Self-adaptive load adjusting method and system for heat pipe air conditioner

Abstract

The invention discloses a self-adaptive load adjusting method and system for a heat pipe air conditioner, and the method comprises the steps: collecting the working state data of the air conditioner through a sensor, and enabling the working state data to at least comprise temperature data, pressure data, working medium circulation flow data and load power data; performing data preprocessing on the working state data and then performing fusion to obtain initial working state data; calculating a real-time load coefficient based on the initial working state data, and dividing a low-load working condition, a medium-load working condition and a high-load working condition according to the real-time load coefficient; and according to different working conditions, the working medium flow and the fan speed are dynamically adjusted through a fuzzy PID algorithm and a self-learning mechanism. And the operation key parameters of the heat pipe are covered by multiple types of sensors, so that one-sidedness of single temperature control is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving control of air-conditioning systems, and in particular to an adaptive load regulation method and system for a heat pipe air conditioner. Background Art

[0002] The heat pipe air conditioner realizes efficient heat transfer through the phase change of the working medium in the heat pipe, and has the advantages of energy saving and reliability. However, the existing heat pipe air conditioners have the following technical defects: Coarse load regulation: Traditional control methods rely on preset thresholds and cannot respond to dynamic load changes in real time, resulting in a decrease in energy efficiency or overcooling and overheating phenomena. Multivariable coupling problem: The performance of the heat pipe is affected by multiple parameters such as the flow rate of the working medium, the temperature difference between the evaporation section and the condensation section, and the fan air speed. It is difficult for traditional PID control to balance complex coupling relationships and the regulation accuracy is insufficient. The energy-saving potential is not fully exploited: In low-load conditions (such as at night or in the off-season), the system still operates in the high-load mode, causing energy waste. Summary of the Invention

[0003] The purpose of the present invention is to solve the above problems and design an adaptive load regulation method for a heat pipe air conditioner.

[0004] Furthermore, in the above-mentioned adaptive load regulation method for a heat pipe air conditioner, the adaptive load regulation method for the heat pipe air conditioner includes the following steps:

[0005] Collect the working state data of the air conditioner through sensors, and the working state data at least includes temperature data, pressure data, working medium circulation flow rate data, and load power data;

[0006] After preprocessing the working state data, fuse them to obtain the initial working state data;

[0007] Calculate the real-time load coefficient based on the initial working state data, and divide the low-load condition, medium-load condition, and high-load condition according to the real-time load coefficient;

[0008] For different working conditions, dynamically adjust the working medium flow rate and fan air speed through the fuzzy PID algorithm and the self-learning mechanism.

[0009] Furthermore, in the above-mentioned adaptive load regulation method for a heat pipe air conditioner, the step of collecting the working state data of the air conditioner through sensors, where the working state data at least includes temperature data, pressure data, working medium circulation flow rate data, and load power data, includes:

[0010] Arrange temperature sensors at the inlet of the evaporation section and the outlet of the condensation section to monitor the temperature difference between the hot and cold ends in real time; arrange temperature sensors in the indoor target area to obtain the temperature data of the controlled object;

[0011] Install a pressure sensor in the main circulation pipeline of the heat pipe to obtain the pressure data of the air conditioner;

[0012] Install an electromagnetic flowmeter and a vortex street flowmeter in the working medium circulation pipeline to obtain the working medium circulation flow data;

[0013] Install a power sensor at the equipment end served by the air conditioner to obtain the load power data.

[0014] Furthermore, in the above-mentioned adaptive load regulation method for a heat pipe air conditioner, the fusion is performed after data preprocessing of the working state data to obtain the initial working state data, including:

[0015] Perform median filtering on the working state data to eliminate accidental interference and obtain the filtered state data;

[0016] Calibrate the zero drift of the temperature and pressure sensors in the filtered state data through a reference source to obtain the calibrated state data;

[0017] Set the temperature to exceed the critical temperature of the working medium and the pressure to exceed the pipeline safety limit value, and eliminate the invalid data in the calibrated state data to obtain the complete state data;

[0018] Map the temperature, pressure, flow rate, and load power data in the complete state data to a unified space-time coordinate system. With the indoor target temperature as the core, the evaporation section temperature is associated to reflect the heat absorption capacity, the condensation section temperature reflects the heat dissipation efficiency, the pressure and flow rate data jointly characterize the working medium circulation state, and the load power quantifies the heat load intensity to obtain the initial working state data.

[0019] Furthermore, in the above-mentioned adaptive load regulation method for a heat pipe air conditioner, the calculation of the real-time load coefficient based on the initial working state data and the division of low-load conditions, medium-load conditions, and high-load conditions include:

[0020] Establish a comprehensive load characteristic index according to the temperature difference between the hot and cold ends, load power, and working medium flow rate parameters in the initial working state data;

[0021] Divide into low-load conditions, medium-load conditions, and high-load conditions according to the comprehensive load characteristic index;

[0022] The low-load condition is that the index value is in the low range, characterized by the indoor temperature approaching the target value, a small temperature difference between the hot and cold ends, and low load power;

[0023] The medium-load condition is that the index value is in the middle range, corresponding to the normal operation state, and stable temperature control needs to be maintained;

[0024] The high-load condition is that the indoor temperature deviates significantly from the target value, the temperature difference between the hot and cold ends expands, and the load power surges.

[0025] Further, in the above-mentioned adaptive load regulation method for a heat pipe air conditioner, for different working conditions, dynamically adjusting the working fluid flow rate and the fan air speed through a fuzzy PID algorithm and a self-learning mechanism includes:

[0026] If it is determined to be an electric load condition, the working fluid circulation volume is reduced through an electric control valve to 40%-70% of the rated flow rate; the condensing section fan is started and stopped in stages, and 1-2 units are retained to operate at a low speed;

[0027] If it is determined to be a medium load condition, with the temperature difference between the hot and cold ends as the control variable, combined with the indoor temperature deviation, the parameters of the PID controller are dynamically adjusted through fuzzy logic, and the rotational speed of the condensing section fan and the working fluid flow rate are adjusted synchronously;

[0028] Using a time series algorithm to identify the optimal combination of adjustment parameters under different seasons, day and night, and load patterns. If the indoor temperature deviation still exceeds 1°C after 3 consecutive adjustments, switch to a compensation strategy based on the heat pipe physical model.

[0029] Further, in a system for an adaptive load regulation method of a heat pipe air conditioner, the adaptive load regulation system of the heat pipe air conditioner includes the following modules:

[0030] A data acquisition module, used to collect the working state data of the air conditioner through sensors, and the working state data at least includes temperature data, pressure data, working fluid circulation flow rate data, and load power data;

[0031] A data processing module, used to preprocess and fuse the working state data to obtain initial working state data;

[0032] A state division module, used to calculate the real-time load coefficient based on the initial working state data, and divide the low load condition, medium load condition, and high load condition according to the real-time load coefficient;

[0033] A load adjustment module, used to dynamically adjust the working fluid flow rate and the fan air speed through a fuzzy PID algorithm and a self-learning mechanism for different working conditions.

[0034] Further, in the system for implementing the above-mentioned adaptive load regulation method of a heat pipe air conditioner, the data acquisition module includes the following sub-modules:

[0035] A temperature acquisition sub-module, used to arrange temperature sensors at the inlet of the evaporation section and the outlet of the condensing section to monitor the temperature difference between the hot and cold ends in real time; arrange temperature sensors in the indoor target area to obtain the temperature data of the controlled object;

[0036] A pressure acquisition sub-module, used to install a pressure sensor in the main circulation pipeline of the heat pipe to obtain the pressure data of the air conditioner;

[0037] A flow acquisition sub-module, which is used to install an electromagnetic flowmeter and a vortex street flowmeter in the working medium circulation pipeline to obtain the working medium circulation flow data;

[0038] A power acquisition sub-module, which is used to install a power sensor at the equipment end served by the air conditioner to obtain the load power data.

[0039] Furthermore, in the system for implementing the above-mentioned adaptive load regulation method of a heat pipe air conditioner, the data processing module includes the following sub-modules:

[0040] A filtering processing sub-module, which is used to perform median filtering processing on the working state data, eliminate accidental interference, and obtain filtered state data;

[0041] A state calibration sub-module, which is used to calibrate the zero drift of the temperature and pressure sensors in the filtered state data through a reference source to obtain calibrated state data;

[0042] A data elimination sub-module, which is used to set that the temperature exceeds the critical temperature of the working medium and the pressure exceeds the pipeline safety limit value, and eliminate the invalid data in the calibrated state data to obtain complete state data;

[0043] A data obtaining sub-module, which is used to map the temperature, pressure, flow rate, and load power data in the complete state data to a unified space-time coordinate system, with the indoor target temperature as the core, associate the evaporation section temperature to reflect the heat absorption capacity, the condensation section temperature to reflect the heat dissipation efficiency, the pressure and flow rate data jointly characterize the working medium circulation state, and the load power quantifies the heat load intensity to obtain the initial working state data.

[0044] Its beneficial effects are as follows: the working state data of the air conditioner is collected through sensors, and the working state data at least includes temperature data, pressure data, working medium circulation flow data, and load power data; after preprocessing the working state data, it is fused to obtain the initial working state data; based on the initial working state data, the real-time load coefficient is calculated, and the low-load working condition, medium-load working condition, and high-load working condition are divided according to the real-time load coefficient; for different working conditions, the working medium flow rate and the fan air speed are dynamically adjusted through the fuzzy PID algorithm and the self-learning mechanism. 1. Full-dimensional perception: cover the key parameters of the heat pipe operation through multiple types of sensors to avoid the one-sidedness of single-temperature control; 2. Precise working condition matching: based on the load characteristics, dynamically switch the strategy to solve the problem of the imbalance between energy efficiency and accuracy caused by the "one-size-fits-all" of traditional control; 3. Self-evolution ability: adapt to environmental changes (such as seasons, equipment load rules) through learning historical data, without frequent manual calibration, and improve the long-term reliability of the system. Description of the Drawings

[0045] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention.

[0046] Figure 1 Schematic diagram of the first embodiment of an adaptive load regulation method for a heat pipe air conditioner in an embodiment of the present invention;

[0047] Figure 2 Schematic diagram of the second embodiment of an adaptive load regulation method for a heat pipe air conditioner in an embodiment of the present invention;

[0048] Figure 3 Schematic diagram of the first embodiment of an adaptive load regulation system for a heat pipe air conditioner in an embodiment of the present invention. Detailed implementation manners

[0049] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0050] Those skilled in the art of the present technology can understand that unless specifically stated, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0051] The present invention will be specifically described below with reference to the drawings. As Figure 1 shown, an adaptive load regulation method for a heat pipe air conditioner, the adaptive load regulation method for the heat pipe air conditioner includes the following steps:

[0052] Step 101: Collect the working state data of the air conditioner through sensors, and the working state data at least includes temperature data, pressure data, working medium circulation flow data and load power data;

[0053] Specifically, in this embodiment, temperature sensors are arranged at the inlet of the evaporation section and the outlet of the condensation section to monitor the temperature difference between the hot and cold ends in real time; temperature sensors are arranged in the indoor target area to obtain the temperature data of the controlled object; pressure sensors are installed in the main heat pipe circulation pipeline to obtain the pressure data of the air conditioner; electromagnetic flow meters and vortex street flow meters are installed in the working medium circulation pipeline to obtain the working medium circulation flow data; power sensors are installed at the equipment end served by the air conditioner to obtain the load power data.

[0054] Step 102: Perform data preprocessing on the working state data and then fuse it to obtain the initial working state data;

[0055] Specifically, in this embodiment, median filtering is performed on the working state data to eliminate accidental interference and obtain the filtered state data; the zero drift of the temperature and pressure sensors in the filtered state data is calibrated through a reference source to obtain the calibrated state data; it is set that the temperature exceeds the critical temperature of the working medium and the pressure exceeds the pipeline safety limit value, and the invalid data in the calibrated state data is eliminated to obtain the complete state data; the temperature, pressure, flow rate, and load power data in the complete state data are mapped to a unified space-time coordinate system. With the indoor target temperature as the core, the evaporation section temperature is associated to reflect the heat absorption capacity, the condensation section temperature is associated to reflect the heat dissipation efficiency, the pressure and flow rate data jointly characterize the working medium circulation state, and the load power quantifies the heat load intensity to obtain the initial working state data.

[0056] Step 103: Calculate the real-time load factor based on the initial working state data, and divide the low load condition, medium load condition, and high load condition according to the real-time load factor;

[0057] Specifically, in this embodiment, a comprehensive load characteristic index is established according to the temperature difference between the hot and cold ends, load power, and working medium flow rate parameters in the initial working state data; it is divided into a low load condition, a medium load condition, and a high load condition according to the comprehensive load characteristic index; the low load condition is that the index value is in the low range, and the characteristics are that the indoor temperature is close to the target value, the temperature difference between the hot and cold ends is small, and the load power is low; the medium load condition is that the index value is in the middle range, corresponding to the normal operation state, and stable temperature control needs to be maintained; the high load condition is that the indoor temperature deviates significantly from the target value, the temperature difference between the hot and cold ends expands, and the load power surges.

[0058] Step 104: For different working conditions, dynamically adjust the working medium flow rate and the fan wind speed through a fuzzy PID algorithm and a self-learning mechanism.

[0059] If it is judged as the electric load condition, the working medium circulation volume is reduced through an electric control valve to 40%-70% of the rated flow rate; the condensation section fan is started and stopped in stages, and 1-2 units are reserved to run at a low speed; if it is judged as the medium load condition, with the temperature difference between the hot and cold ends as the control variable, combined with the indoor temperature deviation, the PID controller parameters are dynamically adjusted through fuzzy logic, and the rotation speed of the condensation section fan and the working medium flow rate are adjusted synchronously; the optimal adjustment parameter combination under different seasons, day and night, and load modes is identified by using a time series algorithm. If the indoor temperature deviation still exceeds 1°C after 3 consecutive adjustments, switch to the compensation strategy based on the heat pipe physical model.

[0060] The beneficial effects are as follows: The working state data of the air conditioner is collected through sensors, and the working state data at least includes temperature data, pressure data, working medium circulation flow data, and load power data; after data preprocessing of the working state data, fusion is performed to obtain initial working state data; based on the initial working state data, the real-time load factor is calculated, and the low-load condition, medium-load condition, and high-load condition are divided according to the real-time load factor; for different conditions, the working medium flow rate and the fan air speed are dynamically adjusted through the fuzzy PID algorithm and the self-learning mechanism. 1. Full-dimensional perception: Cover the key parameters of the heat pipe operation through multiple types of sensors, avoiding the one-sidedness of single-temperature control; 2. Precise condition matching: Based on the load characteristics, dynamically switch the strategy to solve the problem of the imbalance between energy efficiency and accuracy caused by the one-size-fits-all traditional control; 3. Self-evolution ability: Adapt to environmental changes (such as seasons, equipment load rules) through historical data learning, without frequent manual calibration, and improve the long-term reliability of the system.

[0061] Please refer to Figure 2 , in an adaptive load regulation method of a heat pipe air conditioner, after data preprocessing of the working state data, the steps for fusion to obtain the initial working state data include the following:

[0062] Step 201: Perform median filtering on the working state data to eliminate accidental interference and obtain filtered state data;

[0063] Step 202: Calibrate the zero drift of the temperature and pressure sensors in the filtered state data through a reference source to obtain calibrated state data;

[0064] Step 203: Set the temperature to exceed the critical temperature of the working medium and the pressure to exceed the pipeline safety limit value, and eliminate the invalid data in the calibrated state data to obtain complete state data;

[0065] Step 204: Map the temperature, pressure, flow rate, and load power data in the complete state data to a unified space-time coordinate system;

[0066] Taking the indoor target temperature as the core, the evaporation section temperature is associated to reflect the heat absorption capacity, the condensation section temperature is associated to reflect the heat dissipation efficiency, the pressure and flow rate data jointly characterize the working medium circulation state, and the load power quantifies the heat load intensity to obtain the initial working state data.

[0067] Please refer to Figure 3 , in an adaptive load regulation system of a heat pipe air conditioner, the surface resource permission management system includes the following modules:

[0068] The data acquisition module is used to collect the working state data of the air conditioner through sensors, and the working state data at least includes temperature data, pressure data, working medium circulation flow data, and load power data;

[0069] A data processing module, which is used to perform data preprocessing on the working state data and then fuse them to obtain the initial working state data;

[0070] A state division module, which is used to calculate the real-time load factor based on the initial working state data, and divide the low-load condition, medium-load condition and high-load condition according to the real-time load factor;

[0071] A load adjustment module, which is used to dynamically adjust the working medium flow rate and the fan air speed through a fuzzy PID algorithm and a self-learning mechanism for different working conditions.

[0072] Specifically, in this embodiment,

[0073] 1. Low-load condition (energy saving priority)

[0074] Working medium flow rate adjustment: Reduce the working medium circulation amount through an electric control valve (such as a proportional-integral valve) to 40%-70% of the rated flow rate (the specific ratio is dynamically adjusted according to the load factor), and reduce the phase change cycle energy consumption.

[0075] Fan control: Start and stop the condensing section fans in stages (such as multiple groups of parallel fans), only keep 1-2 units running at low speed, or use a variable-frequency fan to reduce the speed to 30%-50% of the rated speed to reduce the fan power consumption.

[0076] Temperature tolerance relaxation: Allow the indoor temperature to fluctuate within the range of ±2°C from the target value (in a non-strict temperature control scenario), avoid the valve / fan action loss caused by frequent adjustment, and at the same time maintain the basic temperature control through the natural heat transfer characteristics of the heat pipe.

[0077] 2. High-load condition (heat dissipation priority)

[0078] Fuzzy PID dynamic adjustment:

[0079] Taking the temperature difference between the hot and cold ends as the core control variable, combining with the indoor temperature deviation, dynamically adjust the PID controller parameters (proportional / integral / differential coefficients) through fuzzy logic to solve the regulation lag problem of traditional PID in a multi-variable coupling scenario. For example:

[0080] When the temperature difference rapidly expands, automatically increase the fan air speed adjustment gain to accelerate the improvement of the heat dissipation capacity;

[0081] When the temperature deviation persists, compensate the working medium flow rate through the integral term to avoid static error.

[0082] Fan and valve coordinated control: Synchronously adjust the fan speed of the condensing section (increase to 80%-120% of the rated value) and the working medium flow rate (fully open or nearly fully open) to make the heat pipe operate in the optimal heat transfer temperature difference range calibrated in the experiment (such as 10-15°C, customized according to the heat pipe model).

[0083] Feedforward compensation: Introduce real-time monitoring of load power. When a sudden increase in equipment power is detected (such as the startup of a server cluster), the fan and valve are pre-adjusted in advance to shorten the system response time and avoid temperature overshoot.

[0084] 3. Full-condition self-learning mechanism

[0085] Data accumulation and model update:

[0086] The system has a built-in historical database that stores at least 7 days of operation data (including load indicators, adjustment parameters, and energy efficiency data). The self-learning program is triggered at midnight (low-load period) every day.

[0087] Use a time series analysis algorithm (not described formulaically) to identify the optimal combination of adjustment parameters under different seasons, day and night, and load patterns. For example:

[0088] In winter when the outdoor temperature is low, automatically reduce the minimum speed of the condenser fan and use natural cold sources to improve efficiency;

[0089] In summer when the temperature is high and the load is high, dynamically optimize the membership function of the fuzzy PID to enhance the adjustment sensitivity.

[0090] Fault tolerance and robustness design: If the indoor temperature deviation still exceeds 1°C after 3 consecutive adjustments, switch to a compensation strategy based on the physical model of the heat pipe (such as increasing the flow rate and wind speed in a fixed proportion) to avoid system oscillation caused by excessive algorithm iteration.

[0091] Closed-loop feedback and system optimization (implied in step four)

[0092] Establish a real-time monitoring closed-loop: Refresh the load indicators every 5 seconds, dynamically switch the adjustment strategy according to the latest working conditions, and form a complete control loop of "data acquisition - analysis and decision - execution of adjustment - effect feedback".

[0093] Long-term energy efficiency optimization: Continuously iterate the adjustment strategy through the self-learning mechanism. For example, when it is identified that all condenser fans can be turned off under low load in a certain period and the temperature control requirements can still be met only by natural convection heat dissipation, an energy-saving strategy for this working condition is automatically generated to further reduce energy consumption.

[0094] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and do not limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive load regulation method for a heat pipe air conditioner, characterized in that The adaptive load regulation method of the heat pipe air conditioner includes the following steps: Collect the working state data of the air conditioner through sensors. The working state data at least includes temperature data, pressure data, working medium circulation flow data, and load power data; Perform data preprocessing on the working state data and then fuse it to obtain the initial working state data; Calculate the real-time load coefficient based on the initial working state data, and divide the low-load condition, medium-load condition, and high-load condition according to the real-time load coefficient; For different conditions, dynamically adjust the working medium flow rate and fan air speed through the fuzzy PID algorithm and self-learning mechanism.

2. The adaptive load adjustment method of a heat pipe air conditioner according to claim 1, characterized in that, The step of collecting the working state data of the air conditioner through sensors. The working state data at least includes temperature data, pressure data, working medium circulation flow data, and load power data, includes: Arrange temperature sensors at the inlet of the evaporation section and the outlet of the condensation section to monitor the temperature difference between the hot and cold ends in real time; arrange temperature sensors in the indoor target area to obtain the temperature data of the controlled object; Install a pressure sensor on the main heat pipe circulation pipeline to obtain the pressure data of the air conditioner; Install an electromagnetic flowmeter and a vortex flowmeter on the working medium circulation pipeline to obtain the working medium circulation flow data; Install a power sensor at the equipment end served by the air conditioner to obtain the load power data.

3. The adaptive load regulation method of a heat pipe air conditioner according to claim 1, characterized in that The step of performing data preprocessing on the working state data and then fusing it to obtain the initial working state data, includes: Perform median filtering on the working state data to eliminate accidental interference and obtain the filtered state data; Calibrate the zero drift of the temperature and pressure sensors in the filtered state data through a reference source to obtain the calibrated state data; Set that the temperature exceeds the critical temperature of the working medium and the pressure exceeds the safety limit of the pipeline, and eliminate the invalid data in the calibrated state data to obtain the complete state data; Map the temperature, pressure, flow, and load power data in the complete state data to a unified space-time coordinate system. With the indoor target temperature as the core, the evaporation section temperature is associated to reflect the heat absorption capacity, the condensation section temperature is associated to reflect the heat dissipation efficiency, the pressure and flow data jointly characterize the working medium circulation state, and the load power quantifies the heat load intensity to obtain the initial working state data.

4. The adaptive load adjustment method of a heat pipe air conditioner according to claim 1, characterized in that, The step of calculating the real-time load coefficient based on the initial working state data and dividing the low-load condition, medium-load condition, and high-load condition according to the real-time load coefficient, includes: Establish a comprehensive load characteristic index according to the temperature difference between the hot and cold ends, load power, and working medium flow parameters in the initial working state data; Divide it into a low-load condition, a medium-load condition, and a high-load condition according to the comprehensive load characteristic index; The low-load condition is that the index value is in the low range, and the characteristics are that the indoor temperature is close to the target value, the temperature difference between the hot and cold ends is small, and the load power is low; The medium-load condition is that the index value is in the middle range, corresponding to the normal operation state, and stable temperature control needs to be maintained; The high-load condition is that the indoor temperature deviates significantly from the target value, the temperature difference between the hot and cold ends expands, and the load power surges.

5. The adaptive load adjustment method of a heat pipe air conditioner according to claim 1, characterized in that The step of dynamically adjusting the working medium flow rate and fan air speed through the fuzzy PID algorithm and self-learning mechanism for different conditions, includes: If it is determined to be an electric load condition, the working fluid circulation amount is reduced through an electric control valve to 40%-70% of the rated flow rate; the condensing section fans are started and stopped in stages, and 1-2 units are reserved to operate at low speed; If it is determined to be a medium load condition, with the cold and hot end temperature difference as the control variable, combined with the indoor temperature deviation, the PID controller parameters are dynamically adjusted through fuzzy logic, and the rotational speed of the condensing section fans and the working fluid flow rate are adjusted synchronously; The optimal adjustment parameter combination under different seasons, day and night, and load modes is identified using a timing algorithm. If the indoor temperature deviation still exceeds 1°C after 3 consecutive adjustments, switch to a compensation strategy based on the heat pipe physical model.

6. An adaptive load regulation system for a heat pipe air conditioner, characterized in that, The adaptive load adjustment system of the heat pipe air conditioner includes the following modules: A data acquisition module for collecting the working state data of the air conditioner through sensors, where the working state data at least includes temperature data, pressure data, working fluid circulation flow rate data, and load power data; A data processing module for preprocessing and fusing the working state data to obtain initial working state data; A state division module for calculating the real-time load coefficient based on the initial working state data and dividing the low load condition, medium load condition, and high load condition according to the real-time load coefficient; A load adjustment module for dynamically adjusting the working fluid flow rate and the fan wind speed through a fuzzy PID algorithm and a self-learning mechanism for different working conditions.

7. The adaptive load regulation system of a heat pipe air conditioner according to claim 6, characterized in that, The data acquisition module includes the following sub-modules: A temperature acquisition sub-module for arranging temperature sensors at the inlet of the evaporation section and the outlet of the condensing section to monitor the cold and hot end temperature difference in real time; arranging temperature sensors in the indoor target area to obtain the temperature data of the controlled object; A pressure acquisition sub-module for installing a pressure sensor in the main heat pipe circulation pipeline to obtain the pressure data of the air conditioner; A flow rate acquisition sub-module for installing an electromagnetic flowmeter and a vortex flowmeter in the working fluid circulation pipeline to obtain the working fluid circulation flow rate data; A power acquisition sub-module for installing a power sensor at the equipment end served by the air conditioner to obtain the load power data.

8. The adaptive load regulation system of a heat pipe air conditioner according to claim 6, characterized in that, The data processing module includes the following sub-modules: A filtering processing sub-module for performing median filtering processing on the working state data to eliminate accidental interference and obtain filtered state data; A state calibration sub-module for calibrating the zero drift of the temperature and pressure sensors in the filtered state data through a reference source to obtain calibrated state data; A data elimination sub-module for setting the temperature to exceed the critical temperature of the working fluid and the pressure to exceed the pipeline safety limit value, and eliminating the invalid data in the calibrated state data to obtain complete state data; A data obtaining sub-module for mapping the temperature, pressure, flow rate, and load power data in the complete state data to a unified space-time coordinate system, with the indoor target temperature as the core, associating the evaporation section temperature to reflect the heat absorption capacity, the condensing section temperature to reflect the heat dissipation efficiency, the pressure and flow rate data together to characterize the working fluid circulation state, and the load power to quantify the heat load intensity, to obtain the initial working state data.

Images