Intelligent temperature control system and method for refrigerating system

Abstract

The invention relates to the technical field of refrigeration, and particularly discloses an intelligent temperature control system and method for a refrigeration system, and the system comprises a temperature sensing module, a temperature calculation module, a decision optimization module, a controller module, an actuator module, and a self-learning module. The temperature sensing module is used for obtaining the actual temperature value of each controlled object through a temperature sensor, and the integrated refrigeration system obtains the set temperature value corresponding to each controlled object. The temperature calculation module is used for calculating a temperature error according to the actual temperature value and the set temperature value and transmitting the temperature error to the controller module and the decision optimization module; according to the invention, the error between the actual temperature and the set temperature of each controlled object is monitored in real time, and the operation strategy is dynamically adjusted in combination with environmental factors, so that the temperature stability is maintained on the premise of ensuring energy conservation; particularly, the PID gain of the refrigerating system is accurately adjusted by using the neural network PID controller, so that the problems of excessive adjustment or response lag and the like are avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of refrigeration, and particularly relates to an intelligent temperature control system and method for a refrigeration system. Background Art

[0002] In buildings, in order to provide a good and comfortable indoor environment or a stable and clean production environment, refrigeration equipment is required to work to provide cooling capacity for indoor cooling. Among them, many large buildings use a common solution of a refrigeration system composed of equipment such as chillers, pumps, and cooling towers as the source of building cooling capacity, and its energy consumption accounts for 25% - 50% of the building's energy consumption.

[0003] Since the unit selection in HVAC design is based on the regional maximum load, and the cooling load only accounts for less than 60% of the maximum load for most of the time, the air-conditioning refrigeration unit operates in a high-energy consumption mode all year round, and there is a lack of reasonable operation control means and management measures. The operation efficiency of the air-conditioning system is low, the energy consumption is high, and it occupies a large part of the hospital's energy consumption, greatly increasing the use cost of the air conditioner. The controller in the refrigeration system can determine the actual temperature of the compartment according to the temperature sensor in the compartment. When adjusting the temperature of the compartment in the refrigeration system through the controller, if there is a large deviation in the temperature adjustment of the compartment, it will cause a large gap between the actual temperature of the compartment after adjustment and the required temperature, affecting the operation effect of the compartment. Therefore, it is necessary to reliably control the temperature of each compartment in the refrigeration system to prevent temperature disturbances in each compartment.

[0004] Therefore, it is necessary to propose an intelligent temperature control system and method for a refrigeration system to solve the problem of causing temperature fluctuations in compartments in the prior art.

[0005] The above information disclosed in this background art is only used to increase the understanding of the background art of the present invention. Therefore, it may include prior art that is not known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent temperature control system and method for a refrigeration system to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] An intelligent temperature control system for a refrigeration system includes: a temperature sensing module, a temperature calculation module, a decision optimization module, a controller module, an actuator module, and a self-learning module;

[0009] The temperature sensing module is used to obtain the actual temperature values of each controlled object through temperature sensors, and integrate the refrigeration system to obtain the set temperature values corresponding to each controlled object;

[0010] The temperature calculation module is used to calculate the temperature error according to the actual temperature value and the set temperature value, and transmit the temperature error to the controller module and the decision optimization module;

[0011] The decision optimization module is used to adjust the operation strategy of the refrigeration system according to the temperature error and in combination with environmental factors, determine the current operation strategy for energy-saving purposes, and send the current operation strategy to the controller module;

[0012] The controller module is used to output the PID gain value of the cooler of the refrigeration system through a neural network PID controller according to the temperature error and the current operation strategy, generate an adjustment signal according to the PID gain value and transmit it to the actuator module;

[0013] The actuator module is used to convert the adjustment signal into an execution instruction for the cooler, and then send the execution instruction to the corresponding cooler to adjust the control behavior of the cooler;

[0014] The self-learning module is used to analyze the historical operation data obtained by integrating the refrigeration system based on machine learning and artificial intelligence technologies, and autonomously learn and optimize the operation strategy and PID control parameters.

[0015] Preferably, the temperature sensing module is further used to compensate for the influence of environmental temperature on the measured value of the temperature sensor through temperature drift to obtain the actual temperature value; match the actual temperature values of each controlled object with the set temperature value to form a temperature value statistical table based on time stamps; and use wireless transmission technology to transmit the real-time temperature value statistical table to the temperature calculation module.

[0016] Preferably, the decision optimization module is further used to obtain the current environmental factors according to the integrated refrigeration system, use data mining technology to discover the temperature change trend within a preset time period; integrate the historical operation data of the refrigeration system, and use a decision tree algorithm to predict the operation strategy within the preset time period; and find the optimal balance between energy saving and comfort according to the operation strategy through a genetic algorithm to determine the current operation strategy.

[0017] Preferably, the controller module is further used to have the network structure of the neural network PID controller as a three-layer perceptron, and optimize the output by using the backpropagation algorithm under the minimum tracking error entropy criterion; automatically adjust the PID gain value according to the temperature error and the temperature change trend; calculate the adjustment signal through the neural network PID controller, and send the adjustment signal to the actuator module.

[0018] Preferably, the actuator module is further configured to convert the adjustment signal into a continuous analog signal through a digital-to-analog converter for use by the control terminal of the cooler; control the switching frequency and duty cycle of the cooler according to the adjustment signal through pulse width modulation technology to control the motor speed of the cooler or the power of the compressor; detect the working state of the motor or compressor through current feedback, and integrate a safety protection mechanism to prevent equipment damage or abnormal operation.

[0019] Preferably, the self-learning module is further configured to identify important features through principal component analysis technology to reduce the influence of redundant data; use an LSTM network to capture long-term dependencies in the historical operation data to optimize the response strategy of the neural network PID controller; each module can learn independently and share information to complete the overall optimization of the control system.

[0020] An intelligent temperature control method for a refrigeration system, comprising the following steps:

[0021] Step 1: Real-time collect the actual temperature values of each controlled object through a temperature sensor, obtain the set temperature value of each controlled object, and calculate the difference between the two to obtain the temperature error.

[0022] Step 2: Adjust the operation strategy of the refrigeration system according to the temperature error in combination with environmental factors, and determine the current operation strategy for energy-saving purposes.

[0023] Step 3: According to the temperature error and the current operation strategy, use a neural network PID controller to calculate the required PID gain value, and generate an adjustment signal according to the PID gain value.

[0024] Step 4: Convert the adjustment signal into an execution instruction for the cooler of the refrigeration system, and then send the execution instruction to the cooler corresponding to the controlled object to adjust the control behavior of the cooler to achieve control of the temperature change.

[0025] Step 5: Analyze the historical operation data integrated with the refrigeration system using machine learning and artificial intelligence technologies to continuously optimize the operation strategy and PID control parameters.

[0026] Preferably, introduce a multivariable control algorithm to simultaneously control multiple controlled objects and adjust their actual temperature values; determine the control strength according to the current temperature error, the greater the temperature error, the greater the control strength; set a tolerance threshold for the temperature error to reduce unnecessary energy consumption.

[0027] Preferably, based on the historical operation data of the refrigeration system and the environmental factors, data mining technology is used to discover the temperature change trend and refrigeration demand within a preset time period; based on the refrigeration demand, the operation mode of the refrigeration system is adjusted to minimize energy consumption and meet the comfort requirements.

[0028] Preferably, based on the historical operation data and real-time feedback, machine learning is used to establish a mapping relationship between the temperature and the load of the refrigeration system; the feedforward control method is applied to adjust the adjustment signal in advance by predicting external disturbances, reducing the temperature fluctuation caused by time delay.

[0029] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0030] By monitoring the error between the actual temperature and the set temperature of each controlled object in real time and dynamically adjusting the operation strategy in combination with environmental factors, the present invention maintains the temperature stability on the premise of ensuring energy conservation; in particular, the neural network PID controller is used to accurately adjust the PID gain of the refrigeration system, avoiding problems such as over-regulation or reaction lag, and reducing the disturbance caused by temperature fluctuation. In addition, through the analysis and optimization of historical operation data in an autonomous learning manner, the temperature adjustment is made more efficient, and it can adapt to changes in different environments and loads, fundamentally improving the stability and energy efficiency of the refrigeration system, and significantly reducing the temperature disturbance phenomenon in each compartment caused by improper temperature adjustment.

[0031] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further directions, embodiments and features of the present invention will be readily apparent by reference to the drawings and the following detailed description. Brief Description of the Drawings

[0032] Figure 1 It is a framework diagram of an intelligent temperature control system for a refrigeration system of the present invention;

[0033] Figure 2 It is a flowchart of an intelligent temperature control method for a refrigeration system of the present invention. Detailed Description of the Embodiments

[0034] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.

[0035] Embodiment 1:

[0036] Please refer to Figure 1 As shown, an intelligent temperature control system for a refrigeration system includes: a temperature sensing module, a temperature calculation module, a decision optimization module, a controller module, an actuator module, and a self-learning module;

[0037] The temperature sensing module is used to obtain the actual temperature values of each controlled object through temperature sensors, and the integrated refrigeration system obtains the set temperature values corresponding to each controlled object;

[0038] The temperature calculation module is used to calculate the temperature error based on the actual temperature value and the set temperature value, and transmit the temperature error to the controller module and the decision optimization module;

[0039] The decision optimization module is used to adjust the operation strategy of the refrigeration system according to the temperature error and in combination with environmental factors, determine the current operation strategy for energy-saving purposes, and send the current operation strategy to the controller module;

[0040] The controller module is used to output the PID gain value of the refrigerator of the refrigeration system through a neural network PID controller according to the temperature error and the current operation strategy, generate an adjustment signal according to the PID gain value, and transmit it to the actuator module;

[0041] The actuator module is used to convert the adjustment signal into an execution instruction for the refrigerator, and then send the execution instruction to the corresponding refrigerator to adjust the control behavior of the refrigerator;

[0042] The self-learning module is used to analyze the historical operation data obtained through the integrated refrigeration system based on machine learning and artificial intelligence technologies, and autonomously learn and optimize the operation strategy and PID control parameters.

[0043] The temperature sensing module is also used to compensate for the influence of environmental temperature on the measured value of the temperature sensor through temperature drift to obtain the actual temperature value; match the actual temperature values of each controlled object with the set temperature values to form a temperature value statistical table based on timestamps; use wireless transmission technology to transmit the real-time temperature value statistical table to the temperature calculation module.

[0044] The temperature sensors include but are not limited to RTD (platinum resistance sensor), thermistor (NTC, PTC), infrared sensor, etc. When selecting, factors such as measurement range, accuracy requirements, and response time should be considered according to the actual situation.

[0045] The decision optimization module is also used to obtain the current environmental factors through the integrated refrigeration system, use data mining technology to discover the temperature change trend within a preset time period; integrate the historical operation data of the refrigeration system, and use the decision tree algorithm to predict the operation strategy within a preset time period; find the optimal balance between energy saving and comfort through the genetic algorithm according to the operation strategy to determine the current operation strategy.

[0046] The controller module is also used for the network structure of the neural network PID controller to be a three-layer perceptron, and the backpropagation algorithm under the minimum tracking error entropy criterion is used to optimize the output; according to the temperature error and the temperature change trend, the neural network PID controller automatically adjusts the PID gain value; the adjustment signal is calculated by the neural network PID controller and sent to the actuator module.

[0047] The neural network PID controller automatically adjusts the PID gain through a deep learning algorithm, combined with the real-time data of the system (including temperature error, environmental data, etc.). The neural network can optimize the adaptive adjustment of the PID gain to achieve better dynamic response and higher control accuracy. The PID controller (Proportional-Integral-Derivative controller) is the core of the controller module, mainly generating a control signal according to the current temperature error (the difference between the set temperature and the actual temperature).

[0048] Since the disturbances in the temperature control system are not necessarily Gaussian, and the actual refrigeration process is non-linear, entropy is introduced to measure the discreteness of the compartment temperature. The tracking error entropy can construct the performance index of the outer closed-loop control system, and thus the minimum tracking error entropy is selected as the closed-loop performance index for updating the weights of the neural network PID controller. The formula is as follows:

[0049]

[0050] In the formula, e is the tracking error, and γ(e) represents the probability of the tracking error e.

[0051] To calculate the above performance index, it is necessary to use the Gaussian kernel function to recursively estimate the probability density function of the closed-loop tracking error K from the error sequence e :

[0052]

[0053] In the formula, λ is the forgetting factor, 0 < λ < 1, and σ 2 represents the scale of the Gaussian kernel; therefore, the information potential of the tracking error can also be recursively approximated:

[0054]

[0055] In the formula, L is the width of the rolling time domain window, and its size should be selected to include the dynamic characteristics of the object.

[0056] The actuator module is also used to convert the adjustment signal into a continuous analog signal through a digital-to-analog converter for use at the control end of the cooler; control the switching frequency and duty cycle of the cooler according to the adjustment signal through pulse width modulation technology to control the motor speed of the cooler or the power of the compressor; detect the working state of the motor or compressor through current feedback, and integrate a safety protection mechanism to prevent equipment damage or abnormal operation.

[0057] The self-learning module is also used to identify important features through principal component analysis technology to reduce the influence of redundant data; use the LSTM network to capture long-term dependencies in historical operation data and optimize the response strategy of the neural network PID controller; each module can learn independently and share information to complete the overall optimization of the control system.

[0058] Embodiment 2:

[0059] Please refer to Figure 2 As shown, an intelligent temperature control method for a refrigeration system includes:

[0060] Step 1: Real-time collect the actual temperature values of each controlled object through a temperature sensor, obtain the set temperature values of each controlled object, and calculate the difference between the two to obtain the temperature error.

[0061] Step 2: Adjust the operation strategy of the refrigeration system according to the temperature error combined with environmental factors, and determine the current operation strategy for energy-saving purposes.

[0062] Step 3: According to the temperature error and the current operation strategy, use a neural network PID controller to calculate the required PID gain value, and generate an adjustment signal according to the PID gain value.

[0063] Step 4: Convert the adjustment signal into an execution instruction for the cooler of the refrigeration system, and then send the execution instruction to the cooler corresponding to the controlled object to adjust the control behavior of the cooler and realize the control of temperature change.

[0064] Step 5: Use machine learning and artificial intelligence technologies to analyze the historical operation data obtained by integrating with the refrigeration system, and continuously optimize the operation strategy and PID control parameters.

[0065] By introducing a multivariable control algorithm to control multiple controlled objects simultaneously and adjust their actual temperature values; determine the control strength according to the current temperature error, the greater the temperature error, the greater the control strength; set the tolerance threshold of the temperature error to reduce unnecessary energy consumption.

[0066] Based on the historical operation data and environmental factors of the refrigeration system, data mining technology is used to discover the temperature change trend and refrigeration demand within a preset time period; based on the refrigeration demand, the operation mode of the refrigeration system is adjusted to minimize energy consumption and meet the comfort requirements. Using Q-learning, it can self-learn and adjust the PID gain through interaction with the environment, and finally achieve the goal of maximizing energy saving and comfort.

[0067] Aiming at the high energy consumption problem in the operation of the refrigeration system, the air-conditioning chilled water system is optimized by adopting a constant flow variable water temperature control and a variable flow constant temperature difference chilled water system control strategy. According to the actual situation, the water temperature change mode adopted by the constant flow variable water temperature control strategy can be determined. The software can be used to model the refrigeration system equipment, and based on the above operation strategy, the state simulation is carried out to obtain the operation data of the refrigeration system equipment and the energy consumption calculation results. It is found through analysis that both the constant flow variable water temperature and the variable flow constant temperature difference operation control strategies have a certain degree of energy-saving effect compared with the original control method.

[0068] Based on the historical operation data and real-time feedback, machine learning is used to establish the mapping relationship between the temperature and the load of the refrigeration system; the feedforward control method is applied to adjust the control signal in advance by predicting external disturbances, and reduce the temperature fluctuation caused by time delay.

[0069] As can be seen from the above, the present invention monitors the error between the actual temperature and the set temperature of each controlled object in real time, and dynamically adjusts the operation strategy in combination with environmental factors, so as to maintain the temperature stability on the premise of ensuring energy saving; in particular, the neural network PID controller is used to accurately adjust the PID gain of the refrigeration system, avoiding problems such as over-adjustment or reaction lag, and reducing the disturbance caused by temperature fluctuation. In addition, through the analysis and optimization of historical operation data in an autonomous learning manner, the temperature regulation is made more efficient, and it can adapt to the changes of different environments and loads, fundamentally improving the stability and energy efficiency of the refrigeration system, and significantly reducing the temperature disturbance phenomenon in each compartment caused by improper temperature regulation.

[0070] Embodiment 3:

[0071] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes each process of the above temperature control system embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium, such as a read-only memory (Read-Only Memory, abbreviated as ROM), a random access memory (Random ACGess Memory, abbreviated as RAM), a magnetic disk or an optical disk, etc.

[0072] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0073] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (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 can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a program, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a method for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0074] In the drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present invention are involved. For other structures, reference can be made to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0075] The flowchart shown in the drawings is only an example illustration, and does not necessarily include all the content and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0076] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent temperature control system for a refrigeration system, characterized in that, Including: A temperature sensing module, a temperature calculation module, a decision optimization module, a controller module, an actuator module, and a self-learning module; The temperature sensing module is used to obtain the actual temperature values of each controlled object through a temperature sensor, and integrate the refrigeration system to obtain the set temperature values corresponding to each controlled object; The temperature calculation module is used to calculate the temperature error based on the actual temperature value and the set temperature value, and transmit the temperature error to the controller module and the decision optimization module; The decision optimization module is used to adjust the operation strategy of the refrigeration system according to the temperature error and combined with environmental factors, determine the current operation strategy for energy-saving purposes, and send the current operation strategy to the controller module; The controller module is used to output the PID gain value of the cooler of the refrigeration system through a neural network PID controller according to the temperature error and the current operation strategy, generate an adjustment signal according to the PID gain value, and transmit it to the actuator module; The actuator module is used to convert the adjustment signal into an execution instruction for the cooler, and then send the execution instruction to the corresponding cooler to adjust the control behavior of the cooler; The self-learning module is used to analyze the historical operation data obtained by integrating the refrigeration system based on machine learning and artificial intelligence technologies, and autonomously learn and optimize the operation strategy and PID control parameters.

2. The intelligent temperature control system of a refrigeration system according to claim 1, wherein The temperature sensing module is further used for: Compensating the influence of the ambient temperature on the measured value of the temperature sensor through temperature drift to obtain the actual temperature value; Matching the actual temperature values of each controlled object with the set temperature values to form a temperature value statistical table based on time stamps; Using wireless transmission technology to transmit the real-time temperature value statistical table to the temperature calculation module.

3. The intelligent temperature control system of a refrigeration system according to claim 2, characterized in that, The decision optimization module is further used for: Obtaining the current environmental factors according to the integrated refrigeration system, and using data mining technology to discover the temperature change trend within a preset time period; Integrating the historical operation data of the refrigeration system, and using a decision tree algorithm to predict the operation strategy within a preset time period; Finding the optimal balance between energy saving and comfort according to the operation strategy through a genetic algorithm to determine the current operation strategy.

4. The intelligent temperature control system of a refrigeration system according to claim 3, characterized in that, The controller module is further used for: The network structure of the neural network PID controller is a three-layer perceptron, and the output is optimized by using a backpropagation algorithm under the minimum tracking error entropy criterion; According to the temperature error and the temperature change trend, the neural network PID controller automatically adjusts the PID gain value; Calculating the adjustment signal through the neural network PID controller, and sending the adjustment signal to the actuator module.

5. The intelligent temperature control system of a refrigeration system according to claim 4, characterized in that, The actuator module is further used for: Converting the adjustment signal into a continuous analog signal through a digital-to-analog converter for use by the control end of the cooler; Controlling the switching frequency and duty cycle of the cooler according to the adjustment signal through pulse width modulation technology, and controlling the motor speed of the cooler or the power of the compressor; Detect the operating state of the motor or compressor through current feedback, and integrate a safety protection mechanism to prevent equipment damage or abnormal operation.

6. The intelligent temperature control system of a refrigeration system according to claim 5, characterized in that, The self-learning module is also used for: Identifying important features through principal component analysis technology to reduce the influence of redundant data; Using an LSTM network to capture long-term dependencies in the historical operation data and optimize the response strategy of the neural network PID controller; Each of the modules can learn independently and share information to complete the overall optimization of the control system.

7. An intelligent temperature control method for a refrigeration system, characterized in that, Including the following steps: Step 1: Real-time collect the actual temperature values of each controlled object through a temperature sensor, obtain the set temperature values of each controlled object, and calculate the difference between the two to obtain the temperature error; Step 2: Adjust the operation strategy of the refrigeration system according to the temperature error combined with environmental factors, and determine the current operation strategy for energy-saving purposes; Step 3: According to the temperature error and the current operation strategy, use a neural network PID controller to calculate the required PID gain value, and generate an adjustment signal according to the PID gain value; Step 4: Convert the adjustment signal into an execution instruction for the cooler of the refrigeration system, and then send the execution instruction to the cooler corresponding to the controlled object to adjust the control behavior of the cooler and realize the change of the controlled temperature; Step 5: Analyze the historical operation data obtained by integrating with the refrigeration system using machine learning and artificial intelligence technologies, and continuously optimize the operation strategy and PID control parameters.

8. An intelligent temperature control method for a refrigeration system according to claim 7, characterized in that: The real-time collection of the actual temperature values of each controlled object through a temperature sensor, obtaining the set temperature values of each controlled object, and calculating the difference between the two to obtain the temperature error includes: Simultaneously control multiple controlled objects by introducing a multivariable control algorithm and adjust their actual temperature values; Determine the control strength according to the current temperature error, the greater the temperature error, the greater the control strength; Set a tolerance threshold for the temperature error to reduce unnecessary energy consumption.

9. The intelligent temperature control method of a refrigeration system according to claim 8, characterized in that: The adjustment of the operation strategy of the refrigeration system according to the temperature error combined with environmental factors and determining the current operation strategy for energy-saving purposes includes: Discover the temperature change trend and refrigeration demand within a preset time period using data mining technology based on the historical operation data of the refrigeration system and the environmental factors; Adjust the operation mode of the refrigeration system based on the refrigeration demand to minimize energy consumption and meet the comfort requirements.

10. The intelligent temperature control method of a refrigeration system according to claim 9, characterized in that: The calculation of the required PID gain value using a neural network PID controller according to the temperature error and the current operation strategy, and generating an adjustment signal according to the PID gain value includes: Establish a mapping relationship between temperature and the load of the refrigeration system using machine learning based on the historical operation data and real-time feedback; Apply a feedforward control method to adjust the adjustment signal in advance by predicting external disturbances to reduce temperature fluctuations caused by time delay.

Images