Heat pump unit AI energy-saving group control module and method based on IOE

Abstract

The invention relates to the technical field of energy-saving group control, and discloses a heat pump unit AI energy-saving group control module and method based on IOE, the module comprises an acquisition unit, a processing unit and a control unit; according to the invention, environment and operation parameters are periodically acquired through multiple sensors, and preprocessing is carried out by using a moving average algorithm and a median filtering algorithm, so that noise interference is effectively eliminated, and data accuracy is guaranteed; real-time power, heating efficiency and refrigerating efficiency can be accurately calculated, correlation characteristics and comprehensive indexes between the environment and operation parameters are deeply excavated, and the relation between the unit and the environment is clarified; an operation mode is accurately judged according to comparison of the comprehensive index and a threshold value, and on-demand operation of the unit is achieved; for high and low loads and a normal mode, the refrigerant flow, the power and the fan rotating speed are finely adjusted, output is enhanced in the high load, energy consumption is reduced in the low load, execution is carried out according to the standard in the normal mode, the energy utilization efficiency is remarkably improved, the operation cost is reduced, and the system stability is enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy-saving group control, and particularly relates to an AI energy-saving group control module and method for a heat pump unit based on IOE. BACKGROUND

[0002] A heat pump unit can transfer heat from a low-temperature heat source to a high-temperature heat source by consuming a small amount of electrical energy, thereby achieving the functions of heating or cooling. Compared with traditional heating and cooling equipment, the heat pump unit has a significant energy-saving advantage. However, in actual operation, the energy efficiency of the heat pump unit is affected by various factors, such as environmental parameters such as temperature, humidity, and wind speed, and operating parameters such as working current, voltage, refrigerant flow, and inlet and outlet water temperature of the unit itself. At present, most of the control methods of the heat pump unit still use a relatively traditional mode, such as fixed parameter setting or simple experience-based rules. This control method is difficult to adjust the operating parameters of the heat pump unit in real time and accurately according to complex and variable environmental conditions and actual load demand, resulting in the unit failing to achieve optimal energy efficiency under some operating conditions, causing energy waste.

[0003] In addition, in scenarios where heat pump units are applied on a large scale, such as commercial building groups and industrial parks, there is a lack of effective group control strategies to collaboratively manage the operation of multiple heat pump units. Independent operation of each unit cannot achieve optimal allocation of resources, which not only increases operating costs but also limits the overall energy-saving potential.

[0004] In recent years, the rapid development of artificial intelligence (AI) technology and Internet of Things (IOE) technology has provided new ideas and methods for solving the energy-saving control problem of heat pump units. By collecting and analyzing a large amount of environmental parameter and operating parameter data, and combining AI algorithms to achieve intelligent control of heat pump units, it is expected to improve the energy efficiency of heat pump units, reduce operating costs, and achieve the goal of energy saving and emission reduction. Therefore, researching an AI energy-saving group control method for heat pump units based on IOE has important practical significance and application value for improving the operating performance and energy utilization efficiency of heat pump units. SUMMARY

[0005] The present application aims to provide an AI energy-saving group control module and method for a heat pump unit based on IOE, which solves the technical problems proposed in the background art.

[0006] The object of the present application can be achieved by the following technical solutions: An AI energy-saving group control method for a heat pump unit based on IOE, comprising the following steps: Data acquisition: acquiring environmental parameters of the environment where the heat pump unit is located and operating parameters of the heat pump unit; Data processing: first, the environmental parameters and operating parameters are pre-processed, then the pre-processed environmental parameters and operating parameters are feature extracted, and the real-time power, heating efficiency and refrigeration efficiency of the heat pump unit are obtained, at the same time, the correlation features between the environmental parameters and the operating parameters of the heat pump unit are extracted, and the comprehensive correlation feature index obtained according to the correlation features is extracted; Intelligent control: the comprehensive correlation feature index is compared with the pre-set high load threshold and low load threshold respectively, the operating mode of the heat pump unit is determined according to the comparison result, and then parameter optimization adjustment is carried out according to the operating mode, which includes refrigerant flow adjustment and power adjustment.

[0007] As a further scheme of the application: the environmental parameters include the environmental temperature T env , the environmental humidity H env , and the environmental wind speed V wind of the heat pump unit collected by using temperature sensors, humidity sensors and wind speed sensors; wherein the temperature sensors, humidity sensors and wind speed sensors collect environmental temperature data every t1 minutes, and t1 is a preset value; The operating parameters include the working current L, the working voltage U, the refrigerant flow Q flow , the inlet and outlet water temperature T in and T out of the heat pump unit collected by using current sensors, voltage sensors, flow sensors and temperature sensors; wherein the collection interval of the current sensors, voltage sensors, flow sensors and temperature sensors is t2 minutes, and t2 is a preset value.

[0008] As a further scheme of the application: the data pre-processing method is as follows: Environmental parameter filtering processing: According to the sliding average filtering algorithm, the environmental temperature T env , the environmental humidity H env and the environmental wind speed V wind are filtered; Wherein, the sliding average filtering algorithm of the environmental temperature T env , the environmental humidity H env and the environmental wind speed V wind is consistent; The environmental temperature T env is selected, and the sliding average filtering algorithm formula is: ; In the formula, T env ` is the original data after filtering, i is the filtering window, i=1, 2, ……n, n is the number of environmental temperatures at different time stamps in the filtering window; Heat pump unit operating parameter filtering processing: According to the median filter algorithm, the working current L, working voltage U, and refrigerant flow Q of the heat pump unit are calculated. flow , Inlet and outlet water temperature T in and T out Perform filtering processing; Working current L, working voltage U, refrigerant flow Q flow , Inlet and outlet water temperature T in and T out The filtering process is performed in the same way as the median filtering algorithm; The working current L is selected, and the median filtering algorithm is as follows: based on the working current at a specified timestamp as the base point, the working current at each of the k timestamps before and after it is taken, and then the median of the working current at these 2k+1 timestamps is taken as the working current after filtering at this base point; As a further solution of the present invention: the feature extraction method is as follows: Real-time power extraction of heat pump units: By: P = U × L; Calculate the real-time power P of the heat pump unit; Where U and I are the operating voltage and current of the heat pump unit after filtering, and the unit of real-time power is watt; Extraction of heating / cooling efficiency of heat pump unit: In heating mode, by: ; Calculate the heating capacity Q of the heat pump unit heat ; Where c is the specific heat capacity of water, Ms is the mass flow rate of water, and Ms is calculated based on the refrigerant flow rate and the corresponding preset heat exchange relationship; Where, T in and T out is the inlet and outlet water temperature of the heat pump unit after filtering; pass: ; Calculate the heating efficiency γ of the heat pump unit in heating mode heat ; According to the calculation method of heating efficiency in heating mode, the cooling efficiency γ in cooling mode is determined cool ; Correlation feature extraction: Select the ambient temperature and heat pump unit power, obtain the maximum and minimum ambient temperatures within the preset observation period, and then calculate the absolute value of the difference between them as the ambient temperature change TB env , and extract the initial ambient temperature T0 env ; At the same time, the maximum and minimum real-time power values are obtained, and the absolute value of the difference between them is calculated as the power variation PB, and the initial power P0 is extracted; Then, the change rate correlation coefficient C1 of the ambient temperature and the heat pump unit power is calculated by: Similarly, the change rate correlation coefficients C2, C3 and C4 of the ambient temperature and the refrigeration efficiency, the heating efficiency and the refrigerant flow rate, respectively, are calculated; the change rate correlation coefficients C5, C6, C7 and C8 of the ambient humidity and the heating efficiency, the refrigeration efficiency, the real-time power and the refrigerant flow rate of the heat pump unit, respectively, are calculated; and the change rate correlation coefficients C9, C10, C11 and C12 of the ambient wind speed and the refrigerant flow rate, the real-time power, the refrigeration efficiency and the heating efficiency are calculated.

[0009] As a further scheme of the application, when CZ>CZ high , it indicates that the environment has a large load demand on the operation of the heat pump unit, and the current operation mode is adjusted to a high-load operation mode; When CZ low , it indicates that the environment has a small load demand on the operation of the heat pump unit, and the current operation mode is adjusted to a low-load operation mode; When CZ high ≥CZ≥CZ low , it indicates that the unit is in a normal state, and the current operation mode is adjusted to a normal mode; wherein CZ low and CZ high are the pre-set high-load threshold and low-load threshold, respectively.

[0010] As a further scheme of the application, the parameter optimization adjustment mode is as follows: Refrigerant flow rate adjustment: the refrigerant flow rate Q flow is adjusted according to the size of the comprehensive correlation characteristic index CZ; In the high-load mode, the adjusted refrigerant flow rate Q flow ′ is calculated by the formula: Q flow ′=Q flow ×(1+α1×CZ); Wherein, α1 is a pre-set refrigerant flow rate adjustment coefficient; In the low-load operation mode, the adjusted refrigerant flow rate Q flow ′ is calculated by the formula: Q flow ′=Q flow ×(1−α2×|CZ|); Wherein, α2 is a pre-set refrigerant flow rate reduction coefficient; In the normal mode, the standard refrigerant flow rate is executed according to the pre-set standard refrigerant flow rate; Power adjustment:​ In the high load mode, the adjusted power P' is calculated by the formula: P'=P x (1+α3xCZ); Wherein, α3 is a pre-set power increase coefficient; In the low load mode, the adjusted power P' is calculated by the formula: P'=P x (1-α4x|CZ|); Wherein α4 is a pre-set power reduction coefficient; In the normal mode: then according to the pre-set standard power is executed; Fan speed adjustment: In the refrigeration mode, when it is determined as the high load mode, the fan speed adjustment coefficient r is calculated by: r=1+α5xCZ, and then the current fan speed is multiplied by r to obtain the adjusted fan speed; Wherein, α5 is a pre-set fan speed adjustment coefficient; In the refrigeration mode, when it is determined as the low load mode, the fan speed adjustment coefficient r is calculated by: r=1-α6x|CZ|, and then the current fan speed is multiplied by r to obtain the adjusted fan speed; Wherein, α6 is a pre-set fan speed reduction coefficient; In the refrigeration mode, when it is determined as the normal mode, the pre-set standard fan speed is executed.

[0011] An AI energy-saving group control module of a heat pump unit based on IOE, which is used for executing an AI energy-saving group control method of a heat pump unit based on IOE, and the module comprises: A collection unit, which is used for collecting environmental parameters of an environment where the heat pump unit is located and operation parameters of the heat pump unit; A processing unit, which is used for performing data preprocessing on the collection results of the collection unit, then performing feature extraction, and obtaining real-time power, heating efficiency and refrigeration efficiency of the heat pump unit, meanwhile extracting associated features between the environmental parameters and the operation parameters of the heat pump unit and a comprehensive associated feature index obtained according to the associated features; A control unit, which is used for comparing the comprehensive associated feature index with pre-set high load threshold value and low load threshold value respectively, determining the operation mode of the heat pump unit according to the comparison results, and then performing parameter optimization adjustment according to the operation mode.

[0012] The beneficial effects of the present application are: Comprehensive data collection and processing: by using various sensors, the environmental parameters and operation parameters of the heat pump unit are collected at specific time intervals, and the environmental parameters are preprocessed by using the sliding average filtering algorithm and the operation parameters are preprocessed by using the median filtering algorithm, so that the data noise interference is effectively reduced and the data quality is improved, thereby providing accurate and reliable data basis for subsequent analysis.

[0013] Precise feature extraction and analysis: After preprocessing the data, not only can the real-time power, heating efficiency and refrigeration efficiency of the heat pump unit be accurately calculated, but also various correlation features between environmental parameters and operating parameters can be extracted, and a comprehensive correlation feature index can be obtained, so as to deeply understand the relationship between the heat pump unit operation and environmental factors, and provide a scientific basis for intelligent control.

[0014] Intelligent operation mode judgment and adjustment: According to the comparison result of the comprehensive correlation feature index and the pre-set high load threshold and low load threshold, the operation mode of the heat pump unit can be accurately judged, and the operation mode can be adjusted in time, so that the heat pump unit can reasonably operate according to the environmental load demand, improve the energy utilization efficiency, and reduce the energy consumption.

[0015] Targeted parameter optimization adjustment: For different operation modes, the refrigerant flow, power and fan speed are optimized and adjusted. In the high load mode, the refrigerant flow, power and fan speed are appropriately increased to meet the high load demand; in the low load mode, the refrigerant flow, power and fan speed are reduced to avoid energy waste; in the normal mode, the unit is operated according to the standard parameters to ensure stable and efficient operation of the unit. This fine parameter adjustment strategy further improves the energy saving effect and operation performance of the heat pump unit.

[0016] Modular design improves system reliability: The modular design of the acquisition unit, processing unit and control unit is adopted, the units have clear division of labor and mutual cooperation, the system structure is clear, easy to maintain and expand, and the reliability and stability of the whole group control system are improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] The application will be further described below with reference to the accompanying drawings.

[0018] Figure 1 is a flow diagram of an AI energy-saving group control method for a heat pump unit based on IOE.

[0019] Figure 2 is a system block diagram of an AI energy-saving group control module for a heat pump unit based on IOE. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0021] Embodiment one Please refer toFigure 1 and Figure 2 As shown, the present invention is an AI energy-saving group control method for heat pump units based on IOE, comprising the following steps: Step 1: Data Collection: Step 1.1: Environmental parameter collection: Step 1.1.1: Use the temperature sensor to collect the ambient temperature T of the environment where the heat pump unit is located env , the unit is Celsius; The temperature sensor collects ambient temperature data every t1 minutes. In this example, t1 = 5 minutes. Step 1.1.2: Obtain the ambient humidity H through the humidity sensor env , the unit is percentage; Among them, the humidity sensor also collects environmental humidity data every t1 minutes; Step 1.1.3: Use the wind speed sensor to collect the ambient wind speed V wind , in meters per second; The wind speed sensor collection interval is also t1 minutes; Step 1.2: Collecting operating parameters of heat pump unit: Step 1.2.1: Use the current sensor to collect the operating current L of the heat pump unit in amperes; The current sensor's collection interval is t2 minutes. In this example, t2 = 2 minutes. Step 1.2.2: Use a voltage sensor to collect the operating voltage U of the heat pump unit in volts; Among them, the collection interval of the voltage sensor is t2 minutes; Step 1.2.3: Use the flow sensor to collect the refrigerant flow Q of the heat pump unit flow , the unit is cubic meters per hour; Among them, the flow sensor collection interval is t2 minutes; Step 1.2.4: Use the temperature sensor to collect the inlet and outlet water temperatures T of the heat pump unit. in and T out , the unit is Celsius; Among them, the temperature sensor collection frequency is also t2 minutes; In this embodiment, the sensors used for the ambient temperature and the inlet and outlet water temperatures are different temperature sensors; Step 2: Data processing: The environmental parameters and operating parameters are used for feature extraction. The specific method is as follows: Step 2.2.1: Real-time power extraction of heat pump unit: By: P = U × L; Calculate the real-time power P of the heat pump unit; In the formula, U and I are the working voltage and working current of the heat pump unit after filtering processing, and the unit of real-time power is watt; Step 2.2.2, heat pump unit heating / cooling efficiency extraction: In the heating mode, by: ; The heating capacity Q of the heat pump unit is calculated heat ; In the formula, c is the specific heat capacity of water, and Ms is the mass flow of water, and Ms is converted according to the refrigerant flow and the corresponding preset heat exchange relationship; In the formula, T in and T out are the inlet and outlet water temperatures of the heat pump unit after filtering processing; By: ; The heating efficiency γ of the heat pump unit in the heating mode is calculated heat ; According to the calculation method of the heating efficiency in the heating mode, the cooling efficiency γ in the cooling mode is determined cool ; Step 2.2.3, correlation characteristics between environmental parameters and heat pump unit operating parameters: Step 2.2.3.1: In the pre-set observation period, the maximum and minimum values of the environmental temperature are obtained, and the absolute value of the difference between them is calculated as the environmental temperature variation TB env , and the initial environmental temperature T0 env is extracted; At the same time, the maximum and minimum values of the real-time power are obtained, and the absolute value of the difference between them is calculated as the power variation PB, and the initial power P0 is extracted; Then by: , the change rate correlation coefficient C1 of the environmental temperature and the heat pump unit power is calculated; By analogy, the correlation characteristics of the environmental temperature with the cooling efficiency, the heating efficiency and the refrigerant flow, i.e. the change rate correlation coefficients C2, C3 and C4 of the environmental temperature with the cooling efficiency, the heating efficiency and the refrigerant flow, are calculated; Step 2.2.3.2: In the pre-set observation period, the maximum and minimum values of the environmental humidity are obtained, and the absolute value of the difference between them is calculated as the environmental humidity variation HB env , and the initial environmental humidity H0 env is extracted; At the same time, the maximum and minimum values of the heating efficiency are obtained, and the absolute value of the difference between them is calculated as the heating efficiency variation γB heat , and the initial heating efficiency γ0 is extracted;heat ; Then, the correlation coefficient C5 between the change rate of the ambient humidity and the heating efficiency of the heat pump unit is calculated by: According to the method of obtaining the correlation coefficient between the change rate of the ambient humidity and the heating efficiency of the heat pump unit, the correlation coefficient C6 between the change rate of the ambient humidity and the refrigeration efficiency of the heat pump unit is determined; Similarly, the correlation characteristics of the ambient humidity with the real-time power and the refrigerant flow rate are calculated, i.e., the correlation coefficients C7 and C8 between the change rate of the ambient humidity and the real-time power and the refrigerant flow rate, respectively; Step 2.2.3.3, the maximum and minimum ambient wind speeds are obtained within a predetermined observation period, and the absolute value of the difference between them is calculated as the ambient wind speed variation VB wind Meanwhile, the initial ambient wind speed V0 is extracted wind ; Meanwhile, the maximum and minimum refrigerant flow rates are obtained, and the absolute value of the difference between them is calculated as the refrigerant flow rate variation QB flow Meanwhile, the initial refrigerant flow rate Q0 is extracted flow ; Then, the correlation coefficient C9 between the change rate of the ambient wind speed and the refrigerant flow rate is calculated by: Similarly, the correlation characteristics of the ambient wind speed with the real-time power, the refrigeration efficiency, and the heating efficiency are calculated, i.e., the correlation coefficients C10, C11, and C12 between the change rate of the ambient wind speed and the real-time power, the refrigeration efficiency, and the heating efficiency, respectively; Step 2.2.4, comprehensive correlation characteristic index calculation: According to the change rate correlation coefficients C1, C2, …, C12 between the environmental parameters and the operating parameters of the heat pump unit, the comprehensive correlation characteristic index CZ is calculated; The calculation method of the comprehensive correlation characteristic index is as follows: ; In the formula, Cg is the change rate correlation coefficient between different environmental parameters and different operating parameters of the heat pump unit, βg is the correlation weight coefficient preset according to the relationship between different environmental parameters and different operating parameters of the heat pump unit, g = 1, 2, …, 12, and ; Third step, intelligent control: Step 3.1, running mode decision: The comprehensive correlation characteristic index CZ is compared with the pre-set high load threshold CZ high and the low load threshold CZ low : When CZ > CZ high ​​When , it indicates that the environment has generated a large load demand on the operation of the heat pump unit, and the current operation mode is adjusted to the high-load operation mode; When CZ<CZ low When , it means that the environment has a small demand on the operation load of the heat pump unit, and the current operation mode is adjusted to the low-load operation mode; When CZ high ≥CZ≥CZ low When , it indicates that the unit is in normal state, and the current operation mode is adjusted to normal mode; Step 3.2, parameter optimization and adjustment: Step 3.2.1, refrigerant flow adjustment: Adjust the refrigerant flow rate Q according to the size of the comprehensive correlation characteristic index CZ flow ; In high load mode, the formula: Q flow ′=Q flow × (1 + α1 × CZ), calculate the adjusted refrigerant flow Q flow '; Wherein, α1 is a preset refrigerant flow adjustment coefficient, which is determined based on experimental data. In this embodiment, α1=0.1; In low load operation mode, the formula: Q flow ′=Q flow ×(1−α2×|CZ|), calculate the adjusted refrigerant flow Q flow '; Wherein, α2 is a preset refrigerant flow reduction coefficient, which is determined based on experimental data. In this embodiment, α2=0.1; In normal mode, it is executed according to the pre-set standard refrigerant flow rate; Step 3.2.2, power adjustment: In high load mode, the adjusted power P′ is calculated by the formula: P′=P×(1+α3×CZ); Wherein, α3 is a preset power increase coefficient. In this embodiment, α3=0.05; In low-load operation mode, the adjusted power P′ is calculated using the formula: P′=P×(1−α4×|CZ|); Wherein, α4 ​​is a preset power reduction coefficient. In this embodiment, α4=0.05; In normal mode: it is executed according to the pre-set standard power; Step 3.2.3, fan speed adjustment: In the refrigeration mode, when it is determined that the high load mode, it is explained that the environmental condition can need better heat dissipation, the fan rotating speed is improved, and then the fan rotating speed adjustment coefficient r is calculated through: r = 1 + alpha5 * CZ, and then the current fan rotating speed is multiplied by r to obtain the adjusted fan rotating speed; Wherein, alpha5 is a pre-set fan rotating speed adjustment coefficient, in this embodiment, alpha5 = 0.08; In the refrigeration mode, when it is determined that the low load mode, the fan rotating speed adjustment coefficient r is calculated through: r = 1 - alpha6 * |CZ|, and then the current fan rotating speed is multiplied by r to obtain the adjusted fan rotating speed; Wherein, alpha6 is a pre-set fan rotating speed reduction coefficient, in this embodiment, alpha6 = 0.08; In the refrigeration mode, when it is determined that the normal mode, the pre-set standard fan rotating speed is executed.

[0022] Embodiment one collects environmental parameters (environmental temperature, humidity, wind speed) and heat pump unit operating parameters (operating current, voltage, refrigerant flow, inlet and outlet water temperature, etc.) comprehensively, and carries out in-depth data processing, extracts real-time power, heating / cooling efficiency and other key indicators, and the correlation characteristics between environmental parameters and operating parameters, and calculates the comprehensive correlation characteristic index. Based on the index, intelligent control can accurately determine the operating mode (high load, low load, normal mode) of the heat pump unit, and optimizes and adjusts the refrigerant flow, power and fan rotating speed accordingly. This way can make the heat pump unit dynamically adjust the operating state according to the environmental change and actual load demand, effectively improve the energy utilization efficiency, realize energy-saving operation, at the same time ensure the stable and efficient work of the unit under different working conditions, meet the use demand.

[0023] Embodiment two As embodiment two of the present application, compared with embodiment one, the technical scheme of the present embodiment is only different from that of embodiment one in that in the present embodiment, the data processing correction also carries out data preprocessing on the environmental parameters and operating parameters: Step 2.1.1, environmental parameter filtering processing: According to the sliding average filtering algorithm, the environmental temperature T env , the environmental humidity H env , and the environmental wind speed V wind are filtered to remove noise interference; Wherein, the sliding average filtering algorithm of the environmental temperature T env , the environmental humidity H env , and the environmental wind speed V wind is consistent; Taking the environmental temperature T env as an example, the sliding average filtering algorithm formula is: ; In the formula, T env is the original data after filtering processing, i is the filter window, i = 1, 2, … n, n is the number of environmental temperature under different time stamps in the filter window; Step 2.1.2, filter processing of heat pump unit operating parameters: According to the median filter algorithm, the working current L, working voltage U, refrigerant flow Q flow , inlet and outlet water temperature T in and T out of the heat pump unit are filtered and processed to remove noise interference; The working current L, working voltage U, refrigerant flow Q flow , inlet and outlet water temperature T in and T out are filtered and processed by the median filter algorithm in the same way; Taking the working current L as an example, the median filter algorithm is as follows: according to the working current at the specified time stamp as the base point, taking the working current at each of the k time stamps before and after it, and then taking the median value of the working current at the 2k+1 time stamps as the working current after filtering processing of the base point; In this embodiment, k = 2; Example two is based on example one, and adds a data preprocessing link of environmental parameters and operating parameters. The sliding average filter algorithm is used for environmental parameters, and the median filter algorithm is used for heat pump unit operating parameters, which effectively removes the noise interference in the data. The data after filtering processing is more accurate and stable, which provides a more reliable basis for subsequent data processing and feature extraction. This makes the operation mode decision and parameter adjustment based on data more accurate, avoids misjudgment and unreasonable operation parameter adjustment caused by data noise, and further improves the stability and energy saving effect of the heat pump unit operation, and improves the reliability of the system and the scientificity of data processing.

[0024] Example three As example three of the present application, compared with example one and example two, the technical scheme of the present embodiment is to combine the schemes of example one and example two.

[0025] Embodiment three combines the schemes of embodiment one and embodiment two, having the advantages of both. On the one hand, it can comprehensively collect environmental and operating parameters and deeply analyze the correlation between parameters to calculate a comprehensive correlation characteristic index to realize intelligent operation mode decision and parameter optimization adjustment. On the other hand, it filters environmental and operating parameters through data preprocessing to ensure the accuracy and reliability of data. This combined approach enables the heat pump unit not only to dynamically adjust the operating state according to environmental and load requirements to achieve energy saving, but also to perform more accurate control based on high-quality data, effectively improving the overall operating performance, energy utilization efficiency and working stability of the heat pump unit, and bringing better user experience and economic benefits to users.

[0026] An IOE-based AI energy-saving group control module for a heat pump unit, the module being used to implement an IOE-based AI energy-saving group control method for a heat pump unit, the module comprising: a collection unit configured to collect environmental parameters of an environment in which the heat pump unit is located and operating parameters of the heat pump unit; a processing unit configured to perform data preprocessing on the collection results of the collection unit, then perform feature extraction, and obtain real-time power, heating efficiency and cooling efficiency of the heat pump unit, as well as correlation characteristics between the environmental parameters and the operating parameters of the heat pump unit and a comprehensive correlation characteristic index derived from the correlation characteristics; a control unit configured to compare the comprehensive correlation characteristic index with a pre-set high-load threshold value and a pre-set low-load threshold value respectively, determine an operating mode of the heat pump unit according to the comparison results, and then perform parameter optimization adjustment according to the operating mode.

[0027] The above formulas are all dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of collected data to obtain a formula for the most recent real situation. The pre-set parameters and threshold values in the formula are set by a person skilled in the art according to the actual situation.

[0028] The above description is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An IOE-based heat pump unit AI energy-saving group control method, characterized in that, Comprising the following steps: Data acquisition: collect the environmental parameters of the environment where the heat pump unit is located and the operating parameters of the heat pump unit; Data processing: first, the environmental parameters and operating parameters are preprocessed, then the preprocessed environmental parameters and operating parameters are feature extracted, and the real-time power, heating efficiency and cooling efficiency of the heat pump unit are obtained, and the correlation features between the environmental parameters and the operating parameters of the heat pump unit are extracted, and the comprehensive correlation feature index obtained according to the correlation features; Intelligent control: compare the comprehensive correlation feature index with the pre-set high load threshold and low load threshold respectively, determine the operating mode of the heat pump unit according to the comparison result, and then optimize and adjust the parameters according to the operating mode, which includes refrigerant flow adjustment and power adjustment. 2.The IOE-based heat pump unit AI energy-saving group control method of claim 1, wherein, The environmental parameters include an environmental temperature T of an environment where the heat pump unit is located, which is collected by using a temperature sensor, a humidity sensor, and a wind speed sensor env , an environmental humidity H env , and an environmental wind speed V wind ; The operating parameters include working current L, working voltage U, refrigerant flow Q of the heat pump unit collected by the current sensor, the voltage sensor, the flow sensor, inlet and outlet water temperature T flow , T in and T out . 3.The IOE-based group control method for AI energy-saving of a heat pump unit according to claim 2, wherein, The data preprocessing method is as follows: The environmental temperature T env , the environmental humidity H env , and the environmental wind speed V wind are filtered according to a sliding average filtering algorithm. Wherein, the ambient temperature T env , the ambient humidity H env , the ambient wind speed V wind The moving average filtering algorithm is consistent; Selecting the ambient temperature T env The formula of the sliding average filter algorithm is: In the formula, T env ` is the original data after filtering processing, i is the filter window, i = 1, 2, … n, n is the number of environmental temperatures under different time stamps in the filter window; According to the median filter algorithm, the working current L, working voltage U, and refrigerant flow Q of the heat pump unit are calculated. flow , Inlet and outlet water temperature T in and T out Perform filtering processing; Working current L, working voltage U, refrigerant flow rate Q flow , inlet and outlet water temperature T in and T out The filtering processing manner by the median filtering algorithm is consistent; Select the working current L, the median filtering algorithm is: according to the working current on the specified timestamp as the base point, take the working current on each of the k time stamps before and after it, and then take the median value of the working current on the 2k+1 time stamps as the working current after filtering processing of the base point.

4. The IOE-based group control method for AI energy-saving of a heat pump unit according to claim 3, characterized in that, The extraction method of real-time power in feature extraction is as follows: Through: P=U×L; Calculate the real-time power P of the heat pump unit; In the formula, U and I are the working voltage and working current of the heat pump unit after filtering processing, and the unit of real-time power is watt.

5. The IOE-based group control method for AI energy-saving of a heat pump unit according to claim 4, characterized in that, The extraction method of heating / cooling efficiency in feature extraction is as follows: In heating mode, by: Q heat = c x M s x (T out - T in ); The heating capacity Q of the heat pump unit is calculated heat ; In the formula, c is the specific heat capacity of water, Ms is the mass flow of water, and Ms is converted according to the refrigerant flow and the corresponding pre-set heat exchange relationship; In the formula, T in and T out are the inlet and outlet water temperatures of the heat pump unit after filtering processing; By: The heating efficiency γ of the heat pump unit in the heating mode is calculated heat ; According to the calculation method of the heating efficiency in the heating mode, the refrigeration efficiency γ in the refrigeration mode is determined cool .

6. The IOE-based group control method for AI energy-saving of a heat pump unit according to claim 5, characterized in that, The extraction method of correlation features in feature extraction is as follows: Selecting the ambient temperature and the heat pump unit power, obtaining the maximum and minimum ambient temperature in the preset observation period, and then calculating the absolute value of the difference between them as the ambient temperature variation TB env At the same time, the initial ambient temperature T0 is extracted env ; At the same time, the maximum and minimum real-time power values are obtained, and the absolute value of the difference between them is calculated as the power variation PB, and the initial power P0 is extracted; Then, by: calculating the correlation coefficient C1 between the ambient temperature and the rate of change of the heat pump unit power; In this way, the change rate correlation coefficients C2, C3 and C4 of the environmental temperature with the cooling efficiency, heating efficiency and refrigerant flow are calculated; the change rate correlation coefficients C5, C6, C7 and C8 of the environmental humidity with the heating efficiency, cooling efficiency, real-time power and refrigerant flow of the heat pump unit are calculated; the change rate correlation coefficients C9, C10, C11 and C12 of the environmental wind speed with the refrigerant flow, real-time power, cooling efficiency and heating efficiency are calculated.

7. The IOE-based group control method for AI energy-saving of a heat pump unit according to claim 6, characterized in that, When CZ>CZ high When CZ>CZ high When CZ>CZ high When CZ>CZ high When CZ>CZ high When CZ>CZ high When CZ>CZ high When CZ>CZ high When CZ>CZ high When CZ>CZ <000003 When CZ < CZ low When CZ < CZ low When CZ < CZ low When CZ < CZ low When CZ < CZ low When CZ < CZ low When CZ < CZ low When CZ < CZ low When CZ < CZ low When CZ When CZ high ≥ CZ ≥ CZ low If so, it indicates that the unit is in normal state, and the current operation mode is adjusted to normal mode. wherein CZ low and CZ high are a pre-set high load threshold and a low load threshold, respectively. 8.The IOE-based group control method for AI energy saving of a heat pump unit according to claim 7, wherein, The refrigerant flow rate adjustment method is as follows: adjusting the refrigerant flow rate Q according to the size of the comprehensive correlation characteristic index CZ flow ; In the high load mode, the adjusted refrigerant flow rate Q flow ′ is calculated by the formula: Q flow ′ = Q flow × (1 + α1×CZ) Wherein, α1 is a pre-set refrigerant flow adjustment coefficient; In the low load operation mode, the adjusted refrigerant flow rate Q flow ′ is calculated by the formula: Q flow flow ′ = Q flow × (1 - a2 x |CZ|) Wherein, α2 is a pre-set refrigerant flow reduction coefficient; In normal mode, the standard refrigerant flow is executed according to the pre-set standard refrigerant flow. 9.The IOE-based group control method for AI energy-saving of a heat pump unit according to claim 7, wherein, The power adjustment method is as follows: In high load mode, the adjusted power P' is calculated by the formula: P'=P×(1+α3×CZ); wherein, α3 is a pre-set power increase coefficient; In low load mode, the adjusted power P' is calculated by the formula: P'=P×(1-α4×|CZ|); wherein, α4 is a pre-set power reduction coefficient; In normal mode, the standard power is executed according to the pre-set standard power.

10. An IOE-based AI energy-saving group control module for heat pump units, which is used to perform an IOE-based AI energy-saving group control method for heat pump units according to any one of claims 1-9, characterized in that, The module comprises: The acquisition unit is used for collecting the environmental parameters of the environment where the heat pump unit is located and the operating parameters of the heat pump unit; The processing unit is used for data preprocessing of the acquisition result of the acquisition unit, then feature extraction is carried out, real-time power, heating efficiency and refrigeration efficiency of the heat pump unit are obtained, meanwhile, the associated features between the environmental parameters and the operation parameters of the heat pump unit are extracted, and the comprehensive associated feature index obtained according to the associated features is obtained; The control unit is used for comparing the comprehensive associated feature index with the pre-set high load threshold value and low load threshold value respectively, determining the operation mode of the heat pump unit according to the comparison result, and then carrying out parameter optimization adjustment according to the operation mode.

Images