Energy-saving control method and system of fresh air system

Abstract

The application provides an energy-saving control method and system of a fresh air system, and relates to the technical field of regulating a fresh air system. The method comprises the following steps: collecting real-time environmental data, personnel physical data of a target area, and historical fresh air regulation amount, historical environmental data and historical personnel physical data; calculating real-time PMV values and historical PMV values respectively through a heat balance equation, constructing a BI-LSTM model, training the model with the historical PMV values and the historical fresh air regulation amount, inputting the real-time PMV values into the trained BI-LSTM model to obtain a predicted fresh air regulation amount; and regulating the air supply amount of the fresh air system according to the predicted fresh air regulation amount. The application can save energy to a certain extent and improve the comfort of indoor personnel.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of regulating fresh air systems, in particular to an energy-saving control method and system for a fresh air system. BACKGROUND

[0002] In modern building environments, fresh air systems, as important equipment for ensuring indoor air quality and comfort, are widely used in various types of building spaces. However, the current fresh air systems generally have the problem of regulation lag during operation.

[0003] A Chinese invention patent with publication number CN117109133A provides an air conditioning system regulation method based on changes in the number of personnel. The patent designs a simulation model based on parameters and calculates the PMV index based on the simulation results. Then it is determined whether the absolute value of the PMV index is less than 1. The absolute value of the PMV index is less than 1, and the opening of the valve is adjusted.

[0004] The above patent only adjusts the valve opening when the absolute value of the PMV index is less than 1. Once the absolute value of the PMV index exceeds 1, it means that some people may have felt hot or cold, especially for the elderly, children and people with sensitive constitutions. This discomfort will be more pronounced. If valve adjustment is performed at this time, people will still have to wait for a period of time in an uncomfortable environment during the adjustment process, which undoubtedly reduces the overall quality of the indoor environment. And in the process of waiting for the PMV index to reach the adjustment threshold, the air conditioning system will continue to operate at an inappropriate power. In order to restore the indoor environment to a comfortable state, the air conditioning system needs to consume more energy to adjust, thereby causing energy waste. SUMMARY

[0005] In order to save energy to some extent and improve the comfort of indoor personnel, the present application provides an energy-saving control method and system for a fresh air system.

[0006] In a first aspect, the present application provides an energy-saving control method for a fresh air system, which adopts the following technical solution:

[0007] An energy-saving control method for a fresh air system, comprising the following steps:

[0008] Data acquisition: acquiring real-time environmental data and real-time personnel constitution data of a target area; acquiring historical fresh air regulation amount, historical environmental data and historical personnel constitution data of the target area;

[0009] Prediction: input real-time environmental data and real-time personnel physical data into the heat balance equation to calculate real-time PMV value, input historical environmental data and historical personnel physical data into the heat balance equation to calculate historical PMV value; build a BI-LSTM model, train the BI-LSTM model using historical PMV value and historical fresh air regulation amount, and obtain the trained BI-LSTM model; input the real-time PMV value into the trained BI-LSTM model to obtain the predicted fresh air regulation amount;

[0010] Regulation: regulating the air supply amount of the fresh air system according to the predicted fresh air regulation amount.

[0011] The present application first collects real-time environmental data and real-time personnel physical data, and calculates real-time PMV value accordingly to accurately reflect the thermal comfort state of the current personnel in the indoor environment. The PMV value calculated by the present application takes into account the physical differences of personnel, such as different ages, genders, and health conditions, which affect temperature and humidity perception. The above method can make the regulation more in line with individual needs. Subsequently, the present application predicts the fresh air regulation amount and regulates the fresh air system in real time, so that the fresh air system can quickly respond to changes in indoor environment, minimize the feeling of cold or heat caused by environmental discomfort, and maintain a comfortable indoor microclimate. Subsequently, the present application trains a BI-LSTM model using historical data to mine potential laws among the data and predict the fresh air regulation amount in advance. The active regulation of the fresh air system is realized before the absolute value of the real-time PMV value exceeds 1. Compared with the traditional fixed air supply amount mode, the present application can reduce the situation of lagging regulation.

[0012] The present application can reduce the air supply amount when there are few people, reducing the energy consumption of the fan. Conversely, when the number of people increases, the present application can increase the air supply amount to keep the personnel in a comfortable zone while reducing energy waste, effectively improving energy utilization efficiency and reducing the operating cost of the fresh air system. The present application considers the influence of various factors on the indoor environment, including environmental factors such as temperature and humidity, as well as personnel physical differences, thereby building a more comprehensive regulation basis. Training the BI-LSTM model to learn the complex relationships in historical data enables accurate prediction of fresh air regulation amount under different conditions. The predicted fresh air regulation amount can provide accurate regulation instructions for the fresh air system, and compared with single parameter regulation, the present application can significantly improve the regulation accuracy.

[0013] Optionally, the data collection step further comprises collecting the volume, real-time CO2 concentration and real-time VOCs concentration of the target area;

[0014] After the data collection step is performed, the method further comprises:

[0015] Concentration judgment: determining whether the real-time CO2 concentration and the real-time VOCs concentration are both less than the corresponding concentration threshold value, if yes, no processing is performed; if no, the step of determining the ventilation amount is performed;

[0016] determining a target ventilation volume according to the volume of the target area, the concentration threshold, the real-time CO2 concentration and the real-time VOCs concentration, and performing the step of regulating;

[0017] The step of regulating further comprises calculating the sum of the target ventilation volume and the predicted fresh air regulation volume, denoted as first data, and using the first data to replace the predicted fresh air regulation volume to regulate the supply air volume of the fresh air system.

[0018] The present application can determine the target ventilation volume according to the volume of the target area, the concentration threshold, the real-time CO2 concentration and the real-time VOCs concentration, and adjust the supply air volume of the fresh air system according to the target ventilation volume to introduce fresh air and discharge indoor polluted air in time, thereby reducing the pollutant concentration and improving the indoor air quality, when the CO2 concentration or the VOCs concentration exceeds the corresponding concentration threshold by monitoring the real-time CO2 concentration and the real-time VOCs concentration and comparing them with the corresponding concentration threshold.

[0019] The present application combines the target ventilation volume determined based on the real-time CO2 concentration and the real-time VOCs concentration with the predicted fresh air regulation volume based on the real-time PMV value, and comprehensively considers the indoor thermal comfort and air quality. The above-mentioned multi-factor regulation mode enables the fresh air system to achieve better operation effect under different environmental conditions, further enhancing the flexibility and adaptability. When the real-time CO2 concentration and the real-time VOCs concentration are both less than the corresponding concentration threshold, the present application does not make any treatment, reducing unnecessary fresh air supply in the case of good air quality, thereby reducing energy waste. Only when the real-time CO2 concentration or the real-time VOCs concentration exceeds the standard, the fresh air volume is increased according to the actual situation, making the use of energy more accurate and efficient.

[0020] Optionally, before the step of performing the concentration judgment, the method further comprises:

[0021] calculating the CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air regulation volume; adjusting the real-time CO2 concentration by using the CO2 concentration change amount to obtain the adjusted CO2 concentration; adjusting the real-time VOCs concentration by using the VOCs concentration change amount to obtain the adjusted VOCs concentration; and performing the step of concentration judgment;

[0022] In the step of concentration judgment, the adjusted CO2 concentration is used to replace the real-time CO2 concentration, and the adjusted VOCs concentration is used to replace the real-time VOCs concentration.

[0023] The application calculates the CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air adjustment amount, then adjusts the real-time CO2 concentration based on the CO2 concentration change amount and adjusts the real-time VOCs concentration based on the VOCs concentration change amount. By using the above scheme, the application can not only determine whether the fresh air amount needs to be adjusted according to the real-time CO2 concentration and the real-time VOCs concentration, but also can predict the change of the real-time CO2 concentration and the real-time VOCs concentration caused by the fresh air adjustment amount in advance. The traditional method of judging based on real-time concentration is to judge based on the real-time CO2 concentration and the real-time VOCs concentration. However, the predicted fresh air adjustment amount will have the effect of adjusting the real-time CO2 concentration and the real-time VOCs concentration. When determining the target air exchange amount, the application can more accurately determine the target air exchange amount according to the real-time CO2 concentration, the real-time VOCs concentration and the effect of the fresh air adjustment amount, which helps to reduce the situation of excessive or insufficient air exchange amount, so that the fresh air system can provide the right amount of fresh air supply according to the actual demand, and further improve the accuracy of regulation.

[0024] The application no longer simply judges the real-time CO2 concentration and the real-time VOCs concentration, but also considers the predicted fresh air adjustment effect, so that the concentration judgment is more accurate. By using the above scheme, the misjudgment caused by not considering the fresh air adjustment effect can be reduced. For example, when the fresh air amount is about to reduce the pollutant concentration to a reasonable range, unnecessary fresh air supply is no longer increased, reducing energy waste.

[0025] Optionally, the step of judging the concentration further comprises:

[0026] The CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air adjustment amount are calculated, and the concentration threshold is adjusted by using the CO2 concentration change amount and the VOCs concentration change amount to obtain a new concentration threshold.

[0027] The application calculates the CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air adjustment amount to adjust the concentration threshold, so that the air quality judgment standard can change in real time according to the adjustment of the fresh air system. After dynamic adjustment, the application can more accurately determine when the fresh air amount needs to be increased or maintained according to the dilution ability of the pollutant by the fresh air adjustment amount, so that the indoor pollutant concentration is always within the health standard, effectively improving the air quality. Before adjusting the fresh air system according to the predicted fresh air adjustment amount, the application can lower the concentration threshold according to the concentration change amount, so that the judgment result in the concentration judgment step is more in line with the actual situation.

[0028] Optionally, when the real-time CO2 concentration and the real-time VOCs concentration are both less than the corresponding new concentration threshold, the step of judging the concentration further comprises:

[0029] judging whether the real-time PMV value is within a range of ±5% for a preset time length, and if yes, controlling to reduce the opening degrees of the fresh air valve and the exhaust air valve of the fresh air system and to increase the opening degree of the return air valve of the fresh air system, and if not, not processing.

[0030] When the real-time CO2 concentration and the real-time VOCs concentration are both less than the new concentration threshold, it indicates that the current indoor air quality is good. At this time, the application further judges whether the real-time PMV value is within a range of ±5% for a preset time length, and if the condition is met, the opening degrees of the fresh air valve and the exhaust air valve of the fresh air system are controlled to be reduced, and the opening degree of the return air valve is increased. By adopting the above scheme, the application can reduce the amount of outdoor fresh air introduced and the amount of indoor air exhausted, thereby reducing the energy consumption of the fresh air system. Because introducing outdoor air often needs to consume additional energy to adjust its temperature and humidity to adapt to the indoor environment, reducing the amount of introduction can effectively save this part of energy consumption. Increasing the opening degree of the return air valve means that more indoor air is recycled. Since the temperature and humidity of the indoor air have approached the comfortable state, recycling again can reduce the energy required for temperature and humidity adjustment of new air. That is, the application can realize the optimal allocation of energy and improve the energy utilization efficiency on the premise of ensuring the indoor environmental comfort.

[0031] Optionally, after the step of performing prediction, before the step of performing regulation, further comprising:

[0032] setting a range: generating a plurality of regulation strategies according to the predicted fresh air regulation amount, the regulation strategies comprising: a real fresh air regulation amount, a target temperature setting value and a target PMV value; inputting the target PMV value into the trained BI-LSTM model to obtain a target fresh air regulation amount, the real fresh air regulation amount being between the target fresh air regulation amount and the predicted fresh air regulation amount; setting a value range of the target temperature setting value;

[0033] initialization: setting a target function of the NSGA-II algorithm, the target function comprising an energy saving function and a comfort function, performing binary coding processing on the real fresh air regulation amount and the target temperature setting value in each regulation strategy respectively to obtain a coding result of each real fresh air regulation amount and a coding result of each target temperature setting value, splicing the coding result of a real fresh air regulation amount and the coding result of a target temperature setting value into a binary string, and taking a binary string as a chromosome of the NSGA-II algorithm;

[0034] Determine the target strategy: adopt the NSGA-II algorithm to obtain the target chromosome in multiple chromosomes, take the control strategy corresponding to the target chromosome as the Pareto optimal solution, repeat the execution of this step multiple times, until the execution times reach the maximum iteration times, integrate all the Pareto optimal solutions into a Pareto optimal solution set, and select the control strategy with the minimum energy consumption in the Pareto optimal solution set as the target strategy;

[0035] In the step of regulation, the air supply amount of the fresh air system is regulated according to the target strategy.

[0036] The present application finds the Pareto optimal solution in multiple control strategies through the NSGA-II algorithm, and finally selects the control strategy with the minimum energy consumption as the target strategy, which comprehensively considers the influence of the real fresh air regulation amount and the target temperature set value on energy consumption, and can effectively reduce the energy waste caused by excessive regulation. Under different indoor and outdoor environments and personnel activity conditions, the present application can accurately match the fresh air regulation scheme that can meet the indoor environment demand and reduce the energy consumption to the maximum extent. Compared with the traditional fixed mode or simple regulation mode, the present application can greatly reduce the operating energy consumption of the fresh air system. The present application introduces the target PMV value into the control strategy, and obtains the target fresh air regulation amount through the trained BI-LSTM model, which can fully consider the thermal comfort feeling of personnel when regulating the air supply amount, and then adjusts the fresh air regulation amount and the target temperature set value according to the demand of personnel for thermal comfort, so as to create a comfortable and healthy indoor environment and improve the comfort experience of personnel in the indoor environment.

[0037] The introduction of the NSGA-II algorithm enables the present application to find a balance between multiple conflicting objectives (i.e. energy saving and comfort). Through binary coding and chromosome selection of the real fresh air regulation amount and the target temperature set value, fine search and optimization of the control parameters are realized. Compared with simple regulation of a single parameter, the multi-objective optimization method adopted by the present application can more accurately adjust the fresh air system according to the changes of indoor and outdoor environments and personnel demand, and improve the accuracy and stability of regulation. Under different seasons, different outdoor climate conditions, and frequent changes of indoor personnel number and activity, the present application can quickly adapt to the dynamic changes of the environment by continuously adjusting the control strategy. Using the predicted fresh air regulation amount to generate multiple strategies, and then screening the optimal solution through the algorithm, the fresh air system can always maintain a good operating state in a complex and variable environment, and maintain the stability and adaptability of the indoor environment.

[0038] Optionally, the step of initialization further comprises:

[0039] determine the control precision of the real fresh air regulation amount and the target temperature set value, determine the number of binary coding bits based on the control precision, and perform binary coding processing on the real fresh air regulation amount and the target temperature set value in each control strategy respectively according to the number of binary coding bits;

[0040] The calculation model of the number of binary coding bits is as follows:

[0041] ;

[0042] wherein, is the number of binary coding bits of the real fresh air regulation amount; is the number of binary coding bits of the target temperature set value; is the maximum value of the real fresh air regulation amount; is the maximum value of the target temperature set value; is the minimum value of the real fresh air regulation amount; is the minimum value of the target temperature set value; is the control precision of the real fresh air regulation amount; is the control precision of the target temperature set value.

[0043] By determining the control precision and calculating the number of binary coding bits according to the control precision, the real fresh air regulation amount and the target temperature set value can be binary coded with appropriate precision, so that the fresh air system can be adjusted more accurately according to actual needs, and the adjustment error caused by insufficient precision can be avoided as much as possible, thereby improving the accuracy of indoor environment control. The control precision can be adjusted according to actual conditions, thereby enhancing the adaptability and flexibility of the fresh air system.

[0044] The appropriate number of binary coding bits helps the NSGA-II algorithm to search and optimize more efficiently. Too few coding bits will result in too small search space, which cannot find the optimal solution; while too many coding bits will increase the computational complexity and search time of the algorithm. By calculating the number of binary coding bits based on the control precision, the size of the search space can be reasonably controlled under the premise of ensuring the search precision, the search efficiency of the algorithm is improved, and the Pareto optimal solution is found faster, so that the operation strategy of the fresh air system can be adjusted in time.

[0045] Optionally, the step of determining the target strategy further comprises:

[0046] segmenting the target chromosome according to the number of binary coding bits of the real fresh air regulation amount and the number of binary coding bits of the target temperature set value to obtain a coding block of the real fresh air regulation amount and a coding block of the target temperature set value, and decoding the coding block of the real fresh air regulation amount and the coding block of the target temperature set value respectively to obtain a decoded real fresh air regulation amount and a decoded target temperature set value;

[0047] determining whether the decoded real fresh air regulation amount and the decoded target temperature setting value meet expectations, and if so, not processing; and if not, issuing an alarm signal.

[0048] The application obtains the decoded real fresh air regulation amount and the decoded target temperature setting value by segmenting and decoding the target chromosome, so as to convert the optimization result obtained by the NSGA-II algorithm into parameters that can be actually used to regulate and control the fresh air system. By determining whether these parameters meet expectations, the application can timely find abnormal situations that may occur in the algorithm optimization process. If the decoded parameters do not meet expectations, it means that the regulation and control strategy obtained by the algorithm has a problem, and the target strategy cannot be applied to actual regulation and control at this time, thereby reducing the situation that the fresh air system abnormally operates due to incorrect parameters and ensuring the reliability of the operation of the fresh air system.

[0049] In a second aspect, the application provides an energy-saving control system of a fresh air system, which adopts the following technical scheme:

[0050] An energy-saving control system of a fresh air system, comprising a processor and a memory,

[0051] The memory stores program codes;

[0052] The processor executes the steps of the method of the first aspect when calling the program codes in the memory.

[0053] In summary, the application has the following at least one beneficial technical effect:

[0054] 1. The application comprehensively considers the influence of various factors on the indoor environment, covering not only environmental factors such as temperature and humidity, but also physical differences of personnel, to build a more comprehensive regulation and control basis. The BI-LSTM model trains and learns the complex relationship in the historical data to accurately predict the fresh air regulation amount under different conditions and provide accurate regulation and control instructions for the fresh air system. Compared with single parameter regulation, the regulation and control accuracy can be significantly improved.

[0055] 2. The application takes into account the influence of the fresh air regulation amount when determining the concentration of pollutants, which helps to reduce the situation that the air exchange amount is too large or too small, so that the fresh air system can provide just the right amount of fresh air supply according to the actual demand, reducing energy waste. BRIEF DESCRIPTION OF DRAWINGS

[0056] Fig. 1 is a flowchart of embodiment 1 of the application;

[0057] Fig. 2 is a flowchart of embodiment 2 of the application;

[0058] Fig. 3 is a flowchart of embodiment 4 of the application. DETAILED DESCRIPTION

[0059] The following description Figs. 1 to 3 The present application is further described in detail.

[0060] Embodiment 1: The embodiment discloses an energy-saving control method of a fresh air system, referring to Fig. 1 , the method comprises: S11 data acquisition, S12 prediction and S13 regulation, first, real-time environmental data, personnel physical data of a target area, and historical fresh air regulation amount, historical environmental data and historical personnel physical data are collected; then, the real-time PMV value and the historical PMV value are calculated respectively through the heat balance equation, the BI-LSTM model is constructed, the model is trained by the historical PMV value and the historical fresh air regulation amount, then the real-time PMV value is input into the trained BI-LSTM model to obtain the predicted fresh air regulation amount; finally, the air supply amount of the fresh air system is regulated according to the predicted fresh air regulation amount, and the embodiment comprises the following steps:

[0061] S11 data acquisition, real-time environmental data and real-time personnel physical data of a target area are collected; historical fresh air regulation amount, historical environmental data and historical personnel physical data of the target area are collected.

[0062] The real-time environmental data comprises temperature, humidity, wind speed and radiation temperature.

[0063] The personnel physical data comprises metabolic rate, clothing thermal resistance and personnel distribution and quantity, and the collection mode of the personnel physical data is as follows:

[0064] The metabolic rate is estimated by detecting the activity level of the personnel.

[0065] The clothing thermal resistance is estimated according to the dressing condition of the personnel.

[0066] The personnel distribution and quantity are the number and distribution of personnel in the target area.

[0067] The historical environmental data is the same as the real-time environmental data in type, but the time range covered by the data is longer, and the collection time is several weeks or months.

[0068] The historical personnel physical data is the same as the real-time personnel physical data in type, the collection time is the same as the historical environmental data, and the collection time stamp of the historical personnel physical data, the collection time stamp of the historical environmental data and the collection time stamp of the historical fresh air regulation amount should be similar or the same in principle.

[0069] In other embodiments, if the collection timestamps of the historical personnel constitution data, the collection timestamps of the historical environment data, and the collection timestamps of the historical fresh air adjustment amount are different, a DTW algorithm is used for time alignment processing, and in the S12 prediction, the historical personnel constitution data, the historical environment data, and the historical fresh air adjustment amount processed by the DTW algorithm are used to train the BI-LSTM model.

[0070] In the S12 prediction, the real-time collected environment data and personnel constitution data are input into the heat balance equation to calculate the real-time PMV value. The historical environment data and personnel constitution data are input into the heat balance equation to calculate the historical PMV value.

[0071] The PMV value is based on Fanger's heat balance equation, which comprehensively considers the influence of environmental parameters (temperature, humidity, radiant temperature) and personnel parameters (metabolic rate, clothing thermal resistance) on human thermal comfort. The calculation method of the PMV value is already very mature, and this embodiment will not be described in more detail. The core idea of the PMV value is to calculate the heat exchange balance between the human body and the environment, and to obtain a value between -3 (cold) and +3 (hot). 0 represents a neutral state.

[0072] The BI-LSTM model is constructed. The BI-LSTM model is a variant of a recurrent neural network (RNN) that can simultaneously learn forward and backward information of data, has strong ability to capture long-term dependencies in data, and the bidirectional structure of the BI-LSTM model allows the BI-LSTM model to consider past and future information (future information is not available when predicting, but can be used when training), improving prediction accuracy.

[0073] The training process of the BI-LSTM model is as follows: the historical PMV value is used as training data, the historical fresh air adjustment amount is used as training label, the training set and validation set are divided, the weights and biases of the BI-LSTM model are initialized, the model parameters are adjusted using the backpropagation algorithm and the optimizer (such as Adam), the error (such as mean square error MSE) between the predicted value and the true value is minimized, the model performance is evaluated on the validation set, and the phenomenon of overfitting is reduced.

[0074] The real-time calculated PMV value is input into the trained BI-LSTM model, and the predicted fresh air adjustment amount is output.

[0075] In the S13 regulation, the predicted fresh air adjustment amount is directly sent to the controller of the fresh air system, and the speed of the air supply fan or the opening of the fresh air valve in the fresh air system is regulated according to the predicted fresh air adjustment amount, so as to change the air supply amount of the fresh air system.

[0076] The embodiment first acquires real-time environmental parameters and real-time personnel physical data of a target area, and synchronously collects historical fresh air adjustment amount, historical environmental data and historical personnel physical data of the target area; then, based on a heat balance equation, real-time PMV value and historical PMV value are calculated to quantify thermal comfort, a BI-LSTM model is trained by using historical PMV and fresh air adjustment amount, and the fresh air adjustment amount is predicted by using the trained BI-LSTM model; finally, the predicted fresh air adjustment amount is converted into a fresh air system control instruction, the air supply amount of the fresh air system is dynamically adjusted, and a closed-loop feedback is formed in combination with real-time monitoring data. The embodiment can, after the fresh air system is turned on and the real-time PMV value is initially adjusted to a comfortable state, predict the fresh air adjustment amount based on the real-time PMV value and the BI-LSTM model, so as to adjust the indoor environment in advance before the absolute value of the real-time PMV value exceeds 1, thereby realizing energy saving optimization while ensuring personnel thermal comfort.

[0077] Embodiment 2: Refer to Fig. 2 The difference between the embodiment and Embodiment 1 is that the S11 data collection further includes collection of the volume of the target area, real-time CO2 concentration and real-time VOCs (volatile organic compounds) concentration.

[0078] After performing the S11 data collection, the method further includes:

[0079] S21 concentration judgment, double threshold checking is performed on the real-time CO2 concentration and the real-time VOCs concentration, that is, checking whether the real-time CO2 concentration and the real-time VOCs concentration meet the condition that the real-time CO2 concentration is less than the CO2 concentration threshold and the real-time VOCs concentration is less than the VOCs concentration threshold, if yes, it is determined that the indoor air quality meets the standard, and the current state of the fresh air system is maintained; otherwise, S22 determination of air exchange amount is immediately performed.

[0080] S22 determination of air exchange amount, the target air exchange amount is determined according to the volume of the target area, the concentration threshold, the real-time CO2 concentration and the real-time VOCs concentration, so that the target air exchange amount can dilute the concentration of pollutants (i.e. the real-time CO2 concentration and the real-time VOCs concentration) and reduce energy waste caused by excessive ventilation, and then S13 regulation is performed.

[0081] The calculation method of the target air exchange amount is as follows:

[0082] Target air exchange amount = |real-time CO2 concentration - CO2 concentration threshold| x volume of target area + |real-time VOCs concentration - VOCs concentration threshold| x volume of target area.

[0083] S13 regulation, the target ventilation volume is summed with the predicted fresh air regulation volume to obtain first data, and the first data is used to replace the predicted fresh air regulation volume to generate a control instruction of the fresh air system. This step superimposes the rigid ventilation volume driven by the pollutants and the flexible regulation volume driven by the thermal comfort, and takes into account the air quality guarantee and the energy saving optimization target, to form a multi-objective collaborative regulation scheme.

[0084] In other embodiments, before performing S21 concentration judgment, the method further comprises:

[0085] S20 concentration regulation, the CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air regulation volume are calculated, and the calculation method is as follows:

[0086] CO2 concentration change amount = real-time CO2 amount ÷ target area volume;

[0087] Real-time CO2 amount = original CO2 amount - exhaust CO2 amount + fresh air CO2 amount;

[0088] Original CO2 amount = CO2 concentration before input of fresh air × target area volume;

[0089] Exhaust CO2 amount = CO2 concentration before input of fresh air × exhaust indoor air amount;

[0090] Fresh air CO2 amount = predicted fresh air regulation volume × 0.00042;

[0091] Exhaust indoor air amount = exhaust speed of the fresh air system × exhaust time.

[0092] The exhaust time is equal to the time for which the fresh air system inputs the supply air into the indoor.

[0093] The calculation method of the VOCs concentration change amount is the same as that of the CO2 concentration change amount, which will not be described herein.

[0094] The real-time CO2 concentration is adjusted by using the CO2 concentration change amount to obtain the adjusted CO2 concentration, which is equal to the difference between the real-time CO2 concentration and the CO2 concentration change amount.

[0095] The real-time VOCs concentration is adjusted by using the VOCs concentration change amount to obtain the adjusted VOCs concentration, which is equal to the difference between the real-time VOCs concentration and the VOCs concentration change amount.

[0096] In S21 concentration judgment, the adjusted CO2 concentration is used to replace the real-time CO2 concentration, and the adjusted VOCs concentration is used to replace the real-time VOCs concentration, that is, whether the adjusted CO2 concentration and the adjusted VOCs concentration are less than the corresponding concentration threshold is judged.

[0097] After the execution of the S12 prediction, the embodiment obtains the fresh air adjustment amount input into the room (i.e., the predicted fresh air adjustment amount), which has a certain dilution effect on the real-time CO2 concentration and the real-time VOCs concentration. When the real-time CO2 concentration and the real-time VOCs concentration are judged in terms of concentration, the influence of the predicted fresh air adjustment amount on the real-time CO2 concentration and the real-time VOCs concentration is considered, and the target air exchange amount is reduced. Therefore, the embodiment can guarantee indoor air quality while reducing the energy consumption of the fresh air system by using a multi-target collaborative strategy.

[0098] Embodiment 3: The difference between this embodiment and Embodiment 2 is that the S21 concentration judgment further includes:

[0099] The CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air adjustment amount are calculated. In this embodiment, the calculation method of the CO2 concentration change amount and the VOCs concentration change amount is the same as that in Embodiment 2, which will not be described again here.

[0100] The concentration threshold is adjusted using the CO2 concentration change amount and the VOCs concentration change amount to obtain a new concentration threshold. Each time this step is executed, the original concentration threshold, i.e., the original CO2 concentration threshold and the original VOCs concentration threshold, is adjusted as follows:

[0101] New CO2 concentration threshold = original CO2 concentration threshold - CO2 concentration change amount

[0102] New VOCs concentration threshold = original VOCs concentration threshold - VOCs concentration change amount

[0103] In the S21 concentration judgment, it is judged whether the real-time CO2 concentration and the real-time VOCs concentration are both less than the corresponding new concentration threshold. If so, it is further judged whether the real-time PMV value is within ±5% for a preset time length. If so, the opening of the fresh air valve and the exhaust valve of the fresh air system is reduced, and the opening of the return air valve of the fresh air system is increased. If not, no processing is performed.

[0104] The embodiment adjusts the original concentration threshold by the predicted fresh air adjustment amount, so that the concentration judgment step can judge the real-time CO2 concentration and the real-time VOCs concentration according to the actual environment. When the real-time CO2 concentration and the real-time VOCs concentration are both less than the corresponding new concentration threshold, it is further judged whether the PMV value is continuously within ±5%. If so, the opening of different valves is adjusted. The embodiment can lower the concentration threshold according to the concentration change amount, so that the judgment result in the concentration judgment step is more in line with the actual situation.

[0105] Embodiment 4: Refer to Embodiment 3 Fig. 3The difference between this embodiment and Embodiment 1 is that, after performing S12 prediction and before performing S13 regulation, the following steps are also included:

[0106] S41 sets a range and generates multiple control strategies based on the predicted fresh air adjustment amount. The control strategies include: actual fresh air adjustment amount, target temperature setpoint, and target PMV value.

[0107] The actual fresh air regulation volume refers to the air volume control value that actually acts on the fresh air system, that is, the actual fresh air regulation volume input into the room. The value range of the actual fresh air regulation volume is between the target fresh air regulation volume and the predicted fresh air regulation volume.

[0108] The target temperature setpoint refers to the target temperature control value of the air conditioning system linked with the fresh air system. The range of the target temperature setpoint is set to [Tmin, Tmax] (e.g., Tmin=24 degrees Celsius, Tmax=30 degrees Celsius). In other embodiments, the range of the target temperature setpoint can be set according to requirements.

[0109] The target PMV value refers to the thermal comfort control target. The target PMV value is set in the range of [-0.5, 0.5] (i.e. the comfort range). By adjusting the target PMV value, the coordination between the fresh air system and the air conditioning system can be indirectly affected.

[0110] The target PMV value is input into the trained BI-LSTM model to derive the target fresh air regulation amount required to maintain the target PMV value.

[0111] S42 Initialization: This step uses the NSGA-II algorithm (Non-Dominated Sorting Genetic Algorithm) to solve the multi-objective optimization problem, and sets the objective function of the NSGA-II algorithm. The objective function includes an energy-saving function and a comfort function, and the calculation models for the energy-saving function and the comfort function are as follows:

[0112] Energy saving function The calculation model is as follows:

[0113] ;

[0114] in, Weighting of the energy consumption of the fresh air system; Energy consumption of the fresh air system; Weighting of air conditioning system energy consumption; This refers to the energy consumption of the air conditioning system.

[0115] Comfort function The calculation model is as follows:

[0116] ;

[0117] in, is a weight of PMV variation; the numerical value of PMV variation is equal to the target PMV value is the absolute value of the difference between the real-time PMV value and the target PMV value is the absolute value of the difference between the real-time PMV value and the target PMV value is a weight of temperature variation; the temperature variation is equal to the target temperature setting value is the absolute value of the difference between the real-time temperature value and the target temperature setting value is the absolute value of the difference between the real-time temperature value and the target temperature setting value

[0118] In other embodiments, the energy saving function and the comfort function can also be set according to requirements.

[0119] The control precision of the real fresh air regulation amount and the target temperature setting value is determined, the number of binary coding bits is determined based on the control precision, and the real fresh air regulation amount and the target temperature setting value in each control strategy are respectively processed by binary coding according to the number of binary coding bits to obtain the coding result of each real fresh air regulation amount and the coding result of each target temperature setting value. The coding result of one real fresh air regulation amount and the coding result of one target temperature setting value are spliced into one binary string, and one binary string is taken as one chromosome of the NSGA-II algorithm.

[0120] The calculation model of the number of binary coding bits is as follows:

[0121] ;

[0122] wherein, is the number of binary coding bits of the real fresh air regulation amount; is the number of binary coding bits of the target temperature setting value; is the maximum value of the real fresh air regulation amount; is the maximum value of the target temperature setting value; is the minimum value of the real fresh air regulation amount; is the minimum value of the target temperature setting value; is the control precision of the real fresh air regulation amount; is the control precision of the target temperature setting value.

[0123] S43 determines a target strategy, acquires a target chromosome from multiple chromosomes by using the NSGA-II algorithm, takes the control strategy corresponding to the target chromosome as a Pareto optimal solution, repeatedly executes this step multiple times, and after the number of executions reaches a maximum iteration number, integrates all the Pareto optimal solutions into a Pareto optimal solution set, selects a control strategy with the minimum energy consumption from the Pareto optimal solution set as the target strategy, and the process is as follows:

[0124] For each chromosome, the numerical value of its objective function is calculated and is denoted as a target value, wherein the target value is equal to the sum of the function value of the energy saving function and the function value of the comfort function.

[0125] The chromosomes are non-dominantly sorted according to the target value, and the non-dominant level of each chromosome is determined.

[0126] Within each non-dominant level, the crowding degree of the chromosome is calculated.

[0127] One or more chromosomes are selected from the non-dominant level 1 as the Pareto optimal solution.

[0128] The above steps (which can include crossover, mutation to generate new chromosomes) are repeated until a maximum number of iterations is reached, and a new Pareto optimal solution can be generated after each iteration. Therefore, the embodiment integrates all the selected Pareto optimal solutions in all iterations into a set, removes duplicate solutions in the set, and obtains a Pareto optimal solution set.

[0129] From the Pareto optimal solution set, the control strategy with the minimum energy consumption is selected as the target strategy.

[0130] In S13 regulation, the supply air volume of the fresh air system is regulated according to the target strategy.

[0131] In other embodiments, S43 determining the target strategy further comprises:

[0132] According to the number of binary coded bits of the real fresh air adjustment amount and the number of binary coded bits of the target temperature set value, the target chromosome is segmented to obtain the coding block of the real fresh air adjustment amount and the coding block of the target temperature set value.

[0133] Using the decoding method corresponding to the binary coding, the coding block of the real fresh air adjustment amount and the coding block of the target temperature set value are decoded respectively to obtain the decoded real fresh air adjustment amount and the decoded target temperature set value.

[0134] It is judged whether the decoded real fresh air adjustment amount and the decoded target temperature set value meet the expectation respectively, if yes, no processing is performed; if not, an alarm signal is sent.

[0135] The embodiment balances the energy saving and comfort of the fresh air system through the NSGA-II algorithm, and reduces the risk of deterioration of thermal comfort caused by traditional single-objective control (such as only minimizing energy consumption).

[0136] Embodiment 5: The embodiment provides a fresh air system energy saving control system, comprising: a processor and a memory,

[0137] The memory stores program code;

[0138] The processor executes the steps of the method when calling the program code in the memory.

[0139] The above are all preferred embodiments of the present application, and do not limit the protection scope of the present application, so that: all equivalent changes made according to the structure, shape, principle of the present application should be covered in the protection scope of the present application.

Claims

1. An energy-saving control method of a fresh air system, characterized by, The method comprises the following steps: Data collection: collecting real-time environmental data and real-time personnel physical data of a target area; collecting historical fresh air adjustment amount, historical environmental data and historical personnel physical data of the target area; Prediction: inputting the real-time environmental data and the real-time personnel physical data into a heat balance equation to calculate a real-time PMV value, and inputting the historical environmental data and the historical personnel physical data into the heat balance equation to calculate a historical PMV value; constructing a BI-LSTM model, training the BI-LSTM model by using the historical PMV value and the historical fresh air adjustment amount, and obtaining a trained BI-LSTM model; Inputting the real-time PMV value into the trained BI-LSTM model to obtain a predicted fresh air adjustment amount; Control: controlling the air supply amount of a fresh air system according to the predicted fresh air adjustment amount; After the step of prediction is performed, before the step of control is performed, the method further comprises the following steps: Range setting: generating a plurality of control strategies according to the predicted fresh air adjustment amount, wherein the control strategies comprise a real fresh air adjustment amount, a target temperature setting value and a target PMV value; inputting the target PMV value into the trained BI-LSTM model to obtain a target fresh air adjustment amount, and the real fresh air adjustment amount is between the target fresh air adjustment amount and the predicted fresh air adjustment amount; and setting a value range of the target temperature setting value; Initialization: setting a target function of an NSGA-II algorithm, wherein the target function comprises an energy saving function and a comfort function; performing binary coding processing on the real fresh air adjustment amount and the target temperature setting value in each control strategy respectively to obtain a coding result of each real fresh air adjustment amount and a coding result of each target temperature setting value; splicing the coding result of one real fresh air adjustment amount and the coding result of one target temperature setting value into one binary string; and taking one binary string as one chromosome of the NSGA-II algorithm; Determining a target strategy: obtaining a target chromosome from a plurality of chromosomes by using the NSGA-II algorithm, taking the control strategy corresponding to the target chromosome as a Pareto optimal solution, repeatedly performing the step of determining a target strategy for multiple times, until the number of execution times reaches a maximum iteration number, integrating all the Pareto optimal solutions into a Pareto optimal solution set, and selecting a control strategy with the minimum energy consumption from the Pareto optimal solution set as the target strategy; In the step of control, the air supply amount of the fresh air system is controlled according to the target strategy.

2. The energy-saving control method of the fresh air system according to claim 1, characterized in that, The step of data collection further comprises collecting the volume, real-time CO2 concentration and real-time VOCs concentration of the target area; After the step of data collection is performed, the method further comprises the following steps: Concentration judgment: judging whether the real-time CO2 concentration and the real-time VOCs concentration are less than corresponding concentration thresholds, if yes, no processing is performed, and if no, the step of determining a ventilation amount is performed; Determining a ventilation amount: determining a target ventilation amount according to the volume, the concentration threshold, the real-time CO2 concentration and the real-time VOCs concentration of the target area, and performing the step of control; The step of control further comprises calculating the sum of the target ventilation amount and the predicted fresh air adjustment amount, denoted as first data, and controlling the air supply amount of the fresh air system by using the first data instead of the predicted fresh air adjustment amount.

3. The energy-saving control method of the fresh air system according to claim 2, characterized in that, Before the step of concentration judgment is performed, the method further comprises the following steps: The CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air adjustment amount are calculated; the real-time CO2 concentration is adjusted by using the CO2 concentration change amount to obtain an adjusted CO2 concentration; the real-time VOCs concentration is adjusted by using the VOCs concentration change amount to obtain an adjusted VOCs concentration; and the concentration judgment step is performed; In the concentration judgment step, the adjusted CO2 concentration is used instead of the real-time CO2 concentration, and the adjusted VOCs concentration is used instead of the real-time VOCs concentration.

4. The energy-saving control method of the fresh air system according to claim 2, characterized in that, The concentration judgment step further includes: The CO2 concentration change amount and the VOCs concentration change amount corresponding to the predicted fresh air adjustment amount are calculated; the concentration threshold is adjusted by using the CO2 concentration change amount and the VOCs concentration change amount to obtain a new concentration threshold.

5. The energy-saving control method of the fresh air system according to claim 4, characterized in that, When the real-time CO2 concentration and the real-time VOCs concentration are both less than the corresponding new concentration threshold, the concentration judgment step further includes: It is judged whether the real-time PMV value is within ±5% range within a preset time length, if yes, the opening degree of the fresh air valve and the exhaust air valve of the fresh air system is controlled to be reduced, and the opening degree of the return air valve of the fresh air system is controlled to be increased, if not, no treatment is performed.

6. The energy-saving control method of the fresh air system according to claim 1, characterized in that, The initialization step further includes: The control precision of the real fresh air adjustment amount and the target temperature set value is determined, the number of binary coding bits is determined based on the control precision, and the real fresh air adjustment amount and the target temperature set value in each control strategy are respectively processed by binary coding according to the number of binary coding bits; The calculation model of the number of binary coding bits is as follows: ； wherein, a number of binary coded bits for the real fresh air regulation amount; a number of binary coded bits for the target temperature set value; a maximum value for the real fresh air regulation amount; a maximum value for the target temperature set value; a minimum value for the real fresh air regulation amount; a minimum value for the target temperature set value; a regulation precision for the real fresh air regulation amount; a regulation precision for the target temperature set value.

7. The energy-saving control method of the fresh air system according to claim 6, characterized in that, The step of determining the target strategy further includes: The target chromosome is segmented to obtain the coding block of the real fresh air adjustment amount and the coding block of the target temperature set value, and the coding block of the real fresh air adjustment amount and the coding block of the target temperature set value are respectively decoded to obtain the decoded real fresh air adjustment amount and the decoded target temperature set value; It is judged whether the decoded real fresh air adjustment amount and the decoded target temperature set value meet the expectation, if yes, no treatment is performed, if not, an alarm signal is sent.

8. An energy saving control system for a fresh air system, characterized in that, It includes: A processor and a memory, The memory has program code stored therein; The processor executes the steps of the method of any one of claims 1-7 when calling the program code in the memory.

Images