SCR (Selective Catalytic Reduction) abnormity judgment method and device based on remote data and electronic system

Abstract

The invention relates to the technical field of electric digital data processing, in particular to an SCR abnormity judgment method and device based on remote data and an electronic system.The method comprises the steps that first heavy-duty vehicle remote monitoring data of an SCR system in a preset normal state and second heavy-duty vehicle remote monitoring data of the SCR system in a preset abnormal state are obtained, generating a normal state data set of the SCR system and an abnormal state data set of the SCR system; and constructing an SCR system working state judgment model by using the normal state data set and the abnormal state data set, so as to judge the working state of the SCR system of the to-be-detected vehicle by using the SCR system working state judgment model. Therefore, the technical problems that in the related technology, the urea liquid level data recognition precision is low, the urea consumption condition is difficult to accurately obtain, and the working state of the SCR system is difficult to accurately judge due to the fact that quantitative standards formed based on urea consumption abnormity are lacked are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a method, device and electronic system for determining SCR abnormality based on remote data. Background Art

[0002] Heavy-duty vehicle emission control is crucial to environmental pollution and human health. Among them, NOx is one of the main emissions of heavy-duty vehicles. At present, the main application is SCR (Selective Catalytic Reduction) to use urea to "selectively" react with NOx in the exhaust gas and generate non-toxic and non-polluting N2 and H2O. In actual applications, due to various influences, SCR system abnormalities may occur, which will lead to too low urea consumption levels, and the after-treatment system cannot effectively treat NOx emissions in the engine exhaust, resulting in NOx emissions not meeting the standards of emission regulations.

[0003] In related technologies, with the operation and development of the heavy-duty vehicle remote monitoring platform, the abnormal status of the heavy-duty vehicle SCR system can be determined online, remotely and accurately through the heavy-duty vehicle remote monitoring data, which is of great significance for improving the law enforcement efficiency of regulatory departments and ensuring the emission control performance of heavy-duty vehicles.

[0004] However, in the heavy-duty vehicle remote monitoring platform, due to the low recognition accuracy of the urea level sensor, the sensor will have hysteresis and discontinuity when capturing the level change, resulting in the urea level data showing step-like and mutation characteristics, making it difficult to accurately identify the urea consumption. In addition, there is currently no quantitative standard for abnormal urea consumption, making it difficult for regulatory authorities to respond quickly and take effective measures when faced with possible abnormalities in the SCR system, which needs to be improved. Summary of the invention

[0005] The present invention provides a method, device and electronic system for determining an SCR abnormality based on remote data, so as to solve the technical problems in the related art that the data recognition accuracy of urea liquid level is low, it is difficult to accurately obtain the consumption of urea, and there is a lack of quantitative standards based on the abnormal urea consumption, so it is difficult to accurately determine the working state of the SCR system.

[0006] A first aspect of the present invention provides an SCR abnormality determination method based on remote data, which is applied to a model building stage, wherein the method comprises the following steps: obtaining remote monitoring data of a first heavy-duty vehicle under a preset normal state and remote monitoring data of a second heavy-duty vehicle under a preset abnormal state of the SCR system; generating a normal state data set of the SCR system based on the first heavy-duty vehicle remote monitoring data, and generating an abnormal state data set of the SCR system based on the second heavy-duty vehicle remote monitoring data; constructing an SCR system working state determination model using the normal state data set and the abnormal state data set, so as to determine the working state of the SCR system of the vehicle to be tested using the SCR system working state determination model.

[0007] Optionally, in one embodiment of the present invention, after obtaining the remote monitoring data of a first heavy-duty vehicle under a preset normal state and the remote monitoring data of a second heavy-duty vehicle under a preset abnormal state of the SCR system, it also includes: filtering outliers and abnormal values ​​in the remote monitoring data of the first heavy-duty vehicle to obtain a first data filter value, filtering outliers and abnormal values ​​in the remote monitoring data of the second heavy-duty vehicle to obtain a second data filter value; filtering out first valid data that meets preset validity conditions from the first data filter value, and filtering out second valid data that meets the preset validity conditions from the second data filter value.

[0008] Optionally, in one embodiment of the present invention, the normal state data set of the SCR system is generated based on the first heavy-duty vehicle remote monitoring data, and the abnormal state data set of the SCR system is generated based on the second heavy-duty vehicle remote monitoring data, including: obtaining a first SCR urea consumption segment of the first heavy-duty vehicle remote monitoring data; locating the median value of the first valid data as the first SCR urea consumption segment; calculating a first characterization parameter of the first SCR urea consumption segment, and forming the normal state data set based on the first characterization parameter; obtaining a second SCR urea consumption segment of the second heavy-duty vehicle remote monitoring data; locating the median value of the second valid data as the second SCR urea consumption segment; calculating a second characterization parameter of the second SCR urea consumption segment, and forming the abnormal state data set based on the second characterization parameter.

[0009] Optionally, in one embodiment of the present invention, the use of the normal state data set and the abnormal state data set to construct the SCR system working state determination model includes: randomly dividing all SCR urea consumption fragments in the normal state data set according to a preset ratio to obtain a normal state training data set and a normal state verification data set; randomly dividing all SCR urea consumption fragments in the abnormal state data set according to a preset ratio to obtain an abnormal state training data set and an abnormal state verification data set; using the normal state training data set and the abnormal state training data set to perform model training to obtain an initial SCR system working state determination model; using the normal state verification data set and the abnormal state verification data set to verify the initial SCR system working state determination model to obtain a model prediction failure rate; quantifying the model prediction error based on the model prediction failure rate, and retraining the initial SCR system working state determination model until the model prediction error meets a preset convergence condition to obtain the SCR system working state determination model.

[0010] The second aspect of the present invention provides an SCR abnormality determination method based on remote data, which is applied to the model use stage, wherein the method includes the following steps: obtaining multiple groups of heavy-duty vehicle remote monitoring data of the vehicle to be tested based on a preset sampling frequency; determining multiple SCR urea consumption fragments of the vehicle to be tested based on the multiple groups of heavy-duty vehicle remote monitoring data, and calculating the characterization parameters corresponding to each SCR urea consumption fragment; inputting the characterization parameters corresponding to each SCR urea consumption fragment into a pre-constructed SCR system working state determination model in turn, obtaining multiple initial SCR system working states of the vehicle to be tested, and obtaining the final SCR system working state of the vehicle to be tested based on the multiple initial SCR system working states, wherein the SCR system working state determination model is trained by a normal state data set and an abnormal state data set of the SCR system.

[0011] Optionally, in one embodiment of the present invention, obtaining the final SCR system operating state of the vehicle to be tested based on the multiple initial SCR system operating states includes: obtaining the proportion of normal state and abnormal state based on the multiple initial SCR system operating states; and obtaining the final SCR system operating state based on the proportion.

[0012] The third aspect of the present invention provides an SCR abnormality determination device based on remote data, which is applied to the model building stage, wherein the device includes: an acquisition module, used to obtain remote monitoring data of a first heavy-duty vehicle under a preset normal state and remote monitoring data of a second heavy-duty vehicle under a preset abnormal state of the SCR system; a generation module, used to generate a normal state data set of the SCR system based on the first heavy-duty vehicle remote monitoring data, and to generate an abnormal state data set of the SCR system based on the second heavy-duty vehicle remote monitoring data; a construction module, used to use the normal state data set and the abnormal state data set to construct an SCR system working state determination model, so as to use the SCR system working state determination model to determine the working state of the SCR system of the vehicle to be tested.

[0013] Optionally, in one embodiment of the present invention, it also includes: a filtering module, used to filter outliers and abnormal values ​​in the first heavy-duty vehicle remote monitoring data to obtain a first data filtering value, and filter outliers and abnormal values ​​in the second heavy-duty vehicle remote monitoring data to obtain a second data filtering value; a screening module, used to filter out first valid data that meets preset valid conditions from the first data filtering value, and filter out second valid data that meets the preset valid conditions from the second data filtering value.

[0014] Optionally, in one embodiment of the present invention, the generation module includes: a first acquisition unit, used to acquire a first SCR urea consumption segment of the first heavy-duty vehicle remote monitoring data; a first positioning unit, used to locate the median value of the first valid data as the first SCR urea consumption segment; a first calculation unit, used to calculate a first characterization parameter of the first SCR urea consumption segment, and form the normal state data set based on the first characterization parameter; a second acquisition unit, used to acquire a second SCR urea consumption segment of the second heavy-duty vehicle remote monitoring data; a second positioning unit, used to locate the median value of the second valid data as the second SCR urea consumption segment; a second calculation unit, used to calculate a second characterization parameter of the second SCR urea consumption segment, and form the abnormal state data set based on the second characterization parameter.

[0015] Optionally, in one embodiment of the present invention, the construction module includes: a first division unit, used to randomly divide all SCR urea consumption fragments in the normal state data set according to a preset ratio to obtain a normal state training data set and a normal state verification data set; a second division unit, used to randomly divide all SCR urea consumption fragments in the abnormal state data set according to a preset ratio to obtain an abnormal state training data set and an abnormal state verification data set; a training unit, used to perform model training using the normal state training data set and the abnormal state to obtain an initial SCR system working state determination model; a verification unit, used to verify the initial SCR system working state determination model using the normal state verification data set and the abnormal state verification data set to obtain a model prediction failure rate; a construction unit, used to quantify the model prediction error based on the model prediction failure rate, and retrain the initial SCR system working state determination model until the model prediction error meets a preset convergence condition to obtain the SCR system working state determination model.

[0016] The fourth aspect of the present invention provides an SCR abnormality determination device based on remote data, which is applied to the model use stage, wherein the device includes: a sampling module, which is used to obtain multiple groups of heavy-duty vehicle remote monitoring data of the vehicle to be tested based on a preset sampling frequency; a calculation module, which is used to determine multiple SCR urea consumption fragments of the vehicle to be tested based on the multiple groups of heavy-duty vehicle remote monitoring data, and calculate the characterization parameters corresponding to each SCR urea consumption fragment; a determination module, which is used to input the characterization parameters corresponding to each SCR urea consumption fragment into a pre-constructed SCR system working state determination model in turn, to obtain multiple initial SCR system working states of the vehicle to be tested, and to obtain the final SCR system working state of the vehicle to be tested based on the multiple initial SCR system working states, wherein the SCR system working state determination model is trained by a normal state data set and an abnormal state data set of the SCR system.

[0017] Optionally, in one embodiment of the present invention, the determination module includes: a calculation unit, used to obtain the proportion of normal state and abnormal state based on the multiple initial SCR system operating states; and a determination unit, used to obtain the final SCR system operating state based on the proportion.

[0018] A fifth aspect of the present invention provides an electronic system, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the SCR abnormality determination method based on remote data as described in the above embodiment.

[0019] A sixth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the SCR abnormality determination method based on remote data as described in the above embodiment.

[0020] A seventh aspect of the present invention provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned SCR abnormality determination method based on remote data.

[0021] The embodiment of the present invention can generate a corresponding normal state data set and an abnormal state data set according to the remote monitoring data of the first heavy-duty vehicle under the preset normal state of the SCR system and the remote monitoring data of the second heavy-duty vehicle under the preset abnormal state, and use the normal state data set and the abnormal state data set to construct an SCR system working state determination model, so as to use the SCR system working state determination model to determine the working state of the SCR system of the vehicle to be tested, thereby improving the accuracy of the SCR system working state determination, improving the remote monitoring capability and efficiency of the regulatory department for heavy-duty vehicle emissions, and ensuring the control performance of heavy-duty vehicle emissions. Thus, the technical problem in the related art that the data recognition accuracy of the urea liquid level is low, it is difficult to accurately obtain the urea consumption, and there is a lack of quantitative standards based on the abnormal urea consumption, so that it is difficult to accurately determine the working state of the SCR system.

[0022] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 A flowchart of a method for determining an SCR abnormality based on remote data according to an embodiment of the present invention; Figure 2 A schematic diagram of obtaining the step-shaped distribution characteristics of urea liquid level data and SCR urea consumption fragments according to an embodiment of the present invention; Figure 3 is a flow chart of a method for determining SCR abnormality based on remote data according to an embodiment of the present invention; Figure 4 A schematic diagram of the structure of an SCR abnormality determination device based on remote data according to an embodiment of the present invention; Figure 5 A flowchart of another SCR abnormality determination method based on remote data according to an embodiment of the present invention; Figure 6Schematic diagram of the principle of SCR abnormality determination based on remote data according to an embodiment of the present invention; Figure 7 A schematic diagram of the structure of another SCR abnormality determination device based on remote data according to an embodiment of the present invention; Figure 8 It is a schematic diagram of the structure of an electronic system provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0025] The following describes the SCR abnormality determination method, device and electronic system based on remote data of the embodiment of the present invention with reference to the accompanying drawings. In view of the technical problem that the data recognition accuracy of urea liquid level in the related art mentioned in the above background technology is low, it is difficult to accurately obtain the consumption of urea, and there is a lack of quantitative standards based on the abnormal urea consumption, so it is difficult to accurately determine the working state of the SCR system, the present invention provides a SCR abnormality determination method based on remote data, in which a corresponding normal state data set and an abnormal state data set can be generated according to the remote monitoring data of the first heavy-duty vehicle in the preset normal state of the SCR system and the remote monitoring data of the second heavy-duty vehicle in the preset abnormal state, and the normal state data set and the abnormal state data set are used to construct an SCR system working state determination model, so as to determine the working state of the SCR system of the vehicle to be tested by using the SCR system working state determination model, improve the accuracy of the SCR system working state determination, improve the remote supervision capability and efficiency of the regulatory department on heavy-duty vehicle emissions, and ensure the control performance of heavy-duty vehicle emissions. Thus, the technical problem that the data recognition accuracy of urea liquid level in the related art is low, it is difficult to accurately obtain the consumption of urea, and there is a lack of quantitative standards based on the abnormal urea consumption, so it is difficult to accurately determine the working state of the SCR system is solved.

[0026] Specifically, Figure 1 A flowchart of a method for determining an SCR abnormality based on remote data provided by an embodiment of the present invention.

[0027] like Figure 1 As shown, the SCR abnormality determination method based on remote data is applied to the model building stage, wherein the method includes the following steps: In step S101, remote monitoring data of a first heavy-duty vehicle under a preset normal state and remote monitoring data of a second heavy-duty vehicle under a preset abnormal state of an SCR system are acquired.

[0028] In the actual implementation process, the embodiment of the present invention can obtain the remote monitoring data of the first heavy-duty vehicle in a normal state and the remote monitoring data of the second heavy-duty vehicle in an abnormal state when the SCR system is working.

[0029] The SCR system may be any SCR system, such as a test-specific SCR system, and specifically, may be an SCR system that can be used for data collection and accurately reflects the corresponding relationship between the working status and the remote monitoring data.

[0030] Heavy-duty vehicle remote monitoring data can include parameters such as time, vehicle speed, acceleration, SCR system temperature, engine fuel flow, urea level change, NOx emission rate, etc. The sampling frequency of heavy-duty vehicle remote monitoring data is 1 Hz.

[0031] The preset normal state may refer to a working state in which the SCR function of the vehicle is normal and the SCR system can use urea to normally and effectively process NOx in the engine exhaust.

[0032] The preset abnormal state may refer to a working state in which the SCR system cannot effectively process NOx emissions in the engine exhaust due to various reasons resulting in a too low consumption level of urea.

[0033] Optionally, in one embodiment of the present invention, after obtaining the remote monitoring data of a first heavy-duty vehicle under a preset normal state and the remote monitoring data of a second heavy-duty vehicle under a preset abnormal state of the SCR system, it also includes: filtering outliers and abnormal values ​​in the remote monitoring data of the first heavy-duty vehicle to obtain a first data filter value, filtering outliers and abnormal values ​​in the remote monitoring data of the second heavy-duty vehicle to obtain a second data filter value; filtering out first valid data that meets preset validity conditions from the first data filter value, and filtering out second valid data that meets preset validity conditions from the second data filter value.

[0034] In some embodiments, after acquiring the first heavy-duty vehicle remote monitoring data and the second heavy-duty vehicle remote monitoring data, the embodiments of the present invention may further filter and screen the acquired data.

[0035] For example, the embodiment of the present invention can perform median filtering and screening processing on the remote monitoring data of the first heavy-duty vehicle and the remote monitoring data of the second heavy-duty vehicle respectively to obtain valid data. Among them, the embodiment of the present invention can use the median filtering method to filter out outliers and abnormal values ​​in the remote monitoring data of the first heavy-duty vehicle and the remote monitoring data of the second heavy-duty vehicle. Use screening processing to extract valid data, and valid data refers to the SCR system temperature greater than 200 And it should be no less than 180 for 10 consecutive minutes Remote monitoring data of heavy-duty vehicles.

[0036] In step S102 , a normal state data set of the SCR system is generated based on the first heavy-duty vehicle remote monitoring data, and an abnormal state data set of the SCR system is generated based on the second heavy-duty vehicle remote monitoring data.

[0037] Furthermore, the embodiment of the present invention can use the positioning median method to obtain SCR urea consumption fragments under different working conditions, calculate the characterization parameters of the SCR urea consumption fragments, and form a data set under normal and abnormal working conditions of the SCR system.

[0038] Optionally, in one embodiment of the present invention, a normal state data set of the SCR system is generated based on the remote monitoring data of the first heavy-duty vehicle, and an abnormal state data set of the SCR system is generated based on the remote monitoring data of the second heavy-duty vehicle, including: obtaining a first SCR urea consumption segment of the remote monitoring data of the first heavy-duty vehicle; locating the median value of the first valid data as the first SCR urea consumption segment; calculating a first characterization parameter of the first SCR urea consumption segment, and forming a normal state data set based on the first characterization parameter; obtaining a second SCR urea consumption segment of the remote monitoring data of the second heavy-duty vehicle; locating the median value of the second valid data as the second SCR urea consumption segment; calculating a second characterization parameter of the second SCR urea consumption segment, and forming an abnormal state data set based on the second characterization parameter.

[0039] For example, Figure 2 As shown, the embodiment of the present invention can rely on valid data, that is, the first valid data obtained based on the remote monitoring data of the first heavy-duty vehicle and the second valid data obtained based on the remote monitoring data of the second heavy-duty vehicle, and use the positioning median method to obtain the SCR urea consumption segment, for example: take 100 s as the continuous time step, calculate the standard deviation of the urea liquid level data in the valid data in each continuous time step; obtain the urea liquid level position with a standard deviation of 0 as the urea liquid level stable position; obtain the urea liquid level mutation position between two consecutive urea liquid level stable positions (that is, the first urea liquid level stable position and the second urea liquid level stable position), take the moment when the last standard deviation of the first urea liquid level stable position is 0 as the urea liquid level mutation position starting moment, and take the moment when the first standard deviation of the second urea liquid level stable position is 0 as the urea liquid level mutation position ending moment; take the time median of the urea liquid level mutation position starting moment and the urea liquid level mutation position ending moment as the urea liquid level mutation position moment, determine that the urea liquid level has changed at this time, and use the urea liquid level mutation position moment as the boundary to obtain the SCR urea consumption segment.

[0040] The embodiment of the present invention can calculate the characterization parameters of each SCR urea consumption segment, including: urea liquid level change (L change ), the ratio of urea level change to cumulative fuel consumption (NR ratio), the ratio of urea level change to NOx emission (NN ratio ), the ratio of urea level change to mileage (ND ratio ), thereby forming a normal state data set and an abnormal state data set of the SCR system.

[0041] In step S103, a SCR system working state determination model is constructed using the normal state data set and the abnormal state data set, so as to determine the working state of the SCR system of the vehicle to be tested using the SCR system working state determination model.

[0042] As a possible implementation method, the embodiment of the present invention can be based on the data sets of the SCR system in normal and abnormal working states, that is, the normal state data set and the abnormal state data set, and use methods such as support vector machines to construct an SCR system working state determination model for a single SCR urea consumption fragment, so that when the working state of the SCR system of the vehicle to be tested needs to be determined later, it is only necessary to obtain the heavy-duty vehicle remote monitoring data of the vehicle to be tested to obtain the working state of the SCR system of the vehicle to be tested.

[0043] Optionally, in one embodiment of the present invention, a normal state data set and an abnormal state data set are used to construct an SCR system working state determination model, including: randomly dividing all SCR urea consumption fragments in the normal state data set according to a preset ratio to obtain a normal state training data set and a normal state verification data set; randomly dividing all SCR urea consumption fragments in the abnormal state data set according to a preset ratio to obtain an abnormal state training data set and an abnormal state verification data set; using the normal state training data set and the abnormal state training data set to perform model training to obtain an initial SCR system working state determination model; using the normal state verification data set and the abnormal state verification data set to verify the initial SCR system working state determination model to obtain a model prediction failure rate; quantifying the model prediction error based on the model prediction failure rate, and retraining the initial SCR system working state determination model until the model prediction error meets a preset convergence condition to obtain the SCR system working state determination model.

[0044] When constructing the SCR system working state determination model, the embodiment of the present invention can use the urea liquid level change (L change ), the ratio of urea level change to cumulative fuel consumption (NR ratio ), the ratio of urea level change to NOx emission (NN ratio ), the ratio of urea level change to mileage (ND ratio ) These four characterization parameters are used as the input of the model, and the two working states of the SCR system normal state and the SCR system abnormal state are used as the output of the model.

[0045] Among them, all SCR urea consumption fragments in the normal state data set and the abnormal state data set of the SCR system are randomly divided into training data and verification data in a ratio of 7:3, which are used for model training and verification respectively.

[0046] Furthermore, the embodiment of the present invention can also use the model prediction failure rate to quantify the model prediction error. The model prediction failure rate is defined as the percentage of the number of SCR urea consumption segments in the verification data where the SCR system working state is incorrectly determined to the total number of SCR urea consumption segments in the verification data.

[0047] Combination Figure 2 and Figure 3 As shown, an SCR abnormality determination method based on remote data in the model building stage of an embodiment of the present invention is explained by taking an embodiment as an example.

[0048] like Figure 3 As shown, the embodiment of the present invention may include the following steps: Step S301: Filter and screen the heavy-duty vehicle remote monitoring data under normal and abnormal conditions of the SCR system to obtain valid data.

[0049] The embodiment of the present invention can obtain the remote monitoring data of the first heavy-duty vehicle in the normal working state of the SCR system and the remote monitoring data of the second heavy-duty vehicle in the abnormal state. Ten heavy-duty vehicles with normal and abnormal working states of the SCR system were selected, and the remote monitoring data of 20 heavy-duty vehicles for one month were obtained in total, with a cumulative mileage of more than 50,000 kilometers. The remote monitoring data of heavy-duty vehicles contains parameters such as time, vehicle speed, acceleration, SCR system temperature, engine fuel flow, urea liquid level change, NOx emission rate, etc. The data sampling frequency is 1 Hz.

[0050] The normal working state of the SCR system refers to a working state in which the vehicle SCR functions normally and the SCR system can utilize urea to normally and effectively treat NOx in the engine exhaust.

[0051] Among them, the abnormal working state of the SCR system is a working state in which the urea consumption level is too low due to various reasons, and the SCR system cannot effectively treat the NOx emissions in the engine exhaust.

[0052] Furthermore, the embodiment of the present invention can filter and screen the first heavy-duty vehicle remote monitoring data and the second heavy-duty vehicle remote monitoring data respectively.

[0053] The embodiment of the present invention can perform median filtering and screening processing on the remote monitoring data of the first heavy-duty vehicle and the remote monitoring data of the second heavy-duty vehicle respectively to obtain valid data. Among them, the embodiment of the present invention can use the median filtering method to filter out outliers and abnormal values ​​in the remote monitoring data of the first heavy-duty vehicle and the remote monitoring data of the second heavy-duty vehicle. The screening process is used to extract valid data. Valid data refers to the SCR system temperature greater than 200 And it should be no less than 180 for 10 consecutive minutes Remote monitoring data of heavy-duty vehicles.

[0054] Step S302: using the positioning median method to obtain the SCR urea consumption fragment, and calculating the characterization parameters to form a normal state data set and an abnormal state data set of the SCR system.

[0055] The embodiment of the present invention can use the positioning median method to obtain the SCR urea consumption fragments corresponding to the heavy-duty vehicle remote monitoring data under different working conditions, calculate the characterization parameters of the SCR urea consumption fragments, and form a data set under normal and abnormal working conditions of the SCR system.

[0056] like Figure 2 As shown, the embodiment of the present invention can rely on valid data, that is, the first valid data obtained based on the remote monitoring data of the first heavy-duty vehicle and the second valid data obtained based on the remote monitoring data of the second heavy-duty vehicle, and use the positioning median method to obtain the SCR urea consumption segment, for example: take 100 s as the continuous time step, calculate the standard deviation of the urea liquid level data in the valid data in each continuous time step; obtain the urea liquid level position with a standard deviation of 0 as the urea liquid level stable position; obtain the urea liquid level mutation position between two consecutive urea liquid level stable positions (that is, the first urea liquid level stable position and the second urea liquid level stable position), take the moment when the last standard deviation of the first urea liquid level stable position is 0 as the urea liquid level mutation position starting moment, and take the moment when the first standard deviation of the second urea liquid level stable position is 0 as the urea liquid level mutation position ending moment; take the time median of the urea liquid level mutation position starting moment and the urea liquid level mutation position ending moment as the urea liquid level mutation position moment, determine that the urea liquid level has changed at this time, and use the urea liquid level mutation position moment as the boundary to obtain the SCR urea consumption segment.

[0057] The embodiment of the present invention can calculate the characterization parameters of each SCR urea consumption segment, including: urea liquid level change (L change ), the ratio of urea level change to cumulative fuel consumption (NR ratio ), the ratio of urea level change to NOx emission (NN ratio ), the ratio of urea level change to mileage (ND ratio), thereby forming a normal state data set and an abnormal state data set of the SCR system.

[0058] Step S303: using the support vector machine method, constructing an SCR system working state determination model for a single SCR urea consumption segment.

[0059] When constructing the SCR system working state determination model, the embodiment of the present invention can use the urea liquid level change (L change ), the ratio of urea level change to cumulative fuel consumption (NR ratio ), the ratio of urea level change to NOx emission (NN ratio ), the ratio of urea level change to mileage (ND ratio ) These four characterization parameters are used as the input of the model, and the two working states of the SCR system normal state and the SCR system abnormal state are used as the output of the model.

[0060] Among them, all SCR urea consumption fragments in the normal state data set and the abnormal state data set of the SCR system are randomly divided into training data and verification data in a ratio of 7:3, which are used for model training and verification respectively.

[0061] Furthermore, the embodiment of the present invention can also use the model prediction failure rate to quantify the model prediction error. The model prediction failure rate is defined as the percentage of the number of SCR urea consumption segments in the verification data where the SCR system working state is incorrectly determined to the total number of SCR urea consumption segments in the verification data.

[0062] According to the SCR abnormality determination method based on remote data proposed in the embodiment of the present invention, a corresponding normal state data set and abnormal state data set can be generated according to the remote monitoring data of the first heavy-duty vehicle in the preset normal state of the SCR system and the remote monitoring data of the second heavy-duty vehicle in the preset abnormal state, and the normal state data set and the abnormal state data set are used to construct an SCR system working state determination model, so as to use the SCR system working state determination model to determine the working state of the SCR system of the vehicle to be tested, thereby improving the accuracy of the SCR system working state determination, improving the remote supervision capability and efficiency of the regulatory department on heavy-duty vehicle emissions, and ensuring the control performance of heavy-duty vehicle emissions. Thus, the technical problem in the related art that the data recognition accuracy of the urea liquid level is low, it is difficult to accurately obtain the urea consumption, and there is a lack of quantitative standards based on the abnormal urea consumption, so that it is difficult to accurately determine the working state of the SCR system.

[0063] Next, the SCR abnormality determination device based on remote data proposed in an embodiment of the present invention will be described with reference to the accompanying drawings.

[0064] Figure 44 is a block diagram of an SCR abnormality determination device based on remote data according to an embodiment of the present invention.

[0065] like Figure 4 As shown, the SCR abnormality determination device 10 based on remote data is applied to the model building stage, wherein the device 10 includes: an acquisition module 101 , a generation module 102 and a construction module 103 .

[0066] Specifically, the acquisition module 101 is used to acquire the remote monitoring data of the first heavy-duty vehicle under a preset normal state of the SCR system and the remote monitoring data of the second heavy-duty vehicle under a preset abnormal state.

[0067] The generating module 102 is used to generate a normal state data set of the SCR system based on the first heavy-duty vehicle remote monitoring data, and to generate an abnormal state data set of the SCR system based on the second heavy-duty vehicle remote monitoring data.

[0068] The construction module 103 is used to construct an SCR system working state determination model using the normal state data set and the abnormal state data set, so as to determine the working state of the SCR system of the vehicle to be tested using the SCR system working state determination model.

[0069] Optionally, in one embodiment of the present invention, the SCR abnormality determination device 10 based on remote data further includes: a filtering module and a screening module.

[0070] Among them, the filtering module is used to filter outliers and abnormal values ​​in the remote monitoring data of the first heavy-duty vehicle to obtain a first data filtering value, and filter outliers and abnormal values ​​in the remote monitoring data of the second heavy-duty vehicle to obtain a second data filtering value.

[0071] The screening module is used to screen out first valid data that meets a preset valid condition from the first data screening value, and to screen out second valid data that meets a preset valid condition from the second data screening value.

[0072] Optionally, in one embodiment of the present invention, the generating module 102 includes: a first acquiring unit, a first positioning unit, a first calculating unit, a second acquiring unit, a second positioning unit and a second calculating unit.

[0073] The first acquisition unit is used to acquire a first SCR urea consumption segment of the first heavy-duty vehicle remote monitoring data.

[0074] The first positioning unit is used to locate the median value of the first valid data as the first SCR urea consumption segment.

[0075] The first calculation unit is used to calculate a first characterization parameter of a first SCR urea consumption segment and form a normal state data set based on the first characterization parameter.

[0076] The second acquisition unit is used to acquire a second SCR urea consumption segment of the remote monitoring data of a second heavy-duty vehicle.

[0077] The second positioning unit is used to position a median value of the second valid data as a second SCR urea consumption segment.

[0078] The second calculation unit is used to calculate a second characterization parameter of a second SCR urea consumption segment and form an abnormal state data set based on the second characterization parameter.

[0079] Optionally, in one embodiment of the present invention, the construction module 103 includes: a first division unit, a second division unit, a training unit, a verification unit and a construction unit.

[0080] The first division unit is used to randomly divide all the SCR urea consumption segments in the normal state data set according to a preset ratio to obtain a normal state training data set and a normal state verification data set.

[0081] The second division unit is used to randomly divide all the SCR urea consumption segments in the abnormal state data set according to a preset ratio to obtain an abnormal state training data set and an abnormal state verification data set.

[0082] The training unit is used to perform model training using a normal state training data set and an abnormal state training data set to obtain an initial SCR system working state determination model.

[0083] The verification unit is used to verify the initial SCR system working state determination model using the normal state verification data set and the abnormal state verification data set to obtain the model prediction failure rate.

[0084] The construction unit is used to quantify the model prediction error based on the model prediction failure rate, and retrain the initial SCR system working state determination model until the model prediction error meets the preset convergence condition, thereby obtaining the SCR system working state determination model. It should be noted that the above explanation of the embodiment of the SCR abnormality determination method based on remote data is also applicable to the SCR abnormality determination device based on remote data of this embodiment, and will not be repeated here.

[0085] According to the remote data-based SCR abnormality determination device proposed in the embodiment of the present invention, a corresponding normal state data set and abnormal state data set can be generated according to the remote monitoring data of the first heavy-duty vehicle in the preset normal state of the SCR system and the remote monitoring data of the second heavy-duty vehicle in the preset abnormal state, and the normal state data set and the abnormal state data set are used to construct an SCR system working state determination model, so as to use the SCR system working state determination model to determine the working state of the SCR system of the vehicle to be tested, thereby improving the accuracy of the SCR system working state determination, improving the remote supervision capability and efficiency of the regulatory department on heavy-duty vehicle emissions, and ensuring the control performance of heavy-duty vehicle emissions. Thus, the technical problem in the related art that the data recognition accuracy of the urea liquid level is low, it is difficult to accurately obtain the urea consumption, and there is a lack of quantitative standards based on the abnormal urea consumption, so that it is difficult to accurately determine the working state of the SCR system.

[0086] The above is an explanation of the embodiment of the present invention at the model building stage. The following is an explanation of the embodiment of the present invention at the model use stage.

[0087] Specifically, Figure 5 A flowchart of a method for determining an SCR abnormality based on remote data provided by an embodiment of the present invention.

[0088] like Figure 5 As shown, the SCR abnormality determination method based on remote data is applied to the model use stage, wherein the method includes the following steps: In step S501, multiple groups of heavy-duty vehicle remote monitoring data of the vehicle to be tested are obtained based on a preset sampling frequency.

[0089] In the actual implementation process, the embodiment of the present invention can select a vehicle to be tested, obtain the heavy-duty vehicle remote monitoring data of the vehicle to be tested, and use the heavy-duty vehicle remote monitoring data to perform online and remote identification of the working state of the SCR system of the vehicle to be tested. Among them, the heavy-duty vehicle remote monitoring data contains parameters such as time, vehicle speed, acceleration, intake flow, engine fuel flow, NOx emissions, SCR system upstream temperature, urea liquid level change, etc. The data sampling frequency is 1 Hz, and the accumulated data mileage is not less than 100 kilometers.

[0090] In step S502, a plurality of SCR urea consumption segments of the vehicle to be tested are determined based on a plurality of groups of heavy-duty vehicle remote monitoring data, and a characterization parameter corresponding to each SCR urea consumption segment is calculated.

[0091] Furthermore, the embodiment of the present invention can filter and screen each group of heavy-duty vehicle remote monitoring data respectively to obtain valid data, and based on the valid data, use the positioning median method to obtain multiple SCR urea consumption fragments of the vehicle to be determined and tested, and calculate the characterization parameters corresponding to each SCR urea consumption fragment of the vehicle to be determined and tested.

[0092] In step S503, the characterization parameters corresponding to each SCR urea consumption fragment are input into a pre-constructed SCR system working state judgment model in turn to obtain multiple initial SCR system working states of the vehicle to be tested, and the final SCR system working state of the vehicle to be tested is obtained based on the multiple initial SCR system working states, wherein the SCR system working state judgment model is trained by a normal state data set and an abnormal state data set of the SCR system.

[0093] As a possible implementation method, the embodiment of the present invention can use the characteristic parameters (urea liquid level change (L change ), the ratio of urea level change to cumulative fuel consumption (NR ratio ), the ratio of urea level change to NOx emission (NN ratio ), the ratio of urea level change to mileage (ND ratio )) is used as input, and the SCR system working state judgment model for a single SCR urea consumption segment is used to obtain the SCR system working state judgment results of all SCR urea consumption segments of the vehicle to be tested, and the final SCR system working state is obtained based on all the judgment results.

[0094] Optionally, in one embodiment of the present invention, the final SCR system operating state of the vehicle to be tested is obtained based on multiple initial SCR system operating states, including: obtaining the proportion of normal state and abnormal state based on multiple initial SCR system operating states; and obtaining the final SCR system operating state based on the proportion.

[0095] It is understandable that the result of a single determination may be misjudged. Therefore, in an embodiment of the present invention, the working state of the SCR system of the vehicle to be tested can be determined based on the heavy-duty vehicle remote monitoring data obtained multiple times at a certain sampling frequency, such as a frequency of 1 Hz, and the final working state of the SCR system of the vehicle to be tested can be determined based on the result of each determination.

[0096] For example, the embodiment of the present invention may take the SCR system working state that accounts for more than 50% of the SCR system working state determination results of all SCR urea consumption segments of the vehicle to be tested as the SCR system working state identification result of the vehicle to be tested.

[0097] The main reason for setting the basis for determining the working status of the SCR system of the vehicle to be tested in this way is that: relying on the remote monitoring data of the vehicle to be tested, several SCR urea consumption fragments can be obtained. Due to the influence of the vehicle's operating status, environmental climate factors and model prediction accuracy, for all SCR urea consumption fragments of the same vehicle to be tested, when using the constructed SCR system working status determination model for a single SCR urea consumption fragment to make a judgment, the SCR urea consumption fragment may be judged as normal or abnormal operation of the SCR system, thereby affecting the final identification result of the SCR system status of the vehicle to be tested.

[0098] Through multiple test identification results, the SCR system working state that accounts for more than 50% of the SCR system state determination results of all SCR urea consumption segments of the vehicle to be tested is taken, which is more likely to be a true reflection of the working state of the SCR system of the vehicle to be tested. Therefore, in order to reduce the error in the identification of the working state of the SCR system of the vehicle to be tested due to the error in the determination of a single SCR urea consumption segment caused by various factors such as model error, the SCR system working state that accounts for more than 50% of the SCR system state determination results of all SCR urea consumption segments of the vehicle to be tested is finally taken as the identification result of the working state of the SCR system of the vehicle to be tested.

[0099] Combination Figure 6 As shown, the working principle of the SCR abnormality determination method based on remote data according to an embodiment of the present invention is described in detail with an embodiment.

[0100] First, the embodiment of the present invention can select a heavy-duty vehicle whose SCR system is in an abnormal state as the vehicle to be tested, and obtain the heavy-duty vehicle remote monitoring data of the vehicle to be tested at a sampling frequency of 1 Hz, wherein the accumulated mileage of the data is not less than 100 kilometers.

[0101] After filtering and screening the remote monitoring data of heavy-duty vehicles, valid data is obtained, and based on the valid data, the SCR urea consumption fragment of the vehicle to be tested is obtained, and the characterization parameters of the SCR urea consumption fragment of the heavy-duty vehicle to be determined are calculated.

[0102] The characterization parameters are sequentially substituted into the SCR system working state determination model to obtain determination results of multiple working states.

[0103] like Figure 6As shown, the determination results of all SCR urea consumption segments of the vehicle to be tested are given, among which the SCR urea consumption segments with normal operation of the SCR system account for 27%, and the SCR urea consumption segments with abnormal operation of the SCR system account for 73%. Because the SCR urea consumption segments determined to be abnormal operation of the SCR system account for more than 50%, the embodiment of the present invention can identify the working state of the SCR system of the vehicle to be tested as abnormal operation of the SCR system, which is consistent with the working state of the SCR system of the selected heavy-duty vehicle.

[0104] In summary, the embodiment of the present invention can obtain the remote monitoring data of heavy-duty vehicles under normal and abnormal conditions of the SCR system, and perform filtering and screening processing; use the positioning median method to obtain the SCR urea consumption fragment, and calculate the characterization parameters of the SCR urea consumption fragment, including the urea level change (Lchange), the ratio of the urea level change to the cumulative fuel consumption (NRratio), the ratio of the urea level change to the NOx emission (NNratio), and the ratio of the urea level change to the mileage (NDratio), thereby forming a data set under normal and abnormal conditions of the SCR system; using the support vector machine method, a SCR system working state determination model for a single SCR urea consumption fragment is constructed, and based on this, the SCR system state identification of the heavy-duty vehicle to be determined is carried out. The embodiment of the present invention makes full use of the advantages of remote monitoring data, realizes the online, remote and accurate identification of the working state of the SCR system of heavy-duty vehicles, improves the remote supervision capability and efficiency of the regulatory authorities on heavy-duty vehicle emissions, and provides strong technical support for environmental protection and law enforcement.

[0105] According to the SCR abnormality determination method based on remote data proposed in the embodiment of the present invention, the characterization parameters of the SCR urea consumption segment of the vehicle to be tested can be obtained according to the heavy-duty vehicle remote monitoring data of the vehicle to be tested, and the characterization parameters can be input into the pre-built SCR system working state determination model, so as to determine the working state of the SCR system of the vehicle to be tested, so as to achieve accurate determination of the working state of the SCR system based on the remote monitoring data. Thus, the technical problem in the related art that the data recognition accuracy of the urea liquid level is low, it is difficult to accurately obtain the urea consumption, and there is a lack of quantitative standards based on the abnormal urea consumption, so that it is difficult to accurately determine the working state of the SCR system is solved.

[0106] Next, the SCR abnormality determination device based on remote data proposed in an embodiment of the present invention will be described with reference to the accompanying drawings.

[0107] Figure 7 4 is a block diagram of an SCR abnormality determination device based on remote data according to an embodiment of the present invention.

[0108] like Figure 7As shown, the SCR abnormality determination device 20 based on remote data is applied to the model building stage, wherein the device 20 includes: a sampling module 201 , a calculation module 202 and a determination module 203 .

[0109] Specifically, the sampling module 201 is used to obtain multiple groups of heavy-duty vehicle remote monitoring data of the vehicle to be tested based on a preset sampling frequency.

[0110] The calculation module 202 is used to determine a plurality of SCR urea consumption segments of the vehicle to be tested based on a plurality of sets of heavy-duty vehicle remote monitoring data, and calculate a characterization parameter corresponding to each SCR urea consumption segment.

[0111] The determination module 203 is used to input the characterization parameters corresponding to each SCR urea consumption fragment into a pre-constructed SCR system working state determination model in turn, obtain multiple initial SCR system working states of the vehicle to be tested, and obtain the final SCR system working state of the vehicle to be tested based on the multiple initial SCR system working states, wherein the SCR system working state determination model is trained by a normal state data set and an abnormal state data set of the SCR system.

[0112] Optionally, in one embodiment of the present invention, the determination module 203 includes: a calculation unit and a determination unit.

[0113] The calculation unit is used to obtain the proportion of the normal state and the abnormal state based on multiple initial SCR system working states.

[0114] The determination unit is used to obtain a final SCR system operating state based on the specific gravity.

[0115] It should be noted that the above explanation of the embodiment of the SCR abnormality determination method based on remote data is also applicable to the SCR abnormality determination device based on remote data of this embodiment, and will not be repeated here.

[0116] According to the SCR abnormality determination device based on remote data proposed in the embodiment of the present invention, the characterization parameters of the SCR urea consumption segment of the vehicle to be tested can be obtained according to the heavy-duty vehicle remote monitoring data of the vehicle to be tested, and the characterization parameters can be input into the pre-built SCR system working state determination model, so as to determine the working state of the SCR system of the vehicle to be tested, so as to achieve accurate determination of the working state of the SCR system based on the remote monitoring data. Thus, the technical problems in the related art that the data recognition accuracy of the urea liquid level is low, it is difficult to accurately obtain the urea consumption, and there is a lack of quantitative standards based on the abnormal urea consumption, so that it is difficult to accurately determine the working state of the SCR system are solved.

[0117] Figure 8 A schematic diagram of the structure of an electronic system provided in an embodiment of the present invention. The electronic system may include: A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0118] When the processor 802 executes the program, the SCR abnormality determination method based on remote data provided in the above embodiment is implemented.

[0119] Furthermore, the electronic system further comprises: The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0120] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0121] The memory 801 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0122] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0123] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0124] The processor 802 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0125] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned SCR abnormality determination method based on remote data is implemented.

[0126] An embodiment of the present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for determining an SCR abnormality based on remote data provided by an embodiment of the present invention is implemented.

[0127] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0128] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0129] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0130] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0131] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0132] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0133] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0134] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for determining SCR abnormality based on remote data, characterized in that: Applied to the model building stage, wherein the method comprises the following steps: Obtain remote monitoring data of the first heavy-duty vehicle under a preset normal state of the SCR system and remote monitoring data of the second heavy-duty vehicle under a preset abnormal state; generating a normal state data set of the SCR system based on the first heavy-duty vehicle remote monitoring data, and generating an abnormal state data set of the SCR system based on the second heavy-duty vehicle remote monitoring data; The normal state data set and the abnormal state data set are used to construct an SCR system working state determination model, so as to determine the working state of the SCR system of the vehicle to be tested by using the SCR system working state determination model.

2. The SCR abnormality determination method based on remote data according to claim 1, characterized in that: After obtaining the remote monitoring data of the first heavy-duty vehicle under the preset normal state of the SCR system and the remote monitoring data of the second heavy-duty vehicle under the preset abnormal state, the method further includes: Filtering outliers and abnormal values ​​in the remote monitoring data of the first heavy-duty vehicle to obtain a first data filtering value, and filtering outliers and abnormal values ​​in the remote monitoring data of the second heavy-duty vehicle to obtain a second data filtering value; First valid data satisfying a preset valid condition is filtered out from the first data filter value, and second valid data satisfying the preset valid condition is filtered out from the second data filter value.

3. The SCR abnormality determination method based on remote data according to claim 2, characterized in that: The step of generating a normal state data set of the SCR system based on the first heavy-duty vehicle remote monitoring data, and generating an abnormal state data set of the SCR system based on the second heavy-duty vehicle remote monitoring data, comprises: Obtaining a first SCR urea consumption segment of the first heavy-duty vehicle remote monitoring data; Locating a median value of the first valid data as the first SCR urea consumption segment; calculating a first characterization parameter of the first SCR urea consumption segment, and forming the normal state data set based on the first characterization parameter; Obtaining a second SCR urea consumption segment of the remote monitoring data of the second heavy-duty vehicle; locating a median value of the second valid data as the second SCR urea consumption segment; A second characterization parameter of the second SCR urea consumption segment is calculated, and the abnormal state data set is formed based on the second characterization parameter.

4. The SCR abnormality determination method based on remote data according to claim 1, characterized in that: The method of constructing the SCR system working state determination model by using the normal state data set and the abnormal state data set includes: All SCR urea consumption segments in the normal state data set are randomly divided according to a preset ratio to obtain a normal state training data set and a normal state verification data set; All SCR urea consumption segments in the abnormal state data set are randomly divided according to a preset ratio to obtain an abnormal state training data set and an abnormal state verification data set; Performing model training using the normal state training data set and the abnormal state training data set to obtain an initial SCR system working state determination model; Verifying the initial SCR system working state determination model using the normal state verification data set and the abnormal state verification data set to obtain a model prediction failure rate; The model prediction error is quantified based on the model prediction failure rate, and the initial SCR system working state determination model is retrained until the model prediction error meets a preset convergence condition, thereby obtaining the SCR system working state determination model.

5. A method for determining SCR abnormality based on remote data, characterized in that: Applied to the model use phase, wherein the method comprises the following steps: Acquire multiple sets of heavy-duty vehicle remote monitoring data of the vehicle to be tested based on a preset sampling frequency; Determining a plurality of SCR urea consumption segments of the vehicle to be tested based on the plurality of groups of heavy-duty vehicle remote monitoring data, and calculating a characterization parameter corresponding to each SCR urea consumption segment; The characterization parameters corresponding to each SCR urea consumption segment are sequentially input into a pre-constructed SCR system working state determination model to obtain a plurality of initial SCR system working states of the vehicle to be tested, and a final SCR system working state of the vehicle to be tested is obtained based on the plurality of initial SCR system working states, wherein the SCR system working state determination model is trained by a normal state data set and an abnormal state data set of the SCR system.

6. The SCR abnormality determination method based on remote data according to claim 5, characterized in that: The obtaining the final SCR system operating state of the vehicle to be tested based on the multiple initial SCR system operating states includes: Based on the multiple initial SCR system operating states, obtaining a proportion of a normal state to an abnormal state; The final SCR system operating state is obtained based on the specific gravity.

7. An SCR abnormality determination device based on remote data, characterized in that: Applied to the model building stage, wherein the device comprises: An acquisition module, used to acquire remote monitoring data of a first heavy-duty vehicle under a preset normal state of the SCR system and remote monitoring data of a second heavy-duty vehicle under a preset abnormal state; a generating module, configured to generate a normal state data set of the SCR system based on the first heavy-duty vehicle remote monitoring data, and to generate an abnormal state data set of the SCR system based on the second heavy-duty vehicle remote monitoring data; A construction module is used to construct an SCR system working state determination model using the normal state data set and the abnormal state data set, so as to determine the working state of the SCR system of the vehicle to be tested using the SCR system working state determination model.

8. An SCR abnormality determination device based on remote data, characterized in that: Applied to the model use stage, wherein the device comprises: A sampling module, used to obtain multiple sets of heavy-duty vehicle remote monitoring data of the vehicle to be tested based on a preset sampling frequency; A calculation module, used for determining a plurality of SCR urea consumption segments of the vehicle to be tested based on the plurality of groups of heavy-duty vehicle remote monitoring data, and calculating a characterization parameter corresponding to each SCR urea consumption segment; A determination module is used to sequentially input the characterization parameters corresponding to each SCR urea consumption segment into a pre-constructed SCR system working state determination model to obtain a plurality of initial SCR system working states of the vehicle to be tested, and obtain a final SCR system working state of the vehicle to be tested based on the plurality of initial SCR system working states, wherein the SCR system working state determination model is trained by a normal state data set and an abnormal state data set of the SCR system.

9. An electronic system, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the SCR abnormality determination method based on remote data as described in any one of claims 1-4 or 5-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the SCR abnormality determination method based on remote data as described in any one of claims 1-4 or 5-6.

Images