Remote intelligent monitoring method for health condition of air conditioning system of rail transit vehicle

Abstract

The invention discloses a remote intelligent monitoring method for the health condition of an air conditioning system of a rail transit vehicle, and relates to the technical field of intelligent control, the rail transit air conditioning system is initialized, data are collected in real time, and the data are sent to edge computing equipment through wireless communication; after edge calculation, the preprocessed data are compared with preset parameters, and the current state of the air conditioner system is calculated; based on the state, a physical model is constructed for fault deduction, operation of the air conditioning system is simulated through thermal load prediction and pressure change analysis, and a fault deduction report is generated through comparison with real-time data; inputting the report into a machine learning algorithm for analysis, and judging a fault type and a fault source according to historical fault data and an air conditioning system working mode; and in combination with remote intelligent self-adaptive control, system parameters are optimized, and the state of the air conditioning system is updated. Real-time acquisition, modeling deduction and machine learning are fused, the fault diagnosis accuracy and response speed are improved, and the reliability and intelligence of the rail transit air conditioning system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to a remote intelligent monitoring method for the health status of a rail transit vehicle air conditioning system. Background Art

[0002] With the development of rail transit, the air conditioning system has become an important factor in ensuring passenger comfort and the stable operation of rail transit vehicles. However, the existing air conditioning systems mainly rely on periodic manual inspections or simple fault alarms, making it difficult to achieve comprehensive monitoring. Especially in complex high and low temperature environments, equipment aging or sudden failures may lead to a decline in the efficiency of the air conditioning system and affect its service life.

[0003] Especially in the aspects of fault deduction and fault source location of the air conditioning system, traditional technologies have not fully considered the dynamics and variability of the system, resulting in poor accuracy of fault deduction and the inability to dynamically adjust the early warning model in combination with real-time data. This static processing method makes it impossible for the air conditioning system to respond quickly and repair effectively when encountering complex or sudden failures, affecting the stability of the system and the comfort experience of passengers. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a remote intelligent monitoring method for the health status of a rail transit vehicle air conditioning system to solve the problems of real-time fault diagnosis and precise control of the rail transit air conditioning system.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a remote intelligent monitoring method for the health status of a rail transit vehicle air conditioning system, which includes initializing the rail transit air conditioning system and collecting data in real time, and sending it to edge computing using wireless communication;

[0008] Preprocessing the received data, comparing it with preset working parameters, and calculating the current working state of the air conditioning system;

[0009] Constructing a physical model to conduct fault deduction on the current working state of the air conditioning system, simulating the operation of the air conditioning system through heat load prediction and pressure change analysis, and comparing it with real-time data to generate a fault deduction report;

[0010] Inputting the fault deduction report into a machine learning algorithm for analysis, and judging the fault type and fault source based on historical fault data and the working mode of the air conditioning system;

[0011] Analyzing through a machine learning algorithm, and combining remote intelligent adaptive control to update the current working state of the air conditioning system.

[0012] As a preferred solution of the remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system described in the present invention, the following steps are included: Initialize the rail transit air conditioning system and collect data in real time, and send it to the edge computing using wireless communication, including:

[0013] Use an embedded control platform to initialize the air conditioning system, collect temperature, humidity and refrigerant data in real time through distributed sensors, store them in the control unit cache, and transmit them to the edge computing using narrowband Internet of Things.

[0014] As a preferred solution of the remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system described in the present invention, the following steps are included: Preprocess the received data, compare it with the preset working parameters, and calculate the current working state of the air conditioning system. The specific steps are as follows:

[0015] Normalize the temperature, humidity and refrigerant data, and extract the preset working parameters built in the edge computing;

[0016] Adopt deviation calculation, output the deviation result and mark the abnormality, and evaluate the health status and abnormal status of the air conditioning system by combining parameter weights.

[0017] As a preferred solution of the remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system described in the present invention, the following steps are included: Build a physical model to deduce the faults of the current working state of the air conditioning system, simulate the operation of the air conditioning system through heat load prediction and pressure change analysis, and compare it with the real-time data to generate a fault deduction report. The specific steps are as follows:

[0018] Build a dynamic physical model, couple the heat load and refrigerant flow rate changes, and generate a dynamic temperature prediction model;

[0019] Update the dynamic temperature prediction parameters through real-time data, correct the changes in heat load and refrigerant pressure, and optimize the dynamic temperature prediction model in real time;

[0020] Analyze the temperature deviation trend by combining the real-time collected temperature data, determine the operating state based on the refrigerant pressure change, classify and locate the faults, and generate a fault deduction report.

[0021] As a preferred solution of the remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system described in the present invention, the following steps are included: Build a dynamic physical model, couple the heat load and refrigerant flow rate changes, and generate a dynamic temperature prediction model. The specific steps are as follows:

[0022] Identify the heat load, refrigerant pressure and refrigerant flow rate under the current working state, combine the specific heat capacity of air and the carriage volume, and build the thermodynamic core relationship of the carriage temperature change;

[0023] Based on the core thermodynamic relationships, by dynamically balancing heat input, output, and losses, the changing trend of temperature over time is quantified in the form of dynamic integration, and a dynamic temperature prediction model is constructed.

[0024] As a preferred embodiment of the method for remotely and intelligently monitoring the health status of the air-conditioning system of rail transit vehicles according to the present invention, wherein: by analyzing the temperature deviation trend in combination with the real-time collected temperature data, determining the operating state based on the change in refrigerant pressure, classifying and locating faults, and generating a fault deduction report, the specific steps are as follows:

[0025] Based on the dynamic temperature prediction model, comparing the real-time collected data with the predicted values, deducing the fault type, and displaying the abnormal points through a time series graph;

[0026] Evaluating the state of the air-conditioning system using the fault type results, classifying and summarizing the fault types and causes, combining multi-parameter trend graphs to display the fault evolution process and abnormal points, and generating a fault deduction report.

[0027] As a preferred embodiment of the method for remotely and intelligently monitoring the health status of the air-conditioning system of rail transit vehicles according to the present invention, wherein: inputting the fault deduction report into a machine learning algorithm for analysis, and judging the fault type and fault source according to historical fault data and the working mode of the air-conditioning system, including: extracting the fault parameters in the fault deduction report and performing normalization processing to generate a multi-dimensional feature vector, and using a dynamic physical model to judge the fault type and fault source classification.

[0028] As a preferred embodiment of the method for remotely and intelligently monitoring the health status of the air-conditioning system of rail transit vehicles according to the present invention, wherein: through analysis by a machine learning algorithm, combined with remote intelligent adaptive control, updating the current working state of the air-conditioning system, including:

[0029] Analyzing the fault type and fault source through a machine learning model, generating a control strategy in combination with the current working state parameters and outputting an adjustment instruction, and real-time monitoring and comparing the evaluation results with the expected values to iterate the control strategy.

[0030] In a second aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and wherein: when the computer program is executed by the processor, any step of the method for remotely and intelligently monitoring the health status of the air-conditioning system of rail transit vehicles as described in the first aspect of the present invention is implemented.

[0031] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and wherein: when the computer program is executed by the processor, any step of the method for remotely and intelligently monitoring the health status of the air-conditioning system of rail transit vehicles as described in the first aspect of the present invention is implemented.

[0032] The beneficial effects of the present invention are as follows: By combining dynamic physical modeling and machine learning, the present invention realizes real-time analysis and optimal control. Distributed sensors and edge computing are adopted to improve the accuracy of temperature, humidity, and refrigerant data collection and the real-time performance of data transmission. Through the dynamic temperature prediction model and the coupling analysis of heat load and refrigerant flow, the fault types and sources are accurately deduced. Machine learning deeply mines historical fault data and combines it with real-time monitoring to achieve efficient fault classification and health assessment. Finally, by integrating real-time collection, modeling deduction, and machine learning, the accuracy and response speed of fault diagnosis are improved, and the reliability and intelligence of the rail transit air conditioning system are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0034] Figure 1 It is a flowchart of the remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the drawings of the specification.

[0036] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0037] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0038] Embodiment 1, referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system, including the following steps:

[0039] S1. Initialize the rail transit air conditioning system and collect data in real time, and send it to the edge computing using wireless communication.

[0040] Specifically, first, an embedded control platform is used to initialize the air conditioning system, enabling automatic loading of preset operating parameters and dynamic adjustment in combination with environmental conditions to reduce dependence on the central controller and enhance the adaptability and stability of the air conditioning system.

[0041] Subsequently, real-time data is collected based on a distributed sensor architecture. Sensors are deployed at multiple points to collect temperature, humidity, and refrigerant parameters, which are stored in the control unit cache. At the same time, redundant design is used to enhance the fault tolerance of the air conditioning system and avoid the impact of single-point failure on overall monitoring. The collected data is transmitted to the edge computing unit via Narrowband Internet of Things (NB-IoT). Compared with traditional Wi-Fi or 4G, this communication technology has stronger anti-interference ability and lower power consumption in the rail transit environment, can still transmit stably in high-speed movement or weak signal areas, and supports large-scale device access, improving the expansion of the monitored air conditioning system.

[0042] S2. Preprocess the received data, compare it with the preset working parameters, and calculate the current working state of the air conditioning system.

[0043] Specifically, the dimensional differences of temperature, humidity, and refrigerant data are eliminated through normalization, enabling various data to be on the same scale. The air conditioning system compares with the real-time collected data based on a preset working parameter library (temperature weight, humidity weight, and refrigerant pressure weight) to adapt to the differences in different vehicle types, environmental conditions, and operating conditions.

[0044] Deviation calculation is adopted to output the deviation result and mark abnormalities, and the health status and abnormal status of the air conditioning system are evaluated in combination with parameter weights.

[0045] Specifically, by introducing deviation calculation, the deviation between real-time data and preset parameters is calculated and analyzed in combination with the operating trend, thereby reducing misjudgment caused by short-term fluctuations and improving the accuracy of abnormal identification. Finally, the deviation calculation result is marked as abnormal. When the deviation exceeds the normal range, it is marked as abnormal in a timely manner for subsequent analysis and health assessment.

[0046] Among them, evaluating the health status and abnormal status of the air conditioning system in combination with parameter weights is expressed as:

[0047]

[0048] In the formula, w i ′ is the weight after evaluation, w i is the initial parameter weight, σ i is the real-time data of the air conditioning system, is for normalization to make the sum of dynamic weights equal to 1, w j is the weight of historical fault parameters, σ j is the dynamic adjustment value of the real-time data of the air conditioning system.

[0049] S = w′ T ·Te + w P ′·Pe + w′ H ·He;

[0050] In the formula, S is the health score, w′ T is the dynamic weight of the temperature parameter, w P ′ is the dynamic weight of the refrigerant pressure parameter, w′ H is the dynamic weight of the humidity parameter, Te is the temperature deviation value, Pe is the refrigerant pressure deviation value, and He is the humidity deviation value.

[0051] Set the air - conditioning system state judgment threshold based on the health score as S d :

[0052] If S > S d at this time, it indicates that the air - conditioning system is in an abnormal state;

[0053] If S is less than S d at this time, it indicates that the air - conditioning system is in a healthy state.

[0054] S3. Construct a physical model to conduct fault deduction on the current working state of the air - conditioning system. By predicting the heat load and analyzing the pressure change, simulate the operation of the air - conditioning system and compare it with the real - time data to generate a fault deduction report.

[0055] Specifically, by identifying the heat load, refrigerant pressure, and refrigerant flow rate under the current working state, and combining the specific heat capacity of air and the volume of the carriage, construct the thermodynamic core relationship of the temperature change in the carriage;

[0056] Based on the thermodynamic core relationship, by dynamically balancing the heat input, output, and loss, use the dynamic integral form to quantify the change trend of temperature over time, and construct a dynamic temperature prediction model.

[0057] Among them, the heat load is expressed as:

[0058] Q = m·s p ·(T in - T out );

[0059] In the formula, Q is the heat load of the air - conditioning system, m is the refrigerant flow rate, c p is the specific heat capacity of the refrigerant, T in is the refrigerant inlet temperature, T out is the refrigerant outlet temperature.

[0060] Among them, considering the influence of real - time data on the heat load, the correction is expressed as:

[0061] Q corr (t) = Q(t)·f e (Tenv , H env );

[0062] Wherein, Q corr (t) is the corrected heat load of the air - conditioning system, Q(t) is the heat load during operation, t is time, T env is the real - time external temperature, H env is the real - time external humidity, f e is the environmental correction factor.

[0063] Among them, the change of refrigerant flow rate with temperature and volume is expressed as:

[0064]

[0065] Wherein, P is the pressure of the air - conditioning system, n is the amount of refrigerant substance, R is the gas constant of the refrigerant, T is the refrigerant temperature, and V is the refrigerant volume.

[0066] Among them, the pressure of the refrigerant in the pipeline is expressed as:

[0067]

[0068] Wherein, ΔP is the pressure drop of the refrigerant, L is the pipeline length, D is the pipeline diameter, ρ is the refrigerant density, v is the refrigerant flow velocity, f f is the pipeline friction loss coefficient.

[0069] Among them, checking potential heat loss problems in the air - conditioning system status diagnosis is expressed as:

[0070] Q in -Q out = ΔU + W;

[0071] Wherein, Q in is the heat entering the air - conditioning system, Q out is the heat discharged from the air - conditioning system, ΔU is the change in heat of the air - conditioning system, and W is the work done by the air - conditioning system.

[0072] Combining the heat load, refrigerant pressure and refrigerant flow rate, and combining the specific heat capacity of air and the compartment volume parameters to construct a dynamic temperature model is specifically expressed as:

[0073]

[0074] Wherein, Δt is the change amount of the internal air temperature during the operation of the compartment, c p ·ρ·V represents the ease of temperature change when the compartment air absorbs or releases heat. The larger the heat capacity, the slower the temperature change; the smaller the heat capacity, the faster the temperature change, Q in is the heat entering the air - conditioning system, Q out is the heat discharged from the air - conditioning system.

[0075] Preferably, it describes the dynamic process of the air temperature change inside the carriage, comprehensively considering the influence of input heat, output heat, and the heat capacity of the carriage air. It not only has a clear physical meaning but also provides a basis for dynamic temperature prediction and air-conditioning system optimization.

[0076] S4. Input the fault deduction report into a machine learning algorithm for analysis, and judge the fault type and fault source based on historical fault data and the working mode of the air-conditioning system.

[0077] Specifically, extract the fault parameters in the fault deduction report and perform normalization processing to generate a multi-dimensional feature vector, and use a dynamic physical model to judge the fault type and fault source classification.

[0078] Among them, the normalization processing of the fault parameters in the fault deduction report is expressed as:

[0079]

[0080] In the formula, X′ is the normalized fault parameter data, X is the fault deduction report, X max is the maximum value in the fault deduction report, X min is the minimum value in the fault deduction report.

[0081] Among them, the generation of the multi-dimensional feature vector is expressed as:

[0082] F = {X1′, X2′,..., X′ n};

[0083] In the formula, F is the fault feature vector, X1′, X2′,..., X′ n are the normalized data of each fault parameter.

[0084] Among them, the simulation using the dynamic physical model is expressed as:

[0085]

[0086] In the formula, S is the physical simulation model, W is the working state of the air-conditioning working system, is the temperature change rate, is the refrigerant pressure change rate, is the refrigerant flow rate change rate, and F is the fault feature vector.

[0087] Among them, the construction of the adaptive physical modeling is expressed as:

[0088] M(F, S) = argmaxP(y i |F, S; θ);

[0089] Wherein, M(F, S) is the fault diagnosis model, S is the physical simulation data, argmaxP is the fault type selection, and argmaxP(y i |F, S; θ) is to predict a specific fault type based on the current operating state of the air-conditioning system and the collected fault data, y i is the fault type diagnosis confidence, and θ is the parameter set in the air-conditioning system fault diagnosis model.

[0090] Among them, using the dynamic physical model, the judgment of the fault type and the fault source classification is expressed as:

[0091] y = N(F, S);

[0092] Wherein, y is the fault type or fault source, M is the adaptive physical modeling algorithm, and S is the physical simulation data.

[0093] S5. Analyze the fault type and fault source through the machine learning model, generate a control strategy in combination with the current working state parameters and output an adjustment instruction, and monitor and compare the evaluation results with the expected values in real time to iterate the control strategy.

[0094] Among them, analyzing the fault type and fault source through the machine learning model is expressed as:

[0095] R = f r (y, X');

[0096] Wherein, f r is the deep learning network, R is the fault deduction report, y is the fault type or fault source, and X' is the normalized fault parameter data.

[0097] (F t , F s ) = f m (R, H);

[0098] Wherein, (F t , F s ) is the output fault type and fault source, H is the historical data of the air-conditioning system, and f m is the fault analysis report.

[0099] Generating a control strategy in combination with the current working state parameters and outputting an adjustment instruction is expressed as:

[0100] C = f c (F t , F s , X');

[0101] Wherein, f c is the genetic algorithm, and the air-conditioning system is adjusted, C is the calculated adjustment strategy, F t , F sFor the output fault type and fault source, X′ is the fault parameter data after normalization.

[0102] Among them, the output adjustment instruction is expressed as:

[0103] U = f u (C);

[0104] In the formula, U is the output adjustment instruction, and f u is PID control.

[0105] This embodiment also provides a computer device, which is applicable to the situation of the remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system as proposed in the above embodiment.

[0106] The computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through Wi-Fi, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0107] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for remotely and intelligently monitoring the health status of a rail transit vehicle air conditioning system as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0108] In summary, the present invention combines dynamic physical modeling and machine learning to achieve real-time analysis and optimal control. By using distributed sensors and edge computing, the accuracy of temperature, humidity, and refrigerant data collection and the real-time performance of data transmission are improved. Through the dynamic temperature prediction model and the coupling analysis of heat load-refrigerant flow, the fault type and source are accurately deduced. Machine learning deeply mines historical fault data and combines real-time monitoring to achieve efficient fault classification and health assessment. Finally, by real-time collecting the operating parameters of the air conditioning system and constructing a dynamic temperature prediction model based on the physical model, fault deduction is realized, and the diagnostic accuracy and response speed are improved.

[0109] Embodiment 2, referring to Table 1, is the second embodiment of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the file encryption method is given.

[0110] Three groups of air conditioning systems on a certain urban subway line are selected as test objects (numbered A / B / C), where groups A / B adopt the existing technology (based on Wi-Fi communication + threshold warning), and group C adopts the solution of the present invention. The test period is 30 days, covering complex working conditions such as high temperature, high humidity, and morning and evening rush hours.

[0111] First, for groups A / B: Deploy traditional temperature and humidity sensors (accuracy of ±1°C), refrigerant pressure sensors (range 0-5 MPa, ±2% FS), and Wi-Fi communication modules (rate 54 Mbps, packet loss rate 8%-15%).

[0112] Next, Group C: Adopt a distributed sensor architecture (temperature ±0.5°C, humidity ±3%RH, refrigerant pressure ±0.5%FS), an NB-IoT communication module (bandwidth 180kHz, transmit power 23dBm), and an edge computing unit (dual-core ARM Cortex-A72, 1.5GHz); Group C dynamically calculates the heat load, combines the carriage volume (120m 3 ) and the specific heat capacity of air to predict the temperature change trend.

[0113] Then, when the refrigerant flow deviation > 15%, trigger the physical model, verify the pressure drop, and combine the machine learning model (confidence > 90%) to locate the fault source.

[0114] Finally, Group C generates PID control parameters through the genetic algorithm, adjusts the compressor frequency (20 - 60Hz) and the fan speed, and the response time < 3 seconds (manual intervention in Group A / B requires more than 30 seconds).

[0115] Specifically, it is shown in Table 1 below:

[0116] Table 1 Comparison Table of Experimental Data

[0117]

[0118] Through the data analysis in the above table, the advantages of the solution of the present invention are as follows:

[0119] The prior art A / B uses Wi-Fi communication, and due to the Doppler effect, the signal decays when the train moves at a high speed (80km / h), and the peak packet loss rate reaches 15%. The present invention uses the NB-IoT narrowband technology (anti-interference coding + retransmission mechanism), and the communication stability is improved to 99.1% under the same working conditions, ensuring the complete transmission of data.

[0120] The traditional solution relies on threshold alarms (such as alarm when the refrigerant pressure > 4MPa), and cannot distinguish short-term fluctuations (such as frequent opening and closing of doors) from real faults. The present invention quantifies the heat load change trend through a dynamic model, combines the LSTM network to analyze the historical fault characteristics, and reduces the misjudgment rate from 28% to 5.3%. For example, during the test, the refrigerant flow has a short-term anomaly (deviation 18%) due to sensor noise. The physical model verifies the relationship between the pressure drop and the flow rate, confirms that there is no actual leakage, and avoids false triggering of shutdown.

[0121] The prior art requires manual confirmation of faults and then adjustment of parameters, while the present invention generates control instructions in real time through edge computing (genetic algorithm optimizes PID parameters), reducing the compressor frequency adjustment delay by 90%. For example, when the carriage temperature deviates from the set value (25°C → 28°C) due to a sudden increase in passengers, Group C increases the refrigerant flow rate from 0.8kg / s to 1.2kg / s within 3 seconds, and the temperature recovery rate reaches 0.5°C / min (Group A / B requires more than 5 minutes).

[0122] In the traditional solution, the compressor starts and stops frequently due to communication delay (the number of starts and stops per day is 45 times). However, in the present invention, the dynamic temperature prediction model is used to predict the heat load in advance, and the smooth control strategy is adopted to reduce the number of starts and stops to 12 times per day, extending the equipment life and reducing energy consumption.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A remote intelligent monitoring method for the health status of a rail transit vehicle air conditioning system, characterized in that: including Initializing the rail transit air conditioning system and collecting data in real time, and sending it to edge computing using wireless communication; Preprocessing the received data, comparing it with preset working parameters, and calculating the current working state of the air conditioning system; Constructing a physical model to conduct fault deduction on the current working state of the air conditioning system, simulating the operation of the air conditioning system through heat load prediction and pressure change analysis and comparing it with real-time data, and generating a fault deduction report; Inputting the fault deduction report into a machine learning algorithm for analysis, and judging the fault type and fault source based on historical fault data and the working mode of the air conditioning system; Analyzing through a machine learning algorithm, and combining with remote intelligent adaptive control to update the current working state of the air conditioning system.

2. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 1, characterized in that: Initializing the rail transit air conditioning system and collecting data in real time, and sending it to edge computing using wireless communication, including: Initializing the air conditioning system using an embedded control platform, collecting temperature, humidity, and refrigerant data in real time through distributed sensors and storing them in the control unit cache, and transmitting them to edge computing using narrowband Internet of Things.

3. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 2, wherein: Preprocessing the received data, comparing it with preset working parameters, and calculating the current working state of the air conditioning system. The specific steps are as follows: Normalizing the temperature, humidity, and refrigerant data, and extracting the preset working parameters built in edge computing; Adopting deviation calculation, outputting the deviation result and marking abnormalities, and evaluating the health state and abnormal state of the air conditioning system in combination with parameter weights.

4. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 3, characterized in that: Constructing a physical model to conduct fault deduction on the current working state of the air conditioning system, simulating the operation of the air conditioning system through heat load prediction and pressure change analysis and comparing it with real-time data, and generating a fault deduction report. The specific steps are as follows: Constructing a dynamic physical model, coupling the changes in heat load and refrigerant flow rate, and generating a dynamic temperature prediction model; Updating the dynamic temperature prediction parameters through real-time data, correcting the changes in heat load and refrigerant pressure, and optimizing the dynamic temperature prediction model in real time; Combining the analysis of the temperature deviation trend of the real-time collected temperature data, judging the operating state based on the change in refrigerant pressure, classifying and locating faults, and generating a fault deduction report.

5. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 4, characterized in that: Constructing a dynamic physical model, coupling the changes in heat load and refrigerant flow rate, and generating a dynamic temperature prediction model. The specific steps are as follows: By identifying the heat load, refrigerant pressure, and refrigerant flow rate under the current working state, combining the specific heat capacity of air and the volume of the carriage, constructing the thermodynamic core relationship of the temperature change in the carriage; Based on the thermodynamic core relationship, by dynamically balancing heat input, output, and loss, using the dynamic integral form to quantify the change trend of temperature over time, and constructing a dynamic temperature prediction model.

6. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 5, characterized in that: Combining the analysis of the temperature deviation trend of the real-time collected temperature data, judging the operating state based on the change in refrigerant pressure, classifying and locating faults, and generating a fault deduction report. The specific steps are as follows: Based on the dynamic temperature prediction model, comparing the real-time collected data with the predicted value, deducing the fault type, and displaying the abnormal points through a time series graph; Evaluating the state of the air conditioning system using the fault type result, classifying and summarizing the fault types and causes, and combining with a multi-parameter trend graph to display the fault evolution process and display the abnormal points, and generating a fault deduction report.

7. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 6, characterized in that: Input the fault deduction report into a machine learning algorithm for analysis, and determine the fault type and source based on historical fault data and the working mode of the air conditioning system, including: Extract the temperature, pressure, and refrigerant fault parameters from the fault deduction report, perform normalization processing, and generate a multi-dimensional feature vector; Use a physical simulation model to establish a model to simulate the fault state, and use a machine learning algorithm to classify the fault type and infer the fault source.

8. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 7, characterized in that: The analysis through the machine learning algorithm, combined with remote intelligent adaptive control, updates the current working state of the air conditioning system, including: Generate a control strategy and output an adjustment instruction by combining the output fault type and source with the current working state parameters; Real-time remotely monitor the working state of the air conditioning system and compare it with the expected value, evaluate the result through a real-time feedback mechanism, and adjust the state of the air conditioning system by updating the strategy.

9. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 3, characterized in that: Evaluating the healthy state and abnormal state of the air conditioning system by combining parameter weights includes the following steps: The dynamic threshold is calculated based on the mean and standard deviation of the health score, and is dynamically adjusted through an adjustment coefficient to adapt to the health state evaluation under different working conditions.

10. The remote intelligent monitoring method for the health status of the rail transit vehicle air conditioning system according to claim 7, characterized in that: The analysis through the machine learning algorithm includes the following steps: Adopt a long short-term memory network as the machine learning algorithm, and judge the fault type and source by analyzing the multi-dimensional feature vector in the fault deduction report.

Images