A management method, device, medium and equipment of a methanol vehicle emission detection strategy

Abstract

The application provides a methanol vehicle emission detection strategy management method, device, medium and equipment. The sensor configuration parameters, state parameters and historical emission detection strategy parameters of the methanol vehicle are collected; the feature information of the sensor configuration parameters is extracted; the feature information of the state parameters is extracted; and the current emission detection strategy parameters are determined based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters. That is, the sensor configuration parameters and state parameters of the methanol vehicle are collected in real time, and the feature information is extracted. The feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters are comprehensively considered to comprehensively consider the complex relationship between different parameters and the information between time sequences, so that the emission detection strategy of the methanol vehicle is more accurately determined, and the accuracy and adaptability of the detection system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of methanol vehicle emission detection, in particular to a management method and device of a methanol vehicle emission detection strategy, a medium and equipment. BACKGROUND

[0002] The methanol vehicle refers to a vehicle using methanol as fuel. The combustion of methanol not only produces conventional combustion products such as carbon dioxide, but also emits unburned formaldehyde and the like. These emissions will pollute the atmospheric environment, so it is necessary to detect the emissions.

[0003] However, the existing emission detection is mostly based on a fixed detection strategy. However, the vehicle state and the consumption of various sensors and other devices during the use of the methanol vehicle will have certain effects on the emission detection, thereby reducing the effect of the emission detection strategy of the methanol vehicle, and then affecting the accuracy and adaptability thereof. Therefore, an emission detection strategy that is accurate and suitable for the use of the methanol vehicle is needed. SUMMARY

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a management method, device, medium and equipment of a methanol vehicle emission detection strategy.

[0005] According to one aspect of the present application, a management method of a methanol vehicle emission detection strategy is provided, which comprises: collecting sensor configuration parameters, state parameters and historical emission detection strategy parameters of the methanol vehicle; extracting feature information of the sensor configuration parameters; extracting feature information of the state parameters; determining current emission detection strategy parameters based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters.

[0006] In an embodiment, the extraction of the feature information of the sensor configuration parameters comprises: performing feature extraction on the sensor configuration parameters by using a self-encoder to obtain the feature information of the sensor configuration parameters.

[0007] In an embodiment, the parameter determination method of the self-encoder comprises: performing encoding calculation on a training sample by using an encoder to obtain a sample feature of the training sample; performing decoding calculation on the sample feature by using a decoder to obtain a reconstructed sample of the sample feature; calculating a reconstruction difference between the training sample and the reconstructed sample; and if the reconstruction difference is greater than a preset difference threshold, adjusting the parameters of the encoder and the decoder until the reconstruction difference is less than the difference threshold.

[0008] In an embodiment, the extracting the feature information of the state parameter comprises: dividing the state parameter into key state parameters and non-key state parameters; merging all the non-key state parameters to obtain a merged state parameter; and obtaining the feature information of the state parameter based on the key state parameters and the merged state parameter.

[0009] In an embodiment, the merging all the non-key state parameters to obtain a merged state parameter comprises: performing weighted average calculation on all the non-key state parameters to obtain the merged state parameter.

[0010] In an embodiment, the determining the current emission detection strategy parameter based on the feature information of the sensor configuration parameter, the feature information of the state parameter and the historical emission detection strategy parameter comprises: inputting the feature information of the sensor configuration parameter, the feature information of the state parameter and the historical emission detection strategy parameter into a network model as input quantities to obtain the current emission detection strategy parameter.

[0011] In an embodiment, the network model comprises a plurality of control gates; wherein the inputting the feature information of the sensor configuration parameter, the feature information of the state parameter and the historical emission detection strategy parameter into a network model as input quantities to obtain the current emission detection strategy parameter comprises: inputting the historical emission detection strategy parameter into the plurality of control gates as input quantities to obtain the feature information of the historical emission detection strategy parameter; and inputting the feature information of the sensor configuration parameter, the feature information of the state parameter and the feature information of the historical emission detection strategy parameter into the network model as input quantities to obtain the current emission detection strategy parameter.

[0012] According to another aspect of the present application, there is provided a device for managing an emission detection strategy of a methanol vehicle, comprising: an original data acquisition module configured to acquire sensor configuration parameters, state parameters and historical emission detection strategy parameters of the methanol vehicle; a configuration feature extraction module configured to extract feature information of the sensor configuration parameters; a state feature extraction module configured to extract feature information of the state parameters; and a detection strategy determination module configured to determine a current emission detection strategy parameter based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters.

[0013] According to another aspect of the present application, there is provided a computer readable storage medium storing a computer program for executing any of the above-mentioned methods.

[0014] According to another aspect of the present application, there is provided an electronic device comprising: a processor; a memory for storing instructions executable by the processor; the processor configured to perform any of the methods described above.

[0015] The application provides a methanol vehicle emission detection strategy management method, device, medium and equipment. The sensor configuration parameters, state parameters and historical emission detection strategy parameters of a methanol vehicle are collected. The feature information of the sensor configuration parameters is extracted. The feature information of the state parameters is extracted. The current emission detection strategy parameters are determined based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters. That is, the sensor configuration parameters and the state parameters of the methanol vehicle are collected in real time, and the feature information is extracted. The feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters are comprehensively considered to comprehensively consider the complex relationship between different parameters and the information between time sequences, so that the emission detection strategy of the methanol vehicle is more accurately determined, and the accuracy and adaptability of the detection system are improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of embodiments of the present application taken in conjunction with the accompanying drawings. The accompanying drawings are provided to aid in understanding the embodiments of the present application, and constitute a part of the specification. The accompanying drawings together with the specification serve to explain the present application, and do not constitute a limitation on the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 FIG. 1 is a flowchart of a methanol vehicle emission detection strategy management method according to an example embodiment of the present application.

[0018] Figure 2 FIG. 2 is a structural diagram of a methanol vehicle emission detection strategy management device according to an example embodiment of the present application.

[0019] Figure 3 FIG. 3 is a structural diagram of an electronic device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0020] Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein.

[0021] Figure 1 FIG. 1 is a flowchart of a methanol vehicle emission detection strategy management method according to an example embodiment of the present application. As shown in FIG. 1, the methanol vehicle emission detection strategy management method includes the following steps: Figure 1 The sensor configuration parameters, state parameters and historical emission detection strategy parameters of a methanol vehicle are collected. The feature information of the sensor configuration parameters is extracted. The feature information of the state parameters is extracted. The current emission detection strategy parameters are determined based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters. That is, the sensor configuration parameters and the state parameters of the methanol vehicle are collected in real time, and the feature information is extracted. The feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters are comprehensively considered to comprehensively consider the complex relationship between different parameters and the information between time sequences, so that the emission detection strategy of the methanol vehicle is more accurately determined, and the accuracy and adaptability of the detection system are improved.

[0022] Step 110: Collect sensor configuration parameters, status parameters, and historical emission detection strategy parameters of the methanol vehicle.

[0023] The data acquisition system of this application consists of three main parts working together: a cloud platform, a T-BOX, and emission testing equipment. The cloud platform serves as the core data processing and storage hub, undertaking key tasks such as data management, analysis, and equipment calibration. The T-BOX acts as a bridge between the vehicle and the cloud platform, responsible for collecting and uploading vehicle operation data. The emission testing equipment focuses on the accurate collection of exhaust emission data. These three parts work closely together to achieve comprehensive, efficient collection, transmission, and in-depth processing of various data from methanol vehicles.

[0024] The T-BOX is the core device for vehicle data acquisition, connecting to the complex electronic control unit (ECU) network inside the methanol vehicle via a standard OBD interface. The OBD interface follows specific communication protocols, such as ISO 15765 and SAE J1939. The T-BOX utilizes its integrated protocol parsing chip to analyze signals transmitted from the ECU according to these protocols, thereby acquiring a wealth of vehicle operating data. This includes data such as vehicle speed, engine speed, coolant temperature, and oil pressure.

[0025] These data are collected rapidly at a set frequency (e.g., once per second). The collected data is initially processed and cached in the high-speed cache chip inside the T-BOX, waiting to be aligned with the data from the emission detection equipment.

[0026] The emission detection equipment is installed at a key location in the exhaust pipe of methanol vehicles. It uses a variety of advanced sensor technologies to achieve real-time and accurate detection of various emissions and their concentrations.

[0027] Carbon monoxide (CO) and carbon dioxide (CO) Detection: A non-dispersive infrared (NDIR) sensor is used, which detects concentration based on the absorption characteristics of different gases for specific wavelengths of infrared light. Taking CO detection as an example, when infrared light passes through exhaust gas containing CO, some of the infrared light is absorbed by CO, according to Lambert-Beer's Law. The CO concentration was calculated, where The intensity of infrared radiation after the exhaust gas passes through. The initial infrared intensity, This represents the absorption coefficient of CO for a specific wavelength of infrared light. CO concentration, This represents the propagation path length of infrared light in the exhaust gas. This is achieved by measuring... and known The CO concentration can then be calculated.

[0028] Nitrogen oxides (NOx) detection: A chemiluminescence sensor is used to react NOx in the exhaust gas with a specific chemical reagent to generate a light signal. The intensity of the light signal is proportional to the NOx concentration. The light signal is converted into an electrical signal by a photodetector, and after amplification and processing, the NOx concentration is calculated based on a pre-calibrated light intensity-concentration curve.

[0029] Particulate matter (PM) detection: Particulate matter sensors are used, such as electrostatic induction sensors or laser scattering sensors. Taking electrostatic induction sensors as an example, particulate matter generates electrostatic charges when moving in exhaust gas. The amount of charge detected by the sensor is related to the mass concentration or number concentration of particulate matter. The PM concentration is calculated by using the calibrated charge-concentration relationship.

[0030] The emission detection equipment collects emission data at a set frequency (e.g., once every 5 seconds) and temporarily stores this data in a local high-performance flash memory chip.

[0031] Because the T-BOX and emissions testing equipment have different data acquisition frequencies, strict data alignment processing is required to ensure the consistency and correlation of the data uploaded to the cloud platform. Both the T-BOX and emissions testing equipment have built-in high-precision real-time clock modules (RTC) and achieve time synchronization through GPS or network time synchronization to ensure that each data point is accurately timestamped.

[0032] Before data transmission, a time window-based pairing algorithm is used. A time error range (e.g., ±0.5 seconds) is set as the time window. For vehicle operation data collected by the T-BOX at a certain moment, emission data with timestamps within this time window are searched for and paired in the emission detection equipment's data. For example, for vehicle speed data at 10:00:00, emission data with timestamps between 9:59:59.5 and 10:00:00.5 are searched for and paired to form a complete dataset for subsequent uploading to the cloud platform for unified analysis.

[0033] The data after data alignment processing is uploaded to the cloud platform through a high-speed and stable wireless network (such as 4G, 5G). T-BOX and emission detection equipment respectively establish a reliable TCP / IP connection with the cloud platform through the built-in communication module (such as 4G / 5G module), and send the packaged data to the specified server port of the cloud platform according to the specific communication protocol (such as MQTT, HTTP). After receiving the data, the cloud platform first performs data format verification to ensure the integrity and accuracy of the data, and then stores different types of data in the corresponding database table, such as storing vehicle operation data in the vehicle operation data table of the MySQL relational database and storing emission data in the InfluxDB time series database, to prepare for subsequent data analysis and processing.

[0034] The cloud platform configures a special emission detection equipment accuracy calculation algorithm to regularly calibrate the emission detection equipment and ensure its long-term stable and accurate operation. A large number of emission data samples under different working conditions are collected, including the concentration data of exhaust emissions of the vehicle under idle, acceleration, constant speed, and deceleration. The collected data is preprocessed to remove abnormal values and noise data. For example, for CO concentration data, if a data point exceeds the normal range (such as greater than 10%) and differs greatly from the previous and subsequent data points, it is determined as an abnormal value and is removed.

[0035] Combined with the running conditions of the vehicle (such as vehicle speed, engine speed, etc.), the theoretical emission concentration value of each sample is calculated using an empirical formula or a method based on a physical model. Taking NOx emission as an example, for a certain engine speed and load rate , the theoretical NOx concentration is calculated according to the empirical formula , where is the empirical coefficient

[0036] The actual concentration value measured by the emission detection equipment is compared with the theoretical concentration value to calculate the deviation value . By statistical methods (such as the least squares method), a large number of deviation values are analyzed to determine the systematic error and random error of the emission detection equipment. Let the measured data be (the actual concentration value), the theoretical value be , and the fitted straight line equation be . According to the least squares method, the and values that make minimum are solved, where represents the systematic error, represents the deviation of measurement sensitivity.

[0037] Based on the error analysis results, calibration parameters are generated, such as the sensor gain coefficient. and offset For a linear sensor, if the actual measurement sensitivity is... The theoretical sensitivity is Then the gain coefficient Offset .

[0038] Calibration parameters are transmitted to the emission detection equipment via a wireless network, and the equipment calibrates its own measurement data based on these parameters. For example, for newly measured emission concentration values... calibrated concentration value This improves the accuracy of measurements.

[0039] Through such a comprehensive and meticulous hardware system design and rigorous and scientific data processing procedures, it is possible to achieve comprehensive and accurate collection of methanol vehicle emission data and vehicle data. Furthermore, through the calibration algorithm of the cloud platform, the long-term stability and accuracy of the emission detection equipment are ensured, providing solid and reliable data support for methanol vehicle emission monitoring and vehicle operation status analysis.

[0040] Step 120: Extract feature information of sensor configuration parameters.

[0041] The sensor configuration parameters specifically include four dimensions: sensor type, number of sensors, sensor location, and monitored object. All sensor configuration parameters form a high-dimensional data set, with each parameter carrying a timestamp. This application reduces the data volume of sensor configuration parameters by extracting their feature information, thereby reducing the computational complexity for determining subsequent emission detection strategy parameters.

[0042] Step 130: Extract feature information of state parameters.

[0043] The state parameters of methanol vehicles include multiple states across multiple dimensions, and each state parameter carries a timestamp. This application reduces the amount of data for state parameters by extracting feature information, thereby reducing the computational difficulty for determining subsequent emission detection strategy parameters.

[0044] Step 140: Determine the current emission detection strategy parameters based on the feature information of the sensor configuration parameters, the feature information of the state parameters, and the historical emission detection strategy parameters.

[0045] This application combines the characteristic information of sensor configuration parameters, the characteristic information of state parameters, and historical emission detection strategy parameters. Under the premise of integrating data from multiple dimensions, it also considers the correlation of emission detection strategies over time, so as to improve the accuracy and adaptability of the current emission detection strategy.

[0046] This application provides a management method for methanol vehicle emission detection strategies. This method involves collecting sensor configuration parameters, status parameters, and historical emission detection strategy parameters of the methanol vehicle; extracting feature information from the sensor configuration parameters; extracting feature information from the status parameters; and determining the current emission detection strategy parameters based on the feature information from the sensor configuration parameters, status parameters, and historical emission detection strategy parameters. Specifically, by collecting sensor configuration parameters and status parameters of the methanol vehicle in real time and extracting their feature information, and by integrating the feature information from the sensor configuration parameters, status parameters, and historical emission detection strategy parameters, the method comprehensively considers the complex relationships between different parameters and the information between time series, thereby more accurately determining the emission detection strategy for the methanol vehicle and improving the accuracy and adaptability of the detection system.

[0047] In one embodiment, step 120 can be implemented by using an autoencoder to extract features from the sensor configuration parameters to obtain feature information of the sensor configuration parameters.

[0048] This application employs an autoencoder to extract features and reduce the dimensionality of sensor configuration parameters. The autoencoder includes an encoder and a decoder. Specifically, the high-dimensional data set formed by the sensor configuration parameters is denoted as... (wherein, the dimension is) The encoder converts high-dimensional data into... Mapping to a low-dimensional latent space representation The decoder then represents the low-dimensional representation. The original data space is restored, and feature information of the sensor configuration parameters is extracted through encoding and decoding operations.

[0049] In one embodiment, the method for determining the parameters of the autoencoder may be as follows: an encoder is used to encode and calculate the training samples to obtain the sample features of the training samples; a decoder is used to decode and calculate the sample features to obtain the reconstructed samples of the sample features; the reconstruction difference between the training samples and the reconstructed samples is calculated; if the reconstruction difference is greater than a preset difference threshold, the parameters of the encoder and the decoder are adjusted until the reconstruction difference is less than the difference threshold.

[0050] Specifically, the encoding process can be implemented using a fully connected neural network, for example:

[0051]

[0052] in, For activation functions (such as ReLU). and These are the weight matrices and bias vectors for each layer. The calculation results for each layer, The number of layers in the encoder. Dimensions This refers to the dimension after dimensionality reduction, which mainly reflects the types of sensor configurations and the configuration strategies for each type of sensor.

[0053] The decoder is used for error calculation during training. It adjusts the parameters of the encoder and decoder through backpropagation to minimize the reconstruction differences, for example:

[0054]

[0055] in, and These are the weight matrices and bias vectors for each layer. The calculation results for each layer, This represents the number of layers in the decoder.

[0056] The formula for calculating the reconstruction difference is:

[0057]

[0058] in, For the sample size, and The first The original and reconstructed data of each sample.

[0059] In one embodiment, step 130 can be implemented as follows: dividing the state parameters into key state parameters and non-key state parameters; merging all non-key state parameters to obtain merged state parameters; and obtaining the feature information of the state parameters based on the key state parameters and the merged state parameters.

[0060] For the state parameters of methanol vehicles (Assuming it contains) The state parameters are divided into several state dimensions (state values). Based on a state-focused strategy, key state dimensions are identified. For example, by analyzing historical data or expert knowledge, certain state dimensions (such as engine speed, vehicle speed, and intake air volume) are determined to have a significant impact on the emission detection strategy, and these key state dimensions are marked. Non-key state dimensions are merged into a new feature dimension, thereby reducing the dimensionality of the state parameters to a single feature dimension. dimension( It retains key status information and highlights the impact of key status dimensions on emission detection strategies.

[0061] In one embodiment, step 130 can be implemented by performing a weighted average calculation on all non-key state parameters to obtain the merged state parameters.

[0062] For non-key state dimensions, the application can use simple weighted average or other fusion methods to combine them into a new feature dimension.

[0063] In an embodiment, the specific implementation of step 140 can be: inputting the feature information of the sensor configuration parameters, the feature information of the state parameters, and the historical emission detection strategy parameters as input quantities into the network model to obtain the current emission detection strategy parameters.

[0064] The reduced dimension sensor configuration parameters and the methanol vehicle state parameters are spliced together as part of the input of the neural network, with a dimension of , and the historical emission detection strategy parameters are input as input quantities into the neural network model to obtain the current emission detection strategy parameters.

[0065] In an embodiment, the network model includes multiple control gates; wherein the specific implementation of step 140 can be: inputting the historical emission detection strategy parameters as input quantities into the multiple control gates to obtain the feature information of the historical emission detection strategy parameters; inputting the feature information of the sensor configuration parameters, the feature information of the state parameters, and the feature information of the historical emission detection strategy parameters as input quantities into the network model to calculate the current emission detection strategy parameters.

[0066] The long short-term memory (LSTM) model is used to extract features from the historical emission detection strategy parameters. Assuming that the historical emission detection strategy parameters include detection frequency data of multiple sensors at multiple time steps , the data is sorted into a sequence format suitable for LSTM input to obtain the current emission detection strategy parameters, wherein is the detection frequency vector at the th time step.

[0067] Specifically, LSTM processes time series data through a gating mechanism, and its core formula is as follows:

[0068] Input gate:

[0069]

[0070]

[0071] State update:

[0072]

[0073] Output gate:

[0074]

[0075] wherein, is a sigmoid function, and are sigmoid function values, tanh is a hyperbolic tangent function, is a hyperbolic tangent function value, , are weight matrices, are bias vectors, is an output hidden state of the LSTM at the time step, is a state parameter at the time step.

[0076] After the LSTM processing, the output hidden state at the last time step is taken as a reduced dimension representation of the historical emission detection strategy parameter, and the dimension is The time sequence feature not only captures the trend of the change of the historical detection strategy, but also serves as an input directly affecting the structure parameters of the neural network model and a parameter directly affecting a special neuron of the neural network. Meanwhile, the reduced dimension sensor configuration parameter and the methanol vehicle state parameter are spliced together as part of the input of the neural network. The reduced dimension sensor configuration parameter , the methanol vehicle state parameter and the feature information of the historical emission detection strategy parameter can also be spliced together as part of the input of the neural network.

[0077] Figure 2 is a structural schematic diagram of a methanol vehicle emission detection strategy management device provided by an exemplary embodiment of the present application. As shown in Figure 2 , the methanol vehicle emission detection strategy management device 20 comprises: an original data acquisition module 21, configured to acquire sensor configuration parameters, state parameters and historical emission detection strategy parameters of a methanol vehicle; a configuration feature extraction module 22, configured to extract feature information of the sensor configuration parameters; a state feature extraction module 23, configured to extract feature information of the state parameters; and a detection strategy determination module 24, configured to determine a current emission detection strategy parameter based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters.

[0078] The application provides a management device of a methanol vehicle emission detection strategy, which acquires sensor configuration parameters, state parameters and historical emission detection strategy parameters of a methanol vehicle through an original data acquisition module 21; a configuration feature extraction module 22 extracts feature information of the sensor configuration parameters; a state feature extraction module 23 extracts feature information of the state parameters; and a detection strategy determination module 24 determines current emission detection strategy parameters based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters; that is, by acquiring the sensor configuration parameters and the state parameters of the methanol vehicle in real time and extracting the feature information therein, the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters are comprehensively considered to comprehensively consider the complex relationship between different parameters and the information between time sequences, so that the emission detection strategy of the methanol vehicle is more accurately determined, and the accuracy and adaptability of the detection system are improved.

[0079] In an embodiment, the configuration feature extraction module 22 can be further configured to extract features of the sensor configuration parameters by using a self-encoder, to obtain the feature information of the sensor configuration parameters.

[0080] In an embodiment, the configuration feature extraction module 22 can be further configured to encode and calculate training samples by using an encoder to obtain sample features of the training samples, decode and calculate the sample features by using a decoder to obtain reconstructed samples of the sample features, calculate reconstruction differences between the training samples and the reconstructed samples, and adjust parameters of the encoder and the decoder until the reconstruction differences are less than a preset difference threshold if the reconstruction differences are greater than the preset difference threshold.

[0081] In an embodiment, the state feature extraction module 23 can be further configured to divide the state parameters into key state parameters and non-key state parameters, combine all the non-key state parameters to obtain combined state parameters, and obtain the feature information of the state parameters based on the key state parameters and the combined state parameters.

[0082] In an embodiment, the state feature extraction module 23 can be further configured to perform weighted average calculation on all the non-key state parameters to obtain the combined state parameters.

[0083] In an embodiment, the detection strategy determination module 24 can be further configured to input the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters as input quantities into a network model to obtain the current emission detection strategy parameters.

[0084] In an embodiment, the network model comprises a plurality of control gates; wherein the detection strategy determination module 24 can be further configured to: input the historical emission detection strategy parameters as input quantities into the plurality of control gates to obtain feature information of the historical emission detection strategy parameters; input the feature information of the sensor configuration parameters, the feature information of the state parameters and the feature information of the historical emission detection strategy parameters as input quantities into the network model to calculate the current emission detection strategy parameters.

[0085] In the following, an electronic device according to embodiments of the application will be described with reference to Figure 3 The electronic device can be either one or both of the first and second devices, or a standalone device independent of them, which can communicate with the first and second devices to receive the acquired input signals therefrom.

[0086] Figure 3 Fig. 1 illustrates a block diagram of an electronic device according to embodiments of the application.

[0087] As shown in Fig. 1, the electronic device 10 comprises one or more processors 11 and a memory 12. Figure 3 The processor 11 can be a central processing unit (CPU), or other form of processing unit having data processing and / or instruction executing capabilities, and can control other components in the electronic device 10 to perform desired functions.

[0088] The memory 12 can comprise one or more computer program products, which can comprise various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read-only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, which can be run by the processor 11 to implement the methods according to the embodiments of the application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, and the like can also be stored in the computer-readable storage media.

[0089] In one example, the electronic device 10 can further comprise input means 13 and output means 14, which are interconnected through a bus system and / or other form of connection mechanism (not shown).

[0090] When the electronic device is a standalone device, the input means 13 can be a communication network connector for receiving the acquired input signals from the first and second devices.

[0091] When the electronic device is a standalone device, the input means 13 can be a communication network connector for receiving the acquired input signals from the first and second devices.

[0092] In addition, the input device 13 can include, for example, a keyboard, a mouse, and the like.

[0093] The output device 14 can output various information, including the determined distance information, direction information, and the like, to the outside. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0094] Of course, in order to simplify, Figure 3 Only some of the components in the electronic device 10 related to the present application are shown in FIG. 1, and components such as a bus, an input / output interface, and the like are omitted. In addition, the electronic device 10 can include any other appropriate components according to a specific application.

[0095] In addition to the methods and devices described above, an embodiment of the present application can be a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform steps of the methods according to various embodiments of the present application described in the above "Exemplary Methods" section of the specification.

[0096] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, and the like, and conventional procedural programming languages, such as the "C" programming language, or the like, for executing operations of embodiments of the present application. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server.

[0097] In addition, an embodiment of the present application can also be a computer readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps of the methods according to various embodiments of the present application described in the above "Exemplary Methods" section of the specification.

[0098] The computer readable storage medium can be a combination of one or more computer readable media. The computer readable media can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] The above description of the disclosed aspects is merely exemplary in nature and is not intended to limit the present disclosure, application, and uses. The description of the aspects together with the accompanying drawings are intended to illustrate and not to limit the scope of the disclosure. The scope of the disclosure is given by the appended claims, and their equivalents.

[0100] The block diagrams of the devices, apparatuses, systems, etc. involved in the present disclosure are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. shown in the block diagrams are required or implied. As will be recognized by one of ordinary skill in the art, the devices, apparatuses, systems, etc. can be connected, arranged, configured, etc. in any manner. Words such as "include," "contain," "have," etc. are used synonymously with each other and mean "including but not limited to." The word "or" is used synonymously with "and / or" unless context clearly indicates otherwise. The word "such as" is used synonymously with the phrase "such as but not limited to."

[0101] It is also important to note that the devices, apparatuses, and methods described in the present disclosure can be embodied in a variety of other forms; thus, the specific design features are not to be construed as limitations on the scope of the disclosure. Rather, the specific design features should be understood to be merely exemplary in nature and not limiting.

[0102] The above description of the disclosed aspects is merely exemplary in nature and is not intended to limit the present disclosure, application, and uses. The description of the aspects together with the accompanying drawings are intended to illustrate and not to limit the scope of the disclosure. The scope of the disclosure is given by the appended claims, and their equivalents.

[0103] The above description has been given for illustrative and descriptive purposes. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method of managing a methanol vehicle emission detection strategy, characterized by, The method comprises the following steps: Collecting sensor configuration parameters, state parameters and historical emission detection strategy parameters of the methanol vehicle; wherein the sensor configuration parameters comprise four-dimensional data of sensor type, sensor quantity, sensor position and sensor monitoring object; Extracting feature information of the sensor configuration parameters; Extracting feature information of the state parameters; Determining current emission detection strategy parameters based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters; The determination of the current emission detection strategy parameters based on the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters comprises: Inputting the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters into a network model as input quantities to obtain the current emission detection strategy parameters; The network model comprises a plurality of control gates; wherein the inputting of the feature information of the sensor configuration parameters, the feature information of the state parameters and the historical emission detection strategy parameters into the network model as input quantities to obtain the current emission detection strategy parameters comprises: Inputting the historical emission detection strategy parameters into the plurality of control gates as input quantities to obtain feature information of the historical emission detection strategy parameters; Inputting the feature information of the sensor configuration parameters, the feature information of the state parameters and the feature information of the historical emission detection strategy parameters into the network model as input quantities to calculate the current emission detection strategy parameters.

2. The method of claim 1, wherein the method further comprises: The extraction of the feature information of the sensor configuration parameters comprises: Using an autoencoder to extract features of the sensor configuration parameters to obtain the feature information of the sensor configuration parameters.

3. The method of claim 2, wherein the method further comprises: The parameter determination method of the autoencoder comprises: Using an encoder to encode and calculate training samples to obtain sample features of the training samples; Using a decoder to decode and calculate the sample features to obtain reconstructed samples of the sample features; Calculating reconstruction differences between the training samples and the reconstructed samples; If the reconstruction differences are greater than a preset difference threshold, adjusting parameters of the encoder and the decoder until the reconstruction differences are less than the difference threshold.

4. The method of claim 1, wherein the method further comprises: The extraction of the feature information of the state parameters comprises: Dividing the state parameters into key state parameters and non-key state parameters; Combining all the non-key state parameters to obtain combined state parameters; Based on the key state parameters and the combined state parameters, obtaining the feature information of the state parameters.

5. The method of claim 4, wherein the method further comprises: The combination of all the non-key state parameters to obtain the combined state parameters comprises: Performing weighted average calculation on all the non-key state parameters to obtain the combined state parameters.

6. A management device for a methanol vehicle emission detection strategy, characterized by, The method comprises the following steps: An original data acquisition module is configured to collect sensor configuration parameters, state parameters and historical emission detection strategy parameters of the methanol vehicle; wherein the sensor configuration parameters comprise four-dimensional data of sensor type, sensor quantity, sensor position and sensor monitoring object; A configuration feature extraction module is configured to extract feature information of the sensor configuration parameters; The state feature extraction module is configured to extract feature information of the state parameter; The detection strategy determination module is configured to determine a current emission detection strategy parameter based on the feature information of the sensor configuration parameter, the feature information of the state parameter, and the historical emission detection strategy parameter; The detection strategy determination module is configured to: input the feature information of the sensor configuration parameter, the feature information of the state parameter, and the historical emission detection strategy parameter as input quantities into a network model to obtain a current emission detection strategy parameter; The network model includes a plurality of control gates; wherein the detection strategy determination module is configured to: input the historical emission detection strategy parameter as an input quantity into the plurality of control gates to obtain feature information of the historical emission detection strategy parameter; input the feature information of the sensor configuration parameter, the feature information of the state parameter, and the feature information of the historical emission detection strategy parameter as input quantities into the network model to calculate a current emission detection strategy parameter.

7. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is configured to execute the method in any one of claims 1-5.

8. An electronic device, comprising: comprise: a processor; a memory for storing instructions executable by the processor; the processor is configured to execute the method in any one of claims 1-5.

Images