Refrigerant leakage detection method, device and equipment and medium
By constructing training samples and abnormal detection algorithms, the accuracy and reliability of refrigerant leakage detection are solved, real-time and accurate detection of refrigerant leakage is achieved, and user experience is improved.
Patent Information
- Application Number
- CN202510576962.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-06
- Publication Date
- 2025-07-11
AI Technical Summary
In the prior art, the accuracy and reliability of refrigerant leakage detection are low, and it cannot cover different operating scenarios of air conditioners, affecting passenger comfort and vehicle performance.
By obtaining the operating data of the air conditioner, building training samples, using anomaly detection algorithm to determine normal samples and abnormal samples, and training the refrigerant detection model based on these samples to achieve real-time detection of refrigerant leakage.
It improves the accuracy and reliability of refrigerant leakage detection, reduces misjudgment and missed inspection, and improves user experience.
Smart Images
Figure CN120287794A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of vehicle detection, and in particular, to a refrigerant leakage detection method, device, equipment and medium. Background Art
[0002] In the field of new energy vehicles, the refrigeration system of the air conditioner, as an important configuration for improving riding comfort, its performance and stability are directly related to the driving and riding experience of users. It undertakes the important task of transferring heat and achieving the refrigeration effect through the key medium of refrigerant. However, in the actual application process, due to the influence of various factors, such as road surface bumps, slight component expansion, poor welding or loose connections, etc., refrigerant leakage may occur. This will not only reduce the refrigeration effect of the air conditioner system, increase energy consumption, but also may cause potential damage to other systems of the vehicle and reduce the user experience. The conventional detection methods for refrigerant leakage mainly include visual inspection or pressure detection, etc., but there is often a problem of long detection cycle. Therefore, it is particularly important to develop a method that can detect refrigerant leakage in real time and accurately. In the related art, in order to shorten the detection cycle, it usually relies on comparing the data of a single sensor related to the refrigerant with a fixed threshold to determine whether the refrigerant leaks.
[0003] However, in actual applications, the refrigerant circulation of the air conditioner is often interfered by various factors. Only through a single threshold comparison, different operating scenarios of the air conditioner cannot be covered, resulting in low accuracy and reliability of refrigerant leakage detection, which will in turn affect the comfort of passengers and may also cause damage to the overall performance of the vehicle. Summary of the Invention
[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a comprehensive review, nor is it intended to identify key / important elements or delineate the scope of protection of these embodiments. Instead, it serves as a preamble to the subsequent detailed description.
[0005] In view of the above-mentioned disadvantages of the prior art, this application discloses a refrigerant leakage detection method, device, equipment and medium to solve the above technical problem of how to improve refrigerant leakage detection.
[0006] In a first aspect, the present application provides a refrigerant leakage detection method, which includes: obtaining the operation data of the air conditioner in a vehicle, where the operation data is the node data of each sampling point in the refrigerant circulation loop, and the node data includes the temperature data and pressure data corresponding to different opening degrees of the refrigerant circulation loop; calculating the mean values of the pressure data and temperature data of each sampling point in the operation data respectively according to a preset first time period to obtain a plurality of training samples; performing anomaly detection on each training sample to determine normal samples and abnormal samples, where the abnormal samples indicate refrigerant leakage; training a preset detection model based on the normal samples and abnormal samples to obtain a refrigerant detection model for detecting refrigerant leakage in a vehicle to be tested.
[0007] In an embodiment of the present application, calculating the mean values of the pressure data and temperature data of each sampling point in the operation data respectively according to a preset first time period to obtain a plurality of training samples includes: aggregating the operation data of the same vehicle according to each preset first time period to obtain a plurality of data sets, where the data sets include the operation data of the vehicle within the same preset first time period; calculating the mean values of the pressure data and temperature data of each sampling point in each data set respectively; performing standardization processing on the mean values of the pressure data and the mean values of the temperature data in each data set to construct each training sample.
[0008] In an embodiment of the present application, performing anomaly detection on each training sample to determine normal samples and abnormal samples includes: performing anomaly detection on each training sample to determine the anomaly score of each training sample; if the anomaly score of a training sample is greater than a preset score, determining that the training sample is an abnormal sample; if the anomaly score of a training sample is less than or equal to the preset score, determining that the training sample is a normal sample.
[0009] In an embodiment of the present application, detecting refrigerant leakage in a vehicle to be tested includes: obtaining the current operation data of the air conditioner in the vehicle to be tested; if the compressor of the air conditioner operates within a preset power range, calculating the mean values of the pressure data and temperature data of each sampling point in the current operation data as a detection sample; inputting the detection sample into the refrigerant detection model for detection, and determining whether the vehicle to be tested has refrigerant leakage based on the detection result.
[0010] In an embodiment of the present application, determining whether the vehicle to be tested has refrigerant leakage based on the detection result includes: determining the number of times the detection result is abnormal within a preset second time period; if the number of times the detection result is abnormal reaches a preset number, determining that the vehicle to be tested has refrigerant leakage, where the preset second time period is greater than the preset first time period; if the number of times the detection result is abnormal is less than the preset number, determining that the vehicle to be tested has no refrigerant leakage.
[0011] In one embodiment of the present application, the operation data of the air conditioner in the vehicle is obtained, including: obtaining the operation data of the air conditioners in each vehicle within a preset historical time; screening the operation data corresponding to the compressor of the air conditioner operating within a preset power range; dividing the operation data according to the unique identification code of each vehicle to determine the screened operation data corresponding to each vehicle.
[0012] In one embodiment of the present application, after obtaining the operation data of the air conditioner in the vehicle, it further includes: calculating the median of the pressure data and the temperature data of each sampling point respectively; identifying the missing values and abnormal values of each pressure data and each temperature data respectively; filling the missing values and abnormal values of the same pressure data based on the median, and filling the missing values and abnormal values of the same temperature data based on the median.
[0013] In a second aspect, the present application provides a refrigerant leakage detection device, which includes: an acquisition module for obtaining the operation data of the air conditioner in the vehicle, where the operation data is the node data of each sampling point in the refrigerant circulation loop, and the node data includes the temperature data and pressure data corresponding to different opening degrees of the refrigerant circulation loop; a calculation module for calculating the mean values of the pressure data and the temperature data of each sampling point in the operation data respectively according to a preset first time period to obtain a plurality of training samples; a detection module for performing anomaly detection on each training sample to determine normal samples and abnormal samples, where the abnormal samples indicate that refrigerant leakage has occurred; a training module for training a preset detection model based on the normal samples and the abnormal samples to obtain a refrigerant detection model for detecting refrigerant leakage in a vehicle to be tested.
[0014] In a third aspect, the present application further provides an electronic device, which includes: a processor, a memory, and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute the computer program stored in the memory to implement the method in the above embodiment.
[0015] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor of the computer, the computer is enabled to execute the method in the above embodiment.
[0016] Advantages of the present application: The present application proposes a refrigerant leakage detection method, device, equipment and medium. By obtaining the operation data of the air conditioner in the vehicle, the operation data being the node data of each sampling point in the refrigerant circulation loop, and the node data including the temperature data and pressure data corresponding to different opening degrees of the refrigerant circulation loop; calculating the mean values of the pressure data and temperature data of each sampling point in the operation data respectively according to a preset first time period to obtain a plurality of training samples, so that the training samples cover various types of data during the operation of the air conditioner and the covered operation scenarios are more comprehensive; performing anomaly detection on each training sample to determine normal samples and abnormal samples, where the abnormal samples indicate refrigerant leakage; training a preset detection model based on the normal samples and abnormal samples to obtain a refrigerant detection model for detecting refrigerant leakage in a vehicle to be tested. In this way, by constructing training samples in combination with different data affecting refrigerant circulation during the operation of the air conditioner, it is possible to more effectively and comprehensively reflect the operation state of the air conditioner, which helps the trained refrigerant detection model learn more extensive and reliable features, thereby improving the accuracy and reliability of refrigerant leakage detection.
[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings:
[0019] Figure 1 is a schematic diagram of a refrigerant circulation loop shown in an exemplary embodiment of the present application;
[0020] Figure 2 is a flowchart of a refrigerant leakage detection method shown in an exemplary embodiment of the present application;
[0021] Figure 3 is a schematic diagram of a data processing flow shown in an exemplary embodiment of the present application;
[0022] Figure 4 is a schematic diagram of a model prediction flow shown in an exemplary embodiment of the present application;
[0023] Figure 5 is a block diagram of a refrigerant leakage detection device shown in an exemplary embodiment of the present application;
[0024] Figure 6It is a schematic structural diagram of a computer system suitable for implementing the electronic device of the present application shown in an exemplary embodiment of the present application. Detailed implementation manners
[0025] The following will describe the implementation manners of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for explaining the present application, rather than limiting the protection scope of the present application.
[0026] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.
[0027] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.
[0028] The vehicle air conditioner is a key system in an automobile. Its main function is to adjust the temperature and humidity inside the vehicle to create a comfortable environment for the driver and passengers. For example, through the operation of the refrigerant cycle, the air conditioning system can absorb the heat inside the vehicle and discharge it outside the vehicle, thereby reducing the temperature inside the vehicle; the refrigerant, also known as the refrigerant or refrigerant fluid, is the medium used to transfer heat energy in the air conditioning system. In the refrigerant cycle loop, the refrigerant realizes the refrigeration effect by absorbing, transferring, and releasing heat. Among them, the refrigerant cycle loop is a closed circulation path for transferring heat energy in the automotive air conditioning system, which is mainly composed of a compressor, a condenser, a liquid storage tank and a dryer, an expansion valve (or throttling device), an evaporator, and the pipelines connecting these components.
[0029] Please refer to Figure 1 , which is a schematic diagram of a simplified refrigerant cycle loop shown in an exemplary embodiment of the present application. Figure 1The solid line in it represents the liquid phase of the refrigerant, and the dashed line represents the gaseous phase of the refrigerant. The air conditioner realizes cooling or heating inside the vehicle through the phase change of the refrigerant. The working principle of the refrigerant circulation circuit is as follows: The low-temperature and low-pressure gaseous refrigerant from the in-vehicle evaporator is compressed by the compressor into a high-temperature and high-pressure gaseous refrigerant and then enters the out-of-vehicle condenser, and condenses into a medium-temperature and high-pressure liquid refrigerant after releasing heat in the condenser; the heat released by the refrigerant is carried away by the out-of-vehicle air flowing through the condenser, and the liquid refrigerant flowing out of the condenser is filtered and then flows into the expansion valve. Subsequently, through the expansion valve, it throttles and reduces pressure, becoming a low-temperature and low-pressure liquid refrigerant; then the low-temperature and low-pressure liquid refrigerant flows into the in-vehicle evaporator and evaporates into a gaseous state inside the evaporator to absorb the heat inside the vehicle. Among them, the evaporation temperature of the refrigerant inside the evaporator is lower than the outdoor ambient temperature. Therefore, the refrigerant will absorb the heat in the air sent into the compartment, making the air entering the compartment become a gas with a lower temperature, thereby producing a cooling effect; finally, the gaseous refrigerant at the outlet of the evaporator is sucked into the compressor again, and such a cycle forms a refrigeration cycle.
[0030] The technical solution of the embodiment of the present application relates to the above technology, and a refrigerant leakage detection method is proposed to improve the accuracy and reliability of refrigerant leakage detection.
[0031] Please refer to Figure 2 , which is a flowchart of a refrigerant leakage detection method shown in an exemplary embodiment of the present application. As Figure 2 shown, in an exemplary embodiment, the refrigerant leakage detection method at least includes steps S210 to S240, which are introduced in detail as follows:
[0032] Step S210, obtain the operation data of the air conditioner in the vehicle. The operation data is the node data of each sampling point in the refrigerant circulation circuit, and the node data includes the temperature data and pressure data corresponding to different opening degrees of the refrigerant circulation circuit.
[0033] In an embodiment of the present application, during the working process of the refrigerant circulation circuit, both temperature and pressure affect the working state of the refrigerant circulation and change with the flow of the refrigerant. For example, when the refrigerant leaks, the temperature near the leakage point may change abnormally, such as a decrease or increase in temperature, and it may also cause pressure imbalance in the refrigerant circulation circuit, manifested as a decrease or an increase in pressure fluctuation. Moreover, the opening degree of the refrigerant circulation circuit (such as the opening degree of the throttle valve) affects the flow rate and pressure distribution of the refrigerant. Therefore, it is necessary to collect the temperature data and pressure data at different opening degrees to more comprehensively and deeply understand the performance of the refrigerant circulation circuit under different working conditions, so as to more accurately judge whether there is refrigerant leakage. In addition, by combining the data of multiple sampling points, multiple sampling points can more comprehensively cover the refrigerant circulation circuit, ensuring that each key part can be monitored, which helps to reduce the missed detection caused by the monitoring blind area and improve the reliability of detection.
[0034] In an embodiment of the present application, the positions of multiple sampling points are usually set near the key parts and potential leakage points of the refrigerant circulation circuit. For example, sampling points are set at the inlet and outlet of the compressor, at the inlet and outlet of the condenser, at the inlet and outlet of the evaporator, before and after the expansion valve, at the connecting pipes and joints, or at other key components (such as dryers, filters, etc.).
[0035] In an embodiment of the present application, taking Figure 1 the set sampling points shown as an example, Figure 1 the positions of the 6 sampling points in it are respectively before and after the expansion valve (1 and 2 marked by circles), at the outlet of the in-vehicle evaporator (3 marked by circles), at the inlet and outlet of the compressor (4 and 5 marked by circles), and at the inlet of the out-of-vehicle condenser (6 marked by circles). Among them, the pressure, temperature, and the opening degree before the expansion valve at each sampling point can be collected through sensors, so as to determine the temperature data and pressure data at different opening degrees. Figure 1 The collected data in it is shown in Table 1:
[0036] Table 1
[0037]
[0038] As can be seen from Table 1, under the known compressor power C1 of the air conditioner, Figure 1 the sampling point set at position 1 (before the expansion valve) in it can sample and obtain the temperature data P1_t and pressure data P1_p at the opening degree P1_f, the sampling point set at position 1 (after the expansion valve) can sample and obtain the opening degree data P1_f, temperature data P2_t, and pressure data P2_p, the sampling point set at position 3 (at the outlet of the in-vehicle evaporator) can sample and obtain the temperature data P3_t and pressure data P3_p, the sampling point set at position 4 (at the inlet of the compressor) can sample and obtain the temperature data P4_t and pressure data P5_p, the sampling point set at position 5 (at the outlet of the compressor) can sample and obtain the temperature data P5_t and pressure data P5_p, and the sampling point set at position 6 (at the inlet of the out-of-vehicle condenser) can sample and obtain the temperature data P6_t and pressure data P6_p, a total of 13 data. Among them, by correlating the opening degree data with the temperature data and pressure data, all processing of the opening degree data with the temperature data and pressure data can be carried out, jointly constituting the training samples.
[0039] In an embodiment of the present application, in order to further improve the reliability of training, the operation data of each vehicle of the same vehicle model is obtained to enrich the operation data, so that the training samples can cover a more comprehensive operation scenario and be targeted, which helps to improve the accuracy of the subsequent refrigerant detection model. Moreover, when the compressor power is abnormal, it may indirectly reflect that there is a problem with the air conditioning system, and these problems may sometimes be related to refrigerant leakage. Therefore, the operation data of the air conditioner in each vehicle within a preset historical time is obtained; the operation data corresponding to the compressor of the air conditioner operating within a preset power range is screened; the operation data is divided according to the unique identification code of each vehicle to determine the screened operation data corresponding to each vehicle. In this way, while enriching the operation scenario of the operation data, screening the operation data based on the power of the compressor can greatly exclude invalid data, ensure that the data for subsequent analysis is more accurate, and reduce the data volume for subsequent calculation and training.
[0040] In an embodiment of the present application, the preset historical time can be adjusted according to actual needs. For example, it can be set within one week, and there is no limitation on this.
[0041] In an embodiment of the present application, the preset power range is usually set as the fluctuation range of the rated power of the compressor. For example, the preset power range is set as the fluctuation range of plus or minus 5% of the rated power of the compressor. The reason is that through experiments, it is found that when the compressor is at the rated power, refrigerant leakage is more likely to occur, and it can also be adjusted according to actual needs.
[0042] In an embodiment of the present application, since abnormalities may occur during actual collection of operation data, in order to ensure the integrity and accuracy of the operation data, after obtaining the operation data, it is necessary to calculate the median of the pressure data and the temperature data of each sampling point respectively; identify the missing values and abnormal values of each of the pressure data and each of the temperature data; fill in the missing values and abnormal values of the same pressure data based on the median, and fill in the missing values and abnormal values of the same temperature data based on the median.
[0043] In an embodiment of the present application, the pressure data and temperature data of each sampling point can be respectively subjected to anomaly identification based on the standard deviation method (the Pauta criterion), or other anomaly detection methods can be used for anomaly identification. Taking the standard deviation method as an example, for the pressure data and temperature data of each sampling point, their mean values and standard deviations are respectively calculated, and a judgment threshold (usually the mean value plus or minus an appropriate multiple of the standard deviation) is selected to define the range of outliers. Then, each pressure data and each temperature data are respectively compared with their corresponding judgment thresholds. If it exceeds the judgment threshold, it is determined as an outlier. In addition, considering that the median is a robust statistic and is not sensitive to outliers, it can be used as a benchmark for anomaly identification and missing value filling. The median of the pressure data or temperature data of the same sampling point is directly used to fill the corresponding missing value, and the median of the pressure data or temperature data of the same sampling point is also used to replace the corresponding outlier. Among them, the processing of the median, outlier, and lack value of the pressure data and temperature data of each sampling point is relatively independent. Moreover, the calculation of the above mean value, standard deviation, and median is performed on all the obtained operation data and is not related to the preset first time period.
[0044] Please refer to Figure 3 , which is a schematic diagram of the data processing flow shown in an exemplary embodiment of the present application. As Figure 3 shown, the operation data of the air conditioners in each vehicle within a week is obtained, and then the operation data is filtered according to the compressor power of the air conditioner, that is, the operation data with the compressor power within the preset power range is screened out, and the missing values and outliers are filled with the median. According to the vin (identification number) of the vehicle, the screened operation data is aggregated every minute, and the aggregated operation data of each minute is standardized. Among them, Figure 3 the data processing flow in
[0045] Step S220, respectively calculate the mean values of the pressure data and temperature data of each sampling point in the operation data according to the preset first time period to obtain a plurality of training samples.
[0046] Specifically, in order to improve the training efficiency of the subsequent preset detection model, the operation data of the same vehicle is aggregated according to each preset first time period to obtain a plurality of data sets. The data set includes the operation data of the vehicle within the same preset first time period; the mean values of the pressure data and temperature data of each sampling point in each data set are respectively calculated; the mean values of the pressure data and the mean values of the temperature data in each data set are standardized to construct each training sample.
[0047] In an embodiment of the present application, taking the preset first time period set to 1 minute as an example, each vehicle has a unique identification code. Based on the identification code, the operation data of the same vehicle is divided, and then the operation data of the same vehicle within the same minute is aggregated every minute to obtain a data set, so that the data set can reflect the overall operation state of the vehicle within one minute. For example, if the sampling frequency of the operation data is once per second, then there are 60 operation data within each minute. The mean values of the pressure data and the temperature data are respectively calculated for each sampling point (i.e., each time point within each preset first time period) in each data set, which means that within each time period, the mean value of the pressure data and the mean value of the temperature data of each sampling point will be obtained, which helps to smooth the fluctuations in the data and reduce noise.
[0048] In an embodiment of the present application, the mean values of the pressure data and the temperature data are normalized. The purpose is to convert the data into a form with a specific mean value (usually 0) and standard deviation (usually 1) to eliminate the influence of the differences in dimension and value range between different features. In this way, the constructed training samples can be more suitable for the training of the model, the convergence speed of the model can be accelerated, the performance of the model can be improved, and thus the accuracy of refrigerant leakage detection can be improved. Schematically, the expression of mean normalization is as follows:
[0049] N(x i )=(x i -μ) / σ Equation (1)
[0050] Among them, in Equation (1), represents the mean value of a target data within the i-th preset first time period, represents the mean value of the standardized target data, represents the average value of the mean values of a target data within each preset first time period, represents the standard deviation of a target data within the entire duration (such as one week), and the target data is the temperature data or pressure data of a sampling point. In addition, the target data can also be the opening data.
[0051] In an embodiment of the present application, the training samples constructed based on the operation data in Table 1 are shown in Table 2:
[0052] Table 2
[0053]
[0054] Among them, each of Samples 1 to n in Table 2 represents the mean values of the normalization of 13 target data at 6 sampling points within different preset first time periods.
[0055] In an embodiment of the present application, other standardized data preprocessing methods can also be adopted, such as MaxAbs standardization (Maximum Absolute Value Standardization), Robust standardization (Robust Standardization), etc., which are not limited herein.
[0056] Step S230: Perform anomaly detection on each training sample to determine normal samples and abnormal samples, where the abnormal samples indicate refrigerant leakage.
[0057] Specifically, perform anomaly detection on each training sample to determine the anomaly score of each training sample; if the anomaly score of the training sample is greater than the preset score, determine the training sample as an abnormal sample; if the anomaly score of the training sample is less than or equal to the preset score, determine the training sample as a normal sample.
[0058] In an embodiment of the present application, anomaly detection can be performed on training samples based on Isolation Forest (iForest), or other anomaly detection algorithms can also be used. The Isolation Forest algorithm uses the binary search tree structure of isolation trees to isolate samples. Since the number of outliers is small and the distance from most samples is far, outliers are more likely to be isolated, that is, outliers will be closer to the root node of the isolation tree, while normal values will be farther from the root node. That is to say, the preset detection model can be an isolation forest model constructed in advance. Input each training sample into the isolation forest model, calculate the anomaly score of each training sample. The higher the anomaly score, the more likely the training sample is an outlier. Therefore, when the anomaly score exceeds the preset score, the training sample is used as an abnormal sample. In this way, the efficiency and accuracy of anomaly detection help to improve the accuracy of subsequent refrigerant detection.
[0059] In an embodiment of the present application, after detecting the training samples, in order to further improve the detection accuracy, on-site inspections can also be carried out on the vehicles marked as abnormal (i.e., abnormal samples detected as refrigerant leakage) to confirm whether there are errors in the detection results. If there are errors, delete the training sample to avoid its parameters from being used in subsequent model training, and retrain the preset detection model with the updated training samples.
[0060] Step S240: Train the preset detection model based on the normal samples and abnormal samples to obtain a refrigerant detection model for detecting refrigerant leakage in the vehicle to be tested.
[0061] Specifically, obtain the current operating data of the air conditioner in the vehicle to be tested; if the compressor of the air conditioner operates within a preset power range, calculate the mean values of the pressure data and temperature data at each sampling point in the current operating data as the detection samples; input the detection samples into the refrigerant detection model for detection, and determine whether the vehicle to be tested has a refrigerant leak based on the detection results.
[0062] In an embodiment of the present application, before using the mean value as the detection sample, in order to avoid incomplete and inaccurate currently obtained operating data, after calculating the mean value, it is also necessary to identify missing values and outliers in the mean values of the pressure data and temperature data at each sampling point in the current operating data, and use the medians corresponding to the pressure data and temperature data at the same sampling point calculated and recorded in the historical operating data to fill them respectively, so as to ensure the integrity and accuracy of the detection samples, which helps to improve the accuracy and reliability of refrigerant leak detection.
[0063] Specifically, determine the number of times the detection result is abnormal within a preset second time period; if the number of times the detection result is abnormal reaches a preset number, it is determined that the vehicle to be tested has a refrigerant leak, and the preset second time period is greater than the preset first time period; if the number of times the detection result is abnormal is less than the preset number, it is determined that the vehicle to be tested has not had a refrigerant leak.
[0064] In an embodiment of the present application, in order to more accurately determine whether the vehicle has actually had a refrigerant leak, a consideration of the time dimension is introduced. Every preset first time period, the refrigerant detection model is used to detect the current operating data in the vehicle to be tested, and the detection result is normal or abnormal. And within the preset second time period, the number of times the detection result is abnormal is counted. The preset second time period cannot be set too short. The purpose is to capture possible refrigerant leak events and avoid misjudgment caused by short-term fluctuations or false alarms, so as to further improve the accuracy and reliability of refrigerant leak detection. Taking the preset first time period as 1 minute, the preset second time period as 20 minutes, and the preset number as 11 times as an example, continuously monitor the current operating data of the air conditioner in the vehicle to be tested. If within 20 minutes, the detection results in 12 one-minute intervals are all abnormal, that is, the number of times the detection result is abnormal reaches 12 times, it is determined that the vehicle to be tested has a refrigerant leak.
[0065] In an embodiment of the present application, if it is determined that the vehicle to be tested has a refrigerant leak, then a warning message is generated to prompt that the vehicle to be tested needs to be inspected and repaired, which greatly improves the user experience.
[0066] Please refer to Figure 4 For a schematic diagram of a model prediction process shown in an exemplary embodiment of the present application. As Figure 4As shown, first, data is collected in real time, that is, the current operating data of the air conditioner in the vehicle to be tested is obtained in real time. Then, through a data processing model, that is, the average value of each temperature and pressure data in the current operating data is calculated respectively, and outliers and missing values are filled to form a detection sample. Finally, it is input into a judgment model, that is, a refrigerant detection model, to determine whether refrigerant leakage (i.e., leakage) has occurred in the vehicle to be tested. If there is leakage, an external notification is made; if there is no leakage, no processing is done.
[0067] Please refer to Figure 5 , which is a block diagram of a refrigerant leakage detection device shown in an exemplary embodiment of the present application. As Figure 5 shown, in an exemplary embodiment, the refrigerant leakage detection device at least includes an acquisition module 510, a calculation module 520, a detection module 530, and a training module 540, which are introduced in detail as follows:
[0068] The acquisition module 510 is used to acquire the operating data of the air conditioner in the vehicle. The operating data is the node data of each sampling point in the refrigerant circulation loop, and the node data includes the temperature data and pressure data corresponding to different opening degrees of the refrigerant circulation loop;
[0069] The calculation module 520 is used to calculate the average value of the pressure data and temperature data of each sampling point in the operating data according to a preset first time period to obtain a plurality of training samples;
[0070] The detection module 530 is used to perform anomaly detection on each training sample to determine normal samples and abnormal samples. The abnormal samples indicate that refrigerant leakage has occurred;
[0071] The training module 540 is used to train a preset detection model based on the normal samples and abnormal samples to obtain a refrigerant detection model for detecting refrigerant leakage in the vehicle to be tested.
[0072] It should be noted that the refrigerant leakage detection device provided in the above embodiment and the refrigerant leakage detection method provided in the above embodiment belong to the same concept. The content of the operations performed by each module has been described in detail in the method embodiment, and will not be repeated here.
[0073] The present application also provides an electronic device, including: a processor, a memory, and a communication bus; the communication bus is used to connect the processor and the memory; the processor is used to execute the computer program stored in the memory to implement the refrigerant leakage detection method as in the above embodiment.
[0074] Please refer to Figure 6 , which shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiment of the present application. It should be noted that Figure 6The computer system 600 of the illustrated electronic device is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present application.
[0075] As Figure 6 shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage section 608 into the random access memory (RAM) 603, such as executing the method in the above embodiments. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0076] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area NetworK) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read from it can be installed into the storage section 608 as needed.
[0077] Specifically, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, various functions defined in the system of the present application are executed.
[0078] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is enabled to execute the vehicle-end data forwarding method as described above. The computer-readable storage medium may be included in the electronic device described in the foregoing embodiments, or may exist alone without being assembled into the electronic device.
[0079] It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable computer program. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program included on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0080] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, and the above-mentioned module, segment of a program, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.
[0081] The units involved in the embodiments described in the present application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not, in some cases, constitute a limitation on the unit itself.
[0082] The above embodiments are only used to exemplarily illustrate the principles and effects of the present application, rather than to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in the present application should still be covered by the claims of the present application.
Claims
1. A refrigerant leakage detection method, characterized in that, The method includes: Obtaining the operation data of the air conditioner in the vehicle, where the operation data is the node data of each sampling point in the refrigerant circulation loop, and the node data includes the temperature data and pressure data corresponding to different opening degrees of the refrigerant circulation loop; Calculating the average value of the pressure data and the temperature data of each sampling point in the operation data according to a preset first time period to obtain a plurality of training samples; Performing anomaly detection on each of the training samples to determine normal samples and abnormal samples, where the abnormal samples indicate refrigerant leakage; Training a preset detection model based on the normal samples and the abnormal samples to obtain a refrigerant detection model for detecting refrigerant leakage in a vehicle to be tested.
2. The refrigerant leakage detection method according to claim 1, characterized in that The calculating the average value of the pressure data and the temperature data of each sampling point in the operation data according to a preset first time period to obtain a plurality of training samples includes: Aggregating the operation data of the same vehicle according to each preset first time period to obtain a plurality of data sets, where the data sets include the operation data of the vehicle within the same preset first time period; Calculating the average value of the pressure data and the temperature data of each sampling point in each data set respectively; Performing normalization processing on the average value of the pressure data and the average value of the temperature data in each data set to construct each training sample.
3. The refrigerant leakage detection method according to claim 1, wherein, The performing anomaly detection on each of the training samples to determine normal samples and abnormal samples includes: Performing anomaly detection on each of the training samples to determine the anomaly score of each training sample; If the anomaly score of the training sample is greater than a preset score, determining that the training sample is the abnormal sample; If the anomaly score of the training sample is less than or equal to the preset score, determining that the training sample is the normal sample.
4. The refrigerant leakage detection method according to claim 1, wherein The detecting refrigerant leakage in a vehicle to be tested includes: Obtaining the current operation data of the air conditioner in the vehicle to be tested; If the compressor of the air conditioner operates within a preset power range, calculating the average value of the pressure data and the temperature data of each sampling point in the current operation data as a detection sample; Inputting the detection sample into the refrigerant detection model for detection, and determining whether the vehicle to be tested has refrigerant leakage based on the detection result.
5. The refrigerant leakage detection method according to claim 4, characterized in that, The determining whether the vehicle to be tested has refrigerant leakage based on the detection result includes: Determining the number of times the detection result is abnormal within a preset second time period; If the number of times the detection result is abnormal reaches a preset number, determining that the vehicle to be tested has refrigerant leakage, where the preset second time period is greater than the preset first time period; If the number of times the detection result is abnormal is less than the preset number, determining that the vehicle to be tested has no refrigerant leakage.
6. The refrigerant leakage detection method according to claim 4, characterized in that, The obtaining the operation data of the air conditioner in the vehicle includes: Obtaining the operation data of the air conditioner in each vehicle within a preset historical time; Screening the operation data corresponding to when the compressor of the air conditioner operates within the preset power range; Divide the operation data according to the unique identification code of each vehicle to determine the filtered operation data corresponding to each vehicle.
7. The refrigerant leakage detection method according to claim 2, characterized in that, After obtaining the operation data of the vehicle air conditioner, it further includes: Calculate the median of the pressure data and the temperature data at each sampling point respectively; Identify the missing values and outliers of each pressure data and each temperature data respectively; Fill in the missing values and outliers of the same pressure data based on the median, and fill in the missing values and outliers of the same temperature data based on the median.
8. A refrigerant leakage detection device, characterized in that, The device includes: An acquisition module for acquiring the operation data of the vehicle air conditioner. The operation data is the node data of each sampling point in the refrigerant circulation circuit, and the node data includes the temperature data and pressure data corresponding to different opening degrees of the refrigerant circulation circuit; A calculation module for calculating the mean values of the pressure data and the temperature data at each sampling point in the operation data respectively according to a preset first time period to obtain a plurality of training samples; A detection module for performing anomaly detection on each of the training samples to determine normal samples and abnormal samples, where the abnormal samples indicate refrigerant leakage; A training module for training a preset detection model based on the normal samples and the abnormal samples to obtain a refrigerant detection model for detecting refrigerant leakage in a vehicle to be tested.
9. An electronic device, characterized in that, It includes: A processor, a memory, and a communication bus; The communication bus is used to connect the processor and the memory; The processor is configured to execute the computer program stored in the memory to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program is used to cause a computer to execute the method according to any one of claims 1 to 7.