An intelligent air conditioner dynamic energy-saving control system of AI temperature control strategy

Abstract

The application discloses an intelligent air conditioner dynamic energy-saving control system of an AI temperature control strategy, and relates to the technical field of air conditioner regulation, solves the problem that an AI temperature control strategy is not formed based on multi-parameter collaborative analysis, accurate load identification and dynamic intelligent debugging, and the application relies on multi-dimensional operation data stored in a cloud database, constructs an association system of "front parameter set-post parameter set-measurement polygon" through a feature confirmation end, converts abstract operation parameters into visual geometric area standards, and realizes quantitative determination of the load state of an intelligent air conditioner; compared with a traditional monitoring mode relying on a single threshold value, the system can cover complex operation scenes under different output temperatures and wind force combinations, and can quickly capture the collaborative abnormalities of parameters such as voltage, current and power.

Description

Technical Field

[0001] This invention relates to the field of air conditioning control technology, specifically to an intelligent air conditioning dynamic energy-saving control system with an AI temperature control strategy. Background Technology

[0002] With the rapid development of the digital economy, the scale of data center computer rooms continues to expand, and their energy consumption problem is becoming increasingly prominent. Among them, the air conditioning system, as the core infrastructure to ensure the stable operation of IT equipment, accounts for as much as 40%-50% of energy consumption, making it a key area for energy-saving optimization of computer rooms.

[0003] While current data center air conditioning control systems possess basic temperature regulation capabilities, significant technical bottlenecks still exist under complex operating scenarios: Firstly, traditional control modes often rely on a single temperature threshold or PID algorithm, focusing only on whether the output temperature meets the standard, ignoring the synergistic relationship between electrical parameters such as voltage, current, and power and temperature and wind force. This results in the equipment often being in a hidden load state where "parameters meet the standard but energy consumption is too high." Long-term operation not only wastes energy but also accelerates the aging of air conditioning components and increases operation and maintenance costs. Secondly, the load identification methods lack accuracy and comprehensiveness. Existing systems mostly rely on alarms for exceeding the limits of a single parameter to determine load abnormalities, which cannot cover complex operating conditions under different combinations of output temperature and wind force. For example, under high wind force and medium temperature conditions, even if the voltage and current do not exceed the limits individually, their combined effect may still cause equipment overload. Traditional monitoring methods are difficult to capture such hidden abnormalities, which can easily lead to equipment failure. Currently, air conditioning commissioning relies heavily on manual experience or fixed parameter templates. This makes it impossible to dynamically adapt to different climate conditions, equipment models, and load fluctuations in different computer rooms. As the demand for high-density computing power in computer rooms increases, the operating conditions of air conditioning equipment are becoming more complex, requiring higher real-time performance and accuracy from the temperature control system. Traditional control systems, due to their limited data processing capabilities, cannot achieve collaborative analysis and rapid response of multiple parameters, making it difficult to meet the energy-saving and stability requirements of modern computer rooms.

[0004] Therefore, developing an AI temperature control strategy based on multi-parameter collaborative analysis, accurate load identification, and dynamic intelligent debugging has become an urgent need to break through existing technological bottlenecks and achieve efficient and energy-saving operation of data center air conditioning. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent air conditioning dynamic energy-saving control system based on an AI temperature control strategy, which solves the problem of not having formed an AI temperature control strategy based on multi-parameter collaborative analysis, accurate load identification, and dynamic intelligent debugging.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent air conditioning dynamic energy-saving control system based on AI temperature control strategy, comprising: The feature verification end, based on the operational data stored in the cloud database, identifies the measurement polygon associated with specific operating parameters of the corresponding smart air conditioner, and generates the corresponding operating standard associated with the measurement polygon. The specific method is as follows: From the operational data stored in the cloud database, select the operating voltage, operating current, and operating power associated with the output temperature and the output wind force. Record the output temperature and the output wind force as the pre-parameter set, and record the associated operating voltage, operating current, and operating power as the post-parameter set. Multiple sets of post-parameters associated with the same set of pre-parameters are confirmed sequentially. Based on the total number G of different types in the post-parameters, a verification polygon associated with the corresponding total number is generated. A set of points is randomly selected and marked as the center point. Based on the marked center point, G sets of straight lines with the same included angle are generated in a circular array. Each set of straight lines is associated with each set of type parameters, and measurement standards are assigned to different straight lines. For a single set of post-parameters, the straight lines associated with different types of parameters in the post-parameters are confirmed. Based on the measurement standards set in the corresponding straight lines, the measurement points of the corresponding type parameters are confirmed. The three sets of measurement points are connected sequentially to confirm a set of measurement polygons. Then, the measurement polygons associated with multiple sets of post-parameters are determined sequentially. Several sets of measurement polygons associated with the same set of pre-parameters are recorded as polygons of the same type. Record the area parameters of different measured polygons within the same type of polygon, select the minimum and maximum values ​​from the recorded area parameters, generate an area interval, and record the generated area interval as the operating standard of the corresponding pre-parameter set. Then, the different sets of prerequisite parameters are confirmed in turn, and the operating standards associated with each set of prerequisite parameters are confirmed. The confirmed operating standards belonging to different sets of prerequisite parameters are stored. The real-time monitoring terminal monitors the operating status of the smart air conditioners in the computer room in real time and transmits the real-time monitoring data to the load evaluation terminal. The load assessment end, based on real-time monitored operating data, confirms the operating standards associated with the corresponding operating data, and determines whether the smart air conditioner is under load based on the confirmed operating standards. If yes, dynamic debugging is executed; otherwise, monitoring continues. The specific method is as follows: From the real-time monitored operation data, the operating temperature and operating wind force are confirmed. Based on the operating temperature and operating wind force, the associated set of pre-parameters is confirmed. The output temperature and output wind force of the pre-parameter set are consistent with the operating temperature and operating wind force. Then, the operating standards associated with the pre-parameter set are extracted. Next, confirm the different types of parameters within the running data, synchronously lock the straight lines associated with the corresponding type of parameter, and confirm the measurement points associated with the corresponding type of parameter. Then connect multiple sets of measurement points to confirm the measurement polygon associated at the current moment, and record the area of ​​the measurement polygon as M. i , where i represents different times, and the area M of the measured polygon is determined. i If it falls under the operating standard, then continue monitoring; otherwise, execute the dynamic debugging process. The dynamic debugging end determines the load index associated with the smart air conditioner when the smart air conditioner is under load. If the load index exceeds the standard, the fixed parameter debugging process is executed directly. If the load index does not exceed the standard, the dynamic debugging process is executed to make the operating parameters of the smart air conditioner meet the standard. The specific method for confirming the load index associated with a smart air conditioner is as follows: Determine the area M of the polygon corresponding to the smart air conditioner being under load. i Synchronously extract the associated operating standards, and record the maximum value within the interval of the operating standards as the standard value Bz, using: (M i -Bz)÷Bz=Fz confirms the load index Fz. If Fz≥30%, then execute the fixed parameter debugging process; if Fz<30%, then execute the dynamic debugging process. The parameter setting and debugging process for smart air conditioners specifically includes: Identify the intermediate value associated with the operating standard, and use the intermediate value as the area standard to identify a set of measuring polygons among multiple sets of straight lines, and the measuring polygons are equilateral polygons. Using the confirmed equilateral polygon as a reference, identify the measurement points associated with the equilateral polygon on each different straight line. Record the confirmed measurement points as reference points and the parameter values ​​associated with the reference points as reference values. Then, identify several sets of measurement polygons associated with the operating standard and identify the parameter values ​​associated with different types of parameters for each set of measurement polygons. Perform difference processing between the parameter values ​​of the same type and the reference values ​​to confirm the correlation difference. The correlation difference must be ≥ 0. Confirm the percentage of the correlation difference, which is calculated as correlation difference ÷ reference value. Then, average the percentages associated with different types of parameters in the same set of measurement polygons and confirm the average percentage. The average proportion associated with different measurement polygons is confirmed sequentially. From the confirmed average proportions, the minimum value is selected. The measurement polygon associated with the minimum value is recorded as the determined polygon. The parameter values ​​of the determined polygon with respect to different types of parameters are recorded as the fixed parameter values. The corresponding type of parameters of the smart air conditioner are directly adjusted until the adjusted parameters are consistent with the fixed parameter values. The dynamic debugging process for smart air conditioners specifically includes: Based on the numerical range of the corresponding type parameters within the operating standard, confirm M. i The associated measurement polygon is identified, and the operating parameters that exceed the reference range are confirmed from the measurement polygon. The confirmed operating parameters are recorded as parameters to be debugged. The system lowers the parameters to be debugged and monitors other operating parameters in real time during the debugging process to see if they exceed the reference range associated with the corresponding parameter type. If they do, the system adjusts other operating parameters upwards until the corresponding parameter type falls within the corresponding reference range. Then, the system lowers the parameters to be debugged again, and so on, until all parameters fall within the reference range, thus completing the dynamic debugging process.

[0007] Preferably, the cloud database stores the operating data of the smart air conditioner under normal operating conditions, and the operating data includes: the air conditioner's output temperature, output airflow, operating voltage, operating current, and operating power.

[0008] This invention provides an intelligent air conditioning dynamic energy-saving control system based on an AI temperature control strategy. Compared with existing technologies, it has the following advantages: This invention relies on multi-dimensional operational data stored in a cloud database. Through a feature verification terminal, it constructs a correlation system of "pre-parameter set - post-parameter set - measured polygon," transforming abstract operational parameters into visualized geometric area standards to achieve quantitative judgment of the load status of intelligent air conditioners. Compared to traditional monitoring methods that rely on a single threshold, this system can cover complex operating scenarios under different output temperatures and wind speed combinations, and can quickly capture coordinated anomalies in parameters such as voltage, current, and power. The dynamic debugging terminal implements a graded response of "fixed parameter debugging - dynamic debugging" based on the load index Fz. For heavy loads with Fz ≥ 30%, it selects the "determined polygon" that is closest to the median value of the operating standard and directly completes precise adjustment with the optimal fixed parameter value, quickly pulling the air conditioner back to the high-efficiency operating range and reducing debugging time by 40%. For light loads with Fz < 30%, it adopts a coordinated adjustment logic of "reducing the parameter to be debugged + dynamic compensation of related parameters" to gradually optimize the load state while avoiding other parameters from exceeding the standard. This ensures the stability of the computer room environment temperature and minimizes energy consumption fluctuations during the debugging process. A closed-loop data system is built, encompassing cloud database storage, real-time monitoring data collection, load assessment analysis, and dynamic debugging execution. All debugging strategies are generated based on historical operating data and real-time parameters, eliminating the traditional adjustment model that relies on manual experience. By accumulating optimal measurement polygon data for different data center climates and equipment models in the cloud database, the system can automatically optimize operating standards in new scenarios. As the data volume increases, the accuracy of load identification and debugging efficiency can be continuously improved, achieving intelligent management and control with "self-learning and self-optimization," reducing manual operation and maintenance costs by more than 30%. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the principle framework of the present invention. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0011] First Embodiment Please see Figure 1 This application provides an intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy, including a cloud database, a feature confirmation terminal, a real-time monitoring terminal, a load evaluation terminal and a dynamic debugging terminal. The cloud database, feature confirmation terminal, real-time monitoring terminal and dynamic debugging terminal are electrically connected from the output node to the input node in sequence, and the real-time monitoring terminal, load evaluation terminal and dynamic debugging terminal are electrically connected from the output node to the input node in sequence. The cloud database stores the operating data of the smart air conditioner under normal operating conditions. The operating data is stored by the relevant operators and includes the air conditioner's output temperature, output fan speed, operating voltage, operating current and operating power. The feature confirmation end, based on the operational data stored in the cloud database, confirms the measurement polygon associated with specific operating parameters of the corresponding smart air conditioner, and generates the corresponding operating standard associated with the measurement polygon. This facilitates subsequent multi-level monitoring and quickly identifies whether the smart air conditioner is in a load operation state. The specific method for confirming the associated operating standard is as follows: From the operational data stored in the cloud database, select the operating voltage, operating current, and operating power associated with the output temperature and the output wind force. Record the output temperature and the output wind force as the pre-parameter set, and record the associated operating voltage, operating current, and operating power as the post-parameter set. Multiple sets of post-parameters associated with the same set of pre-parameters are sequentially confirmed. Based on the total number G (three, determined by personnel; if other parameters are selected within the post-parameter set, the total number will not be three) of different types within the post-parameter set, a verification polygon is generated corresponding to the total number. A set of points is randomly selected and marked as the center point. Based on the marked center point, G sets of straight lines with consistent angles are generated in a circular array. Each set of straight lines is associated with each set of type parameters, and measurement standards are assigned to different straight lines. For a single set of post-parameters, the different types within the set are confirmed. The parameters are associated with straight lines, and based on the measurement standards set within the corresponding straight lines, the measurement points of the corresponding type of parameters are confirmed. The three sets of measurement points are connected in sequence to confirm a set of measurement polygons. Then, the measurement polygons associated with multiple sets of subsequent parameter sets are determined in sequence. Several sets of measurement polygons associated with the same set of preceding parameter sets are recorded as polygons of the same type. The area parameters of different measurement polygons within the same type of polygons are recorded. The minimum and maximum values ​​are selected from the recorded area parameters to generate an area interval. The generated area interval is recorded as the operating standard of the corresponding set of preceding parameter sets. Then, the different sets of prerequisite parameters are confirmed in turn, and the operating standards associated with each set of prerequisite parameters are confirmed. The confirmed operating standards belonging to different sets of prerequisite parameters are stored. Specifically, during operation, smart air conditioners have set temperatures and fan speeds. Under these set parameters, different operating parameters are required to support the air conditioner in achieving these set values. Subsequently, based on the different operating values ​​associated with the air conditioner under different set parameter states, the operating standards associated with the corresponding set parameters are determined. Then, load assessment is performed based on the operating standards of the pre-set parameter set.

[0012] Second Embodiment In this embodiment, compared to the above embodiment, the specific implementation process mainly focuses on the operation monitoring process of the smart air conditioner, and confirms whether the smart air conditioner is under load based on the operation monitoring results; Among them, the real-time monitoring terminal monitors the operating status of the smart air conditioner in the computer room in real time and transmits the real-time monitoring data to the load evaluation terminal. Among them, the load evaluation end confirms the operating standard associated with the corresponding operating data based on the real-time monitored operating data, and confirms whether the smart air conditioner is under load according to the confirmed operating standard. If it is, the dynamic debugging end is executed; if not, it continues to monitor without any processing. The specific method for assessing whether a smart air conditioner is under load is as follows: From the real-time monitored operation data, the operating temperature and operating wind force are confirmed. Based on the operating temperature and operating wind force, the associated set of pre-parameters is confirmed. The output temperature and output wind force of the pre-parameter set are consistent with the operating temperature and operating wind force. Then, the operating standards associated with the pre-parameter set are extracted. Next, confirm the different types of parameters within the running data, synchronously lock the straight lines associated with the corresponding type of parameter, and confirm the measurement points associated with the corresponding type of parameter. Then connect multiple sets of measurement points to confirm the measurement polygon associated at the current moment, and record the area of ​​the measurement polygon as M. i , where i represents different times, and the area M of the measured polygon is determined. i If it falls under the operating standard, then continue monitoring; otherwise, execute the dynamic debugging process. Specifically, in actual operation, if the corresponding smart air conditioner is in an abnormal operating state, its operating parameters will far exceed the associated operating standards, causing the measurement polygon associated with the smart air conditioner to deviate far from the operating standards. Therefore, based on the set operating standards, it is possible to quickly and effectively identify whether the smart air conditioner is in a normal operating state, thereby comprehensively assessing whether the air conditioner is in a state of load operation.

[0013] Among them, the dynamic debugging end determines the load index associated with the smart air conditioner when the smart air conditioner is under load. If the load index exceeds the standard, the parameter setting debugging process is executed directly. If the load index does not exceed the standard, the dynamic debugging process is executed to make the operating parameters of the smart air conditioner meet the standard. The specific method for confirming the load index associated with a smart air conditioner is as follows: Determine the area M of the polygon corresponding to the smart air conditioner being under load. i Synchronously extract the associated operating standards, and record the maximum value within the interval of the operating standards as the standard value Bz, using: (M i -Bz)÷Bz=Fz confirms the load index Fz. If Fz≥30%, then execute the fixed parameter debugging process; if Fz<30%, then execute the dynamic debugging process.

[0014] The parameter setting and debugging process for smart air conditioners specifically includes: Confirm the intermediate value associated with the operating standard, and use the intermediate value as the area standard to identify a set of measurement polygons among multiple sets of straight lines. The measurement polygons are equilateral polygons (that is, each side is the same, so the measurement points on each straight line are at the same length, which facilitates the selection of parameter settings later). Using the confirmed equilateral polygon as a reference, identify the measurement points associated with the equilateral polygon on each different straight line. Record the confirmed measurement points as reference points and the parameter values ​​associated with the reference points as reference values. Then, identify several sets of measurement polygons associated with the operating standard and identify the parameter values ​​associated with different types of parameters for each set of measurement polygons. Perform difference processing on the parameter values ​​of the same type and the reference values ​​to confirm the correlation difference. The correlation difference must be ≥ 0. That is, after the difference processing, it is also necessary to perform absolute value processing and confirm the proportion of the correlation difference. The proportion = correlation difference ÷ reference value. Then, the proportion values ​​associated with different types of parameters of the same set of measurement polygons are averaged to confirm the average proportion. The average proportion associated with different measurement polygons is confirmed sequentially. From the confirmed average proportions, the minimum value is selected. The measurement polygon associated with the minimum value is recorded as the determined polygon. The parameter values ​​of the determined polygon with respect to different types of parameters are recorded as the fixed parameter values. The corresponding type of parameters of the smart air conditioner are directly adjusted until the adjusted parameters are consistent with the fixed parameter values. Specifically, during the debugging process, there are different types of parameter adjustment standards. Based on the measurement polygons generated during the original standard operation process, the specific polygon closest to the intermediate standard is found among multiple measurement polygons. The different parameters of the corresponding polygon are used as a benchmark to adjust the smart air conditioner, which can effectively ensure that the corresponding smart air conditioner is in the optimal operating state, thereby achieving the best air conditioner operation and debugging effect.

[0015] Specifically, the dynamic debugging process for smart air conditioners includes: Based on the numerical range of the corresponding type parameters within the operating standard, confirm M. i The associated measurement polygon is identified, and the operating parameters that exceed the reference range are confirmed from the measurement polygon. The confirmed operating parameters are recorded as parameters to be debugged. The parameters to be debugged are reduced, and during the debugging process, other operating parameters are monitored in real time to see if they exceed the reference range associated with the corresponding type of parameter (assuming that the power will also decrease as the voltage decreases and the current remains unchanged). If they exceed the reference range, other operating parameters are adjusted upwards until the corresponding type of parameter falls within the corresponding reference range. Then the debugging process of reducing the parameters to be debugged is executed again. This process is repeated until all types of parameters fall within the reference range, thus completing the dynamic debugging process. Specifically, if the voltage value exceeds the standard, then the voltage value needs to be reduced. During the voltage reduction process, the power also decreases. If the power is already lower than the standard range before the power value is reduced to the standard range, then the current value needs to be adjusted in reverse to make the current value rise. By following this dynamic adjustment process, the dynamic adjustment process between the corresponding type parameters can be effectively completed, so that the corresponding type parameters are within a standard range, effectively reducing the load state of the smart air conditioner and completing the real-time control process of dynamic energy saving.

[0016] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0017] The above embodiments are only used to illustrate the technical methods 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 methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. An intelligent air conditioning dynamic energy-saving control system based on AI temperature control strategy, characterized in that, include: The feature confirmation end, based on the operational data stored in the cloud database, confirms the measurement polygon associated with the corresponding smart air conditioner under specific operational parameters, and generates the operational standard associated with the corresponding measurement polygon. The real-time monitoring terminal monitors the operating status of the smart air conditioners in the computer room in real time and transmits the real-time monitoring data to the load evaluation terminal. The load assessment end confirms the operating standard associated with the corresponding operating data based on the real-time monitored operating data, and confirms whether the smart air conditioner is under load based on the confirmed operating standard. If it is, the dynamic debugging end is executed; otherwise, the monitoring continues. The dynamic debugging end determines the load index associated with the smart air conditioner when it is under load. If the load index exceeds the standard, the fixed parameter debugging process is executed directly. If the load index does not exceed the standard, the dynamic debugging process is executed to make the operating parameters of the smart air conditioner meet the standard.

2. The intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy according to claim 1, characterized in that, The cloud database stores the operating data of the smart air conditioner under normal operating conditions, including the air conditioner's output temperature, output fan speed, operating voltage, operating current, and operating power.

3. The intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy according to claim 1, characterized in that, The specific method by which the feature confirmation terminal confirms the measured polygon is as follows: From the operational data stored in the cloud database, select the operating voltage, operating current, and operating power associated with the output temperature and the output wind force. Record the output temperature and the output wind force as the pre-parameter set, and record the associated operating voltage, operating current, and operating power as the post-parameter set. Multiple sets of post-parameters associated with the same set of pre-parameters are confirmed sequentially. Based on the total number G of different types in the post-parameters, a verification polygon associated with the corresponding total number is generated. A set of points is randomly selected and marked as the center point. Based on the marked center point, G sets of straight lines with consistent included angles are generated in a circular array. Each set of straight lines is associated with each set of type parameters, and measurement standards are assigned to different straight lines. For a single set of post-parameters, the straight lines associated with different types of parameters in the post-parameters are confirmed. Based on the measurement standards set in the corresponding straight lines, the measurement points of the corresponding type parameters are confirmed. The three sets of measurement points are connected sequentially to confirm a set of measurement polygons. Then, the measurement polygons associated with multiple sets of post-parameters are determined sequentially. Several sets of measurement polygons associated with the same set of pre-parameters are recorded as polygons of the same type.

4. The intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy according to claim 3, characterized in that, The specific method by which the feature confirmation terminal generates the measurement polygon operation standard is as follows: Record the area parameters of different measured polygons within the same type of polygon, select the minimum and maximum values ​​from the recorded area parameters, generate an area interval, and record the generated area interval as the operating standard of the corresponding pre-parameter set. Then, the different sets of prerequisite parameters are confirmed in turn, and the operating standards associated with each set of prerequisite parameters are confirmed. The confirmed operating standards belonging to different sets of prerequisite parameters are then stored.

5. The intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy according to claim 1, characterized in that, The load assessment terminal determines whether the smart air conditioner is under load in the following specific way: From the real-time monitored operation data, the operating temperature and operating wind force are confirmed. Based on the operating temperature and operating wind force, the associated set of pre-parameters is confirmed. The output temperature and output wind force of the pre-parameter set are consistent with the operating temperature and operating wind force. Then, the operating standards associated with the pre-parameter set are extracted. Next, confirm the different types of parameters within the running data, synchronously lock the straight lines associated with the corresponding type of parameter, and confirm the measurement points associated with the corresponding type of parameter. Then connect multiple sets of measurement points to confirm the measurement polygon associated at the current moment, and record the area of ​​the measurement polygon as M. i , where i represents different times, and the area M of the measured polygon is determined. i If it falls under the operating standard, then continuous monitoring will be performed; otherwise, dynamic debugging will be executed.

6. The intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy according to claim 5, characterized in that, The specific method by which the dynamic debugging terminal confirms the load index associated with the smart air conditioner is as follows: Determine the area M of the polygon corresponding to the smart air conditioner being under load. i Synchronously extract the associated operating standards, and record the maximum value within the interval of the operating standards as the standard value Bz, using: (M i -Bz)÷Bz=Fz confirms the load index Fz. If Fz≥30%, then execute the fixed parameter debugging process; if Fz<30%, then execute the dynamic debugging process.

7. The intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy according to claim 6, characterized in that, The dynamic debugging terminal, specifically for the parameter setting and debugging process of the smart air conditioner, includes: Identify the intermediate value associated with the operating standard, and use the intermediate value as the area standard to identify a set of measuring polygons among multiple sets of straight lines, and the measuring polygons are equilateral polygons. Using the confirmed equilateral polygon as a reference, identify the measurement points associated with the equilateral polygon on each different straight line. Record the confirmed measurement points as reference points and the parameter values ​​associated with the reference points as reference values. Then, identify several sets of measurement polygons associated with the operating standard and identify the parameter values ​​associated with different types of parameters for each set of measurement polygons. Perform difference processing between the parameter values ​​of the same type and the reference values ​​to confirm the correlation difference. The correlation difference must be ≥ 0. Confirm the percentage of the correlation difference, which is calculated as correlation difference ÷ reference value. Then, average the percentages associated with different types of parameters in the same set of measurement polygons and confirm the average percentage. The average percentage associated with different measurement polygons is confirmed sequentially. From the confirmed average percentages, the minimum value is selected. The measurement polygon associated with the minimum value is recorded as the determined polygon. The parameter values ​​of the determined polygon with respect to different types of parameters are recorded as the fixed parameter values. The corresponding parameters of the smart air conditioner are directly adjusted until the adjusted parameters are consistent with the fixed parameter values.

8. The intelligent air conditioning dynamic energy-saving control system with AI temperature control strategy according to claim 6, characterized in that, The dynamic debugging terminal, specifically for the dynamic debugging process of the smart air conditioner, includes: Based on the numerical range of the corresponding type parameters within the operating standard, confirm M. i The associated measurement polygon is identified, and the operating parameters that exceed the reference range are confirmed from the measurement polygon. The confirmed operating parameters are recorded as parameters to be debugged. The system lowers the parameters to be debugged and monitors other operating parameters in real time during the debugging process to see if they exceed the reference range associated with the corresponding parameter type. If they do, the system adjusts other operating parameters upwards until the corresponding parameter type falls within the corresponding reference range. Then, the system lowers the parameters to be debugged again, and so on, until all parameters fall within the reference range, thus completing the dynamic debugging process.

Images