CN-122020602-A - Intelligent AI (advanced technology attachment) evaluation method and system for supply effect of central air conditioner

CN122020602ACN 122020602 ACN122020602 ACN 122020602ACN-122020602-A

Abstract

The invention relates to the technical field of air conditioning system use monitoring, in particular to an intelligent evaluation method and system for a central air conditioner supply effect AI, wherein the indoor current air conditioner operation data and target area environment data are collected in real time, the air conditioner operation data comprise an operation gear, operation time and set temperature, and the environment data comprise indoor target area room temperature; the preprocessed air conditioner operation data and the preprocessed environment data are input into an AI intelligent evaluation model, the AI intelligent evaluation model is utilized to evaluate the air conditioner supply effect of the current indoor area, and the AI intelligent evaluation model is constructed by weighting and combining an air conditioner temperature change effect function, an air conditioner gear effect function and an air conditioner temperature effect function, and is trained by utilizing marked air conditioner effect observation data samples. The invention can prejudge the next operation of the air conditioner, is convenient for an operator to maintain and manage, is suitable for analyzing the operation effect in various air conditioner use scenes, and can be applied to the aspects of air conditioner controllers, air conditioner intelligent control systems and the like.

Inventors

YANG DONG
CHEN CHUANWEI
LIU MING
ZHA ZHENHUAI
CHEN YUJUN
LI YUQIN

Assignees

郑州春泉节能股份有限公司

Dates

Publication Date: 20260512
Application Date: 20251230

Claims (10)

1. An intelligent evaluation method for the supply effect AI of a central air conditioner is characterized by comprising the following steps: collecting indoor current air conditioner operation data and target area environment data in real time, wherein the air conditioner operation data comprise an operation gear, operation time and set temperature, and the environment data comprise indoor target area room temperature; The preprocessed air conditioner operation data and the preprocessed environment data are input into an AI intelligent evaluation model, the AI intelligent evaluation model is utilized to evaluate the air conditioner supply effect of the current indoor area, and the AI intelligent evaluation model is constructed by weighting and combining an air conditioner temperature change effect function, an air conditioner gear effect function and an air conditioner temperature effect function, and is trained by utilizing marked air conditioner effect observation data samples.
2. The intelligent evaluation method of the air conditioner supply effect AI according to claim 1, wherein the intelligent evaluation model is expressed as η=a×f1 (δt, T) +b×f2 (δt2, D, T) +c×f3 (δt3, T0, T1, T), wherein a, b, c are weight coefficients, f1 (δt, T) is an air conditioner temperature change effect function, f2 (δt2, D, T) is an air conditioner shift effect function, f3 (δt3, T0, T1, T) is an air conditioner temperature effect function, δt is a unit time room temperature change amount, T is an air conditioner operation time, δt2 is an air conditioner shift start operation time duty ratio during air conditioner operation, D is an air conditioner operation shift position, δt3 is a time duty ratio during air conditioner operation in which an absolute value of a difference between room temperature T0 and an air conditioner set temperature T1 is smaller than a temperature difference threshold.
3. The intelligent assessment method for the air conditioner supply effect AI according to claim 1, wherein the air conditioner supply effect of the current indoor area is assessed by using an AI intelligent assessment model, further comprising: If the indoor multiple areas are respectively provided with temperature sensors for collecting the room temperature of the corresponding target area, the air conditioner temperature change effect function adopts weighted arithmetic average of the air conditioner temperature change effect functions of the areas, and the air conditioner temperature effect function adopts weighted arithmetic average of the air conditioner temperature effect functions of the areas; If the air conditioner has a plurality of gears to operate, the air conditioner gear effect function adopts the ratio of the operation time weighted arithmetic sum of each air conditioner gear to the time length t.
4. The intelligent evaluation method of the supply effect AI of the central air conditioner according to claim 1, wherein the intelligent evaluation AI model adopts a linear regression model to realize comprehensive evaluation of the supply effect of the air conditioner by using an air conditioner temperature change effect function, an air conditioner gear effect function and an air conditioner temperature effect function.
5. The intelligent assessment method for the supply effect AI of a central air conditioner according to claim 4, wherein the training process of the intelligent assessment model comprises the following steps: collecting a plurality of groups of air conditioner operation effect historical observation data as samples, and manually marking the air conditioner operation effect corresponding to each group of observation data, wherein the historical observation data comprises historical time air conditioner operation data and corresponding environment data; Preprocessing sample data, dividing the preprocessed sample data into a training set and a testing set according to a preset proportion, wherein the preprocessing comprises missing value processing and data standardization processing; And training the AI intelligent evaluation model by using a training set, and evaluating the trained AI intelligent evaluation model by using a testing set to obtain the AI intelligent evaluation model which accords with expectations and is used for application deployment on a central air-conditioning control platform.
6. The intelligent evaluation method of the supply effect AI of the central air conditioner according to claim 1, wherein the intelligent evaluation model adopts a random forest algorithm to realize comprehensive evaluation of the supply effect of the air conditioner by using an air conditioner temperature change effect function, an air conditioner gear effect function and an air conditioner temperature effect function.
7. The intelligent assessment method for the supply effect AI of the central air conditioner according to claim 6, wherein the training process of the intelligent assessment model comprises the steps of: collecting a plurality of groups of historical observation data features of the air conditioner operation effect as samples, and manually marking the air conditioner operation effect corresponding to each group of observation data, wherein the historical observation data features comprise historical time air conditioner operation data features and corresponding environment data features; Preprocessing sample data, wherein the preprocessing comprises missing value processing and data standardization processing; Setting the number of trees, the depth of each tree and the number of features used by each node in the tree; extracting training data from the preprocessed sample data in a put-back way to construct a training subset of each tree; and for each training subset, selecting the optimal feature by utilizing the splitting standard of each feature in the feature subset to split to form sub-nodes, constructing corresponding decision trees by recursively generating each sub-node until the depth of the tree is met, repeatedly generating a specified number of decision trees to form a random forest, and obtaining the final prediction output of the random forest by averaging the prediction result of each decision tree.
8. An intelligent evaluation method for the supply effect AI of a central air conditioner is characterized by comprising a data acquisition module and an effect evaluation module, wherein, The data acquisition module is used for acquiring indoor current air conditioner operation data and target area environment data in real time, wherein the air conditioner operation data comprise operation gears, operation time and set temperature, and the environment data comprise indoor target area room temperature; The effect evaluation module is used for inputting the preprocessed air conditioner operation data and the preprocessed environment data into the AI intelligent evaluation model, evaluating the air conditioner supply effect of the current indoor area by utilizing the AI intelligent evaluation model, wherein the AI intelligent evaluation model is constructed by weighting and combining an air conditioner temperature change effect function, an air conditioner gear effect function and an air conditioner temperature effect function, and is obtained by training an marked air conditioner effect observation data sample.
9. An electronic device, comprising: At least one processor, and a memory coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor to implement the method of any one of claims 1-7.
10. A computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, which, when executed, is capable of implementing the method according to any one of claims 1-7.

Description

Intelligent AI (advanced technology attachment) evaluation method and system for supply effect of central air conditioner Technical Field The invention relates to the technical field of air conditioning system use monitoring, in particular to an intelligent evaluation method and system for a central air conditioning supply effect AI. Background The central air conditioning system mainly comprises a refrigeration compressor, a refrigerant circulating system, a fan coil, a cooling tower and other devices which are cooperated to realize the adjustment of indoor temperature. With the continuous appearance of new economy, new industry, new demand and the like, the application scene of the central air conditioner is also continuously expanded, the breadth of the application industry is continuously expanded, for example, the 5G foundation, inter-city high-speed railways, urban rail transit, large data centers and other plates covered by the 'new foundation' industry belong to the important service field of the central air conditioner. Through centralized monitoring platform, the user can carry out centralized monitoring and management to the split air conditioner of a plurality of rooms, can remote control all split air conditioner indoor fan gears, temperature, air conditioning mode etc. also can realize the intelligent energy-saving control to the air conditioner, like adjusting wind speed, adjusting mode, switch air conditioner, adjusting room temperature. Aiming at the characteristics of centralized supply and decentralized use of the central air conditioner, how to evaluate the use effect of the air conditioner, so that the user is comfortable and satisfied, the user always stays in the feedback stage of the user, and the operator is in the passive processing state. Therefore, there is a need for an air conditioning effect evaluation means capable of assisting the air conditioning management of operators by automatic analysis, particularly for buildings with management platforms such as BA automatic control and EMS intelligent energy management, and the like, and the analysis result of the air conditioning effect can provide beneficial support for automatic control and energy saving management. Disclosure of Invention Aiming at the problem of evaluation of the supply effect of the central air conditioner at the current stage, the invention provides an intelligent evaluation method and an intelligent evaluation system for the supply effect AI of the central air conditioner. According to the design scheme provided by the invention, on one hand, an intelligent evaluation method for the supply effect AI of the central air conditioner is provided, which comprises the following steps: collecting indoor current air conditioner operation data and target area environment data in real time, wherein the air conditioner operation data comprise an operation gear, operation time and set temperature, and the environment data comprise indoor target area room temperature; The preprocessed air conditioner operation data and the preprocessed environment data are input into an AI intelligent evaluation model, the AI intelligent evaluation model is utilized to evaluate the air conditioner supply effect of the current indoor area, and the AI intelligent evaluation model is constructed by weighting and combining an air conditioner temperature change effect function, an air conditioner gear effect function and an air conditioner temperature effect function, and is trained by utilizing marked air conditioner effect observation data samples. As the intelligent evaluation method for the supply effect AI of the central air conditioner, the intelligent evaluation model of the invention is further expressed as eta=a×f1 (δt, T) +b×f2 (δt2, D, T) +c×f3 (δt3, T0, T1, T), wherein a, b, c are weight coefficients, f1 (δt, T) is an air conditioner temperature change effect function, f2 (δt2, D, T) is an air conditioner gear effect function, f3 (δt3, T0, T1, T) is an air conditioner temperature effect function, δt is a unit time room temperature change amount, T is an air conditioner operation time, δt2 is an air conditioner operation period air conditioner gear starting operation time duty ratio, D is an air conditioner operation gear, δt3 is a time duty ratio that the absolute value of the difference between the room temperature T0 and the air conditioner setting temperature T1 is smaller than a temperature difference threshold. As the intelligent AI evaluation method for the supply effect of the central air conditioner, the intelligent AI evaluation model further adopts a linear regression model to realize comprehensive evaluation of the supply effect of the air conditioner by using the air conditioner temperature change effect function, the air conditioner gear effect function and the air conditioner temperature effect function. As the intelligent AI evaluation method for the supply effect of the central air conditioner, the training process