake volume corresponding to the difference between , and represents the weight coefficient, .

[0024] A further improvement of the present invention is that the energy consumption adaptation particle mutation strategy includes dynamically adjusting the mutation probability according to the current air humidity and the density of the goods. ,in, Indicates the current air humidity. Indicates the maximum value of air humidity. Indicates the maximum load of the cargo density in the area, and represents the weight coefficient, .

[0025] A further improvement of the present invention is that the energy consumption adaptive particle mutation strategy also includes returning the cooling water temperature corresponding to the PID controller parameters at this time to step S3, recalculating the heat source distribution prediction value, and obtaining a new heat source distribution prediction value. The fitness of the mutated PID controller is calculated in combination with the new heat source distribution prediction value to generate a mutation fitness sequence.

[0026] The present invention is further improved in that the heat source distribution value is obtained by weighted summing the normalized equipment operation status impact value, personnel activity impact value and lighting heat impact value of a certain area; the number of personnel in the area at the current time is obtained. And the number of tasks in the area , obtain the task completion time through historical data and calculate the impact value of personnel activities: ,in, represents the total number of personnel in all regions, Represents the total number of tasks in all regions. represents the number of tasks corresponding to the jth task machine in the historical data, It represents the task completion time corresponding to the j-th task machine in the historical data; the equipment operation status impact value is obtained by multiplying the equipment power, equipment working time and equipment heat conversion efficiency; the lighting heat impact value is obtained by multiplying the bulb power, lighting working time and lighting heat conversion efficiency.

[0027] On the other hand, the present invention provides an evaporative cooling air conditioning energy-saving optimization control system based on a mechanism model, comprising:

[0028] The cold supply partition module is used to perform preliminary partitioning based on the distribution of evaporative cooling air conditioners in the warehouse to obtain cold supply partitions;

[0029] A heat source distribution calculation module is used to monitor the equipment operation status, personnel activities and lighting system in the warehouse in real time, and obtain the heat source distribution values ​​of all partitions in the cold supply partition;

[0030] A heat source distribution calculation module is used to set a regional heat source prediction algorithm according to the heat source distribution value, and predict the heat source distribution prediction value in the partition in combination with the density of goods;

[0031] The evaporative cooling air conditioning parameter adjustment module is used to dynamically adjust the cooling water temperature, air intake volume, air supply temperature and direction according to the predicted value of the heat source distribution and the monitored humidity level.

[0032] A further improvement of the present invention is that the evaporative air conditioning parameter adjustment module includes a parameter variation unit and a control parameter output unit; the parameter variation unit is used to adjust the particle combination of the PID controller; the control parameter output unit is used to combine the PID controller and the particle swarm algorithm to output the control parameters according to the fitness function.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention firstly combines the real-time monitoring of heat source distribution with the dynamic adjustment of heat source fluctuation by LSTM model, and can accurately predict the future trend of heat source changes, and adjust the working parameters of the air-conditioning system accordingly. Especially in the case of high-volatility heat source, the system can quickly adapt and adjust to minimize energy consumption. Through this precise dynamic adjustment, the system can effectively avoid excessive operation of air-conditioning equipment, thereby significantly reducing energy consumption and achieving energy conservation and emission reduction.

[0035] Secondly, through the dynamic adjustment strategy of mutation probability, the mutation probability of the particle swarm algorithm is adjusted in combination with the real-time data of air humidity and product density. When the humidity is high or the product density is high, the system increases the mutation probability of particles and enhances the exploration ability of the search space, so that it can quickly adapt to environmental changes and reduce the possibility of system instability due to external disturbances. This makes the system more robust in the face of environmental changes and can still maintain efficient operation when the load changes drastically.

[0036] By combining the particle swarm algorithm (PSO) with the PID control strategy, the optimal combination of control parameters is automatically found to ensure that the control parameters are always in the optimal state under changing environmental conditions. Combined with the adaptability of the PID controller, the system can automatically adjust various control parameters according to the actual heat source distribution, humidity level and dynamic factors of cargo density, thereby reducing the need for manual intervention and improving the degree of automation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of an energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model of the present invention;

[0038] Figure 2 It is a schematic diagram of an energy-saving optimization control method of an evaporative cooling air conditioner based on a mechanism model of the present invention;

[0039] Figure 3 This is a flow chart of an adaptive evaporative cooling air conditioning parameter adjustment strategy for an evaporative cooling air conditioning energy-saving optimization control method based on a mechanism model of the present invention;

[0040] Figure 4 This is a framework diagram of an evaporative cooling air conditioning energy-saving optimization control system based on a mechanism model of the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0042] The term "and / or" is merely a description of the association relationship between associated objects, indicating that three possible relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone.

[0043] Example 1

[0044] Figure 1 and Figure 2 The flowchart and schematic diagram of an evaporative cooling air conditioning energy-saving optimization control method based on a mechanism model disclosed in this embodiment are respectively shown, and the steps are as follows:

[0045] S1. Perform preliminary zoning based on the distribution of evaporative cooling air conditioners in the warehouse, and use the perpendicular bisector of the center points of adjacent air conditioners as the initial dividing line to obtain the cooling supply zones;

[0046] S2. Real-time monitoring of the equipment operation status, personnel activities and lighting system in the warehouse to obtain the heat source distribution value of all partitions in the cold supply partition; the heat source distribution value is obtained by weighted summing the equipment operation status impact value, personnel activity impact value and lighting heat impact value of a certain area after standardization; obtaining the number of personnel in the area at the current time And the number of tasks in the area , obtain the task completion time through historical data and calculate the impact value of personnel activities: ,in, represents the total number of personnel in all regions, Represents the total number of tasks in all regions. Indicates the number of tasks corresponding to the jth task machine in the historical data, It represents the task completion time corresponding to the j-th task machine in the historical data; the equipment operation status impact value is obtained by multiplying the equipment power, equipment working time and equipment heat conversion efficiency; the lighting heat impact value is obtained by multiplying the bulb power, lighting working time and lighting heat conversion efficiency.

[0047] S3. According to the heat source distribution value, a regional heat source prediction algorithm is set, and the heat source distribution prediction value in the partition is predicted in combination with the density of goods;

[0048] The regional heat source prediction algorithm is based on the LSTM model. Since the equipment and personnel activities in the logistics center have time series and periodic changes, and LSTM can process complex time series data, it is particularly suitable for capturing the complex dynamic relationship between equipment, personnel and environmental factors. Therefore, the present invention regularly updates the model parameters based on the LSTM model according to real-time data. The specific process is as follows:

[0049] The heat source distribution value of any partition is used as input data, and the forget gate of the LSTM model is dynamically adjusted according to the dynamic adjustment parameters of the heat source volatility. The role of the forget gate is to determine how much historical information will be discarded. For the modeling of heat source distribution, some historical heat source distribution data has a greater impact on the current prediction, while some data has a smaller impact. For heat source data with high volatility, such as equipment and personnel, a higher forget gate value can be given so that the model can forget outdated heat source data faster; for heat source data with low volatility, such as long-term environmental changes, a lower forget value can be maintained so that the model can retain more historical information. Therefore, the calculation formula for the dynamic adjustment parameter of heat source volatility is: ,in, is a bias term used to adjust the basic state of the forget gate when volatility is small to prevent excessive forgetting of historical information. represents the sigmoid activation function, represents the heat source distribution value of the partition at time i, t represents the number of timestamps, Indicates the sensitivity coefficient of the adjustment factor of the partition;

[0050] Since the cooling water temperature is highly sensitive to the distribution of heat sources, especially under high load conditions, low water temperature can effectively improve the cooling effect; in areas where cargo is densely packed, the natural convection of the air may be disturbed, resulting in the inability to quickly disperse local heat, which causes the temperature in these areas to rise. When air flow is blocked, the cold air flow may not penetrate into the deep layers of cargo accumulation, causing the temperature to gradually rise in the stacking area and accumulate heat sources; in relatively sparse cargo areas (areas with lower density), the air flow is smoother, and heat can be more easily carried away through natural convection, heat conduction, etc., resulting in lower temperatures in these areas. Therefore, the sensitivity coefficient of the adjustment factor is determined by the current actual cooling water temperature, the heat source distribution value and the cargo density, and the current actual cooling water temperature Tem and the cargo density corresponding to the evaporative air conditioner in the current partition are extracted. , the current actual cooling water temperature Tem, the density of the goods The heat source distribution value is normalized and weighted summed to obtain the thermal sensitivity impact value Hse of the current partition. The thermal sensitivity impact benchmark value SHse is set, and the sensitivity coefficient of the adjustment factor is , Represents the initial adjustment factor sensitivity coefficient.

[0051] Then the forget gate is expressed as ,in, represents the weight matrix of the forget gate, Represents the hidden state of the previous time step; the output of the forget gate is used to update the memory unit to obtain the output content of the output gate, which is the predicted value of the heat source distribution. .

[0052] S4. Setting an adaptive evaporative cooling air conditioning parameter adjustment strategy to dynamically adjust the cooling water temperature, air intake volume, air supply temperature and direction according to the predicted value of the heat source distribution and the monitored humidity level.

[0053] Example 2

[0054] Figure 3 The present invention shows a flow chart of an adaptive evaporative cooling air conditioning parameter adjustment strategy for an evaporative cooling air conditioning energy-saving optimization control method based on a mechanism model, and the specific steps include:

[0055] S41. Define control targets, including cooling water temperature, air intake volume, air supply temperature and air supply direction;

[0056] S42. PID can save computing resources in the control system, but it cannot select the optimal solution, resulting in poor control parameter effect, which requires the system to invest more resources and increase energy consumption. Therefore, the particle swarm algorithm is combined to find the most effective parameter solution to overcome the energy consumption problem. A PID parameter combination and a corresponding control target output combination are randomly generated for each particle;

[0057] S43, setting the PID controller fitness function FF. Since the higher the room temperature, the more cooling capacity the air conditioning system needs, so the cooling water temperature needs to be lowered, resulting in increased energy consumption. Therefore, the fitness function calculation formula is expressed as:

[0058]

[0059] in, Indicates room temperature, Indicates the cooling water temperature of the control target output combination, represents the target room temperature, Indicates the air intake volume. Indicates the actual cooling water temperature Tem and room temperature under the current air humidity The ideal air volume corresponding to the difference between , and represents the weight coefficient, .

[0060] S44, setting a PID controller fitness threshold TFF, and extracting a PID parameter combination whose FF is less than the PID controller fitness threshold;

[0061] S45. However, the PID controller is based on the current error for control, and is not very robust to external disturbances or sudden changes, which makes the particle swarm prone to local optimality. If there is a large external disturbance or change in the system, the PID controller may be difficult to make appropriate adjustments in time, resulting in temporary system instability or reduced efficiency. Therefore, the energy consumption adaptation particle variation strategy is set according to the current air humidity and cargo density;

[0062] When the air humidity is high, particles need more mutations to adapt to humidity changes. High humidity means that the cooling system requires more evaporation energy consumption and more parameters need to be adjusted, so a higher mutation probability is needed to accelerate the exploration of the search space.

[0063] Influence of cargo density: When the cargo density is high, the heat source increases, the system load is heavier, and the search space of particle swarm optimization is more complex. Therefore, it is necessary to increase the mutation probability in order to better search for suitable cooling parameters (such as cooling water temperature, air volume, etc.).

[0064] In order to prevent the mutation probability from being too large or too small, an upper limit and a lower limit can be set. In this embodiment, it can be ensured that the value of the mutation probability is always kept in the range of [0.01, 0.1], which can prevent the algorithm from deviating too much from the initial solution. Therefore, the mutation probability calculation formula of the particle mutation is: ,in, Indicates the current air humidity. Indicates the maximum air humidity, usually 100%. Indicates the maximum load of the cargo density in the area, and represents the weight coefficient, .

[0065] The cooling water temperature corresponding to the PID controller parameter at this time is returned to step S3, and the heat source distribution prediction value is calculated again. The new heat source distribution prediction value is obtained, and the fitness of the mutated PID controller is calculated in combination with the new heat source distribution prediction value to generate a mutated fitness sequence.

[0066] S46, selecting a PID parameter combination corresponding to the minimum fitness value in the variant fitness sequence, and using the corresponding control target.

[0067] Example 3

[0068] Figure 4 The framework diagram of an evaporative cooling air conditioner energy-saving optimization control system based on a mechanism model of the present invention is shown. Based on the same inventive concept as that of Embodiment 1 and Embodiment 2, the present invention provides an evaporative cooling air conditioner energy-saving optimization control system based on a mechanism model, comprising:

[0069] The cold supply partition module is used to perform preliminary partitioning based on the distribution of evaporative cooling air conditioners in the warehouse to obtain cold supply partitions;

[0070] A heat source distribution calculation module is used to monitor the equipment operation status, personnel activities and lighting system in the warehouse in real time, and obtain the heat source distribution values ​​of all partitions in the cold supply partition;

[0071] A heat source distribution calculation module is used to set a regional heat source prediction algorithm according to the heat source distribution value, and predict the heat source distribution prediction value in the partition in combination with the density of goods;

[0072] The evaporative cooling air conditioning parameter adjustment module is used to dynamically adjust the cooling water temperature, air intake volume, air supply temperature and direction according to the predicted value of the heat source distribution and the monitored humidity level; it includes a parameter variation unit and a control parameter output unit; the parameter variation unit is used to adjust the particle combination of the PID controller; the control parameter output unit is used to combine the PID controller and the particle swarm algorithm to output the control parameters according to the fitness function.

[0073] The threshold and weight may be set by default according to the present invention, or may be set by an operator.

[0074] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. An energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model, characterized in that: The following steps are involved: S1. Perform preliminary zoning based on the distribution of evaporative cooling air conditioners in the warehouse to obtain cold supply zones; S2. Real-time monitoring of the equipment operation status, personnel activities and lighting system in the warehouse to obtain the heat source distribution values ​​of all partitions in the cold supply partition; S3. According to the heat source distribution value, a regional heat source prediction algorithm is set, and the heat source distribution prediction value in the partition is predicted in combination with the density of goods; S4, setting an adaptive evaporative cooling air conditioning parameter adjustment strategy, dynamically adjusting the cooling water temperature, air intake volume, air supply temperature and direction according to the predicted value of the heat source distribution and the monitored humidity level; The regional heat source prediction algorithm is based on the LSTM model, takes the heat source distribution value of any partition as input data, and dynamically adjusts the forget gate of the LSTM model according to the heat source volatility dynamic adjustment parameter. The heat source volatility dynamic adjustment parameter calculation formula is: ,in, is a bias term, represents the sigmoid activation function, represents the heat source distribution value of the partition at time i, t represents the number of timestamps, represents the sensitivity coefficient of the adjustment factor of the partition; then the forget gate is expressed as ,in, represents the weight matrix of the forget gate, Represents the hidden state of the previous time step; the output of the forget gate is used to update the memory unit to obtain the output content of the output gate, which is the predicted value of the heat source distribution. .

2. The energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model according to claim 1 is characterized in that: The sensitivity coefficient of the adjustment factor is determined by the current actual cooling water temperature, heat source distribution value and product density. The current actual cooling water temperature Tem and product density of the evaporative air conditioner corresponding to the current partition are extracted. , the current actual cooling water temperature Tem, the density of the goods The heat source distribution value is normalized and weighted summed to obtain the thermal sensitivity impact value Hse of the current partition. The thermal sensitivity impact benchmark value SHse is set, and the sensitivity coefficient of the adjustment factor is , Represents the initial adjustment factor sensitivity coefficient.

3. The energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model according to claim 2 is characterized by: The specific steps of the adaptive evaporative cooling air conditioning parameter adjustment strategy include: S41. Define control targets, including cooling water temperature, air intake volume, air supply temperature and air supply direction; S42, randomly generating a PID parameter combination and a corresponding control target output combination for each particle; S43, setting the PID controller fitness function FF; S44, setting a PID controller fitness threshold TFF, and extracting a PID parameter combination whose FF is less than the PID controller fitness threshold TFF; S45, setting an energy consumption adaptation particle mutation strategy, performing particle mutation on all extracted PID parameter combinations, and calculating the fitness of the mutated PID controller to generate a mutation fitness sequence; S46, selecting a PID parameter combination corresponding to the minimum fitness value in the variant fitness sequence, and using the corresponding control target.

4. The energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model according to claim 3 is characterized by: The PID controller fitness function calculation formula is: ； in, Indicates room temperature, Indicates the cooling water temperature of the control target output combination, represents the target room temperature, Indicates the air intake volume. Indicates the actual cooling water temperature Tem and room temperature under the current air humidity The ideal air volume corresponding to the difference between , and represents the weight coefficient, .

5. The energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model according to claim 4 is characterized in that: The energy-adaptive particle mutation strategy includes dynamically adjusting the mutation probability according to the current air humidity and product density. ,in, Indicates the current air humidity. Indicates the maximum value of air humidity. Indicates the maximum load of the cargo density in the area, and represents the weight coefficient, .

6. The energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model according to claim 5 is characterized by: The energy consumption adaptation particle mutation strategy also includes returning the cooling water temperature corresponding to the PID controller parameter at this time to step S3, recalculating the heat source distribution prediction value, and obtaining a new heat source distribution prediction value. The fitness of the mutated PID controller is calculated in combination with the new heat source distribution prediction value to generate a mutation fitness sequence.

7. The energy-saving optimization control method for evaporative cooling air conditioning based on a mechanism model according to claim 6 is characterized by: The heat source distribution value is obtained by weighted summing the normalized equipment operation status impact value, personnel activity impact value and lighting heat impact value of a certain area; the number of personnel in the area at the current time is obtained. And the number of tasks in the area , obtain the task completion time through historical data and calculate the impact value of personnel activities: ,in, represents the total number of personnel in all regions, Represents the total number of tasks in all regions. Indicates the number of tasks corresponding to the jth task machine in the historical data, It represents the task completion time corresponding to the j-th task machine in the historical data; the equipment operation status impact value is obtained by multiplying the equipment power, equipment working time and equipment heat conversion efficiency; the lighting heat impact value is obtained by multiplying the bulb power, lighting working time and lighting heat conversion efficiency.

8. An evaporative cooling air conditioning energy-saving optimization control system based on a mechanism model, used to execute an evaporative cooling air conditioning energy-saving optimization control method based on a mechanism model as claimed in any one of claims 1 to 7, characterized in that: include: The cold supply partition module is used to perform preliminary partitioning based on the distribution of evaporative cooling air conditioners in the warehouse to obtain cold supply partitions; A heat source distribution calculation module is used to monitor the equipment operation status, personnel activities and lighting system in the warehouse in real time, and obtain the heat source distribution values ​​of all partitions in the cold supply partition; A heat source distribution calculation module is used to set a regional heat source prediction algorithm according to the heat source distribution value, and predict the heat source distribution prediction value in the partition in combination with the density of goods; The evaporative cooling air conditioning parameter adjustment module is used to dynamically adjust the cooling water temperature, air intake volume, air supply temperature and direction according to the predicted value of the heat source distribution and the monitored humidity level.

9. The energy-saving optimization control system for evaporative cooling air conditioning based on a mechanism model according to claim 8 is characterized in that: The evaporative cooling air conditioning parameter adjustment module includes a parameter variation unit and a control parameter output unit; the parameter variation unit is used to adjust the particle combination of the PID controller; the control parameter output unit is used to combine the PID controller and the particle swarm algorithm to output the control parameter according to the fitness function.

Images