An energy-saving method and device for optimizing the operation of central air-conditioning units using big data

Abstract

The present invention belongs to the technical field of energy conservation of air-conditioning units, and discloses an energy conservation method and device for optimizing the operation of a central air-conditioning unit by using big data; the method comprises: collecting energy consumption impact data; calculating an energy consumption range according to the energy consumption impact data, optimizing the energy consumption range, and obtaining an optimal energy consumption range; collecting the energy consumption of the unit, and comparing it with the optimal energy consumption range to determine whether to generate an adjustment instruction; if an adjustment instruction is generated, using a clone selection algorithm to filter out an optimal energy consumption value from the optimal energy consumption range; obtaining corresponding optimal operating parameters according to the optimal energy consumption value, and controlling the unit to operate according to the optimal operating parameters; the present invention can dynamically and optimally adjust the unit operating parameters according to the real-time changing external environment and building usage conditions, and realize automatic and intelligent operation of the unit, thereby effectively improving operating efficiency and saving energy consumption, and meeting the comfort requirements of personnel while optimizing energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of energy saving of air conditioning units, and more specifically, to an energy saving method and device for optimizing the operation of a central air conditioning unit by utilizing big data. Background Art

[0002] At present, central air-conditioning systems are widely used in commercial buildings and large office spaces, but their energy consumption accounts for a large proportion of building energy consumption, becoming one of the largest energy consumption parts in commercial buildings; among them, the low operating efficiency of central air-conditioning units has become one of the important reasons for energy waste. Traditional central air-conditioning units adopt a fixed operating mode, which is difficult to respond and optimize quickly according to the real-time changing air-conditioning load. There is a lack of effective energy consumption monitoring and optimization control, which will cause mismatched operating conditions, reduced efficiency and energy waste;

[0003] Of course, there are also intelligent central air-conditioning energy-saving methods. For example, the patent with publication number CN114440409A discloses an adaptive energy-saving control method for a central air-conditioning system, including: real-time monitoring and calculation of the total cooling capacity of the air-conditioning system, and adjusting the number of air-conditioning units according to the value of the total cooling capacity; adjusting the chilled water pump frequency, the cooling water pump frequency and the cooling tower fan frequency through an adaptive PID fuzzy controller according to the chilled water supply and return water temperature difference, the cooling water supply and return water temperature difference and the cooling tower outlet water temperature and the outdoor wet-bulb temperature difference; adjusting the fan speed according to the air supply volume, and adjusting the fresh air ratio according to the season; this invention adopts an adaptive fuzzy PID control method to avoid the control instability caused by the central air-conditioning system due to nonlinearity, large lag, large inertia, time-varying and strong coupling characteristics, so that the operation of the central air-conditioning system is more energy-efficient;

[0004] However, the above technology uses various temperature difference data to adjust the frequency of the central air-conditioning related equipment, thereby realizing the control of the central air-conditioning; however, it does not predict the energy consumption of the central air-conditioning, and cannot fully consider the impact of external factors on energy consumption, such as weather changes, building usage, etc., that is, it cannot adjust the relevant parameters of the central air-conditioning according to external factors; at the same time, without the support of energy consumption prediction, it is impossible to find a solution to optimize energy consumption, and it is difficult to meet comfort requirements while optimizing energy consumption;

[0005] In view of this, the present invention proposes an energy-saving method and device for optimizing the operation of a central air-conditioning unit using big data to solve the above-mentioned problem. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purpose, the present invention provides the following technical solution: an energy-saving method for optimizing the operation of a central air-conditioning unit using big data, comprising:

[0007] Collect energy consumption impact data, including building impact data and environmental impact data;

[0008] Calculate the energy consumption range based on the energy consumption impact data, and optimize the energy consumption range to obtain the optimal energy consumption range;

[0009] Collect the energy consumption of the unit and compare it with the optimal energy consumption range to determine whether to generate an adjustment instruction;

[0010] If an adjustment instruction is generated, the optimal energy consumption value is selected from the optimal energy consumption range using a clonal selection algorithm;

[0011] According to the optimal energy consumption value, the corresponding optimal operating parameters are obtained, and the unit is controlled to operate according to the optimal operating parameters.

[0012] Furthermore, the building impact data includes indoor area, number of people and thermal insulation performance; the indoor area is the area in the building that is temperature-controlled by the unit, and the unit is a central air-conditioning unit; the number of people is the number of people in the building; the thermal insulation performance is the heat conduction capacity of the building's external structure;

[0013] The environmental impact data include sunshine intensity, precipitation and green coverage rate; the sunshine intensity refers to the intensity of sunlight in the area where the building is located; the precipitation refers to the precipitation in the area where the building is located; and the green coverage rate refers to the proportion of vegetation coverage in the area where the building is located.

[0014] Furthermore, the step of calculating the energy consumption range includes:

[0015] Step S1: Calculate the building impact coefficient according to the building impact data;

[0016]

[0017] In the formula, JX is the building influence coefficient, SM is the indoor area, RS is the number of people, GX is the thermal insulation performance, ω1, ω2, ω3 are the preset weight coefficients;

[0018] Step S2: Calculate the environmental impact coefficient according to the environmental impact data;

[0019]

[0020] Where HX is the environmental impact coefficient, RZ is the sunshine intensity, JS is the precipitation, LF is the green coverage rate, ω4, ω5, ω6 are the preset weight coefficients;

[0021] Step S3: Calculate the maximum energy consumption value and the minimum energy consumption value according to the building impact coefficient and the environmental impact coefficient, and construct an energy consumption range according to the maximum energy consumption value and the minimum energy consumption value;

[0022] The expression of the maximum energy consumption value is: P d =ψ1×(JX+sinJX)+ψ2×e HX ;

[0023] Where P d is the maximum energy consumption value, ψ1 and ψ2 are proportional coefficients, and e is a natural constant;

[0024] The expression of the minimum energy consumption value is: P x =ψ1×logJX+ψ2×HX;

[0025] Where P x is the minimum energy consumption value.

[0026] Furthermore, the method for obtaining the optimal energy consumption range includes:

[0027] A set of energy consumption impact data and an energy consumption value within the energy consumption range are taken as a set of analysis data; each set of analysis data is input into the trained temperature analysis model to predict the corresponding supply air temperature; each set of analysis data is input into the trained wind speed analysis model to predict the corresponding fan speed; each set of analysis data is input into the trained mode analysis model to predict the corresponding operation mode; wherein the supply air temperature is the target temperature when the unit is running, the fan speed is the air volume generated when the unit is running, and the operation mode is the operation mode set when the unit is running; the supply air temperature, fan speed and operation mode predicted by a set of analysis data are taken as a set of operation parameters;

[0028] The training process of the temperature analysis model includes:

[0029] Collect the supply air temperature corresponding to a group of analysis data in advance, and convert the analysis data and the corresponding supply air temperature into a corresponding set of feature vectors;

[0030] Each set of feature vectors is used as the input of the temperature analysis model. The temperature analysis model uses a set of supply air temperatures corresponding to each set of analysis data as the output, and uses the actual supply air temperature corresponding to each set of analysis data as the prediction target. The actual supply air temperature is the supply air temperature corresponding to the analysis data collected in advance. Minimizing the sum of prediction errors of all analysis data is used as the training target. The temperature analysis model is trained until the sum of prediction errors reaches convergence and the training is stopped. The temperature analysis model is a deep neural network model.

[0031] The training process of the wind speed analysis model is the same as that of the temperature analysis model, and it is also a deep neural network model;

[0032] The training process of the pattern analysis model includes:

[0033] Collect the operation modes corresponding to the b group of analysis data in advance, set different digital labels for different operation modes, and mark the digital labels corresponding to the operation modes as mode labels; convert the analysis data and the corresponding mode labels into a corresponding set of feature vectors;

[0034] Each group of feature vectors is used as the input of the pattern analysis model. The pattern analysis model uses a group of predicted pattern labels corresponding to each group of analysis data as output, and uses the actual pattern labels corresponding to each group of analysis data as the prediction target, where the actual pattern labels are the pattern labels corresponding to the analysis data collected in advance; the prediction results are evaluated for model accuracy using the mean absolute percentage error (MAPE), and when the calculated MAPE is less than the preset MAPE, the pattern analysis model training is completed; a pattern analysis model is generated that predicts pattern labels based on the analysis data; wherein the pattern analysis model is a deep belief network model;

[0035] A set of operating parameters and a set of energy consumption impact data are used as a set of test data. Each set of test data is input into the trained cold and hot sensation analysis model to predict the corresponding cold and hot sensation index PMV, which is an evaluation index that characterizes the cold and hot sensation of the human body. The training process of the cold and hot sensation analysis model is consistent with that of the temperature analysis model, and it is also a deep neural network model.

[0036] The corresponding dissatisfaction PPD is calculated based on the PMV of the cold and hot sensation index corresponding to each set of test data. The dissatisfaction PPD is the percentage of personnel who are dissatisfied with the building environment.

[0037] The calculation method of unsatisfactory PPD includes:

[0038]

[0039] Preset the dissatisfaction range [C1, C2], C1 is the minimum value that the dissatisfaction PPD can reach, C2 is the maximum value that the dissatisfaction PPD can reach, and compare the dissatisfaction PPD corresponding to each energy consumption value with the dissatisfaction range respectively. If C1≤PPD≤C2, the corresponding energy consumption value is retained in the energy consumption range; if PPD>C2, the corresponding energy consumption value is removed from the energy consumption range;

[0040] The energy consumption range after the completion energy consumption value is removed is taken as the optimal energy consumption range.

[0041] Furthermore, the unit energy consumption is the operating energy consumption of the central air-conditioning unit;

[0042] The method for determining whether to generate an adjustment instruction includes:

[0043] The unit energy consumption P z and the optimal energy consumption range [P x ′,Pd ′] for comparison, P x ′ is the minimum energy consumption value in the optimal energy consumption range, P d ′ is the maximum energy consumption value in the optimal energy consumption range;

[0044] If P x ′≤P z ≤P d ′, no adjustment instruction is generated;

[0045] If P z >P d ′ or P z <P x ′, then an adjustment instruction is generated.

[0046] Furthermore, the step of selecting the optimal energy consumption value from the optimal energy consumption range includes:

[0047] Step 1: Randomly generate an initial antibody population X(0) of size q = {X1, X2, X3, ... X q}; preset iteration threshold; where X q is the qth antibody;

[0048] Step 2: Determine the fitness function;

[0049] Step 3: Calculate the fitness of each antibody in the initial antibody population X(0), select r antibodies with the largest fitness, and construct a memory population X m (t);

[0050] Step 4: Memory population X m Each antibody in (t) is cloned according to the calculated clone size to generate a clone antibody population in is the qth cloned antibody in the clonal antibody group;

[0051] Step 5: Cloning Antibody Group X c Each antibody in (t) is subjected to cloud adaptive mutation using a cloud adaptive mutation operator to generate a mutant antibody group X d (t);

[0052] Step 6: Cloning Antibodies from Group X c (t) randomly selects w antibodies as parent antibodies for antibody recombination to generate progeny antibodies Sc until the cloned antibody population X c When the number of unselected antibodies in (t) is less than w, antibody recombination is stopped and a recombinant antibody group X is generated. r (t);

[0053] Step 7: Merge variant antibody group X d (t) and recombinant antibody group Xr (t), generate a combined antibody population X L (t);

[0054] Step 8: Randomly generate n new antibodies and merge antibody group X L The n antibodies with the smallest fitness in (t) are replaced by n randomly generated new antibodies;

[0055] Step 9: If the number of iterations t is less than the iteration threshold, set t = t + 1 and select the merged antibody group X L The r antibodies with the largest fitness in (t) form a new memory population X m (t+1), loop steps 3 to 8; if the number of iterations t is equal to the iteration threshold, the loop ends and the combined antibody group X is obtained. L The energy consumption value corresponding to the antibody with the largest fitness in (t) is taken as the optimal energy consumption value.

[0056] Furthermore, in step 1, the antibodies in the initial antibody group X(0) correspond one to one with the energy consumption values ​​in the optimal energy consumption range, and the range of the antibodies is the optimal energy consumption range;

[0057] In step 2, the fitness function is expressed as: i =β×P i +(1-β)×PPD i ;

[0058] In the formula, f i is the fitness of the ith antibody, P i is the energy consumption value of the ith antibody, PPD i is the dissatisfaction of the ith antibody, β is the preset weight factor, and 0.5<β<1.

[0059] In step 4, the method for calculating the clone size includes:

[0060]

[0061] Φ i =min(exp(||X i -Xj||));

[0062] In the formula, R i is the clone size of the i-th antibody, Int is the upward rounding function, q is the size of the antibody group, Φ i is the affinity of the ith antibody, min is the minimum function, exp is the natural exponential function, ||X i -X j || is the Euclidean distance between the i-th antibody and the j-th antibody, i≠j, i∈[1,q], j∈[1,q];

[0063] In step 6, the progeny antibody S c The calculation methods include:

[0064]

[0065] In the formula, X′ w is the w-th parent antibody, s w is the w-th scaling factor, which is a randomly generated real number and not all w scaling factors are 0.

[0066] Furthermore, the method for obtaining the optimal operating parameters includes:

[0067] The optimal energy consumption value and energy consumption impact data are used as evaluation data, and the evaluation data are input into the trained temperature analysis model to predict the corresponding supply air temperature and mark it as the optimal supply air temperature; the evaluation data are input into the trained wind speed analysis model to predict the corresponding fan speed and mark it as the optimal fan speed; the evaluation data are input into the trained mode analysis model to predict the corresponding operating mode and mark it as the optimal operating mode; the optimal supply air temperature, optimal fan speed and optimal operating mode are used as the optimal operating parameters.

[0068] Furthermore, the method further comprises: obtaining the number of terminal faults, adjusting the optimal operating parameters, and controlling the unit to operate according to the adjusted optimal operating parameters;

[0069] The number of terminal failures is the number of air conditioning terminals that have failed in the building; the method for obtaining the number of terminal failures is: collect the fan speed and supply air temperature of each air conditioning terminal, subtract the optimal fan speed from the fan speed of each air conditioning terminal to obtain the wind speed error, and subtract the optimal supply air temperature from the supply air temperature of each air conditioning terminal to obtain the temperature error; preset the temperature error range and wind speed error range, compare the wind speed error with the wind speed error range, and compare the temperature error with the temperature error range. If the wind speed error is within the wind speed error range and the temperature error is within the temperature error range, it is judged that the air conditioning terminal is not faulty; if the wind speed error is not within the wind speed error range or the temperature error is not within the temperature error range, it is judged that the air conditioning terminal is faulty; count the number of air conditioning terminal failures to obtain the number of terminal failures;

[0070] Methods for adjusting the optimal operating parameters include:

[0071] Get the total number of air conditioning terminals and calculate the minimum temperature adjustment value and the maximum wind speed adjustment value;

[0072]

[0073] In the formula, T is the minimum temperature adjustment value, M is the total number of air conditioning terminals, M′ is the number of terminal failures, and T′ is the optimal air supply temperature;

[0074]

[0075] In the formula, V is the maximum wind speed adjustment value, and V′ is the optimal fan wind speed;

[0076] According to the minimum temperature adjustment value and the optimal air supply temperature, the temperature adjustment range is constructed; according to the maximum wind speed adjustment value and the optimal fan wind speed, the wind speed adjustment range is constructed;

[0077] Randomly select a temperature value from the temperature adjustment range, randomly select a wind speed value from the wind speed adjustment range, and construct an analysis set with the selected temperature value and wind speed value, and construct N analysis sets in total, N = (T′-T+1)×(VV′+1); take an analysis set, the optimal operation mode and the energy consumption impact data as a set of research data, input N′ groups of research data into the hot and cold sensation analysis model respectively, obtain the hot and cold sensation index PMV corresponding to each group of research data, and calculate the dissatisfaction PPD corresponding to each group of research data, where N′ = N;

[0078] The dissatisfaction PPD corresponding to each group of research data is sorted from small to large, and the analysis set in the research data corresponding to the dissatisfaction PPD ranked first is used as the adjustment set; the fan speed and supply air temperature in the optimal operating parameters are adjusted according to the adjustment set.

[0079] An energy-saving device for optimizing the operation of a central air-conditioning unit using big data, implementing the energy-saving method for optimizing the operation of a central air-conditioning unit using big data, comprising:

[0080] Impact data collection module, used to collect energy consumption impact data, including building impact data and environmental impact data;

[0081] The energy consumption range calculation module is used to calculate the energy consumption range according to the energy consumption impact data, and optimize the energy consumption range to obtain the optimal energy consumption range;

[0082] The adjustment judgment module is used to collect the energy consumption of the unit and compare it with the optimal energy consumption range to determine whether to generate an adjustment instruction;

[0083] The energy consumption matching module is used to select the best energy consumption value from the best energy consumption range by using a clone selection algorithm if an adjustment instruction is generated;

[0084] The unit control module is used to obtain the corresponding optimal operating parameters according to the optimal energy consumption value, and control the unit to operate according to the optimal operating parameters.

[0085] Technical effects and advantages of the energy-saving method and device for optimizing the operation of central air-conditioning units using big data provided by the present invention:

[0086] 1. Building impact data and environmental impact data are used to comprehensively and accurately evaluate the factors affecting the energy consumption of the unit, and deep learning algorithms are used to establish temperature models, wind speed models and pattern models for various impact data, which can accurately predict the operating parameters that should be set for the unit under different conditions; at the same time, the requirements of personnel for indoor environmental comfort are also taken into account, and the optimal energy consumption range that meets the comfort conditions is screened out by calculating the PMV and PPD indicators; and the optimal energy consumption value is screened out from the optimal energy consumption range through the clonal selection algorithm; compared with the traditional fixed operation mode, the unit operation parameters can be dynamically and optimally adjusted according to the real-time changing external environment and building usage, and the unit can be automatically and intelligently operated, thereby effectively improving operating efficiency and saving energy consumption, and meeting the comfort requirements of personnel while optimizing energy consumption.

[0087] 2. Through real-time monitoring and collection of operating data of each air-conditioning terminal, the current fault status of the air-conditioning terminal can be accurately understood, and a reasonable parameter adjustment range can be calculated based on the total number of air-conditioning terminals and the real-time number of terminal faults; a machine learning model is used to evaluate multiple randomly selected analysis sets, and the optimal adjustment plan is determined by calculating the PMV and PPD indicators; automatic parameter optimization and adjustment based on real-time fault conditions is achieved, which greatly improves the flexibility of unit operation, effectively alleviates the impact of some terminal faults on personnel comfort, improves energy utilization efficiency and user satisfaction, and reduces energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 This is a schematic diagram of an energy-saving device for optimizing the operation of a central air-conditioning unit using big data according to Embodiment 1 of the present invention;

[0089] Figure 2 This is a schematic diagram of an energy-saving device for optimizing the operation of a central air-conditioning unit using big data according to Embodiment 2 of the present invention;

[0090] Figure 3 This is a flow chart of an energy-saving method for optimizing the operation of a central air-conditioning unit using big data according to Embodiment 3 of the present invention;

[0091] Figure 4 This is a schematic diagram of an electronic device according to Embodiment 4 of the present invention;

[0092] Figure 5 This is a schematic diagram of a storage medium according to Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0093] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0094] Example 1

[0095] See also Figure 1 As shown, the energy-saving device for optimizing the operation of a central air-conditioning unit by using big data described in this embodiment includes an impact data acquisition module, an energy consumption range calculation module, an adjustment judgment module, an energy consumption matching module, and a unit control module; each module is connected by wire and / or wireless means to realize data transmission between modules;

[0096] Impact data collection module, used to collect energy consumption impact data;

[0097] Energy consumption impact data includes building impact data and environmental impact data;

[0098] Building impact data include interior area, number of occupants, and insulation performance;

[0099] The indoor area is the area in the building that is temperature-controlled by the unit, and the unit is a central air-conditioning unit; the indoor area is obtained by measuring the building in advance by technicians in this field; the larger the indoor area, the larger the volume of air that needs to be temperature-controlled in the building, and the more energy needs to be applied to meet the cooling and heating loads. In addition, the air flow path in the building is longer, and greater resistance needs to be overcome to circulate to every corner of the building. The unit needs a larger air volume and power to promote air flow, so the unit has a higher energy consumption, and vice versa;

[0100] The number of people is the number of people in the building; the method for obtaining the number of people is as follows: infrared sensors are installed at the entrance and exit of the building. When a person passes by, the infrared signal generated by the infrared sensor will change. The number of people passing by can be counted according to the number of changes in the infrared signal. The number of people counted by the infrared sensor at the entrance is subtracted from the number of people counted by the infrared sensor at the exit to obtain the number of people in the building; the more people there are, the higher the heat load and air humidity in the building will be, the more energy the unit needs to adjust the humidity and temperature in the building, and the carbon dioxide concentration in the air will also increase. In order to maintain good indoor air quality, the unit needs to increase the air flow and processing capacity, so the higher the energy consumption of the unit, and vice versa;

[0101] Thermal insulation performance refers to the heat conduction capacity of the building's outer structure; thermal insulation performance is obtained by technical personnel using a heat flow meter to test the building; the better the thermal insulation performance, the more effective it is in preventing heat from being transferred inside and outside the building, and the more stable the indoor temperature can be, that is, the unit needs less energy to adjust the indoor temperature, so the unit has lower energy consumption, and vice versa;

[0102] Environmental impact data include sunshine intensity, precipitation and green coverage;

[0103] The sunshine intensity is the intensity of sunlight in the area where the building is located. The sunshine intensity is obtained from the website of the meteorological bureau in the area where the building is located. The greater the sunshine intensity, the greater the heat load of the building, which means that the unit needs more energy to adjust the indoor temperature, so the energy consumption of the unit is higher, and vice versa.

[0104] The precipitation is the precipitation in the area where the building is located; the precipitation is obtained from the website of the meteorological bureau in the area where the building is located; the greater the precipitation, the greater the humidity in the building, which means that the unit needs more energy to adjust the indoor humidity, so the unit energy consumption is higher, and vice versa;

[0105] The green coverage rate is the coverage ratio of vegetation (such as trees, grass, and gardens) in the area where the building is located. The green coverage rate is obtained from the website of the Ecological Environment Bureau of the area where the building is located. The higher the green coverage rate, the slower the heat island effect will be, the less direct sunlight will hit the building surface, and the vegetation can reduce the temperature of the area where the building is located through transpiration. Therefore, the unit needs less energy to adjust the indoor humidity, that is, the lower the energy consumption of the unit, and vice versa.

[0106] The energy consumption range calculation module is used to calculate the energy consumption range according to the energy consumption impact data, and optimize the energy consumption range to obtain the optimal energy consumption range;

[0107] The steps to calculate the energy consumption range include:

[0108] Step S1: Calculate the building impact coefficient according to the building impact data;

[0109]

[0110] In the formula, JX is the building influence coefficient, SM is the indoor area, RS is the number of people, GX is the thermal insulation performance, ω1, ω2, ω3 are the preset weight coefficients;

[0111] The specific value of the weight coefficient in the formula can be set according to the actual situation. The weight coefficient reflects the influence of the building impact data on the building impact coefficient. Those skilled in the art can preset the corresponding weight coefficient according to the actual influence of the building impact data on the building impact coefficient, so as to accurately evaluate the building impact coefficient; the building impact coefficient is a related parameter of the computer group energy consumption, and the calculation process of the building impact coefficient is a dimensionless calculation;

[0112] Step S2: Calculate the environmental impact coefficient according to the environmental impact data;

[0113]

[0114] Where HX is the environmental impact coefficient, RZ is the sunshine intensity, JS is the precipitation, LF is the green coverage rate, ω4, ω5, ω6 are the preset weight coefficients;

[0115] The specific value of the weight coefficient in the formula can be set according to the actual situation. The weight coefficient reflects the degree of influence of the environmental impact data on the environmental impact coefficient. Those skilled in the art can preset the corresponding weight coefficient according to the actual degree of influence of the environmental impact data on the environmental impact coefficient, so as to accurately evaluate the environmental impact coefficient; the environmental impact coefficient is a related parameter of the energy consumption of the computer group, and the calculation process of the environmental impact coefficient is a dimensionless calculation;

[0116] Step S3: Calculate the maximum energy consumption value and the minimum energy consumption value according to the building impact coefficient and the environmental impact coefficient, and construct an energy consumption range according to the maximum energy consumption value and the minimum energy consumption value;

[0117] The expression of the maximum energy consumption value is: P d =ψ1×(JX+sinJX)+ψ2×e HX ;

[0118] Where P d is the maximum energy consumption value, ψ1 and ψ2 are proportional coefficients, and e is a natural constant;

[0119] The specific value of the proportionality coefficient in the formula can be set according to the actual situation. The proportionality coefficient reflects the influence of the building influence coefficient and the environmental influence coefficient on the energy consumption of the unit. Those skilled in the art can preset the corresponding proportionality coefficient according to the actual influence of the building influence coefficient and the environmental influence coefficient on the energy consumption of the unit, so as to accurately evaluate the energy consumption of the unit;

[0120] The expression of the minimum energy consumption value is: P x =ψ1×logJX+ψ2×HX;

[0121] Where P x is the minimum energy consumption value;

[0122] Methods for obtaining the optimal energy consumption range include:

[0123] A set of energy consumption impact data and an energy consumption value within the energy consumption range are taken as a set of analysis data; each set of analysis data is input into the trained temperature analysis model to predict the corresponding supply air temperature; each set of analysis data is input into the trained wind speed analysis model to predict the corresponding fan speed; each set of analysis data is input into the trained mode analysis model to predict the corresponding operation mode; wherein the supply air temperature is the target temperature when the unit is running, the fan speed is the air volume generated when the unit is running, and the operation mode is the operation mode set when the unit is running (such as cooling mode, dehumidification mode); the supply air temperature, fan speed and operation mode predicted by a set of analysis data are taken as a set of operation parameters;

[0124] The specific training process of the temperature analysis model includes:

[0125] Collect the supply air temperature corresponding to a group of analysis data in advance, and convert the analysis data and the corresponding supply air temperature into a corresponding set of feature vectors;

[0126] Each set of feature vectors is used as the input of the temperature analysis model. The temperature analysis model uses a set of supply air temperatures corresponding to each set of analysis data as output, and uses the actual supply air temperature corresponding to each set of analysis data as the prediction target. The actual supply air temperature is the supply air temperature corresponding to the analysis data collected in advance. The training target is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is Z k =(α k -μ k ) 2 , where Z k is the prediction error, k is the group number of the eigenvector corresponding to the analyzed data, α k is the air supply temperature corresponding to the kth group of analysis data, μ k is the actual supply air temperature corresponding to the kth group of analysis data; the temperature analysis model is trained until the sum of the prediction errors reaches convergence and the training is stopped;

[0127] The temperature analysis model is specifically a deep neural network model, which includes an input layer, a hidden layer, and an output layer. Each hidden layer includes multiple neurons, and each neuron is connected to the neurons in the next layer. The connection contains weights, which determine the importance and influence of data transmission in the neural network. An activation function is applied to each neuron between the hidden layer and the output layer. The activation function maps nonlinearity, allowing the network to learn more complex patterns and features.

[0128] The specific training process of the wind speed analysis model is consistent with that of the temperature analysis model, and it is also a deep neural network model;

[0129] The specific training process of the pattern analysis model includes:

[0130] Collect the operation modes corresponding to the b group of analysis data in advance, set different digital labels for different operation modes, and mark the digital labels corresponding to the operation modes as mode labels; convert the analysis data and the corresponding mode labels into a corresponding set of feature vectors;

[0131] Each set of feature vectors is used as the input of the pattern analysis model. The pattern analysis model uses a set of predicted pattern labels corresponding to each set of analysis data as output, and uses the actual pattern labels corresponding to each set of analysis data as the prediction target. The actual pattern labels are the pre-collected pattern labels corresponding to the analysis data. The mean absolute percentage error (MAPE) is used to evaluate the model accuracy of the prediction results. When the calculated MAPE is less than the preset MAPE, the pattern analysis model training is completed. The calculation formula of MAPE is: Among them, α L is the actual pattern label corresponding to the Lth group of analysis data, μ L is the prediction mode label corresponding to the Lth group of analysis data, L is the group number of the feature vector corresponding to the analysis data, L∈[1,R]; R is the number of prediction mode labels; a mode analysis model for predicting mode labels according to the analysis data is generated; wherein the mode analysis model is a deep belief network model, and the preset MAPE is pre-set by those skilled in the art according to the accuracy required by the mode analysis model;

[0132] It should be noted that the operating parameters corresponding to the analysis data are collected by a group of different energy consumption impact data during the historical unit operation by a technician in this field. Under the condition of each group of energy consumption impact data, different unit energy consumption and operating parameters are collected when the unit is running, and the operating parameters are used as the operating parameters corresponding to the analysis data.

[0133] A set of operating parameters and a set of energy consumption impact data are used as a set of test data. Each set of test data is input into the trained cold and hot sensation analysis model to predict the corresponding cold and hot sensation index PMV, which is an evaluation index that characterizes the cold and hot sensation of the human body. The specific training process of the cold and hot sensation analysis model is consistent with the training process of the temperature analysis model, and it is also a deep neural network model.

[0134] The corresponding dissatisfaction PPD is calculated based on the PMV of the cold and hot sensation index corresponding to each set of test data. The dissatisfaction PPD is the percentage of personnel who are dissatisfied with the building environment.

[0135] The calculation method of unsatisfactory PPD includes:

[0136]

[0137] The dissatisfaction range [C1, C2] is preset, C1 is the minimum value that the dissatisfaction PPD can reach, C2 is the maximum value that the dissatisfaction PPD can reach, and the dissatisfaction PPD corresponding to each energy consumption value is compared with the dissatisfaction range respectively. If C1≤PPD≤C2, the corresponding energy consumption value is retained in the energy consumption range, indicating that the percentage of personnel satisfied with the building environment is high and the comfort level of the building environment is high; if PPD>C2, the corresponding energy consumption value is removed from the energy consumption range, indicating that the percentage of personnel dissatisfied with the building environment is high and the comfort level of the building environment is low; since C1 is the minimum value that the dissatisfaction PPD can reach, there is no PPD<C1;

[0138] It should be noted that the unsatisfactory PPD corresponds to the test data one-to-one, the test data corresponds to the operating parameters one-to-one, the operating parameters correspond to the analysis data one-to-one, and the analysis data corresponds to the energy consumption value one-to-one. Therefore, the unsatisfactory PPD corresponds to the energy consumption value in the energy consumption range one-to-one; the unsatisfactory range [C1, C2] is preset by those skilled in the art by consulting relevant literature and combining practical experience. In this embodiment, C1 is preferably 5% and C2 is preferably 10%;

[0139] The energy consumption range after the completion energy consumption value is removed is taken as the optimal energy consumption range;

[0140] The adjustment judgment module is used to collect the energy consumption of the unit and compare it with the optimal energy consumption range to determine whether to generate an adjustment instruction;

[0141] The unit energy consumption is the operating energy consumption of the central air-conditioning unit; the unit energy consumption is obtained by the power sensor installed on the unit power line;

[0142] The method for determining whether to generate an adjustment instruction includes:

[0143] The unit energy consumption P z and the optimal energy consumption range [P′ x ,P′ d ] for comparison, P′ x is the minimum energy consumption value in the optimal energy consumption range, P′ d is the maximum energy consumption value of the optimal energy consumption range;

[0144] If P x ′≤P z ≤P d ′, no adjustment instruction is generated; this indicates that the unit energy consumption is within the optimal energy consumption range, and there is no need to adjust the unit's operating parameters;

[0145] If P z >P d ′ or P z <P x′, an adjustment instruction is generated; indicating that the unit energy consumption is outside the optimal energy consumption range, and the unit operating parameters need to be adjusted;

[0146] The energy consumption matching module is used to select the best energy consumption value from the best energy consumption range by using a clone selection algorithm if an adjustment instruction is generated;

[0147] The steps of selecting the optimal energy consumption value from the optimal energy consumption range include:

[0148] Step 1: Randomly generate an initial antibody population X(0) of size q = {X1, X2, X3, ... X q}; preset iteration threshold, which is preset according to the algorithm accuracy; where X q is the qth antibody;

[0149] Step 2: Determine the fitness function;

[0150] Step 3: Calculate the fitness of each antibody in the initial antibody population X(0), select r antibodies with the largest fitness, and construct a memory population X m (t);

[0151] Step 4: Memory population X m Each antibody in (t) is cloned according to the calculated clone size to generate a clone antibody population in is the qth cloned antibody in the clonal antibody group;

[0152] Step 5: Cloning Antibody Group X c Each antibody in (t) is subjected to cloud adaptive mutation using a cloud adaptive mutation operator to generate a mutant antibody group X d (t); The cloud adaptive mutation operator is a prior art and will not be described in detail here;

[0153] Step 6: Cloning Antibodies from Group X c (t) randomly selects w antibodies as parent antibodies for antibody recombination to generate offspring antibodies Sc until the cloned antibody population X c When the number of unselected antibodies in (t) is less than w, antibody recombination is stopped and a recombinant antibody group X is generated. r (t); In this embodiment, w is preferably 3; recombinant antibody group X r (t) includes multiple progeny antibodies S c ;

[0154] Step 7: Merge variant antibody group X d (t) and recombinant antibody group X r (t), generate a combined antibody population X L (t);

[0155] Step 8: Randomly generate n new antibodies and merge antibody group X L The n antibodies with the smallest fitness in (t) are replaced by n randomly generated new antibodies;

[0156] Step 9: If the number of iterations t is less than the iteration threshold, set t = t + 1 and select the merged antibody group X L The r antibodies with the largest fitness in (t) form a new memory population X m (t+1), loop steps 3 to 8; if the number of iterations t is equal to the iteration threshold, the loop ends and the combined antibody group X is obtained. L The energy consumption value corresponding to the antibody with the largest fitness in (t) is taken as the optimal energy consumption value; wherein t=t+1 is a computer language, that is, the value of the iteration number t is added by 1 and then assigned to the iteration number t;

[0157] In the above step 1, the antibodies in the initial antibody group X(0) correspond one to one with the energy consumption values ​​in the optimal energy consumption range, and the range of the antibodies is the optimal energy consumption range;

[0158] In step 2 above, the fitness function is expressed as: f i =β×P i +(1-β)×PPD i ;

[0159] In the formula, f i is the fitness of the ith antibody, P i is the energy consumption value of the ith antibody, PPD i is the dissatisfaction of the ith antibody, β is the preset weight factor, and 0.5<β<1;

[0160] It should be noted that the specific value of the weight factor in the formula can be set according to the actual situation. The weight factor reflects the importance of the energy consumption value and the dissatisfaction value. The technicians in this field can preset the corresponding weight coefficient according to the actual importance of the energy consumption value and the dissatisfaction value, so as to optimize the energy consumption while meeting the comfort requirements of the personnel; since the dissatisfaction corresponding to the energy consumption value in the optimal energy consumption range is within the dissatisfaction range, the difference in dissatisfaction corresponding to different energy consumption values ​​is small, so when screening the optimal energy consumption value, it is necessary to pay more attention to the numerical value of the energy consumption value, that is, the corresponding weight of the energy consumption value is larger when calculating the fitness; the fitness is only an evaluation criterion for screening antibodies, so the calculation process of the fitness is a dimensionless calculation;

[0161] In the above step 4, the calculation method of the clone size includes:

[0162]

[0163] Φ i =min(exp(||X i -Xj ||));

[0164] In the formula, R i is the clone size of the i-th antibody, Int is the upward rounding function, q is the size of the antibody group, Φ i is the affinity of the ith antibody, min is the minimum function, exp is the natural exponential function, ||X i -X j || is the Euclidean distance between the i-th antibody and the j-th antibody, i≠j, i∈[1,q], j∈[1,q];

[0165] It should be noted that when calculating the Euclidean distance between the ith antibody and the jth antibody, normalization is performed so that 0≤||X i -X j ||≤1;

[0166] In step 6 above, the progeny antibody S c The calculation methods include:

[0167]

[0168] In the formula, X′ w is the w-th parent antibody, s w is the wth scale factor, the scale factor is a randomly generated real number and the w scale factors are not all 0;

[0169] The unit control module is used to obtain the corresponding optimal operating parameters according to the optimal energy consumption value, and control the unit to operate according to the optimal operating parameters;

[0170] Methods for obtaining optimal operating parameters include:

[0171] The optimal energy consumption value and energy consumption impact data are used as evaluation data, and the evaluation data are input into the trained temperature analysis model to predict the corresponding supply air temperature and mark it as the optimal supply air temperature; the evaluation data are input into the trained wind speed analysis model to predict the corresponding fan speed and mark it as the optimal fan speed; the evaluation data are input into the trained mode analysis model to predict the corresponding operation mode and mark it as the optimal operation mode; the optimal supply air temperature, the optimal fan speed and the optimal operation mode are used as the optimal operation parameters;

[0172] This embodiment uses building impact data and environmental impact data to comprehensively and accurately evaluate the influencing factors of unit energy consumption, and uses deep learning algorithms to establish temperature models, wind speed models and pattern models for various impact data, which can accurately predict the operating parameters that should be set for the unit under different conditions; at the same time, it also takes into account the personnel's requirements for indoor environmental comfort, and screens out the optimal energy consumption range that meets the comfort conditions by calculating the PMV and PPD indicators; and screens out the optimal energy consumption value from the optimal energy consumption range through the clonal selection algorithm; compared with the traditional fixed operation mode, it can dynamically and optimally adjust the unit operation parameters according to the real-time changing external environment and building usage, and realize automatic and intelligent operation of the unit, thereby effectively improving operation efficiency and saving energy consumption, and meeting the comfort requirements of personnel while optimizing energy consumption.

[0173] Example 2

[0174] See also Figure 2 As shown, this embodiment further improves the design on the basis of embodiment 1. Since there are multiple air-conditioning terminals in the unit, when a single air-conditioning terminal fails, the optimal operating parameters obtained according to the method in embodiment 1 cannot meet the comfort requirements of the personnel, so that the comfort of the personnel in the area responsible for the failed air-conditioning terminal decreases. Therefore, this embodiment provides an energy-saving device for optimizing the operation of the central air-conditioning unit using big data, and also includes a unit adjustment module;

[0175] The unit adjustment module is used to obtain the number of terminal faults, adjust the optimal operating parameters, and control the unit to operate according to the adjusted optimal operating parameters;

[0176] The number of terminal failures is the number of air-conditioning terminals that have failed in the building; the method for obtaining the number of terminal failures is as follows: through the intelligent fan coil thermostat installed in the air-conditioning terminal, the fan speed and supply air temperature of each air-conditioning terminal are collected, and the fan speed of each air-conditioning terminal is subtracted from the optimal fan speed to obtain the wind speed error, and the supply air temperature of each air-conditioning terminal is subtracted from the optimal supply air temperature to obtain the temperature error; the temperature error range and wind speed error range are preset, and the wind speed error is compared with the wind speed error range, and the temperature error is compared with the temperature error range. If the wind speed error is within the wind speed error range and the temperature error is within the temperature error range, it is judged that the air-conditioning terminal is not faulty; if the wind speed error is not within the wind speed error range or the temperature error is not within the temperature error range, it is judged that the air-conditioning terminal is faulty; the number of air-conditioning terminal failures is counted to obtain the number of terminal failures;

[0177] Among them, the temperature error range is that the technicians in this field collect Q times of the supply air temperature of each air-conditioning terminal during the normal operation of the historical unit, and respectively subtract the supply air temperature set by the corresponding unit from the supply air temperature of each air-conditioning terminal to obtain multiple temperature errors, and take the temperature error with the smallest value among the multiple temperature errors as the single minimum temperature error, and take the temperature error with the largest value among the multiple temperature errors as the single maximum temperature error, and sequentially obtain Q single minimum temperature errors and Q single maximum temperature errors; according to the average of the Q single minimum temperature errors and the average of the Q single maximum temperature errors, preset the temperature error range; the preset method of the wind speed error range is consistent with the temperature error range;

[0178] Methods for adjusting the optimal operating parameters include:

[0179] Get the total number of air conditioning terminals and calculate the minimum temperature adjustment value and the maximum wind speed adjustment value;

[0180]

[0181] In the formula, T is the minimum temperature adjustment value, M is the total number of air conditioning terminals, M′ is the number of terminal failures, and T′ is the optimal air supply temperature;

[0182]

[0183] In the formula, V is the maximum wind speed adjustment value, and V′ is the optimal fan wind speed;

[0184] According to the minimum temperature adjustment value and the optimal air supply temperature, the temperature adjustment range is constructed; according to the maximum wind speed adjustment value and the optimal fan wind speed, the wind speed adjustment range is constructed;

[0185] Randomly select a temperature value from the temperature adjustment range, randomly select a wind speed value from the wind speed adjustment range, and construct an analysis set with the selected temperature value and wind speed value, and construct N analysis sets in total, N = (T′-T+1)×(VV′+1); take an analysis set, the optimal operation mode and the energy consumption impact data as a set of research data, input N′ groups of research data into the hot and cold sensation analysis model respectively, obtain the hot and cold sensation index PMV corresponding to each group of research data, and calculate the dissatisfaction PPD corresponding to each group of research data, where N′ = N;

[0186] The dissatisfaction PPD corresponding to each group of research data is sorted from small to large, and the analysis set in the research data corresponding to the dissatisfaction PPD ranked first is used as the adjustment set; the fan speed and air supply temperature in the optimal operating parameters are adjusted according to the adjustment set;

[0187] This embodiment can accurately understand the current fault status of the air-conditioning terminal through real-time monitoring and collection of the operating data of each air-conditioning terminal, and calculate a reasonable parameter adjustment range based on the total number of air-conditioning terminals and the real-time number of terminal faults; use a machine learning model to evaluate multiple randomly selected analysis sets, and determine the optimal adjustment plan by calculating the PMV and PPD indicators; realize automatic parameter optimization and adjustment according to real-time fault conditions, greatly improve the flexibility of unit operation, effectively alleviate the impact of some terminal faults on personnel comfort, improve energy utilization efficiency and user satisfaction, and reduce energy consumption.

[0188] Example 3

[0189] See also Figure 3 As shown, the parts not described in detail in this embodiment are described in embodiments 1 and 2, and an energy-saving method for optimizing the operation of a central air-conditioning unit using big data is provided, the method comprising:

[0190] Collect energy consumption impact data, including building impact data and environmental impact data;

[0191] Calculate the energy consumption range based on the energy consumption impact data, and optimize the energy consumption range to obtain the optimal energy consumption range;

[0192] Collect the energy consumption of the unit and compare it with the optimal energy consumption range to determine whether to generate an adjustment instruction;

[0193] If an adjustment instruction is generated, the optimal energy consumption value is selected from the optimal energy consumption range using a clonal selection algorithm;

[0194] According to the optimal energy consumption value, the corresponding optimal operating parameters are obtained, and the unit is controlled to operate according to the optimal operating parameters.

[0195] Example 4

[0196] See also Figure 4 As shown, the present application also provides an electronic device 500. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the energy-saving method for optimizing the operation of a central air-conditioning unit using big data as described above may be executed.

[0197] The method or system according to the embodiment of the present application can also be Figure 4 The electronic device architecture shown in FIG. Figure 4As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as ROM 503 or hard disk 507, may store an energy-saving method for optimizing the operation of a central air-conditioning unit using big data provided in the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of an electronic device are shown.

[0198] Example 5

[0199] See also Figure 5 As shown, the present application discloses a computer-readable storage medium 600. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, an energy-saving method for optimizing the operation of a central air-conditioning unit using big data according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0200] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present application, for example: an energy-saving method for optimizing the operation of a central air-conditioning unit using big data. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0201] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0202] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An energy-saving method for optimizing the operation of central air-conditioning units using big data, It is characterized in that include: Collect energy consumption impact data, including building impact data and environmental impact data; The building impact data includes indoor area, number of people and thermal insulation performance; the indoor area is the area in the building that is temperature-controlled by the unit, and the unit is a central air-conditioning unit; the number of people is the number of people in the building; the thermal insulation performance is the heat conduction capacity of the building's external structure; The environmental impact data include sunshine intensity, precipitation and green coverage rate; the sunshine intensity is the intensity of sunlight in the area where the building is located; the precipitation is the precipitation in the area where the building is located; the green coverage rate is the proportion of vegetation coverage in the area where the building is located; Calculate the energy consumption range based on the energy consumption impact data, and optimize the energy consumption range to obtain the optimal energy consumption range; The calculation steps of the energy consumption range include: Step S1: Calculate the building impact coefficient according to the building impact data; ； In the formula, is the building influence coefficient, is the indoor area, is the number of personnel, For thermal insulation performance, , , is the preset weight coefficient; Step S2: Calculate the environmental impact coefficient according to the environmental impact data; ； In the formula, is the environmental impact coefficient, is the sunlight intensity, is the precipitation, is the green coverage rate, , , is the preset weight coefficient; Step S3: Calculate the maximum energy consumption value and the minimum energy consumption value according to the building impact coefficient and the environmental impact coefficient, and construct an energy consumption range according to the maximum energy consumption value and the minimum energy consumption value; The expression of the maximum energy consumption value is: ; In the formula, is the maximum energy consumption value, , is the proportionality coefficient, e is the natural constant; The expression of minimum energy consumption value is: ; In the formula, is the minimum energy consumption value; The method for obtaining the optimal energy consumption range includes: A set of energy consumption impact data and an energy consumption value within the energy consumption range are taken as a set of analysis data; each set of analysis data is input into the trained temperature analysis model to predict the corresponding supply air temperature; each set of analysis data is input into the trained wind speed analysis model to predict the corresponding fan speed; each set of analysis data is input into the trained mode analysis model to predict the corresponding operation mode; wherein the supply air temperature is the target temperature when the unit is running, the fan speed is the air volume generated when the unit is running, and the operation mode is the operation mode set when the unit is running; the supply air temperature, fan speed and operation mode predicted by a set of analysis data are taken as a set of operation parameters; The training process of the temperature analysis model includes: Collect the supply air temperature corresponding to a group of analysis data in advance, and convert the analysis data and the corresponding supply air temperature into a corresponding set of feature vectors; Each set of feature vectors is used as the input of the temperature analysis model. The temperature analysis model uses a set of supply air temperatures corresponding to each set of analysis data as the output, and uses the actual supply air temperature corresponding to each set of analysis data as the prediction target. The actual supply air temperature is the supply air temperature corresponding to the analysis data collected in advance. Minimizing the sum of prediction errors of all analysis data is used as the training target. The temperature analysis model is trained until the sum of prediction errors reaches convergence and the training is stopped. The temperature analysis model is a deep neural network model. The training process of the wind speed analysis model is the same as that of the temperature analysis model, and it is also a deep neural network model; The training process of the pattern analysis model includes: Collect the operation modes corresponding to the b group of analysis data in advance, set different digital labels for different operation modes, and mark the digital labels corresponding to the operation modes as mode labels; convert the analysis data and the corresponding mode labels into a corresponding set of feature vectors; Each group of feature vectors is used as the input of the pattern analysis model. The pattern analysis model uses a group of predicted pattern labels corresponding to each group of analysis data as output, and uses the actual pattern labels corresponding to each group of analysis data as the prediction target, and the actual pattern labels are the pattern labels corresponding to the analysis data collected in advance; the prediction results are evaluated for model accuracy using the mean absolute percentage error MAPE, and when the calculated MAPE is less than the preset MAPE, the pattern analysis model training is completed; a pattern analysis model is generated that predicts pattern labels based on the analysis data; wherein the pattern analysis model is a deep belief network model; A set of operating parameters and a set of energy consumption impact data are used as a set of test data. Each set of test data is input into the trained cold and hot sensation analysis model to predict the corresponding cold and hot sensation index PMV, which is an evaluation index that characterizes the cold and hot sensation of the human body. The training process of the cold and hot sensation analysis model is consistent with that of the temperature analysis model, and it is also a deep neural network model. The corresponding dissatisfaction PPD is calculated based on the PMV of the cold and hot sensation index corresponding to each set of test data. The dissatisfaction PPD is the percentage of personnel who are dissatisfied with the building environment. The calculation method of unsatisfactory PPD includes: ； Preset Dissatisfaction Range , is the minimum value that the dissatisfaction PPD can reach. is the maximum value that the dissatisfaction PPD can reach. Compare the dissatisfaction PPD corresponding to each energy consumption value with the dissatisfaction range. If , then keep the corresponding energy consumption value in the energy consumption range, if , then remove the corresponding energy consumption value from the energy consumption range; The energy consumption range after the completion energy consumption value is removed is taken as the optimal energy consumption range; Collect the energy consumption of the unit and compare it with the optimal energy consumption range to determine whether to generate an adjustment instruction; If an adjustment instruction is generated, the optimal energy consumption value is selected from the optimal energy consumption range using a clonal selection algorithm; According to the optimal energy consumption value, the corresponding optimal operating parameters are obtained, and the unit is controlled to operate according to the optimal operating parameters.

2. According to claim 1, a method for optimizing the operation of a central air-conditioning unit by using big data for energy saving, It is characterized in that The unit energy consumption is the operating energy consumption of the central air-conditioning unit; The method for determining whether to generate an adjustment instruction includes: The energy consumption of the unit With the best energy consumption range For comparison, is the minimum energy consumption value in the optimal energy consumption range, is the maximum energy consumption value of the optimal energy consumption range; like , no adjustment instruction is generated; like or , then generate adjustment instructions.

3. According to claim 2, a method for optimizing the operation of a central air-conditioning unit by using big data, It is characterized in that The step of selecting the optimal energy consumption value from the optimal energy consumption range comprises: Step 1: Randomly generate an initial antibody population of size q ; Preset iteration threshold; Wherein, is the qth antibody; Step 2: Determine the fitness function; Step 3: Calculate the initial antibody population The fitness of each antibody in , select r antibodies with the largest fitness, and construct a memory population ; Step 4: Memory population Each antibody in is cloned according to the calculated clone size to generate a clone antibody population ;in is the qth cloned antibody in the clonal antibody group; Step 5: Cloning of Antibody Populations Each antibody in the cloud uses a cloud adaptive mutation operator to perform cloud adaptive mutation to generate a mutant antibody group ; Step 6: Cloning antibody populations Randomly select w antibodies as parent antibodies for antibody recombination to generate offspring antibodies , until the clonal antibody population When the number of unselected antibodies is less than w, antibody recombination is stopped and a recombinant antibody group is generated. ; Step 7: Merge the variant antibody groups and recombinant antibody groups , generating a pooled antibody population ; Step 8: Randomly generate n new antibodies and merge the antibody groups The n antibodies with the smallest fitness are replaced by n randomly generated new antibodies; Step 9: If the number of iterations t is less than the iteration threshold, let , and select the combined antibody group The r antibodies with the largest fitness form a new memory population , loop steps 3 to 8; if the number of iterations t is equal to the iteration threshold, the loop ends and the combined antibody group is obtained The energy consumption value corresponding to the antibody with the largest fitness is taken as the optimal energy consumption value.

4. According to claim 3, a method for optimizing the operation of a central air-conditioning unit by using big data, It is characterized in that In step 1, the initial antibody population The antibody in the middle corresponds to the energy consumption value in the optimal energy consumption range, and the range of the antibody is the optimal energy consumption range; In step 2, the expression of the fitness function is: ; In the formula, is the fitness of the ith antibody, is the energy consumption value of the ith antibody, is the dissatisfaction of the ith antibody, is the preset weight factor, and ; In step 4, the method for calculating the clone size includes: ； ； In the formula, is the clone size of the ith antibody, Int is the rounding function, q is the size of the antibody group, is the affinity of the ith antibody, min is the minimum function, exp is the natural exponential function, is the Euclidean distance between the ith antibody and the jth antibody, , , ; In step 6, the progeny antibody The calculation methods include: ； In the formula, is the w-th parent antibody, is the w-th scaling factor, which is a randomly generated real number and not all w scaling factors are 0.

5. According to claim 4, a method for optimizing the operation of a central air-conditioning unit by using big data for energy saving, It is characterized in that Methods for obtaining optimal operating parameters include: The optimal energy consumption value and energy consumption impact data are used as evaluation data, and the evaluation data are input into the trained temperature analysis model to predict the corresponding supply air temperature and mark it as the optimal supply air temperature; the evaluation data are input into the trained wind speed analysis model to predict the corresponding fan speed and mark it as the optimal fan speed; the evaluation data are input into the trained mode analysis model to predict the corresponding operating mode and mark it as the optimal operating mode; the optimal supply air temperature, optimal fan speed and optimal operating mode are used as the optimal operating parameters.

6. According to claim 5, a method for optimizing the operation of a central air-conditioning unit by using big data, It is characterized in that The method further includes: obtaining the number of terminal faults, adjusting the optimal operating parameters, and controlling the unit to operate according to the adjusted optimal operating parameters; The number of terminal failures is the number of air conditioning terminals that have failed in the building; the method for obtaining the number of terminal failures is: collect the fan speed and supply air temperature of each air conditioning terminal, subtract the optimal fan speed from the fan speed of each air conditioning terminal to obtain the wind speed error, and subtract the optimal supply air temperature from the supply air temperature of each air conditioning terminal to obtain the temperature error; preset the temperature error range and wind speed error range, compare the wind speed error with the wind speed error range, and compare the temperature error with the temperature error range. If the wind speed error is within the wind speed error range and the temperature error is within the temperature error range, it is judged that the air conditioning terminal is not faulty; if the wind speed error is not within the wind speed error range or the temperature error is not within the temperature error range, it is judged that the air conditioning terminal is faulty; count the number of air conditioning terminal failures to obtain the number of terminal failures; Methods for adjusting the optimal operating parameters include: Get the total number of air conditioning terminals and calculate the minimum temperature adjustment value and the maximum wind speed adjustment value; ； In the formula, is the minimum temperature adjustment value, is the total number of air-conditioning terminals, is the number of terminal failures, is the optimal air supply temperature; ； In the formula, is the maximum wind speed adjustment value, is the optimal fan speed; According to the minimum temperature adjustment value and the optimal air supply temperature, the temperature adjustment range is constructed; according to the maximum wind speed adjustment value and the optimal fan wind speed, the wind speed adjustment range is constructed; Randomly select a temperature value from the temperature adjustment range, randomly select a wind speed value from the wind speed adjustment range, and construct an analysis set with the selected temperature value and wind speed value, and construct N analysis sets in total. ; Take an analysis set, optimal operation mode and energy consumption impact data as a set of research data, The research data of each group are input into the hot and cold analysis model respectively to obtain the hot and cold index PMV corresponding to each group of research data, and calculate the dissatisfaction PPD corresponding to each group of research data, where ; The dissatisfaction PPD corresponding to each group of research data is sorted from small to large, and the analysis set in the research data corresponding to the dissatisfaction PPD ranked first is used as the adjustment set; the fan speed and supply air temperature in the optimal operating parameters are adjusted according to the adjustment set.

7. An energy-saving device for optimizing the operation of a central air-conditioning unit using big data, implementing an energy-saving method for optimizing the operation of a central air-conditioning unit using big data as described in any one of claims 1 to 6, It is characterized in that include: Impact data collection module, used to collect energy consumption impact data, including building impact data and environmental impact data; The energy consumption range calculation module is used to calculate the energy consumption range according to the energy consumption impact data, and optimize the energy consumption range to obtain the optimal energy consumption range; The adjustment judgment module is used to collect the energy consumption of the unit and compare it with the optimal energy consumption range to determine whether to generate an adjustment instruction; The energy consumption matching module is used to select the best energy consumption value from the best energy consumption range by using a clone selection algorithm if an adjustment instruction is generated; The unit control module is used to obtain the corresponding optimal operating parameters according to the optimal energy consumption value, and control the unit to operate according to the optimal operating parameters.

Images