Air conditioner refrigerating unit energy-saving control method and system based on intelligent algorithm

Abstract

The invention relates to the technical field of energy-saving control, in particular to an energy-saving control method and system for an air conditioner refrigerating unit based on an intelligent algorithm, and the method comprises the steps: carrying out people flow intensity evaluation, personnel retention condition evaluation and equipment use state evaluation, and calculating refrigeration threat coefficients of different indoor sub-regions in a current period in combination with evaluation results; constructing a sub-region operation mode prediction model in combination with activity calendar information, predicting operation modes of different sub-regions in a next period, and setting a target refrigeration temperature range of the next period for the different sub-regions according to operation mode prediction results of the different sub-regions; constructing a sub-region temperature prediction model, predicting a temperature data change curve of different sub-regions in the next period, comparing the temperature data change curve with a set target refrigeration temperature range in the next period, and calculating an energy-saving threat value; and when the energy-saving threat value is greater than or equal to the energy-saving threat value threshold, manual intervention is adopted.

Description

Background Art

[0002] Currently, air conditioning systems are widely used in commercial, industrial and residential areas as a widely used comfort environment adjustment device. However, the energy efficiency of air conditioning has always been a challenge, especially in large-scale air conditioning systems, which often lead to energy waste and inefficient operation due to imprecise control of indoor temperature, humidity and human activities. Therefore, how to effectively reduce air conditioning refrigeration energy consumption while ensuring a comfortable indoor environment has become an urgent problem to be solved.

[0003] Traditional air conditioning control methods usually adjust the temperature based on fixed temperature settings and simple schedules, but this control method lacks dynamic response to the actual indoor conditions. For example, factors such as human traffic, equipment usage, and indoor temperature changes in commercial complexes are not fully considered, which often leads to unreasonable operation of air conditioning systems and wastes a lot of energy. In addition, existing energy-saving control methods often do not make full use of intelligent algorithms for data analysis and optimization, thus missing the opportunity to improve energy efficiency. Summary of the invention

[0004] The main purpose of the present invention is to provide an energy-saving control method for an air-conditioning refrigeration unit based on an intelligent algorithm, and further to provide an energy-saving control system for an air-conditioning refrigeration unit based on an intelligent algorithm that can run and implement the above method, thereby effectively solving the above problems mentioned in the background technology.

[0005] The technical solution of the present invention is as follows: In the first aspect, an energy-saving control method for an air-conditioning refrigeration unit based on an intelligent algorithm is proposed, and the method comprises the following steps: S1. Monitor the flow of people, equipment usage and temperature data of different sub-areas in the room during this period; S2. Evaluate the flow intensity, personnel retention and equipment usage status based on the flow data and equipment usage status, and calculate the cooling threat coefficient of different indoor sub-areas in this cycle based on the evaluation results; S3. Based on the evaluation results of different indoor sub-areas in this cycle and combined with the activity calendar information, a sub-area operation mode prediction model is constructed to predict the operation modes of different indoor sub-areas in the next cycle, and the target cooling temperature range for the next cycle is set for different sub-areas; S4, extracting the temperature data of different sub-areas in the room in this cycle, constructing a sub-area temperature prediction model, predicting the temperature data change curve of different sub-areas in the next cycle and comparing it with the target cooling temperature range set for the next cycle, when the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, cooling is performed according to the target cooling temperature range, and when the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range, calculating the energy-saving threat value; S5. Preset an energy-saving threat value threshold, compare the energy-saving threat value with the energy-saving threat value threshold, and determine whether to take manual intervention.

[0006] A further improvement of the present invention is that S2 comprises the following specific steps: S21, divide the indoor area into n sub-areas according to the spatial layout, and obtain the area of ​​a single sub-area, where the area of ​​the i-th sub-area is , within the preset collection time T of this cycle, for a single sub-area i, collect the number of people in the i-th sub-area , the number of people entering the i-th sub-area , the number of people leaving the i-th sub-area , perform a flow intensity assessment, the calculation formula for the flow intensity assessment is: ;in, is the flow intensity value of the ith sub-area, is the flow density of people in the ith sub-area, is the flow rate of people in and out of the ith sub-area, , are the influencing factors of crowd density and crowd in / out rate, ; S22: within the preset collection time T of this collection cycle, for a single sub-area i, collect the personnel stay time in the i-th sub-area , and the personnel retention status evaluation is performed, and the calculation formula for the personnel retention status evaluation is: ;in, is the personnel retention heat value of the i-th sub-area, is the residence time of the jth person in the i-th sub-area; S23. Within the preset collection time T of this collection cycle, for a single sub-area i, collect the number of running devices in the i-th sub-area , Current power of a single device , Maximum rated power of a single device , perform equipment usage status evaluation, the calculation formula for the equipment usage status evaluation is: ;in, The device usage status value for the i-th sub-area, is the current power of the kth device in the i-th sub-area, is the maximum rated power of the kth device in the i-th sub-area, is the importance weight of the kth device in the i-th sub-area.

[0007] A further improvement of the present invention is that S2 further includes: calculating the refrigeration threat coefficients of different indoor sub-areas in combination with the evaluation results, and the calculation formula of the refrigeration threat coefficients is: ; in, is the cooling threat coefficient of the ith sub-region, , , They are the influencing factors of the flow intensity value, the personnel retention heat value, and the equipment usage status value. .

[0008] A further improvement of the present invention is that S3 comprises the following specific steps: S31, obtaining the historical flow intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information and historical operation mode label of the i-th sub-area in the same season historical cycle; the activity calendar information is specifically divided into promotional weekdays, ordinary shopping days, promotional holidays and ordinary holidays; the operation mode is specifically divided into high load mode, medium load mode and low load mode; S32, extracting features from the historical flow intensity values, historical personnel retention heat values, historical equipment usage status values ​​and historical activity calendar information of the ith sub-region in the same season historical cycle and combining them into the form of feature vectors, constructing a sub-region operation mode prediction model, wherein the sub-region operation mode prediction model takes the set of all groups of feature vectors as input, takes the predicted operation mode label corresponding to each group of feature vectors as output, takes the actual operation mode label corresponding to each group of feature vectors as the prediction target, takes minimizing the sum of squares of the difference between the predicted operation mode label and the actual operation mode label as the training target, trains the sub-region operation mode prediction model, stops training when the sum of squares of the difference between the predicted operation mode label and the actual operation mode label reaches convergence, and outputs the predicted operation mode label of the ith sub-region; the sub-region operation mode prediction model is any one of the classification models; S33: According to the prediction result of the operation mode of the ith sub-region, the target cooling temperature range of the next cycle is set for the ith sub-region ; The minimum value of the target refrigeration temperature range for the next cycle is the average of the minimum value of the target cooling temperature range under this operation mode in the historical cycle of the same season in the i-th sub-area, and the maximum value of the target cooling temperature range is the average of the maximum values ​​of the target cooling temperature range under this operation mode in the i-th sub-area in the same seasonal historical cycle; Repeat the above steps until n sub-areas are traversed.

[0009] A further improvement of the present invention is that S4 comprises the following specific steps: S41. Extract the historical crowd intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information, historical operation mode label and historical temperature data change curve over time of the i-th sub-area in the historical cycle of the same season to construct a sub-area temperature prediction model, divide these data into 70% training set and 30% test set, perform parameter training on the sub-area temperature prediction model to construct a sub-area temperature prediction model with input as the historical crowd intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information and historical operation mode label of the i-th sub-area, and output as the temperature data change curve of the i-th sub-area, train the sub-area temperature prediction model with 70% training set to obtain an initial sub-area temperature prediction model, test the initial sub-area temperature prediction model with 30% coefficient test set, and output the initial sub-area temperature prediction model that meets the optimal accuracy of the indoor actual temperature data change curve over time as the final sub-area temperature prediction model; the sub-area temperature prediction model is an LSTM neural network model, which predicts the temperature data change curve of the next cycle of the i-th sub-area over time.

[0010] A further improvement of the present invention is that the S4 further includes: S42: extract the temperature data of the next cycle of the i-th sub-area and change the time curve, and set the target refrigeration temperature range of the next cycle When the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, When the target cooling temperature range is Cooling is performed when the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range When the temperature data change curve of the next cycle is predicted, the temperature farthest from the target cooling temperature range is extracted. Temperature value , calculate the energy-saving threat value.

[0011] A further improvement of the present invention is that the calculation formula of the energy-saving threat value in S42 is: ; in, is the energy-saving threat value of the i-th sub-area.

[0012] A further improvement of the present invention is that the specific content of S5 is: preset energy-saving threat value threshold , the energy-saving threat value of the i-th sub-area Threshold value for energy saving For comparison, if and only if the energy-saving threat value of the i-th sub-area Greater than or equal to the energy saving threat value threshold When the error occurs, manual intervention is taken.

[0013] Secondly, an energy-saving control system for air-conditioning refrigeration units based on intelligent algorithms is proposed. The system includes: collection and evaluation module, pattern prediction module, threat calculation module, and adjustment and intervention module; The acquisition and evaluation module is used to monitor the human flow data, equipment usage status data and temperature data of different indoor sub-areas in this cycle; perform human flow intensity evaluation, personnel retention status evaluation and equipment usage status evaluation based on the human flow data and equipment usage status data, and calculate the refrigeration threat coefficient of different indoor sub-areas in this cycle based on the evaluation results; The mode prediction module is used to construct a sub-region operation mode prediction model based on the evaluation results of different indoor sub-regions in the current cycle and in combination with the activity calendar information, predict the operation modes of different indoor sub-regions in the next cycle, and set the target cooling temperature range for different sub-regions in the next cycle; The threat calculation module is used to extract the temperature data of different sub-areas in the room in this cycle, build a sub-area temperature prediction model, predict the temperature data change curve of different sub-areas in the next cycle and compare it with the target cooling temperature range set for the next cycle. When the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, cooling is performed according to the target cooling temperature range. When the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range, the energy-saving threat value is calculated; The adjustment intervention module is used to preset an energy-saving threat value threshold, compare the energy-saving threat value with the energy-saving threat value threshold, and determine whether to take manual intervention.

[0014] The technical effects of the present invention are as follows: An energy-saving control method for air-conditioning refrigeration units based on intelligent algorithms was constructed. This method dynamically adjusts the operation mode of the refrigeration system through real-time monitoring and evaluation of data such as the flow of people, equipment usage status, and temperature in different indoor sub-areas. Combined with historical data, an LSTM neural network model was used to predict the temperature changes and operation modes of different sub-areas, so as to set a reasonable target temperature range in advance. The energy-saving threat value was calculated based on the comparison between the predicted temperature changes and the target temperature range. When the threat value exceeds the threshold, manual intervention is taken to avoid energy waste. At the same time, it also solves the problem of uneven heating and cooling in different indoor areas of large commercial complexes and the energy waste caused by continuous high-load operation of the air-conditioning refrigeration system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 This is a flow chart of an energy-saving control method for an air-conditioning refrigeration unit based on an intelligent algorithm according to Embodiment 1 of the present invention; Figure 2 This is a structural schematic diagram of an energy-saving control system for an air-conditioning refrigeration unit based on an intelligent algorithm according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0016] Example 1 This embodiment constructs an energy-saving control method for air-conditioning refrigeration units based on intelligent algorithms. The method dynamically adjusts the operation mode of the refrigeration system through real-time monitoring and evaluation of data such as the flow of people, equipment usage status and temperature in different indoor sub-areas; combines historical data and adopts an LSTM neural network model to predict temperature changes and operation modes in different sub-areas, so as to set a reasonable target temperature range in advance; calculates the energy-saving threat value based on the comparison between the predicted temperature change and the target temperature range, and takes manual intervention when the threat value exceeds the threshold to avoid energy waste; at the same time, it also solves the problem of uneven heating and cooling in different indoor areas of large commercial complexes and energy waste caused by continuous high-load operation of air-conditioning refrigeration systems.

[0017] Energy-saving control method of air-conditioning refrigeration unit based on intelligent algorithm, such as Figure 1 As shown, the specific steps include: S1. Monitor the flow of people, equipment usage and temperature data of different sub-areas in the room during this period; S2. Evaluate the flow intensity, personnel retention and equipment usage status based on the flow data and equipment usage status, and calculate the cooling threat coefficient of different indoor sub-areas in this cycle based on the evaluation results; S3. Based on the evaluation results of different indoor sub-areas in this cycle and combined with the activity calendar information, a sub-area operation mode prediction model is constructed to predict the operation modes of different indoor sub-areas in the next cycle, and the target cooling temperature range for the next cycle is set for different sub-areas; S4, extracting the temperature data of different sub-areas in the room in this cycle, constructing a sub-area temperature prediction model, predicting the temperature data change curve of different sub-areas in the next cycle and comparing it with the target cooling temperature range set for the next cycle, when the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, cooling is performed according to the target cooling temperature range, and when the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range, calculating the energy-saving threat value; S5. Preset an energy-saving threat value threshold, compare the energy-saving threat value with the energy-saving threat value threshold, and determine whether to take manual intervention.

[0018] In this embodiment, S2 includes the following specific steps: S21, divide the indoor area into n sub-areas according to the spatial layout, and obtain the area of ​​a single sub-area, where the area of ​​the i-th sub-area is , within the preset collection time T of this cycle, for a single sub-area i, collect the number of people in the i-th sub-area , the number of people entering the i-th sub-area , the number of people leaving the i-th sub-area , perform a flow intensity assessment, the calculation formula for the flow intensity assessment is: ;in, is the flow intensity value of the ith sub-area, is the flow density of people in the ith sub-area, is the flow rate of people in and out of the ith sub-area, , are the influencing factors of crowd density and crowd in / out rate, , specific , The value is set by technicians in this field according to actual needs; S22: within the preset collection time T of this collection cycle, for a single sub-area i, collect the personnel stay time in the i-th sub-area , and the personnel retention status evaluation is performed, and the calculation formula for the personnel retention status evaluation is: ;in, is the personnel retention heat value of the i-th sub-area, is the residence time of the jth person in the i-th sub-area; S23. Within the preset collection time T of this collection cycle, for a single sub-area i, collect the number of running devices in the i-th sub-area , Current power of a single device , Maximum rated power of a single device , perform equipment usage status evaluation, the calculation formula for the equipment usage status evaluation is: ;in, The device usage status value for the i-th sub-area, is the current power of the kth device in the i-th sub-area, is the maximum rated power of the kth device in the i-th sub-area, is the importance weight of the kth device in the ith sub-area, and the specific value of the importance weight is determined by those skilled in the art based on a large number of experiments.

[0019] In this embodiment, S2 further includes: calculating the refrigeration threat coefficients of different indoor sub-areas in combination with the evaluation results, and the calculation formula of the refrigeration threat coefficients is: ; in, is the cooling threat coefficient of the ith sub-region, , , They are the influencing factors of the flow intensity value, the personnel retention heat value, and the equipment usage status value. In this embodiment, , , The values ​​are 0.4, 0.3, and 0.3 respectively.

[0020] In this embodiment, S3 includes the following specific steps: S31, obtaining the historical flow intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information and historical operation mode label of the i-th sub-area in the same season historical cycle; the activity calendar information is specifically divided into promotional weekdays, ordinary shopping days, promotional holidays and ordinary holidays; the operation mode is specifically divided into high load mode, medium load mode and low load mode; S32, extracting features from the historical flow intensity values, historical personnel retention heat values, historical equipment usage status values ​​and historical activity calendar information of the ith sub-region in the same season historical cycle and combining them into the form of feature vectors, constructing a sub-region operation mode prediction model, wherein the sub-region operation mode prediction model takes the set of all groups of feature vectors as input, takes the predicted operation mode label corresponding to each group of feature vectors as output, takes the actual operation mode label corresponding to each group of feature vectors as the prediction target, takes minimizing the sum of squares of the difference between the predicted operation mode label and the actual operation mode label as the training target, trains the sub-region operation mode prediction model, stops training when the sum of squares of the difference between the predicted operation mode label and the actual operation mode label reaches convergence, and outputs the predicted operation mode label of the ith sub-region; the sub-region operation mode prediction model is any one of the classification models; S33: According to the prediction result of the operation mode of the ith sub-region, the target cooling temperature range of the next cycle is set for the ith sub-region ; The minimum value of the target refrigeration temperature range for the next cycle is the average of the minimum value of the target cooling temperature range under this operation mode in the historical cycle of the same season in the i-th sub-area, and the maximum value of the target cooling temperature range is the average of the maximum values ​​of the target cooling temperature range under this operation mode in the i-th sub-area in the same seasonal historical cycle; Repeat the above steps until n sub-areas are traversed.

[0021] In this embodiment, S4 includes the following specific steps: S41. Extract the historical crowd intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information, historical operation mode label and historical temperature data change curve over time of the i-th sub-area in the historical cycle of the same season to construct a sub-area temperature prediction model, divide these data into 70% training set and 30% test set, perform parameter training on the sub-area temperature prediction model to construct a sub-area temperature prediction model with input as the historical crowd intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information and historical operation mode label of the i-th sub-area, and output as the temperature data change curve of the i-th sub-area, train the sub-area temperature prediction model with 70% training set to obtain an initial sub-area temperature prediction model, test the initial sub-area temperature prediction model with 30% coefficient test set, and output the initial sub-area temperature prediction model that meets the optimal accuracy of the indoor actual temperature data change curve over time as the final sub-area temperature prediction model; the sub-area temperature prediction model is an LSTM neural network model, which predicts the temperature data change curve of the next cycle of the i-th sub-area over time.

[0022] In this embodiment, S4 further includes: S42: extract the temperature data of the next cycle of the i-th sub-area and change the time curve, and set the target refrigeration temperature range of the next cycle When the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, When the target cooling temperature range is Cooling is performed when the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range When the temperature data change curve of the next cycle is predicted, the temperature farthest from the target cooling temperature range is extracted. Temperature value , calculate the energy-saving threat value.

[0023] In this embodiment, the calculation formula of the energy saving threat value in S42 is: ; in, is the energy-saving threat value of the i-th sub-area.

[0024] In this embodiment, the specific content of S5 is: preset energy-saving threat value threshold , the energy-saving threat value of the i-th sub-area Threshold value for energy saving For comparison, if and only if the energy-saving threat value of the i-th sub-area Greater than or equal to the energy saving threat value threshold When the error occurs, manual intervention is taken.

[0025] Example 2 This embodiment proposes an energy-saving control system for air-conditioning refrigeration units based on intelligent algorithms, such as Figure 2 As shown, it includes: collection and evaluation module, pattern prediction module, threat calculation module, and adjustment and intervention module; The acquisition and evaluation module is used to monitor the human flow data, equipment usage status data and temperature data of different indoor sub-areas in this cycle; perform human flow intensity evaluation, personnel retention status evaluation and equipment usage status evaluation based on the human flow data and equipment usage status data, and calculate the refrigeration threat coefficient of different indoor sub-areas in this cycle based on the evaluation results; The mode prediction module is used to construct a sub-region operation mode prediction model based on the evaluation results of different indoor sub-regions in the current cycle and in combination with the activity calendar information, predict the operation modes of different indoor sub-regions in the next cycle, and set the target cooling temperature range for different sub-regions in the next cycle; The threat calculation module is used to extract the temperature data of different sub-areas in the room in this cycle, build a sub-area temperature prediction model, predict the temperature data change curve of different sub-areas in the next cycle and compare it with the target cooling temperature range set for the next cycle. When the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, cooling is performed according to the target cooling temperature range. When the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range, the energy-saving threat value is calculated; The adjustment intervention module is used to preset an energy-saving threat value threshold, compare the energy-saving threat value with the energy-saving threat value threshold, and determine whether to take manual intervention.

[0026] In this embodiment, the implementation of the collection and evaluation module includes the following specific steps: first, the indoor area is divided into n sub-areas according to the spatial layout, and the area of ​​a single sub-area is obtained, where the area of ​​the i-th sub-area is , within the preset collection time T of this cycle, for a single sub-area i, collect the number of people in the i-th sub-area , the number of people entering the i-th sub-area , the number of people leaving the i-th sub-area , perform a flow intensity assessment, the calculation formula for the flow intensity assessment is: ;in, is the flow intensity value of the ith sub-area, is the flow density of people in the ith sub-area, is the flow rate of people in and out of the ith sub-area, , are the influencing factors of crowd density and crowd in / out rate, , specific , The value is set by technicians in this field according to actual needs; then, within the preset collection time T of this collection cycle, for a single sub-area i, the personnel stay time in the i-th sub-area is collected. , and the personnel retention status evaluation is performed, and the calculation formula for the personnel retention status evaluation is: ;in, is the personnel retention heat value of the i-th sub-area, is the residence time of the jth person in the i-th sub-area; further, within the preset collection time T of this collection cycle, for a single sub-area i, the number of equipment running in the i-th sub-area is collected , Current power of a single device , Maximum rated power of a single device , perform equipment usage status evaluation, the calculation formula for the equipment usage status evaluation is: ;in, The device usage status value for the i-th sub-area, is the current power of the kth device in the i-th sub-area, is the maximum rated power of the kth device in the i-th sub-area, is the importance weight of the kth device in the ith sub-area, and the specific value of the importance weight is determined by those skilled in the art based on a large number of experiments.

[0027] In this embodiment, the implementation of the collection and evaluation module further includes: calculating the refrigeration threat coefficients of different indoor sub-areas in combination with the evaluation results, and the calculation formula of the refrigeration threat coefficient is: ; in, is the cooling threat coefficient of the ith sub-region, , , They are the influencing factors of the flow intensity value, the personnel retention heat value, and the equipment usage status value. In this embodiment, , , The values ​​are 0.4, 0.3, and 0.3 respectively.

[0028] In this embodiment, the implementation of the mode prediction module includes the following specific steps: first, the historical passenger flow intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information and historical operation mode label of the ith sub-area in the same season historical cycle are obtained; the activity calendar information is specifically divided into promotional weekdays, ordinary shopping days, promotional holidays and ordinary holidays; the operation mode is specifically divided into high load mode, medium load mode and low load mode; then, the historical passenger flow intensity value, historical personnel retention heat value, historical equipment usage status value and historical activity calendar information of the ith sub-area in the same season historical cycle are feature extracted and combined into the form of feature vectors to construct a sub-area operation mode prediction model, and the sub-area operation model The prediction model takes the set of all groups of feature vectors as input, the predicted operation mode label corresponding to each group of feature vectors as output, the actual operation mode label corresponding to each group of feature vectors as the prediction target, and minimizes the sum of squares of the difference between the predicted operation mode label and the actual operation mode label as the training target. The sub-region operation mode prediction model is trained until the sum of squares of the difference between the predicted operation mode label and the actual operation mode label reaches convergence, and the training is stopped, and the predicted operation mode label of the i-th sub-region is output; the sub-region operation mode prediction model is any one of the classification models; further, according to the operation mode prediction result of the i-th sub-region, the target refrigeration temperature range of the next cycle is set for the i-th sub-region ; The minimum value of the target refrigeration temperature range for the next cycle is the average of the minimum value of the target cooling temperature range under this operation mode in the historical cycle of the same season in the i-th sub-area, and the maximum value of the target cooling temperature range is the average of the maximum values ​​in the target cooling temperature range under this operation mode in the i-th sub-area in the same seasonal historical cycle; finally, repeat the above steps until n sub-areas are traversed.

[0029] In this embodiment, the implementation of the threat calculation module includes the following specific steps: first, extract the historical flow intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information, historical operation mode label and historical temperature data change curve of the ith sub-area in the same season historical period to build a sub-area temperature prediction model, divide these data into 70% training set and 30% test set, and train the parameters of the sub-area temperature prediction model to build the input of the historical flow intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information of the ith sub-area. , historical operation mode labels, output as a sub-area temperature prediction model of the time-varying curve of the temperature data of the ith sub-area, use 70% of the training set to train the sub-area temperature prediction model to obtain the initial sub-area temperature prediction model, use 30% of the coefficient test set to test the initial sub-area temperature prediction model, and output the initial sub-area temperature prediction model that satisfies the optimal accuracy of the curve of the actual indoor temperature data changing over time as the final sub-area temperature prediction model; the sub-area temperature prediction model is an LSTM neural network model, which predicts the time-varying curve of the temperature data of the next cycle of the ith sub-area. Then, extract the output of the time-varying curve of the temperature data of the next cycle of the ith sub-area, and compare it with the target cooling temperature range set for the next cycle When the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, When the target cooling temperature range is Cooling is performed when the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range When the temperature data change curve of the next cycle is predicted, the temperature farthest from the target cooling temperature range is extracted. Temperature value , calculate the energy-saving threat value.

[0030] In this embodiment, the calculation formula of the energy saving threat value is: ; in, is the energy-saving threat value of the i-th sub-area.

[0031] In this embodiment, the specific content of adjusting the intervention module is: presetting the energy-saving threat value threshold , the energy-saving threat value of the i-th sub-area Threshold value for energy saving For comparison, if and only if the energy-saving threat value of the i-th sub-area Greater than or equal to the energy saving threat value threshold When the error occurs, manual intervention is taken.

[0032] The above-mentioned parameters and steps for each unit module to realize the corresponding functions in the energy-saving control system of the air-conditioning refrigeration unit based on the intelligent algorithm of the present invention can refer to the parameters and steps in the embodiment of the energy-saving control method of the air-conditioning refrigeration unit based on the intelligent algorithm in Example 1 above.

[0033] Example 3 This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned air-conditioning refrigeration unit energy-saving control method based on the intelligent algorithm by calling the computer program stored in the memory.

[0034] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the air-conditioning refrigeration unit energy-saving control method based on intelligent algorithms provided in the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as wired or wireless network interfaces and input and output interfaces for data input and output. This embodiment will not be described in detail here.

[0035] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as a "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0036] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0037] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowchart and block diagram, as well as the combination of processes and blocks in the flowchart 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 flowcharts. Figure 1 Process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0038] 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 Process or multiple processes and boxes Figure 1 A step that specifies a function in one or more boxes.

[0039] 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 control method for air-conditioning refrigeration units based on intelligent algorithms, characterized in that: The specific steps include: S1. Monitor the flow of people, equipment usage and temperature data of different sub-areas in the room during this period; S2. Evaluate the flow intensity, personnel retention and equipment usage status based on the flow data and equipment usage status, and calculate the cooling threat coefficient of different indoor sub-areas in this cycle based on the evaluation results; S3. Based on the evaluation results of different indoor sub-areas in this cycle and combined with the activity calendar information, a sub-area operation mode prediction model is constructed to predict the operation modes of different indoor sub-areas in the next cycle, and the target cooling temperature range for different sub-areas in the next cycle is set; S4, extracting the temperature data of different sub-areas in the room in this cycle, constructing a sub-area temperature prediction model, predicting the temperature data change curve of different sub-areas in the next cycle and comparing it with the target cooling temperature range set for the next cycle, when the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, cooling is performed according to the target cooling temperature range, and when the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range, calculating the energy-saving threat value; S5. Preset an energy-saving threat value threshold, compare the energy-saving threat value with the energy-saving threat value threshold, and determine whether to take manual intervention.

2. The energy-saving control method for air-conditioning refrigeration units based on intelligent algorithm according to claim 1 is characterized in that: The S2 comprises the following specific steps: S21, divide the indoor area into n sub-areas according to the spatial layout, and obtain the area of ​​a single sub-area, where the area of ​​the i-th sub-area is , within the preset collection time T of this cycle, for a single sub-area i, collect the number of people in the i-th sub-area , the number of people entering the i-th sub-area , the number of people leaving the i-th sub-area , perform a flow intensity assessment, the calculation formula for the flow intensity assessment is: ;in, is the flow intensity value of the ith sub-area, is the flow density of people in the ith sub-area, is the flow rate of people in and out of the ith sub-area, , are the influencing factors of crowd density and crowd in / out rate, ; S22: within the preset collection time T of this collection cycle, for a single sub-area i, collect the personnel stay time in the i-th sub-area , and the personnel retention status evaluation is performed, and the calculation formula for the personnel retention status evaluation is: ;in, is the personnel retention heat value of the i-th sub-area, is the residence time of the jth person in the i-th sub-area; S23. Within the preset collection time T of this collection cycle, for a single sub-area i, collect the number of running devices in the i-th sub-area , Current power of a single device , Maximum rated power of a single device , perform equipment usage status evaluation, the calculation formula for the equipment usage status evaluation is: ;in, The device usage status value for the i-th sub-area, is the current power of the kth device in the i-th sub-area, is the maximum rated power of the kth device in the i-th sub-area, is the importance weight of the kth device in the i-th sub-area.

3. The energy-saving control method for air-conditioning refrigeration units based on intelligent algorithm according to claim 2 is characterized in that: The step S2 further includes: calculating the refrigeration threat coefficients of different indoor sub-areas in combination with the evaluation results, wherein the calculation formula of the refrigeration threat coefficients is: ； in, is the cooling threat coefficient of the ith sub-region, , , They are the influencing factors of the flow intensity value, the personnel retention heat value, and the equipment usage status value. .

4. The energy-saving control method for air-conditioning refrigeration units based on intelligent algorithm according to claim 3 is characterized in that: The S3 includes the following specific steps: S31, obtaining the historical flow intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information and historical operation mode label of the i-th sub-area in the same season historical cycle; the activity calendar information is specifically divided into promotional weekdays, ordinary shopping days, promotional holidays and ordinary holidays; the operation mode is specifically divided into high load mode, medium load mode and low load mode; S32, extracting features from the historical flow intensity values, historical personnel retention heat values, historical equipment usage status values ​​and historical activity calendar information of the ith sub-region in the same season historical cycle and combining them into the form of feature vectors, constructing a sub-region operation mode prediction model, wherein the sub-region operation mode prediction model takes the set of all groups of feature vectors as input, takes the predicted operation mode label corresponding to each group of feature vectors as output, takes the actual operation mode label corresponding to each group of feature vectors as the prediction target, takes minimizing the sum of squares of the difference between the predicted operation mode label and the actual operation mode label as the training target, trains the sub-region operation mode prediction model, stops training when the sum of squares of the difference between the predicted operation mode label and the actual operation mode label reaches convergence, and outputs the predicted operation mode label of the ith sub-region; the sub-region operation mode prediction model is any one of the classification models; S33: According to the prediction result of the operation mode of the ith sub-region, the target cooling temperature range of the next cycle is set for the ith sub-region ; The minimum value of the target refrigeration temperature range for the next cycle is the average of the minimum value of the target cooling temperature range under this operation mode in the historical cycle of the same season in the i-th sub-area, and the maximum value of the target cooling temperature range is the average of the maximum values ​​in the target cooling temperature range under this operation mode in the i-th sub-area in the same seasonal historical cycle; repeat the above steps until n sub-areas are traversed.

5. The energy-saving control method for air-conditioning refrigeration units based on intelligent algorithm according to claim 4 is characterized in that: The S4 comprises the following specific steps: S41. Extract the historical crowd intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information, historical operation mode label and historical temperature data change curve over time of the i-th sub-area in the historical cycle of the same season to construct a sub-area temperature prediction model, divide these data into 70% training set and 30% test set, perform parameter training on the sub-area temperature prediction model to construct a sub-area temperature prediction model with input as the historical crowd intensity value, historical personnel retention heat value, historical equipment usage status value, historical activity calendar information and historical operation mode label of the i-th sub-area, and output as the temperature data change curve of the i-th sub-area, train the sub-area temperature prediction model with 70% training set to obtain an initial sub-area temperature prediction model, test the initial sub-area temperature prediction model with 30% coefficient test set, and output the initial sub-area temperature prediction model that meets the optimal accuracy of the indoor actual temperature data change curve over time as the final sub-area temperature prediction model; the sub-area temperature prediction model is an LSTM neural network model, which predicts the temperature data change curve of the next cycle of the i-th sub-area over time.

6. The energy-saving control method for air-conditioning refrigeration units based on intelligent algorithm according to claim 5 is characterized in that: The S4 further comprises: S42: extract the temperature data of the next cycle of the i-th sub-area and change the time curve, and set the target refrigeration temperature range of the next cycle When the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, When the target cooling temperature range is Cooling is performed when the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range When the temperature data change curve of the next cycle is predicted, the temperature farthest from the target cooling temperature range is extracted. Temperature value , calculate the energy-saving threat value.

7. The energy-saving control method for air-conditioning refrigeration units based on intelligent algorithm according to claim 6 is characterized in that: The calculation formula of the energy saving threat value in S42 is: ； in, is the energy-saving threat value of the i-th sub-area.

8. The energy-saving control method for air-conditioning refrigeration units based on intelligent algorithm according to claim 7 is characterized in that: The specific content of S5 is: preset energy-saving threat value threshold , the energy-saving threat value of the i-th sub-area Threshold value for energy saving For comparison, if and only if the energy-saving threat value of the i-th sub-area Greater than or equal to the energy saving threat value threshold When the error occurs, manual intervention is taken.

9. An air-conditioning refrigeration unit energy-saving control system based on an intelligent algorithm, which is implemented based on the air-conditioning refrigeration unit energy-saving control method based on an intelligent algorithm as described in any one of claims 1 to 8, characterized in that: The system includes: a collection and evaluation module, a pattern prediction module, a threat calculation module, and an adjustment and intervention module; The acquisition and evaluation module is used to monitor the human flow data, equipment usage status data and temperature data of different indoor sub-areas in this cycle; perform human flow intensity evaluation, personnel retention status evaluation and equipment usage status evaluation based on the human flow data and equipment usage status data, and calculate the refrigeration threat coefficient of different indoor sub-areas in this cycle based on the evaluation results; The mode prediction module is used to construct a sub-region operation mode prediction model based on the evaluation results of different indoor sub-regions in the current cycle and in combination with the activity calendar information, predict the operation modes of different indoor sub-regions in the next cycle, and set the target cooling temperature range for different sub-regions in the next cycle; The threat calculation module is used to extract the temperature data of different sub-areas in the room in this cycle, build a sub-area temperature prediction model, predict the temperature data change curve of different sub-areas in the next cycle and compare it with the target cooling temperature range set for the next cycle. When the predicted temperature data change curve of the next cycle does not exceed the target cooling temperature range, cooling is performed according to the target cooling temperature range. When the predicted temperature data change curve of the next cycle exceeds the target cooling temperature range, the energy-saving threat value is calculated; The adjustment intervention module is used to preset an energy-saving threat value threshold, compare the energy-saving threat value with the energy-saving threat value threshold, and determine whether to take manual intervention.

Images