Clean air conditioning performance prediction method and system based on physical and data hybrid driving technology

Abstract

The present invention relates to the technical field of clean air conditioner performance monitoring, and is a clean air conditioner performance prediction method and system of physical and data hybrid driving technology, comprising: collecting real-time working data and environmental status data of the clean air conditioner; establishing a multimodal physical data analysis model to obtain a real-time performance index of the clean air conditioner; establishing a data-driven model to dynamically predict various working performances of the clean air conditioner; establishing a physical-data hybrid driving model to continuously correct the real-time performance index of the clean air conditioner to obtain an actual performance index of the clean air conditioner; intelligently outputting clean air conditioner maintenance suggestions; generating a visualization report of the working data of the clean air conditioner; and feeding back the real-time monitoring results of the clean air conditioner maintenance suggestions to the background of equipment management personnel; the present invention solves the problems in the prior art that the performance monitoring index of the clean air conditioner is single and the real-time performance of the evaluation results is poor, and at the same time solves the problem of low maintenance efficiency due to experience-based or regular inspection in traditional clean air conditioner maintenance and repair.

Description

Technical Field

[0001] The present invention relates to the technical field of clean air conditioning performance monitoring, and in particular to a clean air conditioning performance prediction method and system using a physical and data hybrid driving technology. Background Art

[0002] Cleanroom air conditioning (also known as cleanroom air conditioning or cleanroom air conditioning system) is an air conditioning system specially designed to maintain a clean environment. It is widely used in semiconductor manufacturing, pharmaceutical industry, food processing, biotechnology and other industries. Cleanroom air conditioning systems usually operate in high-demand environments, such as cleanrooms or areas with strict temperature and humidity control, which makes the monitoring of the operating status and performance of the system complex and sensitive. At the same time, the performance of cleanroom air conditioning is affected by multiple factors, including temperature, humidity, airflow, filtration efficiency, etc. Changes in these factors may affect the overall performance of the system. Therefore, it is necessary to comprehensively consider various data for evaluation and maintenance, and high-precision performance monitoring is very difficult.

[0003] In the existing disclosed invention technologies, the patent application with publication number CN117704609A discloses an air purification control method and system for air-conditioning units, including predicting the number of colonies based on temperature and humidity information and the sweat information on the surface of the skin of personnel. When the number of colonies reaches a threshold, the operating room is indiscriminately purified according to the first clean instruction. When the number of colonies does not reach the threshold, the distribution of the colonies is determined according to the personnel position information, and different degrees of purification are performed on areas with different colony distributions in combination with the second clean instruction.

[0004] The above patent relies too much on environmental data to evaluate air conditioning performance indicators, which is easily affected by environmental factors, especially in complex operating room environments, where there may be a variety of different sources and distributions of colonies. A single data prediction and purification strategy may not be able to fully meet the real-time needs of all scenarios. Summary of the invention

[0005] The technical problem to be solved by the present invention is that in the prior art, the performance monitoring indicators of clean air conditioners are single and the real-time performance of the evaluation results is poor. At the same time, the traditional clean air conditioner inspection and maintenance has the problem of low maintenance efficiency due to experience or regular inspections. A clean air conditioner performance prediction method and system with physical and data hybrid driving technology are proposed.

[0006] In order to achieve the above-mentioned purpose, the technical solution of the clean air conditioning performance prediction method of the physical and data hybrid driving technology of the present invention includes the following steps:

[0007] S1: A sensor system is deployed in the clean air conditioning working area to collect real-time working data and environmental status data of the clean air conditioning;

[0008] S2: Based on the real-time working data and environmental status data of the clean air conditioner, a multimodal physical data analysis model is established to evaluate the various working performance indexes of the clean air conditioner in real time and obtain the real-time performance index of the clean air conditioner;

[0009] S3: Synchronously access the clean air conditioner historical work database, establish a data-driven model based on the clean air conditioner historical work data, and dynamically predict the various working performances of the clean air conditioner;

[0010] S4: Based on S2-S3, a physical-data hybrid driving model is established to continuously correct the real-time performance index of the clean air conditioner and obtain the actual performance index of the clean air conditioner;

[0011] S5: According to the actual performance index of the clean air conditioner, the working state of the clean air conditioner is judged in real time, and the maintenance suggestion of the clean air conditioner is intelligently outputted according to the judgment result;

[0012] S6: Collect and store the actual performance index and working status of the clean air conditioner, generate a visualization report on the working data of the clean air conditioner; and feed back the real-time monitoring results of the clean air conditioner maintenance suggestions to the equipment management personnel backstage.

[0013] Specifically, in S1, the real-time working data of the clean air conditioner includes: gas temperature data at the inlet and outlet of the clean air conditioner compressor, gas pressure data at the inlet and outlet of the clean air conditioner compressor, and clean air conditioner air duct radius data.

[0014] Specifically, S2 includes the following specific steps:

[0015] S21: establishing a multimodal physical data analysis model according to the real-time working data and environmental status data of the clean air conditioner, wherein the multimodal physical data analysis model includes: an air conditioner operation data analysis sub-model and an air conditioner energy efficiency data analysis sub-model;

[0016] S22: Calculate and obtain the air conditioning index, filtration efficiency index and operation noise index of the clean air conditioner through the air conditioning operation data analysis sub-model;

[0017] S23: Calculate and obtain the energy efficiency index of the clean air conditioner through the air conditioner energy efficiency data analysis sub-model;

[0018] S24: The air conditioning index, filtration efficiency index, operation noise index and energy efficiency index of the clean air conditioner are introduced into the working performance index evaluation strategy of the clean air conditioner to obtain the real-time performance index of the clean air conditioner.

[0019] Specifically, S22 includes the following specific steps:

[0020] S221: Calculate and obtain the air conditioning index TJ of the clean air conditioner through the air conditioning index calculation unit in the air conditioning operation data analysis sub-model:

[0021] ;

[0022] in, It is the constant pressure specific heat capacity of air in the clean air-conditioning working environment;

[0023] In a unit monitoring period T, It is the temperature difference between the inlet and outlet gas of the clean air conditioner evaporator; It is the gas temperature difference between the inlet and outlet of the clean air conditioning compressor;

[0024] n is the mass of gas in the compressor; A is the gas constant;

[0025] They are respectively the gas pressure values ​​at the inlet and outlet of the clean air conditioning compressor within a unit monitoring period;

[0026] is the air duct gas mass flow rate at a distance of x meters from the starting point of the air duct in the clean air conditioner;

[0027] The radius of the air duct in the clean air conditioner at a distance of x meters from the starting point of the air duct;

[0028] It is the original radius of the air duct in the clean air conditioner when it leaves the factory;

[0029] S222: Calculate and obtain the filtration efficiency index GL of the clean air conditioner through the filtration efficiency index calculation unit in the air conditioner operation data analysis sub-model, specifically:

[0030] ;

[0031] Among them, within a unit monitoring period T, in a clean air-conditioned working environment, are the concentrations of air particles before and after the clean air conditioner works; t is the monitoring time point;

[0032] The filter area of ​​the clean air conditioning filter;

[0033] They are the air flow rates before and after the filter of the clean air conditioner;

[0034] S223: Calculate and obtain the operating noise index ZS of the clean air conditioner through the operating noise index calculation unit in the air conditioner operating data analysis sub-model, specifically:

[0035] ;

[0036] Among them, a vibration sensor is evenly arranged at the air outlet of the clean air conditioner;

[0037] The vibration frequency data of the air outlet blade surface of the clean air conditioner transmitted by the i-th vibration sensor; is the average vibration frequency of the clean air conditioner air outlet blade surface transmitted by one vibration sensor; It is the target vibration frequency of the clean air conditioner in the laboratory environment.

[0038] Specifically, S23 includes the following specific steps:

[0039] S231: extracting the air conditioning index TJ of the clean air conditioner calculated in S221, and determining an effective conditioning mode of the clean air conditioner;

[0040] S232: setting an air conditioning index threshold, comparing the air conditioning index TJ of the clean air conditioner in real-time working state with the air conditioning index threshold, and when the air conditioning index TJ is greater than or equal to the air conditioning index threshold, determining that the clean air conditioner is in an effective adjustment mode, and recording the duration of the effective adjustment mode;

[0041] S233: Calculate and obtain the energy efficiency index NX of the clean air conditioner. The specific calculation strategy is as follows:

[0042] ;

[0043] Among them, the clean air conditioner is in effective adjustment mode for a total of J continuous periods;

[0044] is the duration of the clean air conditioner being in the jth effective adjustment mode;

[0045] is the energy consumption value of the clean air conditioner in the jth effective adjustment mode;

[0046] It is the overall energy consumption value of the clean air conditioner in a unit monitoring period T.

[0047] Specifically, in S24, the working performance index evaluation strategy of the clean air conditioner is as follows:

[0048] ;

[0049] in, The dynamic weight coefficients of the impact of air conditioning operation data in the air conditioning operation data analysis sub-model and air conditioning energy efficiency data in the air conditioning energy efficiency data analysis sub-model on the clean air conditioning performance, .

[0050] Specifically, S3 includes the following specific steps:

[0051] S31: accessing the clean air conditioner historical operation database, and establishing a data-driven model based on the clean air conditioner historical operation data;

[0052] S32: extracting the working environment temperature data, working environment humidity data, air particulate matter data and working environment space volume data of the clean air conditioner in the clean air conditioner historical working database, forming a multi-dimensional feature matrix, obtaining a feature matrix set of the clean air conditioner historical working data, and performing standardization processing on the feature matrix set of the clean air conditioner historical working data;

[0053] S33: dividing the feature matrix set of the historical working data of the clean air conditioner into a training set and a test set, taking the similarity with the actual working data of the clean air conditioner as the output of the data-driven model, and inputting the training set into the data-driven model for training;

[0054] S34: Testing the data-driven model using a test set, and stopping training when the sum of prediction accuracies reaches convergence.

[0055] Specifically, S4 includes the following specific steps:

[0056] S41: establishing a physical-data hybrid driving model, and extracting the historical working data of the clean air conditioner output by the data driving model that has the highest similarity with the actual working data of the clean air conditioner;

[0057] S42: Importing the historical working data of the clean air conditioner with the highest similarity into the working performance index evaluation strategy of the clean air conditioner, and evaluating the historical working performance index of the historical working data with the highest similarity ;

[0058] S43: According to S42, the prediction deviation ratio pc of the clean air conditioner real-time performance index is calculated, where: , continuously correct the real-time performance index of clean air conditioners and obtain the actual performance index of clean air conditioners , , where e is the exponential operation.

[0059] Specifically, in S5, the working state of the clean air conditioner is judged in real time according to the actual performance index of the clean air conditioner, and the clean air conditioner maintenance suggestion is intelligently outputted according to the judgment result, including:

[0060] When the actual performance index of clean air conditioning When the clean air conditioner is running normally, it is judged that the working parts of the clean air conditioner are operating normally;

[0061] when When the clean air conditioner is running normally, it is judged that the working parts of the clean air conditioner are operating normally, but regular cleaning arrangements need to be made;

[0062] when When the performance of the clean air conditioner working parts is degraded, the reasons for the performance degradation are analyzed and the clean air conditioner parts with degraded performance are replaced;

[0063] when When the clean air conditioner is detected, the performance of the clean air conditioner working parts is judged to be ineffective, and suggestions for replacing the clean air conditioner are output;

[0064] in, These are all thresholds for judging the working status of clean air conditioners.

[0065] In addition, a clean air conditioning performance prediction system of the present invention using a physical and data hybrid driving technology specifically includes the following modules:

[0066] Data acquisition module, physical model building module, data-driven model building module, fusion correction module, performance evaluation module, maintenance suggestion output module and data visualization module;

[0067] The data acquisition module is used to collect real-time working data and environmental status data of the clean air conditioner;

[0068] The physical model building module establishes a data-driven model based on the historical working data of the clean air conditioner, and dynamically predicts various working performances of the clean air conditioner to obtain a clean air conditioner prediction performance index;

[0069] The data-driven model building module establishes a multimodal physical data analysis model based on the real-time working data and environmental status data of the clean air conditioner, evaluates various working performance indexes of the clean air conditioner in real time, and obtains the real-time performance index of the clean air conditioner;

[0070] The fusion correction module is used to establish a physical-data hybrid drive model to continuously correct the clean air conditioner real-time performance index through the clean air conditioner predicted performance index;

[0071] The performance evaluation module is used to obtain the actual performance index of the clean air conditioner;

[0072] The maintenance suggestion output module makes a real-time judgment on the working status of the clean air conditioner according to the actual performance index of the clean air conditioner, and intelligently outputs a maintenance suggestion for the clean air conditioner according to the judgment result;

[0073] The data visualization module is used to collect and store the actual performance index of the clean air conditioner and the working status of the clean air conditioner, generate a visualization report on the working data of the clean air conditioner, and feed back the real-time monitoring results of the clean air conditioner maintenance suggestions to the equipment management personnel backstage.

[0074] A storage medium stores instructions, and when a computer reads the instructions, the computer executes the clean air conditioning performance prediction method using the physical and data hybrid driving technology.

[0075] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the clean air conditioning performance prediction method using the above-mentioned physical and data hybrid driving technology is implemented.

[0076] Compared with the prior art, the technical effects of the present invention are as follows:

[0077] 1. The present invention collects the working data and environmental status data of the clean air conditioner in real time, establishes a real-time performance index, effectively monitors the operating status of the system, and promptly discovers potential problems.

[0078] 2. The multimodal physical data analysis model and data-driven model established by the present invention based on historical and real-time data can improve the accuracy and predictability of the evaluation, support accurate performance evaluation and prediction, and at the same time, establish a physical-data hybrid driven model to continuously correct the real-time performance index to ensure that the evaluation results are closer to reality, thereby optimizing the overall performance of the system

[0079] 3. The present invention determines the working status of the system in real time according to the actual performance index, and intelligently outputs maintenance suggestions, thereby improving maintenance efficiency and accuracy and reducing unexpected downtime. In addition, by generating visual reports of working data and feedback of real-time monitoring results, it provides clear data display and decision support, helping equipment managers to better understand the system operation status. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0081] Figure 1 A schematic flow chart of a clean air conditioning performance prediction method using a physical and data hybrid driving technology of the present invention;

[0082] Figure 2 This is a schematic diagram of the structure of the clean air conditioning performance prediction system using the physical and data hybrid driving technology of the present invention. DETAILED DESCRIPTION

[0083] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0084] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0085] Embodiment 1

[0086] like Figure 1 As shown, the clean air conditioning performance prediction method of the physical and data hybrid driving technology of the embodiment of the present invention includes the following specific steps:

[0087] S1: A sensor system is deployed in the clean air conditioning working area to collect real-time working data and environmental status data of the clean air conditioning;

[0088] In S1, the real-time working data of the clean air conditioner includes: the gas temperature data at the inlet and outlet of the clean air conditioner compressor, the gas pressure data at the inlet and outlet of the clean air conditioner compressor, and the clean air conditioner air duct radius data.

[0089] S2: Based on the real-time working data and environmental status data of the clean air conditioner, a multimodal physical data analysis model is established to evaluate the various working performance indexes of the clean air conditioner in real time and obtain the real-time performance index of the clean air conditioner;

[0090] S2 includes the following specific steps:

[0091] S21: establishing a multimodal physical data analysis model according to the real-time working data and environmental status data of the clean air conditioner, wherein the multimodal physical data analysis model includes: an air conditioner operation data analysis sub-model and an air conditioner energy efficiency data analysis sub-model;

[0092] S22: Calculate and obtain the air conditioning index, filtration efficiency index and operation noise index of the clean air conditioner through the air conditioning operation data analysis sub-model;

[0093] S23: Calculate and obtain the energy efficiency index of the clean air conditioner through the air conditioner energy efficiency data analysis sub-model;

[0094] S24: The air conditioning index, filtration efficiency index, operation noise index and energy efficiency index of the clean air conditioner are introduced into the working performance index evaluation strategy of the clean air conditioner to obtain the real-time performance index of the clean air conditioner.

[0095] Furthermore, S22 includes the following specific steps:

[0096] S221: Calculate and obtain the air conditioning index TJ of the clean air conditioner through the air conditioning index calculation unit in the air conditioning operation data analysis sub-model:

[0097] ;

[0098] in, It is the constant pressure specific heat capacity of air in the clean air-conditioning working environment;

[0099] In a unit monitoring period T, It is the temperature difference between the inlet and outlet gas of the clean air conditioner evaporator; It is the gas temperature difference between the inlet and outlet of the clean air conditioning compressor;

[0100] n is the mass of gas in the compressor; A is the gas constant;

[0101] They are respectively the gas pressure values ​​at the inlet and outlet of the clean air conditioning compressor within a unit monitoring period;

[0102] is the air duct gas mass flow rate at a distance of x meters from the starting point of the air duct in the clean air conditioner;

[0103] The radius of the air duct in the clean air conditioner at a distance of x meters from the starting point of the air duct;

[0104] It is the original radius of the air duct in the clean air conditioner when it leaves the factory;

[0105] S222: Calculate and obtain the filtration efficiency index GL of the clean air conditioner through the filtration efficiency index calculation unit in the air conditioner operation data analysis sub-model, specifically:

[0106] ;

[0107] Among them, within a unit monitoring period T, in a clean air-conditioned working environment, are the concentrations of air particles before and after the clean air conditioner works; t is the monitoring time point;

[0108] The filter area of ​​the clean air conditioning filter;

[0109] They are the air flow rates before and after the filter of the clean air conditioner;

[0110] S223: Calculate and obtain the operating noise index ZS of the clean air conditioner through the operating noise index calculation unit in the air conditioner operating data analysis sub-model, specifically:

[0111] ;

[0112] Among them, a vibration sensor is evenly arranged at the air outlet of the clean air conditioner;

[0113] The vibration frequency data of the air outlet blade surface of the clean air conditioner transmitted by the i-th vibration sensor; is the average vibration frequency of the clean air conditioner air outlet blade surface transmitted by one vibration sensor; It is the target vibration frequency of the clean air conditioner in the laboratory environment.

[0114] Furthermore, S23 includes the following specific steps:

[0115] S231: extracting the air conditioning index TJ of the clean air conditioner calculated in S221, and determining an effective conditioning mode of the clean air conditioner;

[0116] S232: setting an air conditioning index threshold, comparing the air conditioning index TJ of the clean air conditioner in real-time working state with the air conditioning index threshold, and when the air conditioning index TJ is greater than or equal to the air conditioning index threshold, determining that the clean air conditioner is in an effective adjustment mode, and recording the duration of the effective adjustment mode;

[0117] S233: Calculate and obtain the energy efficiency index NX of the clean air conditioner. The specific calculation strategy is as follows:

[0118] ;

[0119] Among them, the clean air conditioner is in effective adjustment mode for a total of J continuous periods;

[0120] is the duration of the clean air conditioner being in the jth effective adjustment mode;

[0121] is the energy consumption value of the clean air conditioner in the jth effective adjustment mode;

[0122] It is the overall energy consumption value of the clean air conditioner in a unit monitoring period T.

[0123] Furthermore, in S24, the working performance index evaluation strategy of the clean air conditioner is specifically as follows:

[0124] ;

[0125] in, The dynamic weight coefficients of the impact of air conditioning operation data in the air conditioning operation data analysis sub-model and air conditioning energy efficiency data in the air conditioning energy efficiency data analysis sub-model on the clean air conditioning performance, .

[0126] S3: Synchronously access the clean air conditioner historical work database, establish a data-driven model based on the clean air conditioner historical work data, and dynamically predict the various working performances of the clean air conditioner;

[0127] S3 includes the following specific steps:

[0128] S31: accessing the clean air conditioner historical operation database, and establishing a data-driven model based on the clean air conditioner historical operation data;

[0129] S32: extracting the working environment temperature data, working environment humidity data, air particulate matter data and working environment space volume data of the clean air conditioner in the clean air conditioner historical working database, forming a multi-dimensional feature matrix, obtaining a feature matrix set of the clean air conditioner historical working data, and performing standardization processing on the feature matrix set of the clean air conditioner historical working data;

[0130] S33: dividing the feature matrix set of the historical working data of the clean air conditioner into a training set and a test set, taking the similarity with the actual working data of the clean air conditioner as the output of the data-driven model, and inputting the training set into the data-driven model for training;

[0131] S34: Testing the data-driven model using a test set, and stopping training when the sum of prediction accuracies reaches convergence.

[0132] S4: Based on S2-S3, a physical-data hybrid driving model is established to continuously correct the real-time performance index of the clean air conditioner and obtain the actual performance index of the clean air conditioner;

[0133] S4 includes the following specific steps:

[0134] S41: establishing a physical-data hybrid driving model, and extracting the historical working data of the clean air conditioner output by the data driving model that has the highest similarity with the actual working data of the clean air conditioner;

[0135] S42: Importing the historical working data of the clean air conditioner with the highest similarity into the working performance index evaluation strategy of the clean air conditioner, and evaluating the historical working performance index of the historical working data with the highest similarity ;

[0136] S43: According to S42, the prediction deviation ratio pc of the clean air conditioner real-time performance index is calculated, where: , continuously correct the real-time performance index of clean air conditioners and obtain the actual performance index of clean air conditioners , , where e is the exponential operation.

[0137] S5: According to the actual performance index of the clean air conditioner, the working state of the clean air conditioner is judged in real time, and the maintenance suggestion of the clean air conditioner is intelligently outputted according to the judgment result;

[0138] In S5, the working state of the clean air conditioner is judged in real time according to the actual performance index of the clean air conditioner, and the clean air conditioner maintenance suggestions are intelligently outputted according to the judgment result, including:

[0139] When the actual performance index of clean air conditioning When the clean air conditioner is running normally, it is judged that the working parts of the clean air conditioner are operating normally;

[0140] when When the clean air conditioner is running normally, it is judged that the working parts of the clean air conditioner are operating normally, but regular cleaning arrangements need to be made;

[0141] when When the performance of the clean air conditioner working parts is degraded, the reasons for the performance degradation are analyzed and the clean air conditioner parts with degraded performance are replaced;

[0142] when When the clean air conditioner is detected, the performance of the clean air conditioner working parts is judged to be ineffective, and suggestions for replacing the clean air conditioner are output;

[0143] in, These are all thresholds for judging the working status of clean air conditioners.

[0144] S6: Collect and store the actual performance index and working status of the clean air conditioner, generate a visualization report on the working data of the clean air conditioner; and feed back the real-time monitoring results of the clean air conditioner maintenance suggestions to the equipment management personnel backstage.

[0145] Embodiment 2

[0146] like Figure 2 As shown, the clean air conditioning performance prediction system of the physical and data hybrid driving technology of the embodiment of the present invention includes the following modules:

[0147] Data acquisition module, physical model building module, data-driven model building module, fusion correction module, performance evaluation module, maintenance suggestion output module and data visualization module;

[0148] The data acquisition module is used to collect real-time working data and environmental status data of the clean air conditioner;

[0149] The physical model building module establishes a data-driven model based on the historical working data of the clean air conditioner, and dynamically predicts various working performances of the clean air conditioner to obtain a clean air conditioner prediction performance index;

[0150] The data-driven model building module establishes a multimodal physical data analysis model based on the real-time working data and environmental status data of the clean air conditioner, evaluates various working performance indexes of the clean air conditioner in real time, and obtains the real-time performance index of the clean air conditioner;

[0151] The fusion correction module is used to establish a physical-data hybrid drive model to continuously correct the clean air conditioner real-time performance index through the clean air conditioner predicted performance index;

[0152] The performance evaluation module is used to obtain the actual performance index of the clean air conditioner;

[0153] The maintenance suggestion output module makes a real-time judgment on the working status of the clean air conditioner according to the actual performance index of the clean air conditioner, and intelligently outputs a maintenance suggestion for the clean air conditioner according to the judgment result;

[0154] The data visualization module is used to collect and store the actual performance index of the clean air conditioner and the working status of the clean air conditioner, generate a visualization report on the working data of the clean air conditioner, and feed back the real-time monitoring results of the clean air conditioner maintenance suggestions to the equipment management personnel backstage.

[0155] Embodiment 3

[0156] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0157] The processor executes the clean air conditioning performance prediction method of the above-mentioned physical and data hybrid driving technology by calling the computer program stored in the memory.

[0158] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the clean air conditioning performance prediction method of the physical and data hybrid drive technology provided in the above method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0159] Embodiment 4

[0160] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0161] When the computer program runs on a computer device, the computer device is enabled to execute the clean air conditioning performance prediction method using the above-mentioned physical and data hybrid driving technology.

[0162] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0163] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0164] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0165] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0166] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0168] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0171] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0172] In summary, compared with the prior art, the technical effects of the present invention are as follows:

[0173] 1. The present invention collects the working data and environmental status data of the clean air conditioner in real time, establishes a real-time performance index, effectively monitors the operating status of the system, and promptly discovers potential problems.

[0174] 2. The multimodal physical data analysis model and data-driven model established by the present invention based on historical and real-time data can improve the accuracy and predictability of the evaluation, support accurate performance evaluation and prediction, and at the same time, establish a physical-data hybrid driven model to continuously correct the real-time performance index to ensure that the evaluation results are closer to reality, thereby optimizing the overall performance of the system

[0175] 3. The present invention determines the working status of the system in real time according to the actual performance index, and intelligently outputs maintenance suggestions, thereby improving maintenance efficiency and accuracy and reducing unexpected downtime. In addition, by generating visual reports of working data and feedback of real-time monitoring results, it provides clear data display and decision support, helping equipment managers to better understand the system operation status.

[0176] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A clean air conditioning performance prediction method based on physical and data hybrid driving technology, characterized in that: The method comprises the following specific steps: S1: A sensor system is deployed in the clean air conditioning working area to collect real-time working data and environmental status data of the clean air conditioning; S2: Based on the real-time working data and environmental status data of the clean air conditioner, a multimodal physical data analysis model is established to evaluate the various working performance indexes of the clean air conditioner in real time and obtain the real-time performance index of the clean air conditioner; S3: Synchronously access the clean air conditioner historical work database, establish a data-driven model based on the clean air conditioner historical work data, and dynamically predict the various working performances of the clean air conditioner; S4: Based on S2-S3, a physical-data hybrid driving model is established to continuously correct the real-time performance index of the clean air conditioner and obtain the actual performance index of the clean air conditioner; S5: According to the actual performance index of the clean air conditioner, the working state of the clean air conditioner is judged in real time, and the maintenance suggestion of the clean air conditioner is intelligently outputted according to the judgment result; S6: collecting and storing the actual performance index of the clean air conditioner and the working status of the clean air conditioner, and generating a visualization report of the working data of the clean air conditioner; And feedback the real-time monitoring results of clean air conditioning maintenance suggestions to the equipment management personnel backstage; In S1, the real-time working data of the clean air conditioner includes: the gas temperature data at the inlet and outlet of the clean air conditioner compressor, the gas pressure data at the inlet and outlet of the clean air conditioner compressor, and the clean air conditioner air duct radius data; S2 includes the following specific steps: S21: establishing a multimodal physical data analysis model according to the real-time working data and environmental status data of the clean air conditioner, wherein the multimodal physical data analysis model includes: an air conditioner operation data analysis sub-model and an air conditioner energy efficiency data analysis sub-model; S22: Calculate and obtain the air conditioning index, filtration efficiency index and operation noise index of the clean air conditioner through the air conditioning operation data analysis sub-model; S23: Calculate and obtain the energy efficiency index of the clean air conditioner through the air conditioner energy efficiency data analysis sub-model; S24: importing the air conditioning index, filtration efficiency index, operation noise index and energy efficiency index of the clean air conditioner into the working performance index evaluation strategy of the clean air conditioner to obtain the real-time performance index of the clean air conditioner; S22 includes the following specific steps: S221: Calculate and obtain the air conditioning index TJ of the clean air conditioner through the air conditioning index calculation unit in the air conditioning operation data analysis sub-model: ； in, It is the constant pressure specific heat capacity of air in the clean air-conditioning working environment; In a unit monitoring period T, It is the temperature difference between the inlet and outlet gas of the clean air conditioner evaporator; It is the gas temperature difference between the inlet and outlet of the clean air conditioning compressor; n is the mass of gas in the compressor; A is the gas constant; They are respectively the gas pressure values ​​at the inlet and outlet of the clean air conditioning compressor within a unit monitoring period; is the air duct gas mass flow rate at a distance of x meters from the starting point of the air duct in the clean air conditioner; The radius of the air duct in the clean air conditioner at a distance of x meters from the starting point of the air duct; It is the original radius of the air duct in the clean air conditioner when it leaves the factory; S222: Calculate and obtain the filtration efficiency index GL of the clean air conditioner through the filtration efficiency index calculation unit in the air conditioner operation data analysis sub-model, specifically: ； Among them, within a unit monitoring period T, in a clean air-conditioned working environment, are the concentrations of air particles before and after the clean air conditioner works; t is the monitoring time point; The filter area of ​​the clean air conditioning filter; They are the air flow rates before and after the filter of the clean air conditioner; S223: Calculate and obtain the operating noise index ZS of the clean air conditioner through the operating noise index calculation unit in the air conditioner operating data analysis sub-model, specifically: ； Among them, a vibration sensor is evenly arranged at the air outlet of the clean air conditioner; The vibration frequency data of the air outlet blade surface of the clean air conditioner transmitted by the i-th vibration sensor; is the average vibration frequency of the clean air conditioner air outlet blade surface transmitted by one vibration sensor; It is the target vibration frequency of clean air conditioner in the laboratory environment; S23 includes the following specific steps: S231: extracting the air conditioning index TJ of the clean air conditioner calculated in S221, and determining an effective conditioning mode of the clean air conditioner; S232: setting an air conditioning index threshold, comparing the air conditioning index TJ of the clean air conditioner in real-time working state with the air conditioning index threshold, and when the air conditioning index TJ is greater than or equal to the air conditioning index threshold, determining that the clean air conditioner is in an effective adjustment mode, and recording the duration of the effective adjustment mode; S233: Calculate and obtain the energy efficiency index NX of the clean air conditioner. The specific calculation strategy is as follows: ； Among them, the clean air conditioner is in effective adjustment mode for a total of J continuous periods; is the duration of the clean air conditioner being in the jth effective adjustment mode; is the energy consumption value of the clean air conditioner in the jth effective adjustment mode; It is the overall energy consumption value of the clean air conditioner in a unit monitoring period T; In S24, the working performance index evaluation strategy of the clean air conditioner is specifically as follows: ； in, The dynamic weight coefficients of the impact of air conditioning operation data in the air conditioning operation data analysis sub-model and air conditioning energy efficiency data in the air conditioning energy efficiency data analysis sub-model on the clean air conditioning performance, ; S3 includes the following specific steps: S31: accessing the clean air conditioner historical operation database, and establishing a data-driven model based on the clean air conditioner historical operation data; S32: extracting the working environment temperature data, working environment humidity data, air particulate matter data and working environment space volume data of the clean air conditioner in the clean air conditioner historical working database, forming a multi-dimensional feature matrix, obtaining a feature matrix set of the clean air conditioner historical working data, and performing standardization processing on the feature matrix set of the clean air conditioner historical working data; S33: dividing the feature matrix set of the historical working data of the clean air conditioner into a training set and a test set, taking the similarity with the actual working data of the clean air conditioner as the output of the data-driven model, and inputting the training set into the data-driven model for training; S34: Testing the data-driven model using a test set until the sum of the prediction accuracies reaches convergence, and stopping the training; S4 includes the following specific steps S41: establishing a physical-data hybrid driving model, and extracting the historical working data of the clean air conditioner output by the data driving model that has the highest similarity with the actual working data of the clean air conditioner; S42: Importing the historical working data of the clean air conditioner with the highest similarity into the working performance index evaluation strategy of the clean air conditioner, and evaluating the historical working performance index of the historical working data with the highest similarity ; S43: According to S42, the prediction deviation ratio pc of the clean air conditioner real-time performance index is calculated, where: , continuously correct the real-time performance index of clean air conditioners and obtain the actual performance index of clean air conditioners , , where e is the exponential operation.

2. The clean air conditioning performance prediction method based on physical and data hybrid driving technology according to claim 1 is characterized in that: In S5, the working state of the clean air conditioner is judged in real time according to the actual performance index of the clean air conditioner, and the clean air conditioner maintenance suggestions are intelligently outputted according to the judgment result, including: When the actual performance index of clean air conditioning When the clean air conditioner is running normally, it is judged that the working parts of the clean air conditioner are operating normally; when When the clean air conditioner is running normally, it is judged that the working parts of the clean air conditioner are operating normally, but regular cleaning arrangements need to be made; when When the performance of the clean air conditioner working parts is degraded, the reasons for the performance degradation are analyzed and the clean air conditioner parts with degraded performance are replaced; when When the clean air conditioner is detected, the performance of the clean air conditioner working parts is judged to be ineffective, and suggestions for replacing the clean air conditioner are output; in, These are all thresholds for judging the working status of clean air conditioners.

3. A clean air conditioning performance prediction system using a physical and data hybrid driving technology, which is used to implement a clean air conditioning performance prediction method using a physical and data hybrid driving technology as described in any one of claims 1-2, characterized in that: The system includes the following modules: Data acquisition module, physical model building module, data-driven model building module, fusion correction module, performance evaluation module, maintenance suggestion output module and data visualization module; The data acquisition module is used to collect real-time working data and environmental status data of the clean air conditioner; Among them, the real-time working data of the clean air conditioner includes: the gas temperature data at the inlet and outlet of the clean air conditioner compressor, the gas pressure data at the inlet and outlet of the clean air conditioner compressor and the clean air conditioner air duct radius data; The physical model building module establishes a data-driven model based on the historical working data of the clean air conditioner, and dynamically predicts various working performances of the clean air conditioner to obtain a clean air conditioner prediction performance index; The physical model building module is used to run the following specific steps: S21: establishing a multimodal physical data analysis model according to the real-time working data and environmental status data of the clean air conditioner, wherein the multimodal physical data analysis model includes: an air conditioner operation data analysis sub-model and an air conditioner energy efficiency data analysis sub-model; S22: Calculate and obtain the air conditioning index, filtration efficiency index and operation noise index of the clean air conditioner through the air conditioning operation data analysis sub-model; S23: Calculate and obtain the energy efficiency index of the clean air conditioner through the air conditioner energy efficiency data analysis sub-model; S24: importing the air conditioning index, filtration efficiency index, operation noise index and energy efficiency index of the clean air conditioner into the working performance index evaluation strategy of the clean air conditioner to obtain the real-time performance index of the clean air conditioner; Wherein, S22 includes the following specific steps: S221: Calculate and obtain the air conditioning index TJ of the clean air conditioner through the air conditioning index calculation unit in the air conditioning operation data analysis sub-model: ； in, It is the constant pressure specific heat capacity of air in the clean air-conditioning working environment; In a unit monitoring period T, It is the temperature difference between the inlet and outlet gas of the clean air conditioner evaporator; It is the gas temperature difference between the inlet and outlet of the clean air conditioning compressor; n is the mass of gas in the compressor; A is the gas constant; They are respectively the gas pressure values ​​at the inlet and outlet of the clean air conditioning compressor within a unit monitoring period; is the air duct gas mass flow rate at a distance of x meters from the starting point of the air duct in the clean air conditioner; The radius of the air duct in the clean air conditioner at a distance of x meters from the starting point of the air duct; It is the original radius of the air duct in the clean air conditioner when it leaves the factory; S222: Calculate and obtain the filtration efficiency index GL of the clean air conditioner through the filtration efficiency index calculation unit in the air conditioner operation data analysis sub-model, specifically: ； Among them, within a unit monitoring period T, in a clean air-conditioned working environment, are the concentrations of air particles before and after the clean air conditioner works; t is the monitoring time point; The filter area of ​​the clean air conditioning filter; They are the air flow rates before and after the filter of the clean air conditioner; S223: Calculate and obtain the operating noise index ZS of the clean air conditioner through the operating noise index calculation unit in the air conditioner operating data analysis sub-model, specifically: ； Among them, a vibration sensor is evenly arranged at the air outlet of the clean air conditioner; The vibration frequency data of the air outlet blade surface of the clean air conditioner transmitted by the i-th vibration sensor; is the average vibration frequency of the clean air conditioner air outlet blade surface transmitted by one vibration sensor; It is the target vibration frequency of clean air conditioner in the laboratory environment; Wherein, S23 includes the following specific steps: S231: extracting the air conditioning index TJ of the clean air conditioner calculated in S221, and determining an effective conditioning mode of the clean air conditioner; S232: setting an air conditioning index threshold, comparing the air conditioning index TJ of the clean air conditioner in real-time working state with the air conditioning index threshold, and when the air conditioning index TJ is greater than or equal to the air conditioning index threshold, determining that the clean air conditioner is in an effective adjustment mode, and recording the duration of the effective adjustment mode; S233: Calculate and obtain the energy efficiency index NX of the clean air conditioner. The specific calculation strategy is as follows: ； Among them, the clean air conditioner is in effective adjustment mode for a total of J continuous periods; is the duration of the clean air conditioner being in the jth effective adjustment mode; is the energy consumption value of the clean air conditioner in the jth effective adjustment mode; It is the overall energy consumption value of the clean air conditioner in a unit monitoring period T; Among them, in S24, the working performance index evaluation strategy of the clean air conditioner is specifically as follows: ； in, The dynamic weight coefficients of the impact of air conditioning operation data in the air conditioning operation data analysis sub-model and air conditioning energy efficiency data in the air conditioning energy efficiency data analysis sub-model on the clean air conditioning performance, ; The data-driven model building module establishes a multimodal physical data analysis model based on the real-time working data and environmental status data of the clean air conditioner, evaluates various working performance indexes of the clean air conditioner in real time, and obtains the real-time performance index of the clean air conditioner; The data-driven model building module is used to run the following specific steps: S31: accessing the clean air conditioner historical operation database, and establishing a data-driven model based on the clean air conditioner historical operation data; S32: extracting the working environment temperature data, working environment humidity data, air particulate matter data and working environment space volume data of the clean air conditioner in the clean air conditioner historical working database, forming a multi-dimensional feature matrix, obtaining a feature matrix set of the clean air conditioner historical working data, and performing standardization processing on the feature matrix set of the clean air conditioner historical working data; S33: dividing the feature matrix set of the historical working data of the clean air conditioner into a training set and a test set, taking the similarity with the actual working data of the clean air conditioner as the output of the data-driven model, and inputting the training set into the data-driven model for training; S34: Testing the data-driven model using a test set until the sum of the prediction accuracies reaches convergence, and stopping the training; The fusion correction module is used to establish a physical-data hybrid drive model to continuously correct the clean air conditioner real-time performance index through the clean air conditioner predicted performance index; The data-driven model building module is used to run the following specific steps: S41: establishing a physical-data hybrid driving model, and extracting the historical working data of the clean air conditioner output by the data driving model that has the highest similarity with the actual working data of the clean air conditioner; S42: Importing the historical working data of the clean air conditioner with the highest similarity into the working performance index evaluation strategy of the clean air conditioner, and evaluating the historical working performance index of the historical working data with the highest similarity ; S43: According to S42, the prediction deviation ratio pc of the clean air conditioner real-time performance index is calculated, where: , continuously correct the real-time performance index of clean air conditioners; The performance evaluation module is used to obtain the actual performance index of the clean air conditioner. , , where e is the exponential operation; The maintenance suggestion output module makes a real-time judgment on the working status of the clean air conditioner according to the actual performance index of the clean air conditioner, and intelligently outputs a maintenance suggestion for the clean air conditioner according to the judgment result; The data visualization module is used to collect and store the actual performance index of the clean air conditioner and the working status of the clean air conditioner, generate a visualization report on the working data of the clean air conditioner, and feed back the real-time monitoring results of the clean air conditioner maintenance suggestions to the equipment management personnel backstage.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the clean air conditioning performance prediction method of the physical and data hybrid driving technology according to any one of claims 1-2 is implemented.

5. An electronic device, characterized in that: include: A memory for storing instructions; A processor is used to execute the instructions so that the device performs operations to implement the clean air conditioning performance prediction method using the physical and data hybrid driving technology as described in any one of claims 1-2.

Images