Multi-zone temperature adjusting system for central air conditioner

Abstract

The invention discloses a multi-area temperature adjusting system for a central air conditioner, relates to the technical field of air conditioner control, and solves the problems that the air conditioner temperature cannot well adapt to environmental requirements due to the fact that the influence of the number of people existing in an area and the time length of people existing on air conditioner temperature adjustment is not considered in the prior art. The temperature adjusting efficiency of the air conditioner is low; and resources are wasted. An aging coefficient is generated according to historical equipment working data; predicting an air conditioner starting time label and equipment preset temperature through the air conditioner prediction model; obtaining a people number label and an age label according to the people identification model, generating decision data, and generating an adjustment preset temperature according to the decision data; the equipment temperature is generated according to the aging coefficient and the adjustment preset temperature, the aging influence of the air conditioner equipment is considered, the number change and the age label are acquired for multiple times within the updating duration range, resource waste caused by air conditioner temperature updating due to temporary occurrence of people is avoided, and the temperature adjustment efficiency of the air conditioner is improved.

Description

Technical Field

[0001] The present application belongs to the field of air conditioning control technology, and specifically is a multi-zone temperature adjustment system for central air conditioning. Background Art

[0002] Traditional central air conditioning systems often use centralized control and unified air supply, which makes it difficult to meet the differentiated needs of different areas for environmental parameters such as temperature and humidity. In addition, this control method often leads to serious energy waste, especially when some areas require lower or higher temperatures, the entire system still needs to maintain a unified operating state.

[0003] The prior art (invention patent application with publication number CN112762579A) discloses a control method for an air-conditioning system, including: dividing a room into multiple areas, and calculating the room load based on the initial ambient temperatures of the multiple areas, refining the load size of each area in the room, and accurately calculating the room load value corresponding to the room as a whole. Based on the difference between the room load value and the preset load, the difference between the current temperature of the room and the expected temperature can be accurately determined, thereby improving the accuracy of the temperature adjustment requirements in the room, so that the actual operation requirements of the air-conditioning system can be more accurately obtained, so that the initial opening of the electronic expansion valve is more matched with the actual operation requirements of the air-conditioning system.

[0004] The above scheme calculates the room load according to the initial ambient temperature in the multiple zones, calculates the difference between the room load and the preset load, and determines the initial opening of the electronic expansion valve of the air conditioning system according to the difference, thereby achieving the function of adjusting the air conditioning temperature. However, the above scheme takes into account the impact of ambient temperature on air conditioning regulation, but lacks consideration of the impact of the number of people in the zone and the duration of their presence on air conditioning temperature regulation, so that the air conditioning temperature cannot adapt well to environmental requirements, resulting in low efficiency of air conditioning temperature regulation and even waste of resources; therefore, the multi-zone temperature regulation system of central air conditioning still needs further improvement. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a multi-zone temperature control system for central air conditioning, which is used to solve the technical problem that the prior art lacks consideration of the impact of the number of people in the area and the length of time people are present on the temperature control of the air conditioner, making the air conditioner temperature unable to adapt well to environmental requirements, resulting in low efficiency of air conditioner temperature control and waste of resources.

[0006] To achieve the above-mentioned purpose, the first aspect of the present application provides a multi-zone temperature adjustment system for a central air conditioner, comprising: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0007] The data acquisition module: acquires environmental data and personnel data through a data acquisition device; and performs image preprocessing on personnel images in the personnel data to obtain preprocessed personnel images; the environmental data includes seasonal data, external environmental temperature, and regional environmental temperature of several regions;

[0008] The data analysis module: obtains historical equipment working data, generates an aging coefficient of the equipment in the corresponding area according to the historical equipment working data; obtains several historical equipment preset temperatures, historical environmental data and their corresponding time tags, and predicts the time tag and equipment preset temperature of the corresponding area when the air conditioner is turned on through the air conditioning prediction model; obtains several images of people within the air conditioning update time, and inputs the images of people into the personnel recognition model to obtain the corresponding number of people tags and age tags; generates decision data according to several number of people tags and age tags; generates an adjusted preset temperature according to the decision data; generates the equipment temperature according to the aging coefficient and the adjusted preset temperature; generates an alarm signal according to the aging coefficient;

[0009] The control module: adjusts the corresponding area equipment of the central air conditioner to the equipment temperature;

[0010] The early warning module: issues an alarm prompt according to the alarm signal and contacts the management personnel.

[0011] The present application generates an aging coefficient of equipment in the corresponding area according to historical equipment working data; predicts the time label of turning on the air conditioner and the equipment preset temperature in the corresponding area through an air conditioning prediction model; inputs a person image into a person recognition model to obtain a corresponding number of people label and age label; generates decision data according to a number of number of people labels and age labels; generates an adjusted preset temperature according to the decision data; generates the equipment temperature according to the aging coefficient and the adjusted preset temperature; generates an alarm signal according to the aging coefficient, takes into account the impact of aging of the air conditioning equipment, obtains the number of people change and the corresponding age label multiple times within the update time range, avoids the waste of resources caused by the short-term appearance of people causing the air conditioning temperature to be updated, and improves the temperature regulation efficiency of the air conditioner.

[0012] Furthermore, the image preprocessing includes image denoising and image enhancement.

[0013] Furthermore, the generating of the aging coefficient of the equipment in the corresponding area according to the historical equipment working data includes:

[0014] Obtain several historical equipment working data of each area; the historical equipment working data includes high-load operation time GTi and its corresponding operating temperature GWi and operating humidity GSi, low-load operation time DTj and its corresponding operating temperatures DWj and DSj; the high-load operation time refers to the operation time when the air conditioner exceeds n% of the normal operating load upper limit; the low-load operation time refers to the operation time when the air conditioner is lower than (100-n)% of the normal operating load upper limit, where 0 <n<100;

[0015] Generate corresponding environmental impact coefficients GHYXi and DHYXj according to the working temperature and working humidity corresponding to each operating time;

[0016] Calculate the aging factor LX of the corresponding equipment through the formula;

[0017] LX=g×arctan(α1×∑(GTi / DGT×(1+GHYXi))+α2×∑(DTj / DGT×(1+DHYXj))); wherein g is the proportional coefficient, g∈(0,2 / π), α1 and α2 are weight coefficients, α1 and α2∈(0,1), and α2<α1; DGT is the unit duration; i represents the number of the high-load operating time, i=1, 2,…, M, where M is the total number of high-load operating time; j represents the number of the low-load operating time, j=1, 2,…, Q, where Q is the total number of low-load operating time.

[0018] Furthermore, the corresponding environmental impact coefficients GHYXi and DHYXj are generated according to the working temperature and working humidity corresponding to each operating time, including:

[0019] Obtain the working temperature GWi and working humidity GSi corresponding to the high-load operation time, the working temperatures DWj and DSj corresponding to the low-load operation time, and the optimum working temperature W and the optimum working humidity S;

[0020] Calculate the temperature influence coefficients GWYXi and DWYXj by the formula;

[0021] GWYXi=1-exp(-(|GWi-W| / DW)^βw);

[0022] DWYXj=1-exp(-(|DWj-W| / DW)^βw);

[0023] Calculate the humidity influence coefficients GSYXi and DSYXj by the formula;

[0024] GSYXi=1-exp(-(|GSi-S| / DS)^βs);

[0025] DSYXj=1-exp(-(|DSj-S| / DS)^βs);

[0026] Calculate the environmental impact coefficients GHYXi and DHYXj through the formula;

[0027] GHYXi=α3×GWYXi+α4×GSYXi;

[0028] DHYXj=α3×DWYXj+α4×DSYXj; wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1); DW is unit temperature, DS is unit humidity, βs and βw are exponential coefficients, βs and βw∈(0,1).

[0029] Furthermore, the air conditioning prediction model is constructed by a time series prediction model, including:

[0030] Obtain several historical equipment preset temperatures, historical environmental data and their corresponding time tags;

[0031] Performing data preprocessing on a number of historical equipment preset temperatures, historical environmental data and their corresponding time tags to obtain a number of preprocessed historical equipment preset temperatures, historical environmental data and their corresponding time tags;

[0032] Integrate the historical equipment preset temperature and historical environment data with the same time tag into a time feature vector;

[0033] Integrate each time feature vector into several prediction sequences according to the order of time labels;

[0034] Divide several prediction sequences into training set, test set and validation set in chronological order;

[0035] Select the LSTM model as the base model;

[0036] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0037] By verifying the pre-trained model on the test set, we finally get the input as environmental data and the output as time label and its corresponding preset temperature of the equipment.

[0038] Furthermore, the data preprocessing includes data cleaning and data standardization.

[0039] Furthermore, the personnel recognition model is constructed by an artificial intelligence model, including:

[0040] Get historical person images and their corresponding number labels and age labels;

[0041] Divide a number of historical personnel images and their corresponding number labels and age labels into training data, verification data and test data; perform image preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0042] Select an AI model as the base model;

[0043] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0044] By verifying the pre-trained model on the test set, we finally obtain a personnel model whose input is personnel images and outputs number labels and age labels.

[0045] Furthermore, the generating of decision data according to a plurality of number labels and age labels includes:

[0046] Obtain several number of headcount labels and their corresponding age labels within the air conditioner update duration; the age labels include old and young labels and young and adult labels;

[0047] By formula Calculate the number of people JR determined within the update time; where t represents the number of times data is obtained within the update time, t = 1, 2, ..., N; N represents the total number of times; is the round-up symbol;

[0048] Extract the total number of people LYR corresponding to the old and young labels and the total number of people ZR corresponding to all labels during the air conditioner update time;

[0049] The number of people LYJR corresponding to the old and young labels in the population is determined by the formula;

[0050]

[0051] The number of people QCJR corresponding to the youth label in the determined population is calculated through the formula QCJR=JR-LYJR;

[0052] The number of decision persons and their corresponding age labels are integrated into decision data.

[0053] The present application obtains multiple data within the update time range, considers the comprehensive data of the multiple data to generate decision data, and controls and updates the air conditioner in the corresponding area based on the decision data, thereby avoiding the problem of mismatched effects after the air conditioner temperature is updated due to the fact that a person happens to pass by when collecting data at a certain moment and the person only exists for a short moment, thereby avoiding waste of resources and improving the temperature regulation efficiency of the air conditioner in the corresponding area.

[0054] Further, the step of adjusting the preset temperature according to the determination data includes:

[0055] Obtain the number of decision persons JR in the decision data and their corresponding age labels and the device preset temperature YW;

[0056] When several age labels are all old and young labels; determine whether the number of people is greater than the old and young threshold LYRY; if yes, calculate and adjust the preset temperature TYW through the formula TYW=YW-k1×arctan(JR-LYRY); if no, when the number of people is greater than the threshold RY, calculate and adjust the preset temperature TYW through the formula TYW=YW+k1×exp(-(JR-RY)); otherwise, TYW=LYZW; where k1 is the temperature coefficient, k1>1; LYZW represents the optimal temperature of the air conditioner required by the old and young;

[0057] When several age labels are all young adult labels; determine whether the number of people is greater than the number threshold RY; if yes, calculate and adjust the preset temperature TYW through the formula TYW=YW-k2×arctan(JR-RY); if no, do nothing; where k2 is the temperature coefficient, k2>1;

[0058] Otherwise, when the determined number of people is less than the threshold value LYRY for the number of the elderly and children, the adjusted preset temperature TYW is calculated by the formula TYW=YW+k3×exp(-LYJR); otherwise, the adjusted preset temperature TYW is calculated by the formula TYW=YW-k3×arctan(JR-LYRY)×exp(-(LYJR-LYRY)); wherein k3 is the temperature coefficient, k3>1.

[0059] This application calculates the number of young and adult tags and old and child tags in the area. When old and child tags exist, the physical condition of the old and child tags is considered as the priority. Since the physical health of the old and young people has a higher impact on the temperature than that of young and adult people, over-adjusting the temperature so that the old and young people feel uncomfortable and catch a cold is avoided. This provides a good temperature environment for the old and young people and improves their comfort and health level.

[0060] Further, generating the device temperature according to the aging coefficient and adjusting the preset temperature includes:

[0061] Obtain the aging coefficient LX and adjust the preset temperature TYW;

[0062] Calculate the equipment temperature SW of the equipment in the corresponding area through the formula;

[0063] SW=TYW / ((1-LX^(1+β)); where β is the exponential coefficient, β∈(0,1).

[0064] Further, generating an alarm signal according to the aging coefficient includes:

[0065] Obtain the aging coefficients of equipment in several areas;

[0066] Determine whether a number of aging coefficients are greater than aging thresholds;

[0067] Yes, generate an air conditioner aging alarm signal;

[0068] No, determine whether the aging coefficient is greater than D times the aging threshold; yes, generate an air conditioner aging warning signal; no, do nothing; D is the proportional coefficient, D∈(0,1).

[0069] Compared with the prior art, the beneficial effects of this application are:

[0070] 1. The present application generates an aging coefficient of equipment in the corresponding area according to historical equipment working data; predicts the time label and equipment preset temperature of turning on the air conditioner in the corresponding area through an air conditioning prediction model; inputs a person image into a person recognition model to obtain a corresponding number of people label and age label; generates decision data according to a number of number of people labels and age labels; generates an adjusted preset temperature according to the decision data; generates equipment temperature according to the aging coefficient and the adjusted preset temperature; generates an alarm signal according to the aging coefficient, takes into account the impact of aging of the air conditioning equipment, obtains changes in the number of people and corresponding age labels multiple times within the update time range, avoids the waste of resources caused by the short-term presence of people causing the air conditioning temperature to be updated, and improves the temperature regulation efficiency of the air conditioner.

[0071] 2. The present application obtains data multiple times within the update time range, considers the comprehensive data of the multiple data to generate decision data, and uses the decision data to control and update the air conditioner in the corresponding area, thereby avoiding the problem of mismatched effects after the air conditioner temperature is updated due to the fact that a person happens to pass by when collecting data at a certain moment and the person only exists for a short moment. This avoids waste of resources and improves the temperature regulation efficiency of the air conditioner in the corresponding area.

[0072] 3. This application calculates the number of young and adult tags and old and child tags in the area. When old and child tags exist, the physical condition of the old and child tags is considered as the focus. Since the physical health of the old and young people has a higher impact on the temperature than that of young and adult people, excessive temperature adjustment that makes the old and young people feel uncomfortable and cause colds is avoided. A good temperature environment is provided for the old and young people, which improves their comfort and health level. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0074] Figure 1This is a schematic diagram of the principle of a multi-zone temperature control system for central air conditioning in the present application;

[0075] Figure 2 This is a flow chart of a multi-zone temperature control system for central air conditioning in the present application. DETAILED DESCRIPTION

[0076] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0077] See also Figure 1-Figure 2 , the first aspect of the present application provides a multi-zone temperature adjustment system for a central air conditioner, including: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0078] Data acquisition module: obtains environmental data and personnel data through data acquisition equipment, which includes high-precision cameras, corresponding sensors, etc., and performs image preprocessing on personnel images in the personnel data to obtain preprocessed personnel images; environmental data includes seasonal data, external environmental temperature, and regional environmental temperature of several areas;

[0079] Data analysis module: obtain historical equipment working data, generate the aging coefficient of the equipment in the corresponding area based on the historical equipment working data, and the aging coefficient refers to the degree of aging of the air-conditioning equipment; obtain several historical equipment preset temperatures, historical environmental data and their corresponding time tags, and predict the time tag and equipment preset temperature of the corresponding area when the air-conditioning is turned on through the air-conditioning prediction model. The equipment preset temperature is the initial optimal temperature when an adult turns on the air-conditioning; obtain several images of people within the air-conditioning update time, and input the images of people into the person recognition model to obtain the corresponding number of people labels and age labels; generate decision data based on several number of people labels and age labels, and the decision data refers to the data that determines the air-conditioning update; generate an adjusted preset temperature based on the decision data, and the adjusted preset temperature is the air-conditioning temperature generated based on the equipment preset temperature according to the decision data, that is, the temperature blown out by the air-conditioning; generate the equipment temperature based on the aging coefficient and the adjusted preset temperature, and the equipment temperature refers to the input temperature value of the equipment; generate an alarm signal based on the aging coefficient;

[0080] Control module: adjust the corresponding area equipment of the central air conditioner to the equipment temperature;

[0081] Early warning module: issues an alarm prompt based on the alarm signal and contacts the management personnel. The alarm signal includes the air conditioner aging alarm signal and the air conditioner aging early warning signal.

[0082] In this embodiment, the aging coefficient of the equipment in the corresponding area is generated according to the historical equipment operation data; the time label for turning on the air conditioner and the preset temperature of the equipment in the corresponding area are predicted through the air conditioner prediction model; the personnel image is input into the personnel recognition model to obtain the corresponding number label and age label; the decision data is generated according to a number of number labels and age labels; the preset temperature is adjusted according to the decision data; the equipment temperature is generated according to the aging coefficient and the adjusted preset temperature; and the alarm signal is generated according to the aging coefficient. Considering the influence of the aging of the air conditioner equipment, the change in the number of people and the corresponding age labels are obtained multiple times within the update duration range, avoiding resource waste caused by the update of the air conditioner temperature due to the short-term appearance of personnel, and improving the temperature adjustment efficiency of the air conditioner.

[0083] Image preprocessing, including image denoising and image enhancement;

[0084] Image denoising: Perform denoising processing on the personnel image, and select the median filtering method to remove the noise in the image to obtain the denoised image;

[0085] Image enhancement: Perform enhancement processing on the denoised image after denoising, and improve the clarity and contrast of the denoised image through the contrast enhancement method to obtain the detected image after preprocessing.

[0086] Generating the aging coefficient of the equipment in the corresponding area according to the historical equipment operation data includes:

[0087] Obtain a number of historical equipment operation data for each area; the historical equipment operation data includes the high-load operation duration GTi and its corresponding working temperature Wi and working humidity Si, and the low-load operation duration DTj and its corresponding working temperature Wj and Sj; the high-load operation duration refers to the operation duration when the air conditioner exceeds n% of the upper limit of the normal operation load; the low-load operation duration refers to the operation duration when the air conditioner is lower than (100 - n)% of the upper limit of the normal operation load, where 0 < n < 100, and the specific value is set according to experience. In this embodiment, n is set to 90;

[0088] Generate the corresponding environmental impact coefficients GHYXi and DHYXj according to the working temperature and working humidity corresponding to each operation duration;

[0089] Calculate the aging coefficient LX of the corresponding equipment through the formula;

[0090] LX=g×arctan(α1×∑(GTi / DGT×(1+GHYXi))+α2×∑(DTj / DGT×(1+DHYXj))); where g is the proportionality coefficient, g∈(0,2 / π), and the specific value is set according to experience. The setting of g is to make the aging coefficient LX∈(0,1); α1 and α2 are weight coefficients, α1 and α2∈(0,1), and α2<α1, and the specific value is set according to experience; the longer the high-load operation time, the greater the impact of air conditioning aging, so the weight coefficient corresponding to the high-load operation time is set to The weight coefficient is set to be larger; DGT is the unit time, and the specific value is set according to experience. In this embodiment, DGT is set to 1 day; i represents the number of the high-load operation time, i=1, 2,..., M, M is the total number of high-load operation time; j represents the number of the low-load operation time, j=1, 2,..., Q, Q is the total number of low-load operation time; the longer the operation time, the greater the environmental impact coefficient during operation, and the more serious the aging of the air conditioner; as the air conditioner runs longer under different loads and the environmental coefficient becomes larger, the aging coefficient of the air conditioner will also increase accordingly.

[0091] The corresponding environmental impact coefficients GHYXi and DHYXj are generated according to the working temperature and working humidity corresponding to each operating time, including:

[0092] Obtain the working temperature GWi and working humidity GSi corresponding to the high-load operation time, the working temperatures DWj and DSj corresponding to the low-load operation time, and the optimum working temperature W and the optimum working humidity S;

[0093] Calculate the temperature influence coefficients GWYXi and DWYXj by the formula;

[0094] GWYXi=1-exp(-(|GWi-W| / DW)^βw);

[0095] DWYXj=1-exp(-(|DWj-W| / DW)^βw); The more the temperature deviates from the optimum working temperature, the more serious the impact of temperature on air conditioner aging will be, so the temperature anomaly coefficient will increase accordingly;

[0096] Calculate the humidity influence coefficients GSYXi and DSYXj by the formula;

[0097] GSYXi=1-exp(-(|GSi-S| / DS)^βs);

[0098] DSYXj=1-exp(-(|DSj-S| / DS)^βs); The more the humidity deviates from the optimum working humidity, the more serious the effect of humidity on air conditioner aging will be, so the humidity anomaly coefficient will increase accordingly;

[0099] Calculate the environmental impact coefficients GHYXi and DHYXj through the formula;

[0100] GHYXi=α3×GWYXi+α4×GSYXi;

[0101] DHYXj=α3×DWYXj+α4×DSYXj; wherein, α3 and α4 are weight coefficients, α3 and α4∈(0,1), and specific values ​​are set according to experience; DW is unit temperature, DS is unit humidity, and specific values ​​are set according to experience. In this embodiment, DW is set to 1°C and DS is set to 1%; βs and βw are exponential coefficients, βs and βw∈(0,1), and specific values ​​are set according to experience; the more the working temperature and working humidity deviate from the normal values, the more severe the aging degree of the air-conditioning equipment will be, and as the temperature abnormality coefficient and the humidity abnormality coefficient increase, the aging coefficient of the air-conditioning equipment will also increase accordingly.

[0102] The air conditioning prediction model is constructed through the time series prediction model, including:

[0103] Obtain several historical equipment preset temperatures, historical environmental data and their corresponding time tags;

[0104] Performing data preprocessing on a number of historical equipment preset temperatures, historical environmental data and their corresponding time tags to obtain a number of preprocessed historical equipment preset temperatures, historical environmental data and their corresponding time tags;

[0105] Integrate the historical equipment preset temperature and historical environment data with the same time tag into a time feature vector;

[0106] Integrate each time feature vector into several prediction sequences according to the order of time labels;

[0107] Divide several prediction sequences into training set, test set and validation set in chronological order; the ratio between training set, test set and validation set is 7:2:1;

[0108] Select the LSTM model as the base model;

[0109] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0110] By verifying the pre-trained model on the test set, we finally get the input as environmental data and the output as time label and its corresponding preset temperature of the equipment.

[0111] Data preprocessing includes data cleaning and data standardization;

[0112] Data cleaning: directly remove missing values ​​in the acquired historical equipment preset temperature, historical environmental data and their corresponding time tags to obtain normal data;

[0113] Data standardization: Normal data is standardized using the maximum and minimum normalization method to obtain the preprocessed historical equipment preset temperature, historical environmental data and their corresponding time tags.

[0114] The person recognition model is built through an artificial intelligence model, including:

[0115] Obtain historical personnel images and their corresponding number labels and age labels; age labels include old and young labels and young and adult labels; old and young labels refer to labels corresponding to old and young personnel, which are composed of the elderly and infants; young and adult labels refer to labels corresponding to young and adult personnel, which are composed of teenagers and adults;

[0116] Several historical personnel images and their corresponding number labels and age labels are divided into training data, verification data and test data; the training data, verification data and test data are image preprocessed to obtain the training set, verification set and test set; the ratio between the training set, the test set and the verification set is 7:2:1;

[0117] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a BP neural network model and a RBF neural network model;

[0118] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0119] By verifying the pre-trained model on the test set, we finally obtain a personnel model whose input is personnel images and outputs number labels and age labels.

[0120] Generate decision data based on several number of labels and age labels, including:

[0121] Get several number of person labels and their corresponding age labels within the air conditioner update duration;

[0122] By formula Calculate the number of people JR determined within the update time; where t represents the number of times data is obtained within the update time, t = 1, 2, ..., N; N represents the total number of times; It is a round-up symbol, the purpose is to make the number of people determined to be an integer; when N is fixed, as the number of people labels obtained each time increases, the number of people determined will also increase;

[0123] Extract the total number of people LYR corresponding to the old and young labels and the total number of people ZR corresponding to all labels during the air conditioner update time;

[0124] The number of people LYJR corresponding to the old and young labels in the population is determined by the formula;

[0125] When the number of people JR and the total number ZR are determined, as the total number of old and young people increases, the number of people corresponding to the old and young labels in the number of people will also increase;

[0126] The number of people QCJR corresponding to the youth label in the decision number is calculated by the formula QCJR = JR-LYJR; the decision number is composed of the number of old and young people and the number of young adults. When the decision number is determined, the more old and young people there are, the fewer young adults there will be;

[0127] The number of decision persons and their corresponding age labels are integrated into decision data.

[0128] This embodiment obtains data multiple times within the update time range, considers the comprehensive data of the multiple data to generate decision data, and controls and updates the air conditioner in the corresponding area based on the decision data, thereby avoiding the problem of mismatched effects after the air conditioner temperature is updated due to a person passing by when collecting data at a certain moment, and the person only exists for a short moment, thereby avoiding waste of resources and improving the temperature regulation efficiency of the air conditioner in the corresponding area.

[0129] Generate and adjust preset temperature based on decision data, including:

[0130] Obtain the number of decision persons JR in the decision data and their corresponding age labels and the device preset temperature YW;

[0131] When several age labels are all old and young labels; determine whether the number of people is greater than the old and young threshold LYRY, which is set based on experience; if yes, the preset temperature TYW is calculated and adjusted by the formula TYW=YW-k1×arctan(JR-LYRY). When the number of old and young people is more, the temperature in the area will rise due to the excessive number of people, causing people to feel hotter. At this time, the air conditioning temperature needs to be lowered to meet the body's needs. Therefore, as the number of people increases, the preset temperature will be adjusted accordingly; No, when the number of people is greater than the threshold RY, the threshold is set based on experience, and the formula TYW=YW+k1×exp(-(JR-RY)) is used. Calculate and adjust the preset temperature TYW. Since the preset temperature of the equipment is set according to adults, and the air-conditioning temperature preferred by adults is lower than that preferred by the elderly and children, in a certain area, when the number of people exceeds the limit of the number of people in the area where the temperature remains unchanged, the air-conditioning temperature needs to be increased according to the number of people, and the more people there are, the smaller the increase will be; therefore, as the number of people increases, the preset temperature is adjusted to decrease; otherwise, TYW=LYZW; wherein k1 is the temperature coefficient, k1>1, the specific value is set according to experience, k1 is a coefficient with units, and in this embodiment, k1 is set to 2°C; LYZW represents the optimal temperature of the air-conditioning required by the elderly and children;

[0132] When several age labels are all young and adult labels; determine whether the number of people is greater than the threshold RY; if yes, calculate and adjust the preset temperature TYW through the formula TYW=YW-k2×arctan(JR-RY). When there are only young and adult people in the area, the more people there are, the higher the temperature in the area will be. Therefore, the air conditioning temperature needs to be lowered to meet the physical needs of the people. Therefore, as the number of people increases, the adjusted temperature will be lowered accordingly; if no, do nothing; where k2 is the temperature coefficient, k2>1, the specific value is set according to experience, and k2 is a coefficient with units, the unit is ℃;

[0133] Otherwise, when the number of people is less than the threshold value LYRY of the number of the elderly and children, the adjusted preset temperature TYW is calculated by the formula TYW=YW+k3×exp(-LYJR); as the number of the elderly and children increases, the adjusted preset temperature will be higher than the device preset temperature, but the increase will decrease accordingly; otherwise, the adjusted preset temperature TYW is calculated by the formula TYW=YW-k3×arctan(JR-LYRY)×exp(-(LYJR-LYRY)). The more people are decided, the higher the ambient temperature in the area will be. However, the more elderly and children there are, the more it is necessary to focus on the temperature requirements of the elderly and children, which will reduce the temperature drop. Therefore, when the number of people is determined, as the number of elderly and children increases, the adjusted preset temperature will be lower than the device preset temperature, but the drop will decrease accordingly; wherein, k3 is the temperature coefficient, k3>1, the specific value is set according to experience, k3 is a coefficient with units, and the unit is ℃.

[0134] This embodiment calculates the number of young and adult tags and old and child tags in the area. When old and child tags exist, the physical condition of the old and child tags is given priority consideration. Since the physical health of the old and young people has a higher impact on the temperature than that of young and adult people, over-adjusting the temperature so that the old and young people feel uncomfortable and catch a cold is avoided. A good temperature environment is provided for the old and young people, and their comfort and health level are improved.

[0135] Generates device temperatures based on aging factors and adjusts preset temperatures, including:

[0136] Obtain the aging coefficient LX and adjust the preset temperature TYW;

[0137] Calculate the equipment temperature SW of the equipment in the corresponding area through the formula;

[0138] SW=TYW / ((1-LX^(1+β)); where β is an exponential coefficient, β∈(0,1), and the specific value is set based on experience; as the aging coefficient increases, the device temperature will increase accordingly.

[0139] Generates alarm signals based on aging factors, including:

[0140] Obtain the aging coefficients of equipment in several areas;

[0141] Determine whether a number of aging coefficients are greater than an aging threshold; the aging threshold is set based on experience;

[0142] Yes, generate an air conditioner aging alarm signal;

[0143] No, determine whether the aging coefficient is greater than D times the aging threshold; Yes, generate an air conditioner aging warning signal; No, do nothing; D is the proportional coefficient, D∈(0,1), the specific value is set according to experience, and in this embodiment, D is set to 0.7.

[0144] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0145] The working principle of the present application is as follows: environmental data and personnel data are obtained through data acquisition equipment; and personnel images in the personnel data are preprocessed to obtain preprocessed personnel images; the aging coefficient of the equipment in the corresponding area is generated according to the historical equipment working data; the time label and equipment preset temperature of the air conditioner in the corresponding area are predicted by the air conditioning prediction model; several personnel images within the air conditioning update time are obtained, and the personnel images are input into the personnel recognition model to obtain the corresponding number of people labels and age labels; decision data is generated according to several number of people labels and age labels; the preset temperature is adjusted according to the decision data; the equipment temperature is generated according to the aging coefficient and the adjusted preset temperature; an alarm signal is generated according to the aging coefficient; the equipment in the corresponding area of ​​the central air conditioner is adjusted to the equipment temperature; an alarm prompt is issued according to the alarm signal, and the management personnel are contacted, considering the impact of the aging of the air conditioning equipment, and the number of people changes and the corresponding age labels are obtained multiple times within the update time range to avoid the waste of resources caused by the short-term appearance of personnel causing the air conditioning temperature update, thereby improving the temperature regulation efficiency of the air conditioner, and avoiding the problem that the existing technology lacks consideration of the impact of the number of people in the area and the duration of their presence on the air conditioning temperature regulation, so that the air conditioning temperature cannot adapt well to environmental requirements, resulting in low efficiency and waste of resources in the air conditioning temperature regulation.

[0146] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. A multi-zone temperature control system for central air conditioning, characterized in that: include: Data acquisition module, data analysis module, control module, early warning module and database; The data acquisition module: acquires environmental data and personnel data through a data acquisition device; and performs image preprocessing on personnel images in the personnel data to obtain preprocessed personnel images; the environmental data includes seasonal data, external environmental temperature, and regional environmental temperature of several regions; The data analysis module: obtains historical equipment working data, generates an aging coefficient of the equipment in the corresponding area according to the historical equipment working data; obtains several historical equipment preset temperatures, historical environmental data and their corresponding time tags, and predicts the time tag and equipment preset temperature of the corresponding area when the air conditioner is turned on through the air conditioning prediction model; obtains several images of people within the air conditioning update time, and inputs the images of people into the personnel recognition model to obtain the corresponding number of people tags and age tags; generates decision data according to several number of people tags and age tags; generates an adjusted preset temperature according to the decision data; generates the equipment temperature according to the aging coefficient and the adjusted preset temperature; generating an alarm signal based on the aging factor; The control module: adjusts the corresponding area equipment of the central air conditioner to the equipment temperature; The early warning module: issues an alarm prompt according to the alarm signal and contacts the management personnel.

2. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The image preprocessing includes image denoising and image enhancement.

3. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The step of generating the aging coefficient of the equipment in the corresponding area according to the historical equipment working data includes: Acquire some historical equipment working data of each area; the historical equipment working data includes high-load operation time GTi and its corresponding operating temperature Wi and working humidity Si, low-load operation time DTj and its corresponding operating temperatures Wj and Sj; Generate corresponding environmental impact coefficients HYXi and HYXj according to the working temperature and working humidity corresponding to each operating time; Calculate the aging factor LX of the corresponding equipment through the formula; LX=g×arctan(α1×∑(GTi / DGT×(1+GHYXi))+α2×∑(DTj / DGT×(1+DHYXj))); wherein g is the proportional coefficient, g∈(0,2 / π), α1 and α2 are weight coefficients, α1 and α2∈(0,1), and α2<α1; DGT is the unit duration; i represents the number of the high-load operating time, i=1, 2,…, M, where M is the total number of high-load operating time; j represents the number of the low-load operating time, j=1, 2,…, Q, where Q is the total number of low-load operating time.

4. A multi-zone temperature control system for central air conditioning according to claim 3, characterized in that: The corresponding environmental impact coefficients GHYXi and DHYXj are generated according to the working temperature and working humidity corresponding to each operating time, including: Obtain the working temperature GWi and working humidity GSi corresponding to the high-load operation time, the working temperatures DWj and DSj corresponding to the low-load operation time, and the optimum working temperature W and the optimum working humidity S; Calculate the temperature influence coefficients GWYXi and DWYXj by the formula; GWYXi=1-exp(-(|GWi-W| / DW)^βw); DWYXj=1-exp(-(|DWj-W| / DW)^βw); Calculate the humidity influence coefficients GSYXi and DSYXj by the formula; GSYXi=1-exp(-(|GSi-S| / DS)^βs); DSYXj=1-exp(-(|DSj-S| / DS)^βs); Calculate the environmental impact coefficients GHYXi and DHYXj through the formula; GHYXi=α3×GWYXi+α4×GSYXi; DHYXj=α3×DWYXj+α4×DSYXj; wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1); DW is unit temperature, DS is unit humidity, βs and βw are exponential coefficients, βs and βw∈(0,1).

5. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The air conditioning prediction model is constructed by a time series prediction model, including: Obtain several historical equipment preset temperatures, historical environmental data and their corresponding time tags; Performing data preprocessing on a number of historical equipment preset temperatures, historical environmental data and their corresponding time tags to obtain a number of preprocessed historical equipment preset temperatures, historical environmental data and their corresponding time tags; Integrate historical equipment preset temperature and historical environmental data with the same time tag into a time feature vector; Integrate each time feature vector into several prediction sequences according to the order of time labels; Divide several prediction sequences into training set, test set and validation set in chronological order; Select the LSTM model as the base model; Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally get the input as environmental data and the output as time label and its corresponding preset temperature of the equipment.

6. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The personnel recognition model is constructed by an artificial intelligence model, including: Get historical person images and their corresponding number labels and age labels; Divide a number of historical personnel images and their corresponding number labels and age labels into training data, verification data and test data; perform image preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain a personnel model whose input is personnel images and output is number labels and age labels.

7. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The generating of decision data according to a number of number labels and age labels includes: Obtain several number of headcount labels and their corresponding age labels within the air conditioner update duration; the age labels include old and young labels and young and adult labels; By formula Calculate the number of people JR determined within the update time; where t represents the number of times data is obtained within the update time, t = 1, 2, ..., N; N represents the total number of times; is the round-up symbol; Extract the total number of people LYR corresponding to the old and young labels and the total number of people ZR corresponding to all labels during the air conditioner update time; The number of people LYJR corresponding to the old and young labels in the population is determined by the formula; The number of people QCJR corresponding to the youth label in the determined population is calculated through the formula QCJR=JR-LYJR; The number of decision persons and their corresponding age labels are integrated into decision data.

8. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The step of generating and adjusting the preset temperature according to the decision data comprises: Obtain the number of decision persons JR in the decision data and their corresponding age labels and the device preset temperature YW; When several age labels are all old and young labels; determine whether the number of people is greater than the old and young threshold LYRY; if yes, calculate and adjust the preset temperature TYW through the formula TYW=YW-k1×arctan(JR-LYRY); if no, when the number of people is greater than the threshold RY, calculate and adjust the preset temperature TYW through the formula TYW=YW+k1×exp(-(JR-RY)); otherwise, TYW=LYZW; where k1 is the temperature coefficient, k1>1; LYZW represents the optimal temperature of the air conditioner required by the old and young; When several age labels are all young adult labels; determine whether the number of people is greater than the number threshold RY; if yes, calculate and adjust the preset temperature TYW through the formula TYW=YW-k2×arctan(JR-RY); if no, do nothing; where k2 is the temperature coefficient, k2>1; Otherwise, when the determined number of people is less than the threshold value LYRY for the number of the elderly and children, the adjusted preset temperature TYW is calculated by the formula TYW=YW+k3×exp(-LYJR); otherwise, the adjusted preset temperature TYW is calculated by the formula TYW=YW-k3×arctan(JR-LYRY)×exp(-(LYJR-LYRY)); wherein k3 is the temperature coefficient, k3>1.

9. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The step of generating the device temperature according to the aging coefficient and adjusting the preset temperature includes: Obtain the aging coefficient LX and adjust the preset temperature TYW; Calculate the equipment temperature SW of the equipment in the corresponding area through the formula; SW=TYW / ((1-LX^(1+β)); where β is the exponential coefficient, β∈(0,1).

10. A multi-zone temperature control system for central air conditioning according to claim 1, characterized in that: The step of generating an alarm signal according to the aging coefficient comprises: Obtain the aging coefficients of equipment in several areas; Determine whether a number of aging coefficients are greater than aging thresholds; Yes, generate an air conditioner aging alarm signal; No, determine whether the aging coefficient is greater than D times the aging threshold; yes, generate an air conditioner aging warning signal; no, do nothing; D is the proportional coefficient, D∈(0,1).

Images