A Smart and Energy-Saving Method for Adjusting Building Fresh Air Ventilation System

Abstract

This invention discloses a method for regulating a smart and energy-saving building ventilation system, relating to the field of intelligent building control. The method includes: collecting building environmental data through multi-source sensors and preprocessing it; encoding fan speed and damper opening as binary variables and calculating the optimization target value of the building environmental data; constructing a quantum optimization model, inputting the optimization target value, and outputting a control command set; setting multi-parameter fixed thresholds, comparing the building environmental data with the multi-parameter fixed thresholds, and determining whether to activate the quantum optimization model; converting the control command set into motor drive signals, controlling the fan speed and damper opening through the motor, and dynamically adjusting the airflow distribution ratio based on the fan speed and damper opening, generating an environmental verification report. This invention achieves high-precision dynamic perception of the building's indoor environment through multi-source sensor data collection and preprocessing, ensuring the reliability of the building environmental data and providing a data foundation for subsequent precise adjustment of the ventilation system.

Description

Technical Field

[0001] This invention relates to the field of intelligent building control, and in particular to a method for regulating a smart and energy-saving building fresh air ventilation system. Background Technology

[0002] As the construction industry continues to improve energy conservation, emission reduction, and indoor environmental quality, fresh air systems are gradually developing towards intelligence and energy efficiency. Therefore, building fresh air ventilation systems have become important facilities for improving indoor air quality and enhancing the comfort of living and working environments.

[0003] While existing building ventilation systems have seen significant improvements in functionality and performance, they still fall short in energy conservation and precise control. These systems employ simple control logic based on fixed thresholds, making dynamic optimization difficult based on complex indoor environmental data. For instance, the demand for fresh air varies considerably depending on the season, time of day, and the intensity of indoor activity. Existing systems cannot precisely adjust fan speeds and valve openings, resulting in poor ventilation. Furthermore, energy efficiency in existing systems needs improvement, particularly in complex building environments where effective optimization mechanisms are lacking, hindering the achievement of optimal energy savings during operation. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a smart and energy-saving method for regulating building ventilation systems to solve the problem of difficulty in dynamically optimizing based on complex indoor environmental data.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for regulating a smart and energy-saving building ventilation system, comprising: collecting building environment data through multi-source sensors and preprocessing it; encoding fan speed and valve opening as binary variables, calculating the optimization target value of the building environment data; constructing a quantum optimization model, inputting the optimization target value, outputting a control instruction set, setting multi-parameter fixed thresholds, comparing the building environment data with the multi-parameter fixed thresholds, determining whether to activate the quantum optimization model, and optimizing the building environment data; converting the control instruction set into motor drive signals, controlling the fan speed and valve opening through the motor, dynamically adjusting the airflow distribution ratio according to the fan speed and valve opening, and generating an environmental verification report.

[0008] As a preferred embodiment of the intelligent energy-saving building fresh air ventilation system adjustment method of the present invention, the multi-source sensor includes a carbon dioxide concentration monitor, an infrared thermal imaging array, a capacitive humidity sensor, and a camera;

[0009] The building environment data includes carbon dioxide concentration, temperature distribution, humidity, and population density.

[0010] The preprocessing includes time synchronization calibration, missing value imputation, and outlier filtering.

[0011] As a preferred embodiment of the intelligent energy-saving building fresh air ventilation system adjustment method of the present invention, the specific steps for encoding the fan speed and damper opening as binary variables and calculating the optimized target value of the building environment data are as follows:

[0012] By employing a non-uniform segmentation strategy, the fan speed and valve opening are encoded into binary sequences;

[0013] Binary sequences are mapped to discretized parameter sets through hierarchical mapping;

[0014] The weighting of the building's fresh air ventilation system's air exchange volume is dynamically adjusted based on personnel density data and humidity values.

[0015] By weighted summation and discretization of the parameter set and weight allocation, the optimization target value of the building environment data is obtained.

[0016] As a preferred embodiment of the intelligent energy-saving building fresh air ventilation system regulation method of the present invention, the pre-constructed quantum optimization model takes an optimization target value as input and outputs a control command set, and the specific steps are as follows:

[0017] A quantum optimization model was constructed using the D-Wave Advantage quantum processor;

[0018] The quantum optimization model refers to coarse-tuning optimization, fine-tuning optimization, and micro-tuning optimization.

[0019] The target value is coarsely optimized by receiving the target value, and a global search for the target value is performed on the D-Wave Advantage quantum processor to obtain a candidate solution set.

[0020] Fine-tuning optimization is based on the discretized parameter set. It performs local optimization on the candidate solution set selected by coarse-tuning optimization to obtain an updated candidate solution set.

[0021] The fine-tuning optimization receives the updated candidate solution set from the fine-tuning optimization, and uses simulated annealing on the CPU to iteratively optimize the updated candidate solution set, compensate for the quantum discretization error generated by the discretization parameter set, and output the control command set for the fan speed and the valve opening.

[0022] As a preferred embodiment of the intelligent energy-saving building fresh air ventilation system adjustment method of the present invention, the steps of setting multi-parameter fixed thresholds, comparing building environment data with multi-parameter fixed thresholds, and determining whether to activate the quantum optimization model are as follows:

[0023] Set fixed thresholds for multiple parameters;

[0024] Compare building environment data with fixed thresholds for multiple parameters;

[0025] When the building environment data does not exceed the fixed threshold of multiple parameters, it indicates that the building's fresh air ventilation system is operating normally.

[0026] When any building environment data exceeds a fixed threshold of multiple parameters, it indicates that the building's fresh air ventilation system is operating abnormally. In this case, the quantum optimization model is activated to optimize the building environment data.

[0027] As a preferred embodiment of the intelligent energy-saving building fresh air ventilation system adjustment method of the present invention, the specific steps of optimizing building environmental data are as follows:

[0028] Re-collect building environment data and calculate new optimization target values;

[0029] Using the D-Wave Advantage quantum processor, new optimization target values ​​are input into the quantum optimization model. After coarse-tuning, fine-tuning, and micro-tuning optimizations, a real-time control command set for fan speed and valve opening is output.

[0030] As a preferred embodiment of the intelligent energy-saving building fresh air ventilation system adjustment method of the present invention, the specific steps of converting the control command set into motor drive signals, and controlling the fan speed and damper opening through the motor are as follows:

[0031] The binary sequence of wind turbine speed is converted into a percentage speed value using a non-uniform segmentation strategy;

[0032] The percentage speed value is converted into a PWM signal through the H-bridge circuit, which drives the EC motor to adjust the fan speed.

[0033] The binary sequence of the valve opening is parsed into physical angles using multi-protocol commands;

[0034] Calculate the number of pulses in the acceleration and deceleration phases of the stepper motor from a physics perspective;

[0035] The pulse interval is adjusted by a timer. When the pulse interval of the acceleration phase gradually decreases and the pulse interval of the deceleration phase gradually increases, a step pulse sequence is generated.

[0036] The stepper motor is driven to rotate the fan valve according to the stepper pulse sequence, thereby controlling the opening degree of the air valve.

[0037] As a preferred embodiment of the intelligent energy-saving building fresh air ventilation system adjustment method of the present invention, the specific steps of dynamically adjusting the airflow distribution ratio according to the fan speed and the valve opening to generate an environmental verification report are as follows:

[0038] Air volume detection nodes are deployed in the air supply duct to detect the air volume of each branch of the air supply duct in real time. Combined with temperature distribution data and carbon dioxide concentration values, the opening difference between adjacent air valves is dynamically adjusted using a PID controller.

[0039] The difference in opening degree between adjacent air valves refers to the physical angle difference between two adjacent air valves on the same branch of the air supply duct.

[0040] Based on the difference in the opening degree of the air valves, the opening degree of the air valves in the building's fresh air ventilation system is dynamically balanced to distribute the airflow evenly to the building's fresh air ventilation system;

[0041] Set the target air exchange rate and calculate the actual air exchange rate in the air supply duct based on the air volume of each branch.

[0042] By comparing the target ventilation rate with the actual ventilation rate and combining the results of uniform airflow distribution, an environmental verification report is generated.

[0043] In a second aspect, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the intelligent energy-saving building fresh air ventilation system adjustment method as described in the first aspect of the present invention.

[0044] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the intelligent energy-saving building ventilation system adjustment method as described in the first aspect of the present invention.

[0045] The beneficial effects of this invention are as follows: By collecting and preprocessing building environment data through multi-source sensors, this invention achieves comprehensive monitoring and high-precision dynamic perception of the building's indoor environment, ensuring the reliability of the building environment data and providing a data foundation for subsequent precise adjustment of the ventilation system. By deploying carbon dioxide concentration monitors, infrared thermal imaging arrays, capacitive humidity sensors, and cameras, it comprehensively covers all functional areas of the building's fresh air ventilation system, synchronously collects building environment data, and generates a three-dimensional spatial thermodynamic distribution map, improving the visualization resolution and accuracy of the indoor environment status. Preprocessing eliminates sensor drift errors and electromagnetic interference noise in real time, effectively improving the accuracy of building environment data collection and significantly enhancing the quality of building environment data. Furthermore, through time synchronization calibration, it effectively solves the problems of time asynchrony and spatial misalignment of building environment data. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart of the adjustment method for the smart energy-saving building fresh air ventilation system in Example 1.

[0048] Figure 2 This is a flowchart of the optimization target value in Example 1.

[0049] Figure 3 This is a flowchart of the control instruction set in Example 1.

[0050] Figure 4 This is a flowchart of the environmental verification report in Example 1. Detailed Implementation

[0051] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0054] Example 1, referring to Figures 1-4 This embodiment provides a method for regulating a smart and energy-saving building fresh air ventilation system, including the following steps:

[0055] S1. Collect building environment data through multi-source sensors and perform preprocessing.

[0056] The multi-source sensors include a carbon dioxide concentration monitor, an infrared thermal imaging array, a capacitive humidity sensor, and a camera;

[0057] Building environment data includes carbon dioxide concentration values, temperature distribution data, humidity values, and population density data;

[0058] Carbon dioxide concentration values ​​are obtained through a carbon dioxide concentration monitor, with a measurement range of 0-5000ppm and an accuracy of ±30ppm.

[0059] Temperature distribution data is measured using an infrared thermal imaging array, with a temperature detection range of -40 to 125℃ and an accuracy of ±0.2℃.

[0060] Humidity values ​​are collected using a capacitive humidity sensor, with a humidity detection range of 0-100%RH and an accuracy of ±1.5%.

[0061] The video stream is captured by a camera, and a convolutional neural network algorithm is applied to perform personnel density statistics on the camera video stream to obtain personnel density data.

[0062] The carbon dioxide concentration monitor detects air composition once per second and updates the reading every 5 seconds. The infrared thermal imaging array generates a heat map every 10 seconds, extracts the highest, lowest, and average temperatures of each area, and updates the temperature distribution data measurement every 10 seconds. The capacitive humidity sensor uploads calibrated data every 30 seconds. Based on the camera video stream, the convolutional neural network counts people at a rate of 25 frames per second, counts the number of people in each area, and calculates the personnel density (people / ㎡) by combining the spatial area. The time synchronization calibration cycle is once every 5 seconds to ensure that the timestamp error is ≤50ms.

[0063] Preprocessing includes time synchronization calibration, missing value imputation, and outlier filtering;

[0064] The IoT gateway uses the Network Time Protocol to synchronize and calibrate the building environment data, aligning the timestamps of multi-source sensors (error ≤ 50ms), and fills in missing values ​​in the building environment data through linear interpolation. The 3σ criterion is applied to filter out abnormal parameters in the building environment data and remove abnormal fluctuation values.

[0065] When aligning the timestamps of multi-source sensors, an interpolation algorithm is used to generate virtual time nodes. For example, aligning 750 frames of video data (25 frames / second × 30 seconds) within 30 seconds with the humidity change curve has an error of ≤50ms.

[0066] The missing value imputation rule is as follows: when building environment data is lost for more than 3 consecutive sampling periods, such as when a capacitive humidity sensor has no data for 90 seconds, linear interpolation is performed. Linear interpolation is divided into forward imputation and backward imputation. Forward imputation is performed using the most recent valid value to fill subsequent missing values. When data is subsequently recovered, backward imputation is performed using the first valid value after recovery. For example, if a capacitive humidity sensor loses humidity values ​​at t=30 and t=60s, then the humidity value at t=30s is taken from the linear interpolation results at t=0s and t=90s.

[0067] It should be noted that the 3σ criterion specifically refers to defining the 3σ criterion by calculating the mean μ and standard deviation σ of the built environment data. The historical data window is updated every 10 minutes, with a window size of 60 sets of built environment data. Applying the 3σ criterion to filter outliers means that if the current value exceeds [μ-3σ, μ+3σ], then the current value is considered an anomaly and replaced with the median within the window. When the population density suddenly changes (such as from 0 people / ㎡ to 5 people / ㎡), triggering a sharp increase in carbon dioxide concentration, this data is not considered an anomaly.

[0068] S2. Encode the fan speed and damper opening as binary variables and calculate the optimization target value of the building environment data.

[0069] By employing a non-uniform segmentation strategy, the fan speed (256 levels) and the damper opening (corresponding to physical angle and equivalent ventilation area) are encoded into binary sequences.

[0070] The binary sequence encoding the wind turbine speed refers to the fine segmentation of the wind turbine speed through a non-uniform segmentation strategy. The wind turbine speed (0-100%) is evenly divided into 256 levels, each level corresponding to a speed increment of 0.39%, which is represented by an 8-bit binary sequence (e.g., 00000000 corresponds to 0%, 11111111 corresponds to 100%). In the quantum optimization model, the energy consumption difference between different speed ranges is nonlinearly compensated through a weighting function (e.g., the weighting coefficient for the high-speed range is 1.5).

[0071] The binary sequence of coded damper opening refers to dividing the damper opening into a small opening zone (0-45°) with a step size of 1°, directly corresponding to the linear ventilation area (e.g., 45° corresponds to 50% of the equivalent area) and a large opening zone (46-90°) with a step size of 3°, where the change in equivalent area becomes slower (e.g., 90° corresponds to 100% of the area). Considering both physical angles and equivalent ventilation area, a dual correspondence is formed. The small opening zone requires fine control to avoid local over-ventilation, while the large opening zone is mainly for rapid global adjustment.

[0072] The binary sequence (such as an 8-bit fan speed code + a 7-bit valve opening code) is mapped into a set of discrete parameters that can be processed by quantum computing through hierarchical mapping.

[0073] Discretized parameter set refers to the segmented encoding result of physical quantities, which converts fan speed and valve opening into discrete quantum-processable parameters through binary sequences;

[0074] The hierarchical mapping divides the wind turbine speed range (0-100%) into 256 discrete levels: low speed zone (0-127 levels), each level corresponding to a speed increment of 0.39% (total range 0-49.8%); medium speed zone (128-191 levels), each level corresponding to a speed increment of 0.78% (total range 50.0-74.6%); and high speed zone (192-255 levels), each level corresponding to a speed increment of 1.56% (total range 75.0-100%). Each level of wind turbine speed is represented by an 8-bit binary sequence (e.g., 00000000 corresponds to level 0, 11111111 corresponds to level 255).

[0075] The damper opening (0-90°) is divided into two discrete ranges: a small opening range (0-45°), with each level corresponding to 1° (45 levels in total), and the binary sequence consisting of the lower 6 bits of a 7-bit sequence (e.g., 0000000 corresponds to 0°, 0001111 corresponds to 45°); and a large opening range (46-90°), with each level corresponding to 3° (15 levels in total), and the binary sequence consisting of the higher 3 bits of a 7-bit sequence (e.g., 0010000 corresponds to 46°, 1111111 corresponds to 90°).

[0076] The weighting of the building's fresh air ventilation system's air exchange volume is dynamically adjusted based on personnel density data and humidity values.

[0077] For example, if the humidity threshold H is set to 70%RH and the personnel density threshold D is set to 2 people / m², when the personnel density exceeds the personnel density threshold H, the air exchange rate weight increases to 60%, and the fan speed is increased first. When the humidity exceeds the humidity threshold D, the air exchange rate weight decreases to 30%, and the forced air valve opening is ≥50° to accelerate dehumidification.

[0078] The optimization target value of the building environment data is obtained by calculating the discretized parameter set and weight allocation through weighted summation;

[0079] S3. Construct a quantum optimization model, input the optimization target value, and output the control instruction set.

[0080] A quantum optimization model was constructed using the D-Wave Advantage quantum processor;

[0081] Quantum optimization models refer to coarse-tuning optimization, fine-tuning optimization, and micro-tuning optimization.

[0082] The target value of the receiver is coarsely optimized. 1000 quantum annealings are performed on the D-Wave Advantage quantum processor with an annealing time of 20ms. A global search is performed on the target value to obtain a candidate solution set.

[0083] The candidate solution set refers to the binary sequence combination of fan speed and valve opening;

[0084] Global search refers to calculating the optimization target value of different binary sequence combinations by weighted summation during each optimization, judging the quality of the candidate solution set. The lower the optimization target value, the better the corresponding candidate solution set. Finally, the top 50 binary sequence combinations are selected as the candidate solution set.

[0085] It should be noted that the global search does not redefine the optimization objective value, but rather performs a rapid evaluation of different combinations of binary sequences to determine the quality of the candidate solution set. Each quantum annealing iteration generates a new combination of binary sequences, requiring a recalculation of the optimization objective value.

[0086] Fine-tuning optimization is based on the discretized parameter set. Local optimization is performed on the candidate solution set selected by coarse-tuning optimization. 2000 local optimizations are performed with a 15ms annealing time (e.g., the high 4 bits of the fixed fan speed represent the main speed range and the middle 3 bits of the damper opening represent the main range of the equivalent ventilation area) to obtain an updated candidate solution set.

[0087] The fine-tuning optimization receives the updated candidate solution set from the fine-tuning optimization, and uses simulated annealing on the CPU to perform 500 iterations of optimization on the updated candidate solution set to compensate for the quantum discretization error generated by the discretization parameter set, and outputs the control command set for the fan speed and the valve opening.

[0088] The simulated annealing process involves setting the initial temperature to 1000, the cooling rate coefficient to 0.95, and the minimum termination temperature to 0.00001. The first 50 sets of binary sequences generated by fine-tuning and optimization are converted into physical parameters, such as fan speed 0-100% and valve angle 0-90°. By adjusting the fan speed and valve opening, a neighborhood solution set is formed. When adjusting the fan speed, 1-2 bits are randomly selected and flipped in the binary sequence, such as changing "11001011" to "11001001". When adjusting the valve opening, in the small opening range (0-45°), only the lower 6 bits are allowed to flip, and in the large opening range (46-90°), only the higher 3 bits are allowed to flip.

[0089] The quantum discretization error originates from the ±0.195% error caused by the 256 levels of fan speed (0.39% per level) and the ±0.5° error caused by the 45 levels of small valve opening (1° per level).

[0090] The compensation for quantum discretization error is divided into fan speed compensation and valve opening compensation.

[0091] The fan speed compensation is divided into a low-speed zone (0-49.8%) and a high-speed zone (75-100%). In the low and medium speed zone, random fine-tuning (±0.15%) is superimposed on the speed value corresponding to the candidate solution set to avoid mechanical resonance caused by long-term operation at a fixed speed. In the high-speed zone, the speed value is dynamically compensated, such as adding 0.37% random compensation in the high-speed zone.

[0092] The damper opening compensation is divided into damper small opening area compensation and damper large opening area compensation. Damper small opening area compensation refers to adding periodic fine adjustment (such as ±0.5° sine fluctuation) to the integer angle value (such as 32°) generated by the candidate solution set to prevent local airflow stagnation. For the large opening area, coarse adjustment compensation is used, allowing an angle error of ±1.2° to reduce mechanical wear.

[0093] It should be noted that coarse adjustment compensation refers to the allowable angle error of ±1.2° when compensating in the large opening range of the air valve (46-90°). This is achieved by reducing the accuracy requirements to decrease the frequent fine-tuning actions of the stepper motor. Specifically, binary high 3-bit control is used to reduce the number of adjustments, and the pulse interval time of the stepper motor in the acceleration phase is increased by 15%, while the pulse interval time in the deceleration phase is shortened by 20%, increasing the proportion of motor inertial gliding to 30% and reducing gear meshing impact. The air valve opening within ±1.2° is considered normal to avoid repeated calibration.

[0094] The control instruction set consists of fan control instructions and valve control instructions. The fan control instructions are 8-bit binary sequences of speed, such as "10111011" which corresponds to the 187th speed level (73.7%) and PWM parameters (duty cycle = speed percentage), such as 73.7% which corresponds to a duty cycle of 73.7%. The valve control instructions are physical angle instructions, such as "0001111" in the small opening area representing 45° with 100 stepper motor pulses, and "1110000" in the large opening area representing 90° with 200 stepper motor pulses.

[0095] When the motor receives a control command, it needs to complete the fan speed adjustment and valve angle positioning within 80ms.

[0096] S4. Set a fixed threshold for multiple parameters, compare the building environment data with the fixed threshold for multiple parameters, determine whether to activate the quantum optimization model, and optimize the building environment data.

[0097] Set fixed thresholds for multiple parameters;

[0098] The fixed thresholds for multiple parameters include carbon dioxide concentration threshold C (e.g., 1000 ppm), temperature threshold T (e.g., 28℃), humidity threshold H (e.g., 70% RH), and personnel density threshold D (e.g., 2 people / m²).

[0099] Compare building environment data with fixed thresholds for multiple parameters;

[0100] When the building environment data does not exceed the fixed threshold of multiple parameters, it indicates that the building's fresh air ventilation system is operating normally and the current operating status of the building's fresh air ventilation system is maintained.

[0101] When any building environment data exceeds a fixed threshold of multiple parameters, it indicates that the building's fresh air ventilation system is operating abnormally. In this case, the quantum optimization model is activated to optimize the building environment data.

[0102] Use fixed threshold values ​​for multiple parameters as constraints on fan speed and valve opening.

[0103] The constraints are as follows: the fan speed range is fixed at 0-255 levels (256 levels in total); the motor drive signal must complete the speed adjustment within ≤100ms; the physical angle of the air valve is limited to 0-90°; the angle adjustment accuracy must be controlled within ±0.5°; and the nonlinear relationship between the opening degree and the ventilation area must be mapped to a piecewise linear function.

[0104] Optimization processing refers to calculating the optimization target value of the building environment data, inputting the optimization target value into the quantum optimization model for iterative optimization, and finally selecting the control command set for fan speed and valve opening.

[0105] It should be noted that when comparing multiple fixed threshold parameters simultaneously, there are priority rules. For example, when the carbon dioxide concentration exceeds the carbon dioxide concentration threshold C, even if the humidity and temperature deviate from the temperature threshold T and humidity threshold H at the same time, the ventilation volume is increased and the fan speed is increased. When the carbon dioxide concentration and humidity value exceed the standard at the same time, the fan speed is increased to the high-speed zone (≥75%) and the air valve opening is forced to ≥50° to accelerate dehumidification.

[0106] Re-collect building environment data and calculate new optimization target values;

[0107] Using the D-Wave Advantage quantum processor, the new optimization target value is input into the quantum optimization model. After coarse-tuning optimization, fine-tuning optimization, and micro-tuning optimization, the real-time control command set for fan speed and valve opening is output.

[0108] The annealing time in the quantum optimization model is adaptively adjusted according to specific circumstances. For example, if the initial annealing time is 20ms and the optimization target value of the candidate solution set generated by three consecutive annealings differs by less than 1%, it is shortened to 15ms to continue accelerating the search. Based on the distribution of the candidate solution set in the coarse-tuning optimization, the adjustment range of the damper opening is dynamically limited. For example, if the candidate solution set is concentrated in 45-60°, the fine-tuning stage only allows an adjustment range of ±10°.

[0109] During the layered annealing optimization process, dynamic calibration is required for each round of optimization. The trigger condition for dynamic calibration is the timestamp of the building environment data before annealing. If the data delay exceeds 2 seconds (e.g., the carbon dioxide concentration value is still the reading from 5 seconds ago), the optimization is paused and the latest building environment data is waited for. Physical safety verification ensures that there are no mechanical conflicts in the linkage of equipment. For example, when the fan speed is >85%, the forced air valve opening is ≥30° to avoid high-speed airflow causing vibration of the building's fresh air ventilation system. When the opening difference between adjacent air valves is >15°, the angle of the high opening area is lowered first (3° each time).

[0110] It should be noted that during physical safety verification, abnormal handling is performed. For example, if the adjustment fails three times in a row within 30 seconds, the fixed fan speed is adjusted to 50% (binary code 01111111), and all air valves are forced to open fully (90°) for 5 minutes.

[0111] S5. Convert the real-time control command set into motor drive signals, control the fan speed and valve opening through the motor, and dynamically adjust the airflow distribution ratio according to the fan speed and valve opening to generate an environmental verification report.

[0112] The binary sequence of fan speed and valve opening (8 bits for fan speed and 7 bits for valve opening) in the control command set is converted into an executable motor drive signal through multi-protocol instruction parsing;

[0113] The 8-bit binary sequence of the 256-level wind turbine speed is converted into a percentage speed value (0-100%) using a non-uniform segmentation strategy;

[0114] For the low-speed zone (levels 0-127), each level corresponds to a 0.39% percentage RPM value. The low-speed zone percentage RPM value = (current level / 255) * 100. For the medium-speed zone (levels 128-191), each level corresponds to a 0.78% percentage RPM value. The medium-speed zone percentage RPM value = (128 + 2 * (current level - 128)) / 255 * 100. For the high-speed zone (levels 192-255), each level corresponds to a 1.56% percentage RPM value. The high-speed zone percentage RPM value = (192 + 4 * (current level - 192)) / 255 * 100. The high-speed zone is subject to speed limiting, with an upper limit set. When the calculated percentage RPM value > 100%, it is forcibly set to 100% (corresponding to binary code 11111111) to ensure that it does not exceed 100%.

[0115] The percentage speed value is converted into a PWM signal (10kHz frequency, linearly corresponding to 0-10V voltage) through the H-bridge circuit, which drives the EC motor to adjust the fan speed.

[0116] PWM signal refers to pulse width modulation signal, which is used to control output power and output voltage by adjusting the duty cycle of the pulse (duty cycle = speed percentage);

[0117] The percentage speed value is converted into a 0-10V voltage signal through voltage linear mapping (voltage value = percentage speed value * 0.1). The H-bridge circuit simulates the voltage value by adjusting the duty cycle, which is equal to the percentage speed value. The H-bridge circuit switches the conduction state of the MOSFET according to the PWM signal to control the winding current of the EC motor and realize the fan speed regulation.

[0118] Through multi-protocol instructions, the 7-bit binary sequence of the opening degree of the 127-level air valve is parsed into a physical angle of 0-90° (for the small opening area (0-45°), the physical angle = current level * (45 / 63), level 63 corresponds to 45°; for the large opening area (46-90°), the physical angle = 46 + (current level - 64) * (45 / 63)).

[0119] Multi-protocol commands refer to Modbus protocol, CAN bus protocol, stepper motor pulse protocol, PWM control protocol and RS-485 protocol;

[0120] Based on the physical angle, calculate the number of pulses in the acceleration and deceleration phases of the stepper motor. Each pulse of the stepper motor corresponds to 0.45°. The number of pulses = physical angle / 0.45°, with an error of ±0.5°. When the number of pulses is a decimal (e.g., 133.33), round the decimal to an integer (133 pulses) to ensure that the error is ≤ ±0.5°.

[0121] The pulse interval is adjusted by a timer. When the pulse interval of the acceleration phase gradually decreases and the pulse interval of the deceleration phase gradually increases, a step pulse sequence (200 pulses / 90°) is generated to prevent mechanical shock.

[0122] The stepper motor is driven to rotate the fan valve according to the stepper pulse sequence to control the valve opening. Each pulse is 0.45°. The error between the actual angle and the target angle is verified by the encoder to be ≤±0.5°.

[0123] Air volume detection nodes are deployed in the air supply duct to detect the air volume of each branch of the air supply duct in real time. Combined with temperature distribution data and carbon dioxide concentration values, the PID controller is used to dynamically adjust the opening difference between adjacent air valves, limiting the opening difference between adjacent air valves to ≤15° to ensure uniform distribution and prevent airflow short circuit.

[0124] When the carbon dioxide concentration exceeds the standard, increase the opening of the air valve in the corresponding area; when the temperature exceeds the standard, decrease the opening of the air valve in the corresponding area to reduce the delivery of cold and hot air.

[0125] When the opening difference between adjacent dampers is too large (e.g., >15°), the high-speed airflow will preferentially pass through the damper with the larger opening, resulting in insufficient airflow in the area with the smaller opening, or even reverse airflow, thus causing airflow short-circuiting.

[0126] The difference in opening degree between adjacent air valves refers to the physical angle difference between two adjacent air valves on the same air supply duct branch (e.g., the opening degree of air valve in area A is 50°, and the opening degree of air valve in adjacent area B is 60°, with an opening degree difference of 10°).

[0127] Based on the valve opening difference (inlet air velocity 1.5m / s, opening difference ≤15°), the valve opening of the building fresh air ventilation system is dynamically balanced to evenly distribute the airflow to the building fresh air ventilation system;

[0128] Set the target ventilation rate (e.g., space volume (m³)). 3 ) × number of air changes (times / hour)), and based on the air volume of each branch, calculate the actual air change in the air supply duct. Actual air change = average value of the detected air volume of each branch;

[0129] By comparing the target ventilation rate with the actual ventilation rate and combining the results of uniform airflow distribution, an environmental verification report is generated.

[0130] An environmental validation report is a structured validation report that compares the target ventilation rate with the actual ventilation rate (with a ventilation rate deviation of ≤ ±8%) and records abnormal events.

[0131] This embodiment also provides a computer device applicable to the adjustment method of a smart energy-saving building fresh air ventilation system, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the smart energy-saving building fresh air ventilation system adjustment method proposed in the above embodiment.

[0132] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0133] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the method for regulating a smart energy-saving building ventilation system as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0134] In summary, this invention achieves comprehensive monitoring and high-precision dynamic perception of the building's indoor environment by collecting and preprocessing building environment data through multi-source sensors. This ensures the reliability of the building environment data and provides a data foundation for subsequent precise adjustment of the ventilation system. By deploying carbon dioxide concentration monitors, infrared thermal imaging arrays, capacitive humidity sensors, and cameras, it comprehensively covers all functional areas of the building's fresh air ventilation system. It synchronously collects building environment data and generates a three-dimensional spatial thermodynamic distribution map, improving the visualization resolution and accuracy of the indoor environment status. Preprocessing eliminates sensor drift errors and electromagnetic interference noise in real time, effectively improving the accuracy of building environment data collection and significantly enhancing the quality of building environment data. Furthermore, through time synchronization calibration, it effectively solves the problems of time asynchrony and spatial misalignment of building environment data.

[0135] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for regulating a smart and energy-saving building fresh air ventilation system, characterized in that: include, Building environment data is collected through multi-source sensors and preprocessed. The fan speed and damper opening are encoded as binary variables to calculate the optimization target value of the building environment data; A quantum optimization model is constructed, with the input of the optimization target value and the output of a control instruction set. This includes using a D-Wave Advantage quantum processor to construct the quantum optimization model, which refers to coarse-tuning optimization, fine-tuning optimization, and micro-tuning optimization. The coarse-tuning optimization receives the optimization target value and performs a global search on the optimization target value on the D-Wave Advantage quantum processor to filter and obtain a candidate solution set. The fine-tuning optimization is based on the discretized parameter set and performs local optimization on the candidate solution set selected by the coarse-tuning optimization to obtain an updated candidate solution set. The micro-tuning optimization receives the updated candidate solution set from the fine-tuning optimization and uses simulated annealing on the CPU to iteratively optimize the updated candidate solution set to compensate for the quantum discretization error generated by the discretized parameter set, and outputs a control instruction set for the fan speed and the valve opening. Set multiple fixed thresholds and compare the building environment data with these thresholds to determine whether to activate the quantum optimization model. This includes setting multiple fixed thresholds and comparing the building environment data with them. If the building environment data does not exceed the multiple fixed thresholds, it indicates that the building's fresh air ventilation system is operating normally. If any building environment data exceeds the multiple fixed thresholds, it indicates that the building's fresh air ventilation system is operating abnormally. In this case, the quantum optimization model is activated to optimize the building environment data. The control command set is converted into motor drive signals, which control the fan speed and damper opening. The airflow distribution ratio is dynamically adjusted based on the fan speed and damper opening to generate an environmental verification report. This includes deploying airflow detection nodes in the air supply duct to monitor the airflow of each branch in real time. Combined with temperature distribution data and carbon dioxide concentration values, a PID controller is used to dynamically adjust the opening difference between adjacent dampers. The opening difference between adjacent dampers refers to the physical angle difference between two adjacent dampers on the same branch of the air supply duct. Based on the damper opening difference, the damper opening of the building's fresh air ventilation system is dynamically balanced to evenly distribute the airflow to the building's fresh air ventilation system. A target air exchange rate is set, and the actual air exchange rate in the air supply duct is calculated based on the airflow of each branch. The target air exchange rate and the actual air exchange rate are compared, and combined with the results of even airflow distribution, an environmental verification report is generated.

2. The method for regulating a smart energy-saving building fresh air ventilation system as described in claim 1, characterized in that... The multi-source sensor includes a carbon dioxide concentration monitor, an infrared thermal imaging array, a capacitive humidity sensor, and a camera; The building environment data includes carbon dioxide concentration, temperature distribution, humidity, and population density. The preprocessing includes time synchronization calibration, missing value imputation, and outlier filtering.

3. The method for regulating a smart energy-saving building fresh air ventilation system as described in claim 2, characterized in that... The specific steps for encoding fan speed and valve opening as binary variables and calculating the optimization target value of building environment data are as follows: By employing a non-uniform segmentation strategy, the fan speed and valve opening are encoded into binary sequences; Binary sequences are mapped to discretized parameter sets through hierarchical mapping; The weighting of the building's fresh air ventilation system's air exchange volume is dynamically adjusted based on personnel density data and humidity values. By weighted summation and discretization of the parameter set and weight allocation, the optimization target value of the building environment data is obtained.

4. The method for regulating a smart energy-saving building fresh air ventilation system as described in claim 3, characterized in that... The specific steps for optimizing the building environment data are as follows: Re-collect building environment data and calculate new optimization target values; Using the D-Wave Advantage quantum processor, new optimization target values ​​are input into the quantum optimization model. After coarse-tuning, fine-tuning, and micro-tuning optimizations, a real-time control command set for fan speed and valve opening is output.

5. The method for regulating a smart energy-saving building fresh air ventilation system as described in claim 4, characterized in that... The specific steps for converting the control command set into motor drive signals, and controlling the fan speed and valve opening via the motor, are as follows: The binary sequence of wind turbine speed is converted into a percentage speed value using a non-uniform segmentation strategy. The percentage speed value is converted into a PWM signal through the H-bridge circuit, which drives the EC motor to adjust the fan speed. The binary sequence of the valve opening is parsed into physical angles using multi-protocol commands; Calculate the number of pulses in the acceleration and deceleration phases of the stepper motor from a physics perspective; The pulse interval is adjusted by a timer. When the pulse interval of the acceleration phase gradually decreases and the pulse interval of the deceleration phase gradually increases, a step pulse sequence is generated. The stepper motor is driven to rotate the fan valve according to the stepper pulse sequence, thereby controlling the valve opening.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent energy-saving building fresh air ventilation system adjustment method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent energy-saving building fresh air ventilation system adjustment method according to any one of claims 1 to 5.

Images