A high-efficiency energy-saving indoor air environment optimization method and device

Abstract

The application discloses an efficient and energy-saving indoor air environment optimization method and device, relates to the air conditioning technical field, and comprises the following steps: calculating an indoor-outdoor temperature difference sequence, deriving a first personnel oxygen consumption rate sequence and a second personnel oxygen consumption rate sequence, and calculating a comprehensive oxygen consumption rate sequence by weighting; predicting an oxygen consumption rate sequence in a future time window based on a current time period and the comprehensive oxygen consumption rate sequence; performing oxygen production unit working quantity optimization according to the predicted oxygen consumption rate sequence and a predicted indoor-outdoor temperature difference sequence in the future time window, outputting an optimal oxygen production unit working quantity sequence, and performing oxygen supply control on a split oxygen generator in the future time window. The technical problems that the prior art cannot predict indoor oxygen consumption changes in advance, the personnel oxygen consumption rate calculated by a single data source has low accuracy, and it is difficult to balance oxygen supply quality and energy saving are solved.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, specifically to a highly efficient and energy-saving method and apparatus for optimizing indoor air environment. Background Technology

[0002] Traditional indoor oxygen supply regulation often uses fixed-power oxygen production or starts and stops based on the current oxygen concentration. It cannot predict changes in indoor oxygen consumption in advance, nor does it take into account the impact of indoor and outdoor heat exchange on oxygen loss.

[0003] Meanwhile, most existing oxygen supply control schemes use a single data source to calculate the oxygen consumption rate of personnel: when relying solely on oxygen concentration, it is easily affected by the measurement accuracy of oxygen sensors and the matching error of natural oxygen loss parameters in buildings, resulting in significant deviations; when relying solely on carbon dioxide concentration, it is also affected by carbon dioxide sensor drift and the error of the preset value of respiratory exchange rate, leading to inaccurate oxygen consumption rate calculations. This results in too many oxygen generating units being turned on, causing unnecessary energy waste, or too few oxygen generating units being turned on, failing to meet the oxygen supply needs of indoor personnel, and making it difficult to balance air quality optimization and energy saving. Summary of the Invention

[0004] This application provides a highly efficient and energy-saving method and apparatus for optimizing indoor air environment, which solves the technical problems of existing technologies that cannot predict changes in indoor oxygen consumption in advance, and that the accuracy of calculating the oxygen consumption rate of personnel from a single data source is low, making it difficult to balance oxygen supply quality and energy saving.

[0005] The technical solution to the above-mentioned technical problems in this application is as follows:

[0006] In a first aspect, this application provides a highly efficient and energy-saving method for optimizing indoor air environment, the method comprising:

[0007] Simultaneously monitor and acquire the oxygen concentration sequence, carbon dioxide concentration sequence, and indoor temperature sequence of the indoor space within a historical time window, as well as the working number sequence of the oxygen generation unit of the split oxygen concentrator, and the outdoor temperature sequence of the outdoor space, and calculate the indoor-outdoor temperature difference sequence.

[0008] The first personnel oxygen consumption rate sequence is derived from the oxygen concentration sequence, the oxygen production unit working quantity sequence, and the indoor-outdoor temperature difference sequence. The second personnel oxygen consumption rate sequence is derived from the carbon dioxide concentration sequence and the indoor-outdoor temperature difference sequence. The combined oxygen consumption rate sequence is then calculated by weighting.

[0009] Based on the current time period and the comprehensive oxygen consumption rate sequence, a predicted oxygen consumption rate sequence for the future time window is obtained.

[0010] Based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, the optimal number of oxygen generating units is determined, and the optimal number of oxygen generating units is output to control the oxygen supply of the split-type oxygen generator within the future time window.

[0011] Secondly, this application provides a highly efficient and energy-saving indoor air environment optimization device, comprising:

[0012] The initial parameter acquisition module is used to synchronously monitor and acquire the oxygen concentration sequence, carbon dioxide concentration sequence, and indoor temperature sequence of the indoor space within a historical time window, as well as the working quantity sequence of the oxygen generation unit of the split oxygen generator, the outdoor temperature sequence of the outdoor space, and calculate the indoor-outdoor temperature difference sequence.

[0013] The comprehensive oxygen consumption rate calculation module is used to derive the first personnel oxygen consumption rate sequence based on the oxygen concentration sequence, the oxygen production unit working quantity sequence and the indoor-outdoor temperature difference sequence, and to derive the second personnel oxygen consumption rate sequence based on the carbon dioxide concentration sequence and the indoor-outdoor temperature difference sequence, and to calculate the comprehensive oxygen consumption rate sequence by weighting.

[0014] The oxygen consumption rate prediction module is used to predict the oxygen consumption rate sequence within a future time window based on the current time period and the comprehensive oxygen consumption rate sequence.

[0015] The oxygen generator oxygen supply control module is used to optimize the number of working oxygen generator units based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, output the optimal number of working oxygen generator units sequence, and control the oxygen supply of the split-type oxygen generator within the future time window.

[0016] This application provides one or more technical solutions, which have at least the following technical effects or advantages:

[0017] This application provides a highly efficient and energy-saving method and apparatus for optimizing indoor air quality. First, it simultaneously collects multi-source data on oxygen concentration, carbon dioxide concentration, indoor and outdoor temperature, and the operating status of the oxygen generator unit. This data is then used to correct for the natural loss rate of oxygen and carbon dioxide due to the indoor and outdoor temperature difference. Second, it employs a weighted fusion method based on dual data sources to calculate the overall oxygen consumption rate. The fusion weights are dynamically adjusted according to the current change rates of the two data sources, reducing the interference of single sensor measurement errors or parameter preset deviations on the calculation results. Finally, a predictive model is trained based on historical operating data to anticipate changes in oxygen consumption within future time windows. Then, by optimizing the oxygen supply to meet demand, the minimum number of oxygen generator units required to operate is determined. This ensures that the indoor oxygen supply quality meets the needs of personnel while avoiding unnecessary operation of oxygen generator units, effectively reducing the operating energy consumption of split-type oxygen generators and balancing indoor air quality optimization with energy saving.

[0018] Through the above technical solution, this application solves the problems in the prior art that it is impossible to predict changes in indoor oxygen consumption in advance and that the accuracy of calculating the oxygen consumption rate of personnel from a single data source is low. Under the premise of ensuring that the indoor oxygen concentration meets the needs of personnel, it minimizes the ineffective operation of the oxygen generation unit and achieves the dual goals of optimizing the indoor air environment and saving energy. It is suitable for application in various enclosed indoor spaces with split-type oxygen generation and supply scenarios. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a highly efficient and energy-saving indoor air environment optimization method provided in an embodiment of this application.

[0021] Figure 2 This is a flowchart illustrating the process of obtaining the optimal sequence of working oxygen generating units in a highly efficient and energy-saving indoor air environment optimization method provided in this application embodiment;

[0022] Figure 3 This is a schematic diagram of the structure of a high-efficiency and energy-saving indoor air environment optimization device provided in the embodiments of this application.

[0023] The components represented by each number in the attached diagram are explained below:

[0024] Initial parameter acquisition module 11, comprehensive oxygen consumption rate calculation 12, oxygen consumption rate prediction module 13, oxygen generator oxygen supply control module 14. Detailed Implementation

[0025] This application provides a highly efficient and energy-saving indoor air environment optimization method and apparatus to address the technical problems of existing technologies that cannot predict changes in indoor oxygen consumption in advance, and that the accuracy of calculating the oxygen consumption rate of personnel from a single data source is low, making it difficult to balance oxygen supply quality and energy saving.

[0026] Example 1, as Figure 1 As shown in the embodiment of this application, a highly efficient and energy-saving method for optimizing indoor air environment is provided, including:

[0027] S10: Simultaneously monitor and acquire the oxygen concentration sequence, carbon dioxide concentration sequence, and indoor temperature sequence of the indoor space within a historical time window, as well as the working quantity sequence of the oxygen generation unit of the split oxygen concentrator, and the outdoor temperature sequence of the outdoor space, and calculate the indoor-outdoor temperature difference sequence.

[0028] The split-type oxygen generator includes an indoor unit and an outdoor unit. The outdoor unit is used to generate oxygen, and the indoor unit is used to diffuse the oxygen generated by the outdoor unit into the room. The outdoor unit is composed of multiple oxygen generating units connected in parallel.

[0029] In this embodiment, an oxygen concentration sensor, a carbon dioxide concentration sensor, and a temperature sensor are installed in the indoor space, with a sampling frequency of 1 time / minute. A temperature sensor is installed in the outdoor space, and the historical time window is selected as the past 30 minutes, that is, data sequences from 30 sampling points are collected.

[0030] Meanwhile, the working status of each oxygen generating unit within the historical time window is read from the controller of the split-type oxygen generator. 0 indicates off and 1 indicates working. The number of working units at each sampling moment is counted. The indoor temperature is subtracted from the outdoor temperature at the same moment to obtain the indoor-outdoor temperature difference sequence.

[0031] Furthermore, the outdoor unit is the oxygen generator, located outdoors, such as on a balcony, wall mount, or outdoor platform. It includes multiple oxygen generator units connected in parallel. Each oxygen generator unit independently contains an air compressor, a molecular sieve adsorption tower, a switching valve group, and an oxygen storage tank. The number of working units can be flexibly adjusted according to oxygen demand, that is, only a few units are turned on when demand is low, and all units are turned on when demand is high. The nitrogen and other waste gases generated by the outdoor unit during the oxygen generation process are directly discharged into the outdoor environment and will not have a negative impact on indoor air quality.

[0032] The indoor unit includes an oxygen supply controller and a diffusion device. The oxygen supply controller receives oxygen from the outdoor unit through the oxygen supply pipeline and releases the oxygen evenly into the indoor space through the diffusion device. The oxygen concentration monitoring module on the oxygen supply controller can monitor the indoor oxygen concentration in real time and upload it to the system controller. The indoor unit and the outdoor unit transmit control signals and status feedback signals through electrical connection wires.

[0033] S20: Based on the oxygen concentration sequence, the oxygen production unit working quantity sequence and the indoor-outdoor temperature difference sequence, the first personnel oxygen consumption rate sequence is derived; based on the carbon dioxide concentration sequence and the indoor-outdoor temperature difference sequence, the second personnel oxygen consumption rate sequence is derived; and a weighted calculation is performed to obtain the comprehensive oxygen consumption rate sequence.

[0034] In the embodiments of this application, such as Figure 2 As shown, based on the oxygen concentration sequence, the oxygen production unit working quantity sequence, the indoor-outdoor temperature difference sequence, the carbon dioxide concentration sequence, and the indoor-outdoor temperature difference sequence, the oxygen consumption rate sequence for the first person and the oxygen consumption rate sequence for the second person are derived. The two derivation paths are independent of each other and serve as mutual verification. Finally, a more reliable comprehensive oxygen consumption rate sequence is obtained through weighted fusion.

[0035] The oxygen consumption rate sequence for the first person is derived from the oxygen concentration sequence, the oxygen generation unit operating quantity sequence, and the indoor-outdoor temperature difference sequence, including:

[0036] The average indoor temperature is calculated based on the indoor temperature sequence, and the initial oxygen loss rate of the indoor building is obtained by matching the average indoor temperature.

[0037] The initial oxygen loss rate is corrected based on the indoor-outdoor temperature difference sequence to obtain a first corrected oxygen loss rate sequence;

[0038] The actual oxygen production rate sequence is calculated based on the working quantity sequence of the oxygen production unit. The first corrected oxygen loss rate sequence is then subtracted from the actual oxygen production rate sequence to obtain the first initial personnel oxygen consumption rate sequence.

[0039] The oxygen concentration change rate is calculated based on the oxygen concentration sequence, and the oxygen consumption rate sequence of the first initial personnel is corrected using the oxygen concentration change rate to obtain the oxygen consumption rate sequence of the first personnel.

[0040] In this embodiment, the oxygen loss rate of an indoor building is related to factors such as building airtightness and indoor-outdoor temperature difference. Under standard operating conditions, i.e., an indoor temperature of 25°C, buildings with different airtightness levels have different initial oxygen loss rates. In this embodiment, the initial oxygen loss rate is obtained based on historical data of the indoor building, i.e., the average of historical oxygen loss rates of the indoor building at multiple indoor temperatures.

[0041] For example, when the average indoor temperature is 18°C, the initial oxygen loss rate is 0.32 L / min; when the average indoor temperature is 20°C, the initial oxygen loss rate is 0.35 L / min; when the average indoor temperature is 22°C, the initial oxygen loss rate is 0.38 L / min; when the average indoor temperature is 25°C, the initial oxygen loss rate is 0.42 L / min; and when the average indoor temperature is 28°C, the initial oxygen loss rate is 0.46 L / min.

[0042] Secondly, because the greater the temperature difference between indoors and outdoors, the faster the natural exchange of air between indoors and outdoors through the gaps in the building envelope, the higher the oxygen loss rate. Therefore, the initial oxygen loss rate is corrected based on the indoor-outdoor temperature difference sequence, and the correction formula can be R. leak,O2 (k)=R leak,O2,base (1+α|ΔT(k)|), where R leak,O2,base (k) is the initial oxygen loss rate, ΔT(k) is the indoor and outdoor temperature difference at the kth sampling time, and α is the temperature difference correction coefficient. In this embodiment, α=0.02, that is, the loss rate increases by 2% for every 1℃ temperature difference. The above calculation is performed for each sampling time within the historical time window to obtain the first corrected oxygen loss rate sequence.

[0043] For example, assuming the indoor and outdoor temperature difference is 10°C at a certain moment, the first corrected oxygen loss rate is R. leak,O2 (k)=0.41×(1+0.02×10)=0.492L / min.

[0044] Then, the oxygen production rate of each oxygen-generating unit per unit time is the rated value. Multiply the number of oxygen-generating units working at the current moment by the rated oxygen production rate of the unit to obtain the actual oxygen production rate at that moment. Subtract the corrected oxygen loss rate from the actual oxygen production rate to obtain the first initial personnel oxygen consumption rate without considering the current oxygen concentration change. That is, the first initial personnel oxygen consumption rate = actual oxygen production rate - first corrected oxygen loss rate. Calculate this sequentially for each sampling moment within the historical time window to obtain the first initial personnel oxygen consumption rate sequence.

[0045] If the oxygen concentration increases during the current sampling period, it indicates that the actual oxygen consumption per person is less than the initial calculated value; if the oxygen concentration decreases, it indicates that the actual oxygen consumption per person is greater than the initial calculated value. Therefore, further correction is made based on the rate of change of oxygen concentration to obtain the final oxygen consumption rate of the first person. Specifically, the correction formula is: Oxygen consumption rate of the first person = Initial oxygen consumption rate of the first person + V × (C) O2 (kn)-C O2 (k0)) / T, where V is the volume of the indoor space, and C O2 (kn) represents the oxygen concentration at the end of the historical time window, CO2 (k0) represents the oxygen concentration at the beginning of the historical time window, and T represents the total duration of the historical time window. If the oxygen concentration increases within the window, the final calculated oxygen consumption rate of personnel will be lower than the initial value, and vice versa. After correction, the first personnel oxygen consumption rate sequence is obtained.

[0046] For example, the indoor space volume is 30m³, the initial oxygen concentration of the historical time window is 20.5%, the final oxygen concentration is 20.7%, and the total duration is 30min. Substituting these values ​​into the correction formula, the correction term is 30×1000L / m³×(20.7%-20.5%) / 30min=2L / min. Adding this correction term to the initial oxygen consumption rate of the first person yields the corrected oxygen consumption rate of the first person.

[0047] Furthermore, based on the carbon dioxide concentration sequence and the indoor-outdoor temperature difference sequence, a second personnel oxygen consumption rate sequence is derived, including:

[0048] The initial carbon dioxide loss rate of the indoor building is obtained by matching the average indoor temperature.

[0049] The initial carbon dioxide loss rate is corrected based on the indoor-outdoor temperature difference sequence to obtain a first corrected carbon dioxide loss rate;

[0050] The carbon dioxide concentration change rate is calculated based on the carbon dioxide concentration sequence, and the personnel carbon dioxide production rate sequence is derived based on the carbon dioxide concentration change rate and the first corrected carbon dioxide loss rate.

[0051] Based on the personnel carbon dioxide production rate sequence and the preset respiratory exchange rate, a second initial personnel oxygen consumption rate sequence is calculated.

[0052] The second initial personnel oxygen consumption rate sequence is corrected based on the carbon dioxide concentration change rate to obtain the second personnel oxygen consumption rate sequence.

[0053] In this embodiment of the application, similar to oxygen, the rate at which indoor CO2 concentration diffuses to the outside is also affected by the building's airtightness. However, under the same temperature difference, the loss rates of CO2 and O2 differ, and are related to molecular weight and diffusion coefficient. For example, when the average indoor temperature is 18°C, the initial CO2 loss rate is 0.28 L / min; when the average indoor temperature is 20°C, the initial CO2 loss rate is 0.31 L / min; when the average indoor temperature is 22°C, the initial CO2 loss rate is 0.34 L / min; when the average indoor temperature is 25°C, the initial CO2 loss rate is 0.38 L / min; and when the average indoor temperature is 28°C, the initial CO2 loss rate is 0.42 L / min.

[0054] Secondly, since a greater temperature difference between indoors and outdoors leads to a higher natural ventilation rate, the rate of carbon dioxide loss also increases. Therefore, a correction method similar to that used for oxygen loss is employed, with the correction formula being R. leak,CO2 (k)=R leak,CO2,base (1+α|ΔT(k)|), where R leak,CO2,base To match the initial carbon dioxide loss rate, ΔT(k) is the indoor and outdoor temperature difference at the corresponding sampling time. α still uses the same temperature difference correction coefficient. The first corrected carbon dioxide loss rate sequence is obtained after calculation for each sampling time.

[0055] For example, assuming the indoor-outdoor temperature difference is 10°C at a certain moment, the first corrected carbon dioxide loss rate is Rl. eak,CO2 (k)=0.38×(1+0.02×10)=0.456L / min.

[0056] Then, people consume oxygen and produce carbon dioxide while breathing. Therefore, based on the change in carbon dioxide concentration and the corrected carbon dioxide loss rate, the carbon dioxide production rate of people can be derived. The specific formula is: Carbon dioxide production rate of people = First corrected carbon dioxide loss rate + V × (C CO2 (kn)-C CO2 (k0)) / T, where V is the volume of the indoor space, and C CO2 (kn) represents the carbon dioxide concentration at the end of the historical time window, C CO2 (k0) represents the carbon dioxide concentration at the beginning of the historical time window, and T represents the total duration of the historical time window. The carbon dioxide production rate sequence of personnel can be obtained by calculating for each sliding window in sequence.

[0057] According to respiratory physiology, the ratio of oxygen consumption to carbon dioxide production in human respiration is called the respiratory exchange rate. In this embodiment, the respiratory exchange rate is preset to 0.8 under quiet conditions. Therefore, the second initial oxygen consumption rate of personnel = personnel carbon dioxide production rate / 0.8. For example, the indoor space volume is 30m³, the initial carbon dioxide concentration of the historical time window is 0.05%, the final carbon dioxide concentration is 0.08%, and the total duration is 30min. Substituting these values ​​into the calculation, the personnel carbon dioxide production rate is 0.456 + 30 × 1000L / m³ × (0.08% - 0.05%) / 30min = 0.756L / min, corresponding to the second initial oxygen consumption rate of personnel being 0.756 / 0.8 = 0.945L / min.

[0058] Furthermore, after further correction using the carbon dioxide concentration change rate, the final oxygen consumption rate sequence for the second personnel is obtained, i.e., the oxygen consumption rate sequence for the second personnel = the oxygen consumption rate of the second initial personnel + V × (C CO2 (kn)-C CO2(k0)) / T, after correction, the second personnel oxygen consumption rate sequence is obtained.

[0059] Furthermore, a weighted calculation yields the overall oxygen consumption rate sequence, including:

[0060] The ratio of the oxygen concentration change rate to the sum of the oxygen concentration change rate and the carbon dioxide concentration change rate is used as the first weighting correction coefficient.

[0061] The product of the first weight correction coefficient and the preset first weight is used as the first correction weight, wherein the first weight is the benchmark confidence weight of the oxygen sensor direct measurement data in the fusion calculation, and the first weight is not less than 0.75;

[0062] The second correction weight is obtained by subtracting the first correction weight from 1.

[0063] Based on the first correction weight and the second correction weight, the oxygen consumption rate sequence of the first person and the oxygen consumption rate sequence of the second person are weighted and calculated to obtain the comprehensive oxygen consumption rate sequence.

[0064] In this embodiment, firstly, when the rate of change in oxygen concentration is more significant than the rate of change in CO2 concentration, it indicates that the information on the change in O2 concentration in the indoor space is richer and more statistically significant, and the reliability of the measurement path based on O2 should be relatively higher. Conversely, if the change in CO2 concentration is more drastic, the reliability of the CO2 path should be relatively higher. Therefore, the ratio of the rate of change in oxygen concentration to the sum of the rates of change in oxygen concentration and the rate of change in carbon dioxide concentration is used as the first weight correction coefficient. The first weight correction coefficient is multiplied by the preset oxygen path benchmark first weight to obtain the first correction weight.

[0065] For example, if the first weight is preset to 0.8, and the absolute value of the change rate of oxygen concentration is 0.2% and the absolute value of the change rate of carbon dioxide concentration is 0.03%, then the first weight correction coefficient is 0.2 / (0.2+0.03)≈0.87, corresponding to a first correction weight of 0.8×0.87≈0.696, and a second correction weight of 1-0.696≈0.304.

[0066] Subsequently, the oxygen consumption rate of the first person is multiplied by the first correction weight, and the oxygen consumption rate of the second person is multiplied by the second correction weight. The results are then added together to obtain the final comprehensive oxygen consumption rate. For example, in the above example, if the calculated oxygen consumption rate of the first person is 0.9 L / min and the calculated oxygen consumption rate of the second person is 0.945 L / min, then the final comprehensive oxygen consumption rate is 0.9 × 0.696 + 0.945 × 0.304 ≈ 0.914 L / min.

[0067] S30: Based on the current time period and the comprehensive oxygen consumption rate sequence, a predicted oxygen consumption rate sequence for the future time window is obtained;

[0068] In this embodiment of the application, based on the current time period, the same comprehensive oxygen consumption rate change pattern as the current time period is retrieved from the historical oxygen supply operation log, and a long short-term memory network is used for time series prediction to output the future predicted oxygen consumption rate sequence.

[0069] Specifically, step S30 in the method includes:

[0070] Based on the current time period, the oxygen supply operation logs of the indoor space in the same historical time period are retrieved. With the time length of the historical time window as a constraint, a sample comprehensive oxygen consumption rate sequence set is collected. With the time length of the future time window as a constraint, the actual comprehensive oxygen consumption rate sequence corresponding to the different sample comprehensive oxygen consumption rate sequences in the historical operation process is collected as the sample predicted comprehensive oxygen consumption rate sequence, thus obtaining the sample predicted comprehensive oxygen consumption rate sequence set.

[0071] Using the sample comprehensive oxygen consumption rate sequence set as input and the sample predicted comprehensive oxygen consumption rate sequence set as supervision, a long short-term memory network is trained until convergence to generate an oxygen consumption rate predictor.

[0072] The comprehensive oxygen consumption rate sequence is input into the oxygen consumption rate predictor, which outputs the predicted oxygen consumption rate sequence for the future time window.

[0073] In this embodiment, firstly, based on the date, day of the week, and outdoor weather parameters of the current time period, the retrieved historical operation samples are filtered, and only samples with a feature matching degree higher than a preset threshold are retained, so as to reduce the interference of different environmental conditions on the prediction results and reduce the noise of model training.

[0074] Subsequently, the compiled samples are input into the Long Short-Term Memory network for training. The network will automatically learn the variation pattern of the comprehensive oxygen consumption rate under different scenarios until the training loss is lower than the set value, at which point training stops and a usable oxygen consumption rate predictor is obtained.

[0075] Finally, by inputting the obtained sliding composite oxygen consumption rate sequence into the trained predictor, the predicted oxygen consumption rate sequence corresponding to the future time window can be directly output, providing a data basis for subsequent oxygen supply regulation.

[0076] For example, an oxygen consumption rate predictor is trained based on a Long Short-Term Memory (LSTM) network. The input is a set of sample comprehensive oxygen consumption rate sequences, and the supervision is provided by a set of sample predicted comprehensive oxygen consumption rate sequences. The LSM network is trained until convergence to generate the oxygen consumption rate predictor. The LSM network architecture is designed as follows:

[0077] The input layer has a time step of 30, corresponding to 30 sampling points within a historical time window. Each time step has a feature dimension of 1, representing the overall oxygen consumption rate. The hidden layer contains two LSTM layers: the first layer has 128 units, and the second layer has 64 units, both using the tanh activation function. Dropout layers are added between the two LSTM layers and between the LSTM and the output layer, with a dropout rate of 0.2 to prevent overfitting. The output layer is a fully connected layer with an output dimension of 30, corresponding to the predicted values ​​for the next 30 time steps. The loss function is the mean squared error function, the optimizer is Adam, and the initial learning rate is set to 1×10⁻⁶. -3 The batch size is set to 16, the training epochs are set to 200, and an early stopping strategy is adopted. When the validation set loss no longer decreases within 20 consecutive training epochs, the training is terminated early. After training is completed, the model weights with the minimum validation set loss are saved, which is the oxygen consumption rate predictor.

[0078] S40: Optimize the number of working oxygen generating units based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, output the optimal number of working oxygen generating units sequence, and control the oxygen supply to the split-type oxygen generator within the future time window.

[0079] In this embodiment, the predicted indoor-outdoor temperature difference sequence is obtained through weather forecasts. Optimizing the number of oxygen generating units means turning on as few oxygen generating units as possible while meeting indoor oxygen consumption needs to achieve energy-saving goals. After outputting the optimal oxygen generating unit operating sequence, the corresponding number of oxygen generating units are controlled to start working, while the remaining oxygen generating units remain in standby mode. This avoids energy waste caused by excessive oxygen production and ensures that the indoor oxygen concentration is maintained within a comfortable range for the human body, meeting the breathing needs of indoor occupants.

[0080] Specifically, the optimal number of oxygen generating units is determined based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, and the optimal number of oxygen generating units is output, including:

[0081] Obtain the predicted indoor temperature sequence and the predicted outdoor temperature sequence within a future time window, and calculate the predicted mean indoor temperature and the predicted indoor-outdoor temperature difference sequence.

[0082] The second initial oxygen loss rate of the indoor building is obtained by matching the predicted average indoor temperature, and the second initial oxygen loss rate is corrected by the predicted indoor-outdoor temperature difference sequence to obtain the adapted oxygen loss rate sequence.

[0083] Based on the predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence, the optimal number of working oxygen generating units is determined, and the optimal number of working oxygen generating units is output.

[0084] In this embodiment of the application, the average value of the predicted indoor temperature within the future time window is first obtained. Then, according to the same matching rules as above, the second initial oxygen loss rate is obtained by matching from the pre-stored correspondence table of average indoor temperature and initial oxygen loss rate.

[0085] Secondly, using the same correction formula as before, the second initial oxygen loss rate at each time point is corrected by predicting the indoor-outdoor temperature difference sequence, and finally the adapted oxygen loss rate sequence corresponding to each prediction time point is obtained.

[0086] Subsequently, for each predicted moment within the future time window, the predicted oxygen consumption rate and the adapted oxygen loss rate at the current moment are added together to obtain the total oxygen production rate required at that moment. Then, based on the rated oxygen production rate of a single oxygen production unit, the minimum number of oxygen production units required to meet the total oxygen production rate requirement is calculated. After iterating through all predicted moments, a complete sequence of optimal oxygen production unit operating numbers can be obtained, which can be directly used to control the operating status of each oxygen production unit in the split-type oxygen concentrator.

[0087] For example, if the predicted oxygen consumption rate at a certain time is 0.914 L / min and the suitable oxygen loss rate is 0.38 L / min, the total oxygen production rate requirement is 0.914 + 0.38 = 1.294 L / min. The rated oxygen production rate of a single oxygen production unit is 1 L / min. Therefore, at this time, only one oxygen production unit needs to be turned on to meet the oxygen supply demand. If the predicted total oxygen production rate requirement at the next time is 2.15 L / min, then at least two oxygen production units need to be turned on. This process is repeated to complete the calculation for all predicted times and output the complete sequence of the optimal number of oxygen production units in operation.

[0088] Specifically, optimizing the number of working oxygen-generating units based on the predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence includes:

[0089] The predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence are summed to obtain the oxygen production demand rate sequence.

[0090] Using the oxygen demand rate greater than the oxygen demand rate sequence as a constraint, the minimum number of working oxygen production units is calculated to obtain the minimum number of working oxygen production units sequence, which is then used as the optimal number of working oxygen production units sequence.

[0091] In this embodiment of the application, firstly, the predicted oxygen consumption rate at each predicted time is calculated separately, and the corresponding oxygen loss rate at that time is added together to obtain the total oxygen production rate required at the current time.

[0092] Secondly, based on the rated oxygen production rate of a single oxygen production unit, the minimum number of oxygen production units required to meet the total oxygen production rate requirement is obtained by rounding up. After calculating all predicted times within the future time window, the sequence of the minimum number of oxygen production units for each predicted time is obtained, which is directly output as the optimal sequence of the number of oxygen production units obtained through optimization.

[0093] For example, if the rated oxygen production rate of a single oxygen generating unit is 1L / min, and the oxygen demand rate at a certain predicted time is 1.294L / min, 1.294 divided by 1 gives 1.294, which is rounded up to 2. Therefore, the minimum number of oxygen generating units to operate at that time is 2, which can meet the oxygen supply demand at the current time, while avoiding unnecessary energy consumption caused by turning on more units.

[0094] In summary, compared with existing technologies, this application, by combining dual-path measurement and fusion of oxygen consumption rate with time series prediction to pre-plan the number of oxygen generating units in operation, can dynamically adjust the oxygen supply scale according to changes in the number of people in the room and environmental conditions. While ensuring that the indoor oxygen concentration meets the human comfort needs, it avoids unnecessary start-up and operation of oxygen generating units, effectively reducing the overall energy consumption of split-type oxygen generators and achieving highly efficient and energy-saving operation of optimized indoor air environment.

[0095] In summary, the embodiments of this application have at least the following technical effects:

[0096] This application provides a highly efficient and energy-saving method for optimizing indoor air quality. First, it simultaneously collects multi-source data on oxygen concentration, carbon dioxide concentration, indoor and outdoor temperature, and the operating status of the oxygen generator unit. This data is then used to correct for the natural loss rate of oxygen and carbon dioxide due to the indoor-outdoor temperature difference. Second, it employs a weighted fusion method based on dual data sources to calculate the overall oxygen consumption rate. The fusion weights are dynamically adjusted according to the current change rates of the two data sources, reducing the interference of single sensor measurement errors or parameter preset deviations on the calculation results. Finally, a predictive model is trained based on historical operating data to anticipate changes in oxygen consumption within future time windows. Then, by optimizing the oxygen supply to meet the minimum required number of oxygen generator units, the method ensures that the indoor oxygen supply quality meets the needs of personnel while avoiding unnecessary operation of oxygen generator units. This effectively reduces the operating energy consumption of split-type oxygen generators, balancing indoor air quality optimization with energy-saving operation.

[0097] Through the above technical solution, this application solves the problems in the prior art that it is impossible to predict changes in indoor oxygen consumption in advance and that the accuracy of calculating the oxygen consumption rate of personnel from a single data source is low. Under the premise of ensuring that the indoor oxygen concentration meets the needs of personnel, it minimizes the ineffective operation of the oxygen generation unit and achieves the dual goals of optimizing the indoor air environment and saving energy. It is suitable for application in various enclosed indoor spaces with split-type oxygen generation and supply scenarios.

[0098] Example 2, as Figure 3 As shown, based on the same inventive concept as the energy-efficient indoor air environment optimization method provided in Embodiment 1, this application also provides an energy-efficient indoor air environment optimization device, including:

[0099] The initial parameter acquisition module 11 is used to synchronously monitor and acquire the oxygen concentration sequence, carbon dioxide concentration sequence, and indoor temperature sequence of the indoor space within a historical time window, as well as the working quantity sequence of the oxygen generation unit of the split oxygen generator, the outdoor temperature sequence of the outdoor space, and calculate the indoor-outdoor temperature difference sequence.

[0100] The comprehensive oxygen consumption rate calculation module 12 is used to derive the first personnel oxygen consumption rate sequence based on the oxygen concentration sequence, the oxygen production unit working quantity sequence and the indoor and outdoor temperature difference sequence, derive the second personnel oxygen consumption rate sequence based on the carbon dioxide concentration sequence and the indoor and outdoor temperature difference sequence, and calculate the comprehensive oxygen consumption rate sequence by weighting.

[0101] Oxygen consumption rate prediction module 13 is used to predict the oxygen consumption rate sequence within a future time window based on the current time period and the comprehensive oxygen consumption rate sequence.

[0102] The oxygen generator oxygen supply control module 14 is used to optimize the number of working oxygen generator units based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, output the optimal number of working oxygen generator units sequence, and control the oxygen supply of the split-type oxygen generator within the future time window.

[0103] Furthermore, the split-type oxygen generator includes an indoor unit and an outdoor unit. The outdoor unit is used to generate oxygen, and the indoor unit is used to diffuse the oxygen generated by the outdoor unit into the room. The outdoor unit is composed of multiple oxygen generating units connected in parallel.

[0104] In one embodiment, the first personnel oxygen consumption rate sequence is derived based on the oxygen concentration sequence, the oxygen generation unit operating quantity sequence, and the indoor-outdoor temperature difference sequence, including:

[0105] The average indoor temperature is calculated based on the indoor temperature sequence, and the initial oxygen loss rate of the indoor building is obtained by matching the average indoor temperature.

[0106] The initial oxygen loss rate is corrected based on the indoor-outdoor temperature difference sequence to obtain a first corrected oxygen loss rate sequence;

[0107] The actual oxygen production rate sequence is calculated based on the working quantity sequence of the oxygen production unit. The first corrected oxygen loss rate sequence is then subtracted from the actual oxygen production rate sequence to obtain the first initial personnel oxygen consumption rate sequence.

[0108] The oxygen concentration change rate is calculated based on the oxygen concentration sequence, and the oxygen consumption rate sequence of the first initial personnel is corrected using the oxygen concentration change rate to obtain the oxygen consumption rate sequence of the first personnel.

[0109] Furthermore, based on the carbon dioxide concentration sequence and the indoor-outdoor temperature difference sequence, a second personnel oxygen consumption rate sequence is derived, including:

[0110] The initial carbon dioxide loss rate of the indoor building is obtained by matching the average indoor temperature.

[0111] The initial carbon dioxide loss rate is corrected based on the indoor-outdoor temperature difference sequence to obtain a first corrected carbon dioxide loss rate;

[0112] The carbon dioxide concentration change rate is calculated based on the carbon dioxide concentration sequence, and the personnel carbon dioxide production rate sequence is derived based on the carbon dioxide concentration change rate and the first corrected carbon dioxide loss rate.

[0113] Based on the personnel carbon dioxide production rate sequence and the preset respiratory exchange rate, a second initial personnel oxygen consumption rate sequence is calculated.

[0114] The second initial personnel oxygen consumption rate sequence is corrected based on the carbon dioxide concentration change rate to obtain the second personnel oxygen consumption rate sequence.

[0115] Furthermore, a weighted calculation yields the overall oxygen consumption rate sequence, including:

[0116] The ratio of the oxygen concentration change rate to the sum of the oxygen concentration change rate and the carbon dioxide concentration change rate is used as the first weighting correction coefficient.

[0117] The product of the first weight correction coefficient and the preset first weight is used as the first correction weight, wherein the first weight is the benchmark confidence weight of the oxygen sensor direct measurement data in the fusion calculation, and the first weight is not less than 0.75;

[0118] The second correction weight is obtained by subtracting the first correction weight from 1.

[0119] Based on the first correction weight and the second correction weight, the oxygen consumption rate sequence of the first person and the oxygen consumption rate sequence of the second person are weighted and calculated to obtain the comprehensive oxygen consumption rate sequence.

[0120] In one embodiment, the oxygen consumption rate prediction module 13 is specifically used for:

[0121] Based on the current time period, the oxygen supply operation logs of the indoor space in the same historical time period are retrieved. With the time length of the historical time window as a constraint, a sample comprehensive oxygen consumption rate sequence set is collected. With the time length of the future time window as a constraint, the actual comprehensive oxygen consumption rate sequence corresponding to the different sample comprehensive oxygen consumption rate sequences in the historical operation process is collected as the sample predicted comprehensive oxygen consumption rate sequence, thus obtaining the sample predicted comprehensive oxygen consumption rate sequence set.

[0122] Using the sample comprehensive oxygen consumption rate sequence set as input and the sample predicted comprehensive oxygen consumption rate sequence set as supervision, a long short-term memory network is trained until convergence to generate an oxygen consumption rate predictor.

[0123] The comprehensive oxygen consumption rate sequence is input into the oxygen consumption rate predictor, which outputs the predicted oxygen consumption rate sequence for the future time window.

[0124] Further, in one embodiment, the optimal number of oxygen generating units to operate is determined based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, and the optimal number of oxygen generating units to operate sequence is output, including:

[0125] Obtain the predicted indoor temperature sequence and the predicted outdoor temperature sequence within a future time window, and calculate the predicted mean indoor temperature and the predicted indoor-outdoor temperature difference sequence.

[0126] The second initial oxygen loss rate of the indoor building is obtained by matching the predicted average indoor temperature, and the second initial oxygen loss rate is corrected by the predicted indoor-outdoor temperature difference sequence to obtain the adapted oxygen loss rate sequence.

[0127] Based on the predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence, the optimal number of working oxygen generating units is determined, and the optimal number of working oxygen generating units is output.

[0128] Further, optimizing the number of working oxygen-generating units based on the predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence includes:

[0129] The predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence are summed to obtain the oxygen production demand rate sequence.

[0130] Using the oxygen demand rate greater than the oxygen demand rate sequence as a constraint, the minimum number of working oxygen production units is calculated to obtain the minimum number of working oxygen production units sequence, which is then used as the optimal number of working oxygen production units sequence.

Claims

1. A highly efficient and energy-saving method for optimizing indoor air environment, characterized in that, The methods include: Simultaneously monitor and acquire the oxygen concentration sequence, carbon dioxide concentration sequence, and indoor temperature sequence of the indoor space within a historical time window, as well as the working number sequence of the oxygen generation unit of the split oxygen concentrator, and the outdoor temperature sequence of the outdoor space, and calculate the indoor-outdoor temperature difference sequence. The first personnel oxygen consumption rate sequence is derived from the oxygen concentration sequence, the oxygen production unit working quantity sequence, and the indoor-outdoor temperature difference sequence. The second personnel oxygen consumption rate sequence is derived from the carbon dioxide concentration sequence and the indoor-outdoor temperature difference sequence. The combined oxygen consumption rate sequence is then calculated by weighting. Based on the current time period and the comprehensive oxygen consumption rate sequence, a predicted oxygen consumption rate sequence for the future time window is obtained. Based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, the optimal number of oxygen generating units is determined, and the optimal number of oxygen generating units is output to control the oxygen supply of the split-type oxygen generator within the future time window.

2. The method for optimizing indoor air environment with high efficiency and energy saving according to claim 1, characterized in that, The split-type oxygen generator includes an indoor unit and an outdoor unit. The outdoor unit is used to generate oxygen, and the indoor unit is used to diffuse the oxygen generated by the outdoor unit into the room. The outdoor unit is composed of multiple oxygen generating units connected in parallel.

3. The method for optimizing indoor air environment with high efficiency and energy saving according to claim 1, characterized in that, Based on the oxygen concentration sequence, the oxygen generation unit operating quantity sequence, and the indoor-outdoor temperature difference sequence, the first personnel oxygen consumption rate sequence is derived, including: The average indoor temperature is calculated based on the indoor temperature sequence, and the initial oxygen loss rate of the indoor building is obtained by matching the average indoor temperature. The initial oxygen loss rate is corrected based on the indoor-outdoor temperature difference sequence to obtain a first corrected oxygen loss rate sequence; The actual oxygen production rate sequence is calculated based on the working quantity sequence of the oxygen production unit. The first corrected oxygen loss rate sequence is then subtracted from the actual oxygen production rate sequence to obtain the first initial personnel oxygen consumption rate sequence. The oxygen concentration change rate is calculated based on the oxygen concentration sequence, and the oxygen consumption rate sequence of the first initial personnel is corrected using the oxygen concentration change rate to obtain the oxygen consumption rate sequence of the first personnel.

4. The method for optimizing indoor air environment with high efficiency and energy saving according to claim 3, characterized in that, Based on the aforementioned carbon dioxide concentration sequence and indoor-outdoor temperature difference sequence, a second personnel oxygen consumption rate sequence was derived, including: The initial carbon dioxide loss rate of the indoor building is obtained by matching the average indoor temperature. The initial carbon dioxide loss rate is corrected based on the indoor-outdoor temperature difference sequence to obtain a first corrected carbon dioxide loss rate; The carbon dioxide concentration change rate is calculated based on the carbon dioxide concentration sequence, and the personnel carbon dioxide production rate sequence is derived based on the carbon dioxide concentration change rate and the first corrected carbon dioxide loss rate. Based on the personnel carbon dioxide production rate sequence and the preset respiratory exchange rate, a second initial personnel oxygen consumption rate sequence is calculated. The second initial personnel oxygen consumption rate sequence is corrected based on the carbon dioxide concentration change rate to obtain the second personnel oxygen consumption rate sequence.

5. The method for optimizing indoor air environment with high efficiency and energy saving according to claim 4, characterized in that, The weighted calculation yielded a comprehensive oxygen consumption rate sequence, including: The ratio of the oxygen concentration change rate to the sum of the oxygen concentration change rate and the carbon dioxide concentration change rate is used as the first weighting correction coefficient. The product of the first weight correction coefficient and the preset first weight is used as the first correction weight, wherein the first weight is the benchmark confidence weight of the oxygen sensor direct measurement data in the fusion calculation, and the first weight is not less than 0.75; The second correction weight is obtained by subtracting the first correction weight from 1. Based on the first correction weight and the second correction weight, the oxygen consumption rate sequence of the first person and the oxygen consumption rate sequence of the second person are weighted and calculated to obtain the comprehensive oxygen consumption rate sequence.

6. The method for optimizing indoor air environment with high efficiency and energy saving according to claim 1, characterized in that, Based on the current time period and the comprehensive oxygen consumption rate sequence, a predicted oxygen consumption rate sequence for the future time window is obtained, including: Based on the current time period, the oxygen supply operation logs of the indoor space in the same historical time period are retrieved. With the time length of the historical time window as a constraint, a sample comprehensive oxygen consumption rate sequence set is collected. With the time length of the future time window as a constraint, the actual comprehensive oxygen consumption rate sequence corresponding to the different sample comprehensive oxygen consumption rate sequences in the historical operation process is collected as the sample predicted comprehensive oxygen consumption rate sequence, thus obtaining the sample predicted comprehensive oxygen consumption rate sequence set. Using the sample comprehensive oxygen consumption rate sequence set as input and the sample predicted comprehensive oxygen consumption rate sequence set as supervision, a long short-term memory network is trained until convergence to generate an oxygen consumption rate predictor. The comprehensive oxygen consumption rate sequence is input into the oxygen consumption rate predictor, which outputs the predicted oxygen consumption rate sequence for the future time window.

7. The method for optimizing indoor air environment with high efficiency and energy saving according to claim 1, characterized in that, Based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, the optimal number of oxygen generating units is determined, and the optimal sequence of oxygen generating unit operating quantities is output, including: Obtain the predicted indoor temperature sequence and the predicted outdoor temperature sequence within a future time window, and calculate the predicted mean indoor temperature and the predicted indoor-outdoor temperature difference sequence. The second initial oxygen loss rate of the indoor building is obtained by matching the predicted average indoor temperature, and the second initial oxygen loss rate is corrected by the predicted indoor-outdoor temperature difference sequence to obtain the adapted oxygen loss rate sequence. Based on the predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence, the optimal number of working oxygen generating units is determined, and the optimal number of working oxygen generating units is output.

8. The method for optimizing indoor air environment with high efficiency and energy saving according to claim 7, characterized in that, Optimizing the number of working oxygen production units based on the predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence includes: The predicted oxygen consumption rate sequence and the adapted oxygen loss rate sequence are summed to obtain the oxygen production demand rate sequence. Using the oxygen demand rate greater than the oxygen demand rate sequence as a constraint, the minimum number of working oxygen production units is calculated to obtain the minimum number of working oxygen production units sequence, which is then used as the optimal number of working oxygen production units sequence.

9. A highly efficient and energy-saving indoor air environment optimization device, characterized in that, A method for implementing an efficient and energy-saving indoor air environment optimization method according to any one of claims 1 to 8, comprising: The initial parameter acquisition module is used to synchronously monitor and acquire the oxygen concentration sequence, carbon dioxide concentration sequence, and indoor temperature sequence of the indoor space within a historical time window, as well as the working quantity sequence of the oxygen generation unit of the split oxygen generator, the outdoor temperature sequence of the outdoor space, and calculate the indoor-outdoor temperature difference sequence. The comprehensive oxygen consumption rate calculation module is used to derive the first personnel oxygen consumption rate sequence based on the oxygen concentration sequence, the oxygen production unit working quantity sequence and the indoor-outdoor temperature difference sequence, and to derive the second personnel oxygen consumption rate sequence based on the carbon dioxide concentration sequence and the indoor-outdoor temperature difference sequence, and to calculate the comprehensive oxygen consumption rate sequence by weighting. The oxygen consumption rate prediction module is used to predict the oxygen consumption rate sequence within a future time window based on the current time period and the comprehensive oxygen consumption rate sequence. The oxygen generator oxygen supply control module is used to optimize the number of working oxygen generator units based on the predicted oxygen consumption rate sequence and the predicted indoor-outdoor temperature difference sequence within the future time window, output the optimal number of working oxygen generator units sequence, and control the oxygen supply of the split-type oxygen generator within the future time window.

Images