A micro-compressor abnormality detection system for a new energy vehicle

Abstract

The application discloses a micro-compressor abnormality detection system for new energy vehicles, and relates to the technical field of data processing, wherein the control parameters of the micro-compressor are interacted, the control duration is read, and a temperature data set is constructed; the control mapping data collection of the micro-compressors of the same type is carried out, and the abnormal value nodes are configured; the real-time temperature data are called based on the temperature data set, the abnormal value nodes are compensated under the current control parameters; the variable parameter nodes are configured, the variable parameter node temperature fitting results are obtained, the initial temperature abnormality coefficients are generated in combination with the equipment temperature set, and the abnormal value calculation is carried out; and the abnormality recognition results are generated through the abnormal value calculation results and the abnormal value node compensation results. The application solves the technical problems of low abnormality detection efficiency and low accuracy of the detection results of the micro-compressors in the prior art, and achieves the technical effects of improving the abnormality detection efficiency and the accuracy of the detection results of the micro-compressors.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a micro-compressor abnormality detection system for new energy vehicles. BACKGROUND

[0002] The micro-compressor refers to a refrigeration compressor with a refrigeration capacity less than 1KW, which has the advantages of small size, light weight, strong durability, quiet operation and almost no vibration, and is the preferred choice for ideal mobile or portable small-sized thermal management systems. However, the abnormality detection of the micro-compressor currently used mostly uses noise detection equipment or temperature detection equipment to achieve the detection, the detection method is relatively single, the influence of environmental temperature and other factors on the detection data is not fully considered, and there is a problem of inaccurate abnormality detection result. SUMMARY

[0003] The present application provides a micro-compressor abnormality detection system for new energy vehicles, which is used to solve the technical problem of poor protection effect caused by inaccurate protection line setting in the prior art.

[0004] In a first aspect, the present application provides a micro-compressor abnormality detection method for new energy vehicles, which comprises: interacting with the control parameters of the micro-compressor and reading the control duration of the micro-compressor, wherein the control parameters and the control duration have a mapping relationship; configuring a start node based on the control duration, collecting environmental temperature data at the start node through the environmental temperature collection unit, and constructing a temperature data set; collecting control mapping data of the same type of equipment for the micro-compressor through big data, and configuring an abnormal value node according to the collection result; calling real-time temperature data based on the temperature data set, and performing abnormal value node compensation under the current control parameter based on the real-time temperature data; configuring a variable parameter node through the mapping relationship, inputting the control parameters corresponding to the variable parameter node, the control duration, and the temperature data set into an equipment temperature fitting model, and outputting a variable parameter node temperature fitting result; collecting temperature data of the micro-compressor through the equipment temperature collection unit, and generating an equipment temperature set, wherein the equipment temperature set includes variable parameter node equipment temperature and variable parameter node post-equipment temperature; generating an initial temperature abnormality coefficient according to the variable parameter node temperature fitting result and the variable parameter node equipment temperature; interacting with the running data after the variable parameter node through the equipment data collection unit, calculating the abnormal value through the running data, the variable parameter node post-equipment temperature, and the initial temperature abnormality coefficient, and generating an abnormality recognition result through the abnormal value calculation result and the abnormal value node compensation result.

[0005] The second aspect of the present application provides a micro-compressor anomaly detection system for new energy vehicles, the system comprising: an interaction module, the interaction module being used to interact with the control parameters of the micro-compressor and read the control duration of the micro-compressor, wherein the control parameters and the control duration have a mapping relationship; a configuration module, the configuration module being used to configure a start node based on the control duration, and to collect ambient temperature data at the start node through the ambient temperature acquisition unit to construct a temperature data set; an acquisition module, the acquisition module being used to collect control mapping data of the same model device for the micro-compressor through big data, and to configure anomaly nodes according to the acquisition results; a calling module, the calling module being used to call real-time temperature data based on the temperature data set, and to compensate for anomaly nodes under the current control parameters based on the real-time temperature data; a fitting module, the fitting module being used to configure the system through the mapping relationship A variable parameter node, which inputs the control parameter, the control duration, and the temperature data set corresponding to the variable parameter node into the device temperature fitting model, and outputs the variable parameter node temperature fitting result; a device temperature acquisition module, which is used to perform temperature data acquisition of the micro compressor through the device temperature acquisition unit, and generate a device temperature set, wherein the device temperature set includes the variable parameter node device temperature and the variable parameter node after the device temperature; an anomaly generation module, which is used to generate an initial temperature anomaly coefficient according to the variable parameter node temperature fitting result and the variable parameter node device temperature; an anomaly identification module, which is used to exchange the operating data after the variable parameter node through the device data acquisition unit, calculate the anomaly value through the operating data, the device temperature after the variable parameter node and the initial temperature anomaly coefficient, and generate the anomaly identification result through the anomaly calculation result and the anomaly node compensation result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides a method for detecting abnormalities in micro-compressors for new energy vehicles, which relates to the field of data processing technology. By interacting with the control parameters of the micro-compressors and reading the control duration, a temperature data set is constructed, control mapping data of micro-compressors of the same model are collected, abnormal value nodes are configured, real-time temperature data is called, abnormal value node compensation is performed, variable parameter nodes are configured, variable parameter node temperature fitting results are obtained, an initial temperature abnormality coefficient is generated, abnormal value calculation is performed, and abnormal identification results are generated based on the abnormal value calculation results and the abnormal value node compensation results. The method solves the technical problems of low abnormality detection efficiency and low accuracy of detection results of micro-compressors in the prior art, and achieves the technical effect of improving the abnormality detection efficiency and accuracy of detection results of micro-compressors. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0009] Figure 1 A schematic flow chart of a method for detecting abnormalities in a micro-compressor for a new energy vehicle provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a process for generating operating data in a method for detecting abnormalities in a micro-compressor for a new energy vehicle provided in an embodiment of the present application;

[0011] Figure 3 A schematic diagram of a process for correcting node data in abnormal value calculation in a method for detecting abnormality of a micro-compressor for a new energy vehicle provided in an embodiment of the present application;

[0012] Figure 4 A schematic structural diagram of a micro-compressor anomaly detection system for new energy vehicles provided in an embodiment of the present application.

[0013] Description of the accompanying drawings: interaction module 11, configuration module 12, acquisition module 13, calling module 14, fitting module 15, device temperature acquisition module 16, anomaly generation module 17, anomaly identification module 18. DETAILED DESCRIPTION

[0014] The present application provides a method for detecting abnormalities of a micro compressor for new energy vehicles, which is used to solve the technical problems of low efficiency and low accuracy of abnormality detection of micro compressors in the prior art.

[0015] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0017] Example 1

[0018] like Figure 1 As shown, the present application provides a method for detecting abnormalities of a micro compressor for a new energy vehicle, the method comprising:

[0019] S100: interacting with control parameters of a micro compressor and reading a control duration of the micro compressor, wherein the control parameters and the control duration have a mapping relationship;

[0020] Specifically, the control parameters of the target micro-compressor before the current abnormality detection are collected, including the speed, flow rate, pressure, etc. of the target micro-compressor. The interaction is data interaction, which is a process of collecting data. It can be simply understood as the process in which the front-end wants to obtain certain data and passes the input parameters to the server through the interface. The server understands the data requirements of the front-end based on the input parameters, queries the database to obtain the required data, and returns the required data to the front-end. The control duration of the micro-compressor is read. The control duration is the operating time of the micro-compressor before the current abnormality detection. The control parameters continuously change within the control duration range and correspond one-to-one with the time nodes within the control duration range. Therefore, the control parameters and the control duration have a mapping relationship.

[0021] S200: configuring a startup node based on the control duration, collecting ambient temperature data at the startup node by the ambient temperature collection unit, and building a temperature data set;

[0022] Specifically, the control duration is used to find the start-up node of the microcompressor, that is, the time node at which the microcompressor begins to operate. The ambient temperature acquisition unit collects ambient temperature change data from the start-up node to the stop-operation node, and the temperature change data during this period is compiled into a temperature data collection. The microcompressor is generally installed in the engine compartment of a vehicle. The ambient temperature acquisition unit is a unit for collecting the ambient temperature at the installation location of the microcompressor. It can be composed of a temperature sensor and a signal generator and is communicatively connected to the microcompressor anomaly detection system. The temperature data collection can subsequently be used to eliminate interference of the ambient temperature data on the operating data of the microcompressor.

[0023] S300: collecting control mapping data of the same model of the micro compressor using big data, and configuring an outlier node according to the collected data;

[0024] Specifically, through Internet big data, control mapping data of multiple micro-compressors of the same model are collected, including control parameters and control durations of multiple micro-compressors of the same model under normal working conditions. The control parameters and control durations of multiple micro-compressors of the same model are respectively matched one by one, and the control parameter values ​​of each operating node of the micro-compressor of this model under normal working conditions are determined, such as the device temperature and ambient temperature at the startup node, and the device temperature and ambient temperature after three minutes of operation. Multiple control parameter nodes within the control duration are used as standard control parameter nodes, such as standard ambient temperature nodes, standard device temperature nodes, etc. Multiple standard control parameter nodes are used as abnormal value nodes, that is, temperature threshold nodes. Subsequently, whether the equipment is abnormal can be judged by comparing whether the temperature of each node is greater than the temperature threshold, that is, comparing whether the temperature of each node is greater than the abnormal value.

[0025] S400: calling real-time temperature data based on the temperature data set, and performing abnormal value node compensation under current control parameters based on the real-time temperature data;

[0026] Specifically, real-time temperature data is called from the temperature data set, and the real-time temperature data is the temperature data of the environment in which the micro-compressor is located at the current time, that is, the ambient temperature data in the engine compartment. The real-time temperature data is compared with the standard ambient temperature of the abnormal value node, and the temperature difference between the real-time temperature data and the standard ambient temperature is calculated. The abnormal value node is compensated using the temperature difference. For example, the standard ambient temperature at a certain time node is 25°C, and the standard equipment operating temperature is 60-70°C. 70°C is used as the temperature abnormal value. Then, when the real-time ambient temperature is 30°C, the operating temperature of the equipment may be 65-75°C, and 75°C is used as the temperature abnormal value. Similarly, the temperature abnormal value of each time node is compensated, that is, the equipment temperature threshold at the current ambient temperature is corrected to eliminate the interference of the ambient temperature on the identification of equipment temperature abnormality.

[0027] S500: configuring a variable parameter node through the mapping relationship, inputting the control parameter, the control duration, and the temperature data set corresponding to the variable parameter node into a device temperature fitting model, and outputting a temperature fitting result of the variable parameter node;

[0028] Specifically, through the mapping relationship between the control parameters and the control duration, a variable parameter node is found. The variable parameter node is the time point when the abnormality detection of the micro compressor is started, and is also the time node when the control parameters change. The control parameters, the control duration, and the temperature data set corresponding to the variable parameter node are input into the device temperature fitting model, and the device temperature fitting model outputs the variable parameter node temperature fitting result. The variable parameter node temperature fitting result is the theoretical value of the device temperature fitted by the ambient temperature and the control data, that is, the predicted device temperature at each time node in the future.

[0029] Furthermore, the device temperature fitting model is a model used to predict the device temperature based on the device's previous control parameters and ambient temperature data. Its construction process can be: extracting the control parameters, ambient temperature, and device temperature data of multiple micro-compressors of the same model as sample data, combining them with a BP neural network to construct the device temperature fitting model, randomly dividing the sample data into a training data set, a validation data set, and a test data set, and performing supervised training on the device temperature fitting model based on the training data set, validation data set, and test data set until the device temperature fitting model reaches convergence and meets the preset accuracy requirements, thereby obtaining the device temperature fitting model. The BP neural network is a multi-layer feedforward neural network trained according to the error back propagation algorithm. It does not require the mathematical equations for the mapping relationship between input and output to be determined in advance. It only learns certain rules through its own training to obtain the result closest to the expected output value when the input value is given. The variable parameter node temperature fitting result can be used as a device temperature standard parameter to determine the temperature anomaly of the device when abnormality detection begins.

[0030] S600: Execute temperature data collection of the micro compressor by the device temperature collection unit to generate a device temperature set, wherein the device temperature set includes a device temperature of a variable parameter node and a device temperature after the variable parameter node;

[0031] Specifically, the device temperature acquisition unit is used to collect the device temperature data of the micro compressor, including extracting the device temperature of the variable parameter node and the device temperature after the variable parameter node, that is, extracting the device temperature data of each time node after the start of abnormality detection, that is, the actual value of the device temperature, and generating a device temperature set, which can be used as basic data for device abnormality identification.

[0032] S700: Generate an initial temperature anomaly coefficient according to the variable parameter node temperature fitting result and the variable parameter node device temperature;

[0033] Specifically, the temperature fitting result of the variable parameter node is compared with the device temperature of the variable parameter node, that is, the theoretical value of the device temperature is compared with the actual value of the device temperature, and the difference between the actual device temperature and the theoretical device temperature of each node after the variable parameter node is calculated, and the initial temperature anomaly coefficient is set according to the size of the temperature difference. The larger the temperature difference, the larger the initial temperature anomaly coefficient, which means that the degree of anomaly of the current device temperature is more serious. The initial temperature anomaly coefficient can be used for subsequent calculation of the anomaly value of the micro compressor.

[0034] S800: obtaining running data after the parametric node interaction by the device data acquisition unit, performing outlier calculation by the running data, the device temperature after the parametric node and the initial temperature anomaly coefficient, and generating an abnormality recognition result by the outlier calculation result and the outlier node compensation result.

[0035] Specifically, the running data after the parametric node is collected by the device data acquisition unit, the device acquisition unit is a unit composed of multiple acquisition devices, which is used to collect multiple running data of the micro-compressor, and the multiple acquisition devices can include pressure sensors, flow sensors, etc., and the running data can include device rotation speed, device flow and other running data, which will all affect the device temperature. The running data, the device temperature after the parametric node and the initial temperature anomaly coefficient are substituted into the outlier calculation formula to perform outlier calculation to obtain the outlier calculation result, that is, the temperature anomaly result of the device. Finally, by comparing the outlier calculation result and the outlier node compensation result, it is determined whether the device temperature of the current device exceeds the preset temperature threshold, and then it is determined whether the device operation is abnormal, and the abnormality recognition result is generated from the determination result. The abnormality recognition result is used as the abnormality detection result of the micro-compressor, which can improve the abnormality detection efficiency and detection result accuracy of the micro-compressor.

[0036] Further, as shown in Figure 2 the step S800 of the embodiment of the present application further comprises:

[0037] S810: performing rotation speed data acquisition of the micro-compressor by the rotation speed data acquisition unit to generate first running data;

[0038] S820: performing flow data acquisition of the micro-compressor by the flow data acquisition unit to generate second running data;

[0039] S830: performing pressure data acquisition of the micro-compressor by the pressure data acquisition unit to generate third running data;

[0040] S840: generating the running data based on the first running data, the second running data and the third running data.

[0041] Specifically, the device operating data after the variable parameter node is collected by the device data collection unit. The device data collection unit includes a speed data collection unit, a flow data collection unit, and a pressure data collection unit. The speed refers to the speed of the compressor rotation, and the size of the compressor speed is related to the compressor exhaust volume. The flow refers to the volume of air passing through the compressor per unit time, and the pressure refers to the exhaust pressure of the compressor. The speed data collection unit collects the speed data of the micro compressor as the first operating data, the flow data collection unit collects the flow data of the micro compressor as the second operating data, and the pressure data collection unit collects the pressure data of the micro compressor as the third operating data. The first operating data, the second operating data, and the third operating data are collectively used as the operating data to characterize the operating status of the device after the variable parameter node.

[0042] Furthermore, step S800 in the embodiment of the present application further includes:

[0043] S850: Calculate the outlier value using a formula, where the calculation formula is as follows:

[0044]

[0045] Where δ is the outlier, i is the time node, and i=1,…,n, n is an integer greater than 1, T ρ is the initial temperature anomaly coefficient, T i is the device temperature at time node i, is the standard temperature under the current control parameters, is the standard speed under the current control parameters, v i is the equipment speed at time node i, Q is the standard flow rate under the current control parameters, and Q i is the device traffic at time node i, is the standard pressure under the current control parameters, p i is the equipment pressure at time node i, K1 is the abnormal speed proportional weight, K2 is the abnormal flow proportional weight, and K3 is the abnormal pressure proportional weight.

[0046] Specifically, the abnormal value calculation formula of the micro compressor is: Among them, δ is the abnormal value, that is, the temperature abnormal value, i is the time node, and i=1,…,n, n is an integer greater than 1, there are multiple time nodes, T ρ is the initial temperature anomaly coefficient, T i is the device temperature at time node i, is the standard temperature under the current control parameters, is the standard speed under the current control parameters, v iis the equipment speed at the i time node, is the standard flow under the current control parameter, i is the equipment flow at the i time node, is the standard pressure under the current control parameter, i is the equipment pressure at the i time node, K1 is the speed abnormality proportion weight, K2 is the flow abnormality proportion weight, and K3 is the pressure abnormality proportion weight.

[0047] The obtained running data, the equipment temperature after the variable parameter node, and the initial temperature abnormality coefficient are substituted into the above abnormal value calculation formula to perform abnormal value calculation, and the abnormal value calculation result is obtained.

[0048] Further, as shown in Figure 3 , the embodiment of the present application further includes step S860, and step S860 further includes:

[0049] S861: drawing a temperature curve based on the temperature data set, wherein the temperature curve is marked with a variable parameter node;

[0050] S862: extracting the temperature curve feature corresponding to the variable parameter node after the variable parameter node, and generating a node correlation compensation value based on the temperature curve feature;

[0051] S863: performing node data correction for abnormal value calculation through the node correlation compensation value.

[0052] Specifically, a time-temperature coordinate system is constructed, and the temperature data in the temperature data set is taken as the basic data. A temperature curve is drawn in the time-temperature coordinate system, wherein the temperature curve specially marks the variable parameter node. Because the change of the environmental temperature data is uncontrollable, the influence of the actual environmental temperature data after the variable parameter node needs to be corrected again. The temperature curve feature corresponding to the variable parameter node after the variable parameter node is extracted, and the temperature curve feature is the change trend of the temperature curve after the variable parameter node, such as the slope of the temperature curve. The influence value of the actual environmental temperature after the variable parameter node on the temperature abnormal value is calculated based on the temperature curve feature, a node correlation compensation value is generated, and node data correction for abnormal value calculation is performed through the node correlation compensation value, so that more accurate abnormal value calculation data of each node is obtained.

[0053] Further, the step S862 of the embodiment of the present application further includes:

[0054] S862-1: configuring a ladder temperature threshold and a node temperature threshold;

[0055] S862-2: performing curve temperature comparison through the ladder temperature threshold and the node temperature threshold, taking the variable parameter node as the initial point;

[0056] S862-3: Generate the temperature curve feature based on the curve temperature comparison result.

[0057] Specifically, the temperature curve is divided into temperature curves of multiple time periods, and the temperature curves of the multiple time periods include step temperatures of multiple time periods. The time span of the step temperature is shorter than the time between two nodes, reflecting the change of the temperature curve within a short time window. A step temperature threshold is set for each step temperature, that is, the maximum value of the absolute value of the slope change of the curve is set, for example, it is set to 0.5. A corresponding node temperature threshold is set for each data node, and the variable parameter node is used as the initial point. The curve temperature comparison is performed through the step temperature threshold and the node temperature threshold. For example, if the curve slope of the starting temperature and the ending temperature of a certain step is 1, and the curve slope of the starting temperature and the ending temperature of the adjacent step is 0.4, then the absolute value of the slope change value of the curve is 0.6, which is greater than the step temperature threshold of 0.5, so the influence of the step temperature needs to be considered. If the node temperature of the node is greater than the node temperature threshold, the influence of the node temperature also needs to be considered. The influence value of the step temperature and the influence value of the node temperature are multiplied by the corresponding weight coefficient respectively to obtain the associated compensation value of the node, that is, the temperature compensation value, which is used as the curve temperature comparison result. The temperature curve feature is generated by multiple curve temperature comparison results.

[0058] Furthermore, step S863 of the embodiment of the present application further includes:

[0059] S863-1: Configure the associated extreme values ​​of temperature;

[0060] S863-2: Calculate the influence of step temperature characteristics and node temperature characteristics based on the temperature comparison results;

[0061] S863-3: Obtain the node-associated compensation value according to the impact calculation result;

[0062] S863-4: Determine whether the node association compensation value satisfies the association extreme value; if so, set the node association compensation value to the association extreme value;

[0063] S863-5: Correct the node data for abnormal value calculation based on the corrected node association compensation value.

[0064] Specifically, based on the normal operating parameter range of the device, the associated extreme value of the temperature, that is, the node associated compensation value threshold, that is, the temperature compensation maximum value, is set. For example, the normal operating temperature of the micro-compressor is generally between 60-90℃, and if the temperature compensation value exceeds the normal operating temperature range too much, it has no reference value. The influence calculation of the step temperature characteristics and the node temperature characteristics is performed through the temperature comparison results, and the node associated compensation value of each node is calculated according to the influence calculation results. The node associated compensation value of each node is compared with the associated extreme value, and if the node associated compensation value is greater than or equal to the associated extreme value, the associated extreme value is taken as the node associated compensation value. Then, the node data correction of the abnormal value calculation is performed using the replaced node associated compensation value, so as to avoid the situation that the abnormal data is too large to be displayed.

[0065] Further, the embodiment of the present application further includes step S900, and step S900 further includes:

[0066] S910: performing identification authentication of the abnormal identification result, and recording the authentication result;

[0067] S920: extracting common features of error identification from the authentication result, and obtaining a common feature extraction result;

[0068] S930: completing identification optimization of abnormal identification through the common feature extraction result.

[0069] Specifically, the target micro-compressor is subjected to abnormal detection in a professional laboratory to obtain more accurate laboratory detection data. The laboratory detection data is used to perform identification authentication of the abnormal identification result, that is, the laboratory detection data of the target micro-compressor abnormal detection is compared with the detection data of the micro-compressor abnormal detection system of the present application to obtain a comparison result, that is, the authentication result. The common features of error identification are extracted from the authentication result, that is, the error identification parameters of the abnormal detection system of the present application are extracted as the common feature extraction result. The error identification parameters are weakened or removed to complete the identification optimization of abnormal identification, so as to achieve the purpose of optimizing the micro-compressor abnormal detection system of the present application.

[0070] In summary, the embodiment of the present application has at least the following technical effects:

[0071] The application interacts with the control parameters of the micro-compressor, reads the control duration, constructs a temperature data set, collects control mapping data of the same type of micro-compressor, configures an abnormal value node, calls real-time temperature data based on the temperature data set, compensates the abnormal value node under the current control parameter, configures a variable parameter node, obtains a variable parameter node temperature fitting result, combines the equipment temperature set to generate an initial temperature abnormality coefficient, calculates the abnormal value, and generates an abnormality identification result through the abnormal value calculation result and the abnormal value node compensation result.

[0072] The technical effect of improving the abnormality detection efficiency and the accuracy of the detection result of the micro-compressor is achieved.

[0073] Embodiment two

[0074] Based on the same inventive concept as the micro-compressor abnormality detection method for new energy vehicles in the foregoing embodiments, as shown in the Figure 4 application provides a micro-compressor abnormality detection system for new energy vehicles, and the system and method embodiments in the application are based on the same inventive concept. The system comprises:

[0075] The interaction module 11 is used to interact with the control parameters of the micro-compressor and read the control duration of the micro-compressor, wherein the control parameters and the control duration have a mapping relationship.

[0076] The configuration module 12 is used to configure a start node based on the control duration, collect environmental temperature data at the start node through the environmental temperature acquisition unit, and construct a temperature data set.

[0077] The acquisition module 13 is used to collect control mapping data of the same type of equipment for the micro-compressor through big data, and configure an abnormal value node according to the acquisition result.

[0078] The calling module 14 is used to call real-time temperature data based on the temperature data set, and compensate the abnormal value node under the current control parameter based on the real-time temperature data.

[0079] The fitting module 15 is used to configure a variable parameter node through the mapping relationship, input the control parameters, the control duration, and the temperature data set corresponding to the variable parameter node into an equipment temperature fitting model, and output a variable parameter node temperature fitting result.

[0080] The device temperature acquisition module 16 is used to collect temperature data of the micro compressor through the device temperature acquisition unit to generate a device temperature set, wherein the device temperature set includes the device temperature of the variable parameter node and the device temperature after the variable parameter node;

[0081] An anomaly generating module 17, the anomaly generating module 17 is used to generate an initial temperature anomaly coefficient according to the variable parameter node temperature fitting result and the variable parameter node device temperature;

[0082] The abnormality identification module 18 is used to obtain the operating data after the variable parameter node through the interactive variable parameter node of the device data acquisition unit, calculate the abnormal value through the operating data, the device temperature after the variable parameter node and the initial temperature abnormality coefficient, and generate the abnormality identification result through the abnormal value calculation result and the abnormal value node compensation result.

[0083] Furthermore, the system further comprises:

[0084] a speed acquisition module, configured to acquire the speed data of the micro compressor through a speed data acquisition unit to generate first operating data;

[0085] a flow rate collection module, configured to collect flow rate data of the micro compressor through a flow rate data collection unit to generate second operation data;

[0086] a pressure acquisition module, configured to acquire pressure data of the micro compressor through a pressure data acquisition unit to generate third operating data;

[0087] An integration module is configured to generate the operation data based on the first operation data, the second operation data, and the third operation data.

[0088] Furthermore, the system further comprises:

[0089] The calculation module is used to calculate the outlier value using a formula, wherein the calculation formula is as follows:

[0090]

[0091] Where δ is the outlier, i is the time node, and i=1,…,n, n is an integer greater than 1, T ρ is the initial temperature anomaly coefficient, T i is the device temperature at time node i, is the standard temperature under the current control parameters, is the standard speed under the current control parameters, v i is the equipment speed at time node i, is the standard flow rate under the current control parameters, Q i is the device traffic at time node i, is the standard pressure under the current control parameters, p i is the equipment pressure at time node i, K1 is the abnormal speed proportional weight, K2 is the abnormal flow proportional weight, and K3 is the abnormal pressure proportional weight.

[0092] Furthermore, the system further comprises:

[0093] A drawing module, the drawing module being configured to draw a temperature curve based on the temperature data set, wherein the temperature curve is provided with variable parameter node identifiers;

[0094] An extraction module, the extraction module is used to extract the temperature curve characteristics corresponding to the parameter-changing node, and generate a node-related compensation value based on the temperature curve characteristics;

[0095] A correction module is used to correct the node data of the abnormal value calculation through the node association compensation value.

[0096] Furthermore, the system further comprises:

[0097] A threshold configuration module, the threshold configuration module is used to configure the step temperature threshold and the node temperature threshold;

[0098] A curve comparison module, configured to perform curve temperature comparison using the step temperature threshold and the node temperature threshold with the variable parameter node as an initial point;

[0099] A feature generation module is used to generate the temperature curve feature based on the curve temperature comparison result.

[0100] Furthermore, the system further comprises:

[0101] An associated extreme value configuration module, wherein the associated extreme value configuration module is used to configure the associated extreme value of temperature;

[0102] An impact calculation module, configured to calculate the impact of step temperature characteristics and node temperature characteristics respectively based on the temperature comparison results;

[0103] A node association compensation module, configured to obtain the node association compensation value according to the impact calculation result;

[0104] a judgment module, configured to judge whether the node association compensation value satisfies the association extreme value, and if so, set the node association compensation value to the association extreme value;

[0105] A node correction module is used to correct the node data of the abnormal value calculation according to the corrected node association compensation value.

[0106] Furthermore, the system further comprises:

[0107] An authentication module, configured to perform authentication on the abnormality recognition result and record the authentication result;

[0108] An extraction module is used to extract common features of error recognition from the authentication results to obtain common feature extraction results;

[0109] An optimization module is used to optimize the recognition of abnormality recognition through the common feature extraction results.

[0110] It should be noted that the above-mentioned order of the embodiments of the present application is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0112] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A micro compressor abnormality detection system for new energy vehicles, characterized in that: The system is in communication with an ambient temperature acquisition unit, a device temperature acquisition unit, and a device data acquisition unit, and includes: An interaction module, the interaction module being used to exchange control parameters of the micro compressor and read the control duration of the micro compressor, wherein the control parameters and the control duration have a mapping relationship; a configuration module configured to configure a startup node based on the control duration, collect ambient temperature data at the startup node through the ambient temperature collection unit, and construct a temperature data set; An acquisition module, the acquisition module is used to collect control mapping data of the same model of the micro compressor through big data, and configure an outlier node according to the acquisition result; A calling module, the calling module being configured to call real-time temperature data based on the temperature data set, and perform abnormal value node compensation under current control parameters based on the real-time temperature data; A fitting module configured to configure a variable parameter node through the mapping relationship, input the control parameter, the control duration, and the temperature data set corresponding to the variable parameter node into a device temperature fitting model, and output a variable parameter node temperature fitting result; A device temperature acquisition module, the device temperature acquisition module is used to perform temperature data acquisition of the micro compressor through the device temperature acquisition unit to generate a device temperature set, wherein the device temperature set includes the device temperature of the variable parameter node and the device temperature after the variable parameter node; An anomaly generation module, the anomaly generation module is used to generate an initial temperature anomaly coefficient according to the variable parameter node temperature fitting result and the variable parameter node device temperature; An abnormality identification module is used to obtain the operating data after the variable parameter node through the interactive variable parameter node of the device data acquisition unit, calculate the abnormal value through the operating data, the device temperature after the variable parameter node and the initial temperature abnormality coefficient, and generate an abnormality identification result through the abnormal value calculation result and the abnormal value node compensation result.

2. The system according to claim 1, wherein The abnormality identification module also includes: a speed acquisition module, configured to acquire the speed data of the micro compressor through a speed data acquisition unit to generate first operating data; a flow rate collection module, configured to collect flow rate data of the micro compressor through a flow rate data collection unit to generate second operation data; a pressure acquisition module, configured to acquire pressure data of the micro compressor through a pressure data acquisition unit to generate third operating data; An integration module is configured to generate the operation data based on the first operation data, the second operation data, and the third operation data.

3. The system according to claim 2, wherein: The system further comprises: The calculation module is used to calculate the outlier value using a formula, wherein the calculation formula is as follows: Where δ is the outlier, i is the time node, and i=1,…,n, n is an integer greater than 1, T ρ is the initial temperature anomaly coefficient, T i is the device temperature at time node i, is the standard temperature under the current control parameters, is the standard speed under the current control parameters, v i is the equipment speed at time node i, is the standard flow rate under the current control parameters, Q i is the device traffic at time node i, is the standard pressure under the current control parameters, p i is the equipment pressure at time node i, K1 is the abnormal speed proportional weight, K2 is the abnormal flow proportional weight, and K3 is the abnormal pressure proportional weight.

4. The system according to claim 3, wherein: The system further comprises: A drawing module, the drawing module being configured to draw a temperature curve based on the temperature data set, wherein the temperature curve is provided with variable parameter node identifiers; An extraction module, the extraction module is used to extract the temperature curve characteristics corresponding to the parameter-changing node, and generate a node-related compensation value based on the temperature curve characteristics; A correction module is used to correct the node data of the abnormal value calculation through the node association compensation value.

5. The system according to claim 4, wherein: The system further comprises: A threshold configuration module, the threshold configuration module is used to configure the step temperature threshold and the node temperature threshold; A curve comparison module, configured to perform curve temperature comparison using the step temperature threshold and the node temperature threshold with the variable parameter node as an initial point; A feature generation module is used to generate the temperature curve feature based on the curve temperature comparison result.

6. The system according to claim 5, wherein: The system further comprises: An associated extreme value configuration module, wherein the associated extreme value configuration module is used to configure the associated extreme value of temperature; An impact calculation module, configured to calculate the impact of step temperature characteristics and node temperature characteristics respectively based on the temperature comparison results; A node association compensation module, configured to obtain the node association compensation value according to the impact calculation result; a judgment module, configured to judge whether the node association compensation value satisfies the association extreme value, and if so, set the node association compensation value to the association extreme value; A node correction module is used to correct the node data of the abnormal value calculation according to the corrected node association compensation value.

7. The system according to claim 1, wherein: The system further comprises: An authentication module, configured to perform authentication on the abnormality recognition result and record the authentication result; An extraction module is used to extract common features of error recognition from the authentication results to obtain common feature extraction results; An optimization module is used to optimize the recognition of abnormality recognition through the common feature extraction results.

8. A method for detecting abnormality of a micro compressor for a new energy vehicle, characterized in that: The method comprises: Interacting with the control parameters of the micro compressor and reading the control duration of the micro compressor, wherein the control parameters and the control duration have a mapping relationship; Based on the control duration, a startup node is configured, and ambient temperature data is collected at the startup node by an ambient temperature collection unit to construct a temperature data set; Collect control mapping data of the same model of the micro compressor through big data, and configure outlier nodes according to the collected results; Calling real-time temperature data based on the temperature data set, and performing abnormal value node compensation under current control parameters based on the real-time temperature data; Configure the variable parameter node through the mapping relationship, input the control parameter, the control duration, and the temperature data set corresponding to the variable parameter node into the device temperature fitting model, and output the variable parameter node temperature fitting result; Performing temperature data collection of the micro compressor through a device temperature collection unit to generate a device temperature set, wherein the device temperature set includes a variable parameter node device temperature and a device temperature after the variable parameter node; Generate an initial temperature anomaly coefficient according to the variable parameter node temperature fitting result and the variable parameter node device temperature; The operating data after the variable parameter node is interactively collected by the device data acquisition unit, and the abnormal value is calculated based on the operating data, the device temperature after the variable parameter node and the initial temperature abnormality coefficient. The abnormal value calculation result and the abnormal value node compensation result are used to generate the abnormality identification result.

Images