Methanol vehicle running state monitoring method and device, medium and equipment

Abstract

The invention provides a running state monitoring method and device of a methanol vehicle, a medium and equipment. The running state monitoring method comprises the steps that state parameters of the methanol vehicle are collected; wherein the state parameters comprise emission parameters and operation parameters; calculating a quantized state value of the state parameter based on the state parameter; identifying an abnormal state value in the quantized state values; extracting time sequence characteristics of the quantized state value; extracting time sequence characteristics of the abnormal state values; based on the state parameters, the time sequence characteristics of the quantized state values and the time sequence characteristics of the abnormal state values, the running state of the methanol vehicle is determined; according to the method, emission parameters and operation parameters of the methanol vehicle are collected, quantized state values are calculated, abnormal state values in the quantized state values are recognized, time sequence characteristics of the quantized state values and the abnormal state values are extracted, and monitoring of the operation state of the methanol vehicle is comprehensively achieved by combining the emission parameters and the operation parameters. The running state of the methanol vehicle is comprehensively monitored from multiple dimensions of state parameters, time sequence characteristics and the like, so that the accuracy of running state monitoring is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of methanol vehicle monitoring, in particular to a methanol vehicle running state monitoring method, device, medium and equipment. BACKGROUND

[0002] The methanol vehicle is 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 other substances, which pollute the atmospheric environment. When the methanol vehicle has an abnormal fault, it will be reflected not only in the running monitoring data of the methanol vehicle, but also in the emission monitoring data of the methanol vehicle. Therefore, the running state of the methanol vehicle can be monitored by detecting the emission data, but it is difficult to accurately monitor through single-dimensional emission monitoring data. Therefore, a method for more accurately monitoring the running state of the methanol vehicle is needed. SUMMARY

[0003] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a methanol vehicle running state monitoring method, device, medium and equipment.

[0004] According to one aspect of the present application, a methanol vehicle running state monitoring method is provided, comprising: collecting state parameters of the methanol vehicle; wherein the state parameters include emission parameters and running parameters; calculating a quantitative state value of the state parameters based on the state parameters; identifying an abnormal state value in the quantitative state value; extracting a time sequence feature of the quantitative state value; extracting a time sequence feature of the abnormal state value; determining the running state of the methanol vehicle based on the state parameters, the time sequence feature of the quantitative state value and the time sequence feature of the abnormal state value.

[0005] In an embodiment, the calculation of the quantitative state value of the state parameters based on the state parameters comprises: inputting the state parameters into a first neural network model to obtain the quantitative state value; wherein the first neural network model comprises a plurality of hidden layers and an output layer, the plurality of hidden layers use a ReLU activation function, and the output layer uses a linear activation function.

[0006] In an embodiment, the identification of the abnormal state value in the quantitative state value comprises: identifying a quantitative state value less than a healthy state threshold value in the quantitative state value as the abnormal state value.

[0007] In an embodiment, the determination of the healthy state threshold value comprises: calculating the average value and the standard deviation of the quantitative state value; and calculating the healthy state threshold value based on the average value and the standard deviation of the quantitative state value.

[0008] In one embodiment, extracting the time series features of the quantized state value includes: inputting the quantized state value into a second neural network model to obtain the time series features of the quantized state value; wherein the input dimension of the second neural network model is 1.

[0009] In one embodiment, extracting the time series features of the abnormal state value includes: inputting two adjacent abnormal state values ​​into a third neural network model to obtain the time series features of the abnormal state value; wherein the input dimension of the third neural network model is 2.

[0010] In one embodiment, determining the operating state of the methanol vehicle based on the state parameters, the time series characteristics of the quantified state values, and the time series characteristics of the abnormal state values ​​includes: concatenating the state parameters, the time series characteristics of the quantified state values, and the time series characteristics of the abnormal state values ​​to obtain an input quantity; and inputting the input quantity into a trained fourth neural network model to obtain the operating state of the methanol vehicle.

[0011] According to another aspect of the present application, a running status monitoring device for a methanol vehicle is provided, comprising: a state parameter acquisition module for acquiring the state parameters of the methanol vehicle; wherein the state parameters include emission parameters and running parameters; a quantitative state calculation module for calculating the quantitative state values ​​of the state parameters based on the state parameters; an abnormal state identification module for identifying abnormal state values ​​in the quantitative state values; a quantitative timing extraction module for extracting the timing characteristics of the quantitative state values; an abnormal timing extraction module for extracting the timing characteristics of the abnormal state values; and an running status determination module for determining the running status of the methanol vehicle based on the state parameters, the timing characteristics of the quantitative state values ​​and the timing characteristics of the abnormal state values.

[0012] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above methods.

[0013] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor for executing any of the above methods.

[0014] The application provides a methanol vehicle running state monitoring method, device, medium and equipment. The method comprises the following steps: collecting state parameters of the methanol vehicle; wherein the state parameters comprise emission parameters and running parameters; calculating quantitative state values of the state parameters based on the state parameters; identifying abnormal state values in the quantitative state values; extracting time sequence characteristics of the quantitative state values; extracting time sequence characteristics of the abnormal state values; and determining a running state of the methanol vehicle based on the state parameters, the time sequence characteristics of the quantitative state values and the time sequence characteristics of the abnormal state values. The emission parameters and the running parameters of the methanol vehicle are collected, the quantitative state values are calculated and the abnormal state values are identified, the time sequence characteristics of the quantitative state values and the abnormal state values are extracted, and the running state of the methanol vehicle is monitored in combination with the emission parameters and the running parameters, so that the running state of the methanol vehicle is monitored in multiple dimensions such as the state parameters and the time sequence characteristics, and the accuracy of the running state monitoring is improved. BRIEF DESCRIPTION OF DRAWINGS

[0015] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0016] Figure 1 FIG. 1 is a flowchart of a methanol vehicle running state monitoring method according to an example embodiment of the present application.

[0017] Figure 2 FIG. 2 is a structural diagram of a methanol vehicle running state monitoring device according to an example embodiment of the present application.

[0018] Figure 3 FIG. 3 is a structural diagram of an electronic device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0019] 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 of the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein.

[0020] Figure 1 FIG. 1 is a flowchart of a methanol vehicle running state monitoring method according to an example embodiment of the present application. As shown in FIG. 1, the methanol vehicle running state monitoring method comprises the following steps: Figure 1 Step 110: collecting state parameters of the methanol vehicle.

[0021] ​The state parameters include emission parameters and operating parameters. Specifically, the emission parameters can include formaldehyde emission concentration, carbon monoxide emission concentration, nitrogen oxide emission concentration, etc., and the operating parameters can include vehicle speed, engine speed, oil temperature, water temperature, etc. The application can periodically collect state parameters (e.g., once per second) and add timestamps to the collected state parameters to form a time series data set.

[0022] Preferably, after collecting the state parameters of the methanol vehicle, the application can normalize the state parameters to improve the data consistency of subsequent calculations. Specifically, for each monitoring parameter representing a certain emission parameter or operating parameter mentioned above), it is normalized to the interval [0, 1] using the following formula:

[0023] wherein and are the minimum and maximum values of the parameter in the historical data set, respectively. For example, for the formaldehyde emission concentration, assuming that the minimum value collected in the past period is and the maximum value is , then the formaldehyde emission concentration normalization value at a certain time is: .

[0024] Step 120: Based on the state parameters, the quantized state value of the state parameters is calculated.

[0025] The application fuses multiple categories of state parameters to calculate a quantized state value that can represent the comprehensive state, and uses a single quantized state value with a timestamp to represent the health or abnormality of the state parameters of the methanol vehicle.

[0026] Step 130: Identify abnormal state values in the quantized state value.

[0027] After calculating the quantized state value of the state parameters, the application identifies abnormal state values in the quantized state value to determine the abnormal time points and corresponding quantized state values of the methanol vehicle during operation.

[0028] Step 140: Extract the time sequence features of the quantized state value.

[0029] The application extracts the correlation features between the quantized state values with timestamps to obtain the time sequence features of the quantized state values, so that the features can be correlated in the time sequence dimension to improve the accuracy of the operating state monitoring.

[0030] Step 150: Extract the time sequence features of the abnormal state value.​

[0031] The application extracts the correlation features between the abnormal state values with timestamps to obtain the timing features of the abnormal state values, so that the time correlation of the abnormal state can be determined from the timing dimension to improve the accuracy of the abnormal running state monitoring.

[0032] Step 160: determining the running state of the methanol vehicle based on the state parameters, the timing features of the quantitative state values and the timing features of the abnormal state values.

[0033] After obtaining the timing features of the quantitative state values and the timing features of the abnormal state values, the application combines the collected state parameters, the timing features of the quantitative state values and the timing features of the abnormal state values to comprehensively determine the running state of the methanol vehicle, so as to ensure the accuracy of the running state monitoring.

[0034] The application provides a methanol vehicle running state monitoring method, which comprises the following steps: collecting state parameters of the methanol vehicle; wherein the state parameters include emission parameters and running parameters; calculating quantitative state values of the state parameters based on the state parameters; identifying abnormal state values in the quantitative state values; extracting timing features of the quantitative state values; extracting timing features of the abnormal state values; and determining the running state of the methanol vehicle based on the state parameters, the timing features of the quantitative state values and the timing features of the abnormal state values. That is, the emission parameters and the running parameters of the methanol vehicle are collected, the quantitative state values are calculated and the abnormal state values are identified, the timing features of the quantitative state values and the abnormal state values are extracted, and the running state of the methanol vehicle is monitored comprehensively based on the emission parameters and the running parameters, so as to monitor the running state of the methanol vehicle from multiple dimensions such as the state parameters and the timing features, thereby improving the accuracy of the running state monitoring.

[0035] In an embodiment, the specific implementation of step 120 can be: inputting the state parameters into a first neural network model to obtain the quantitative state values; wherein the first neural network model comprises multiple hidden layers and an output layer, the multiple hidden layers adopt ReLU activation functions, and the output layer adopts a linear activation function.

[0036] The application adopts a multilayer perceptron (MLP) as the first neural network model, which comprises an input layer, multiple hidden layers and an output layer, wherein the hidden layers adopt ReLU activation functions, and the output layer adopts a linear activation function. Specifically, the number of input layer neurons is equal to the sum of the emission parameters and the running parameters. Assuming that there are parameters in total, then . .

[0037] The first hidden layer is set to neurons, using ReLU as the activation function, the weight matrix is a matrix of size , the bias vector is a vector of length .

[0038] The second hidden layer is set up with neurons, the weight matrix is a matrix of size , the bias vector is a vector of length

[0039] , again using ReLU activation function. The output layer has one neuron, the weight matrix is a matrix of size ( i.e. a row vector of dimension

[0040] ), the bias vector is a vector of length 1, using linear activation function. The data transformation from the input layer to the first hidden layer is given by: where is the normalized input parameter vector, is the output vector of the first hidden layer, the th element of is given by: where is the element in the i th row and j th column of , and is the i th element of .

[0041] The first hidden layer to the second hidden layer: where is the output vector of the second hidden layer, the th element of is given by: where is the element in the th row and th column of k , and i is the th element of .k elements.

[0042] Second hidden layer to output layer: ; Output quantized state value for: ; in, for No. k elements.

[0043] In one embodiment, a specific implementation of the above step 130 may be: identifying a quantized state value that is less than a healthy state threshold among the quantized state values ​​as an abnormal state value.

[0044] This application sets a health status threshold to identify abnormal state values ​​in the quantitative state value, thereby determining the abnormal state moment and corresponding abnormal state value during the operation of the methanol vehicle. This application can also create a data storage structure (such as a database table or Python The list in () is used to record the quantized state value of the methanol vehicle with a timestamp. Each time the neural network model outputs a quantized state value y , compare it to the current timestamp t Recorded together as a tuple ( t, y ) and stored in the structure.

[0045] In one embodiment, the health status threshold may be determined by calculating the average value and standard deviation of the quantified state values; and calculating the health status threshold based on the average value and standard deviation of the quantified state values.

[0046] This application can calculate the mean of the quantitative state value by statistically analyzing the historical data of a large number of normal methanol vehicles running under different working conditions. and standard deviation For example, suppose that after The analysis of the normal quantitative state values ​​of the group shows that the mean of the quantitative state values ​​is , the standard deviation is , then the health status threshold Can be set to ,in is a constant determined according to the actual situation. For example, (It means that when the quantitative status value is lower than the mean minus two standard deviations, it is considered to be abnormal.) , then the quantized state value is recorded as an abnormal record, and the abnormal record includes time and the degree of being below the health threshold degree , degree valuedegree The calculation formula is: ; Exception records are in tuples , degree The data is stored in another data structure specifically used to store exception records.

[0047] In one embodiment, a specific implementation of the above step 140 may be: inputting the quantized state value into the second neural network model to obtain the time series characteristics of the quantized state value; wherein the input dimension of the second neural network model is 1.

[0048] The present application can use a long short-term memory network as the second neural network model to extract the timing characteristics of the quantized state value, wherein the input dimension of the long short-term memory network is 1 (i.e., there is only one input value: the quantized state value), and the hidden layer and output layer of the long short-term memory network both include multiple dimensions, for example, the dimension of the hidden layer can be set to 16 and the dimension of the output layer is set to 8 (i.e., outputting 8 dimensions of timing characteristics).

[0049] Specifically, the calculation process of the long short-term memory network is as follows: ; ; ; in, 、 and are the corresponding weight matrices, 、 and are the corresponding hidden state weight matrices, 、 and are the corresponding bias vectors, yes sigmoid function, tanh is the hyperbolic tangent function, 、 and are the corresponding function values, is the quantized state value at the current moment, is the hidden state at the previous moment, is the memory unit of the current moment, It is the memory unit of the previous moment.

[0050] After the long short-term memory network processes the entire quantized state value sequence, the hidden state at the last moment is taken as the temporal feature of the quantized state value ,Right now ,in is the length of the sequence.

[0051] In one embodiment, a specific implementation of the above step 150 may be: inputting two adjacent abnormal state values ​​into a third neural network model to obtain a time series feature of the abnormal state value; wherein the input dimension of the third neural network model is 2.

[0052] Specifically, this application uses the degree value below the health status threshold in the abnormal record and the time interval of adjacent abnormal records as input features. First, the time interval is normalized. Assume that the timestamps of adjacent abnormal records are and , time interval , the normalized time interval for: ; in, and It is the minimum and maximum value in all abnormal record time intervals.

[0053] This application can use the long short-term memory network as the third neural network model to extract the time series features of the abnormal state value, wherein the input dimension of the third neural network model is 2 (the corresponding input feature vector , ), and the hidden layer and output layer of the third neural network model both include multiple dimensions. For example, the dimension of the hidden layer can be set to 12 and the dimension of the output layer can be set to 6 (that is, 6-dimensional time series features are output).

[0054] Similarly, according to the calculation formula of the long short-term memory network mentioned above, after the long short-term memory network processes the entire abnormal record sequence, the hidden state at the last moment is taken as the temporal feature of the abnormal record ,Right now ,in, is the length of the abnormal record sequence.

[0055] In one embodiment, the specific implementation method of the above-mentioned step 160 can be: splicing the state parameters, the time series characteristics of the quantized state values ​​and the time series characteristics of the abnormal state values ​​to obtain the input quantity; inputting the input quantity into the trained fourth neural network model to obtain the operating state of the methanol vehicle.

[0056] After obtaining the time series characteristics of the quantized state value and the time series characteristics of the abnormal state value, the state parameter

[0057] Figure 2 Figure 2

[0058] ​​​​​​​​​​​​​​​​​​​The application provides a methanol vehicle running state monitoring device, which collects state parameters of the methanol vehicle through a state parameter collection module 21; wherein the state parameters include emission parameters and running parameters; a quantitative state calculation module 22 calculates quantitative state values of the state parameters based on the state parameters; an abnormal state identification module 23 identifies abnormal state values in the quantitative state values; a quantitative time sequence extraction module 24 extracts time sequence characteristics of the quantitative state values; an abnormal time sequence extraction module 25 extracts time sequence characteristics of the abnormal state values; and a running state determination module 26 determines the running state of the methanol vehicle based on the state parameters, the time sequence characteristics of the quantitative state values and the time sequence characteristics of the abnormal state values; that is, the emission parameters and the running parameters of the methanol vehicle are collected, the quantitative state values are calculated and the abnormal state values are identified, the time sequence characteristics of the quantitative state values and the abnormal state values are extracted, and the running state of the methanol vehicle is comprehensively monitored in combination with the emission parameters and the running parameters, so as to comprehensively monitor the running state of the methanol vehicle from multiple dimensions such as the state parameters and the time sequence characteristics, thereby improving the accuracy of the running state monitoring.

[0059] In an embodiment, the quantitative state calculation module 22 described above can be further configured to: input the state parameters into a first neural network model to obtain the quantitative state values; wherein the first neural network model comprises a plurality of hidden layers and an output layer, the plurality of hidden layers adopt a ReLU activation function, and the output layer adopts a linear activation function.

[0060] In an embodiment, the abnormal state identification module 23 described above can be further configured to: identify the quantitative state values less than a healthy state threshold value in the quantitative state values as the abnormal state values.

[0061] In an embodiment, the abnormal state identification module 23 described above can be further configured to: calculate the average value and the standard deviation of the quantitative state values; and calculate the healthy state threshold value based on the average value and the standard deviation of the quantitative state values.

[0062] In an embodiment, the quantitative time sequence extraction module 24 described above can be further configured to: input the quantitative state values into a second neural network model to obtain the time sequence characteristics of the quantitative state values; wherein the input dimension of the second neural network model is 1.

[0063] In an embodiment, the abnormal time sequence extraction module 25 described above can be further configured to: input two adjacent abnormal state values into a third neural network model to obtain the time sequence characteristics of the abnormal state values; wherein the input dimension of the third neural network model is 2.

[0064] In an embodiment, the running state determination module 26 described above can be further configured to: splice the state parameters, the time sequence characteristics of the quantitative state values and the time sequence characteristics of the abnormal state values to obtain an input quantity; and input the input quantity into a fourth neural network model which has been trained to obtain the running state of the methanol vehicle.

[0065] Hereinafter, an electronic device according to an embodiment of the present application will be described with reference to the accompanying drawings. Figure 3 The electronic device can be either one or both of the first and second devices, or a stand-alone device independent of them, which can communicate with the first and second devices to receive the acquired input signals therefrom.

[0066] Figure 3 FIG. 1 illustrates a block diagram of an electronic device according to an embodiment of the present application.

[0067] As shown in FIG. 1, the electronic device 10 includes 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 execution capabilities, and can control other components in the electronic device 10 to perform desired functions.

[0068] The memory 12 can include one or more computer program products, which can include 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 the processor 11 can execute to implement the methods of the various embodiments of the present 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.

[0069] In one example, the electronic device 10 can further include an input device 13 and an output device 14, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0070] When the electronic device is a stand-alone device, the input device 13 can be a communication network connector for receiving the acquired input signals from the first and second devices.

[0071] In addition, the input device 13 can further include, for example, a keyboard, a mouse, and the like.

[0072] 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.

[0073]

[0074] ​Of course, in order to simplify, Figure 3 Only some of the components of the electronic device 10 related to the present application are shown in the figure, and components such as buses, input / output interfaces, and the like are omitted. In addition to these, the electronic device 10 can include any other appropriate components according to the specific application.

[0075] In addition to the methods and devices described above, an embodiment of the present application can also 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.

[0076] 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++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages. 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.

[0077] In addition, an embodiment of the present application can also be a computer readable storage medium having stored thereon computer program instructions which, 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.

[0078] The computer readable storage medium can be any combination of one or more non-transitory media. The non-transitory medium can be a non-transitory signal medium or a non-transitory storage medium. The non-transitory storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the non-transitory storage medium include an electrical connection having one or more wires, a portable disc, 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 above.

[0079] The above describes the basic principles of the present application in combination with specific embodiments, but it needs to be pointed out that the advantages, benefits, effects and the like mentioned in the present application are only examples and are not limiting, and these advantages, benefits, effects and the like cannot be considered as necessary for each embodiment of the present application. In addition, the above specific details disclosed are only for the purpose of example and understanding, and are not limiting, and the above details do not limit the present application to be necessarily implemented with the above specific details.

[0080] The block diagrams of the devices, apparatuses, equipment, systems involved in the present application are only illustrative examples and are not intended to require or imply the connection, arrangement, configuration shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have" and the like are open-ended words, mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0081] It also needs to be pointed out that in the devices, equipment and methods of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present application.

[0082] The above description of the disclosed aspects is provided so that any person skilled in the art can make or use the present application. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but is intended to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0083] The above description has been given for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method of monitoring the operating state of a methanol vehicle, characterized by, The method comprises: collecting state parameters of the methanol vehicle; wherein the state parameters comprise emission parameters and operation parameters; calculating quantized state values of the state parameters based on the state parameters; identifying abnormal state values in the quantized state values; extracting time sequence features of the quantized state values; extracting time sequence features of the abnormal state values; determining an operation state of the methanol vehicle based on the state parameters, the time sequence features of the quantized state values, and the time sequence features of the abnormal state values; the determination of the operation state of the methanol vehicle based on the state parameters, the time sequence features of the quantized state values, and the time sequence features of the abnormal state values comprises: concatenating the state parameters, the time sequence features of the quantized state values, and the time sequence features of the abnormal state values to obtain an input quantity; inputting the input quantity into a fourth neural network model that has been trained to obtain the operation state of the methanol vehicle.

2. The method of claim 1, wherein the calculation of the quantized state values of the state parameters based on the state parameters comprises: inputting the state parameters into a first neural network model to obtain the quantized state values; wherein the first neural network model comprises multiple hidden layers and an output layer, the multiple hidden layers use a ReLU activation function, and the output layer uses a linear activation function.

3. The method of claim 1, wherein the identification of the abnormal state values in the quantized state values comprises: identifying quantized state values less than a healthy state threshold in the quantized state values as the abnormal state values.

4. The method of claim 3, wherein the determination of the healthy state threshold comprises: calculating the average value and the standard deviation of the quantized state values; calculating the healthy state threshold based on the average value and the standard deviation of the quantized state values.

5. The method of claim 1, wherein the extraction of the time sequence features of the quantized state values comprises: inputting the quantized state values into a second neural network model to obtain the time sequence features of the quantized state values; wherein the input dimension of the second neural network model is 1.

6. The method of claim 1, wherein the extraction of the time sequence features of the abnormal state values comprises: inputting adjacent two abnormal state values into a third neural network model to obtain the time sequence features of the abnormal state values; wherein the input dimension of the third neural network model is 2.

7. A running status monitoring device for a methanol vehicle, characterized in that: The method comprises: a state parameter collection module for collecting state parameters of the methanol vehicle; wherein the state parameters comprise emission parameters and operation parameters; a quantized state calculation module for calculating quantized state values of the state parameters based on the state parameters; an abnormal state identification module for identifying abnormal state values in the quantized state values; a quantized time sequence extraction module for extracting time sequence features of the quantized state values; an abnormal time sequence extraction module for extracting time sequence features of the abnormal state values; an operation state determination module for determining an operation state of the methanol vehicle based on the state parameters, the time sequence features of the quantized state values, and the time sequence features of the abnormal state values; the operation state determination module is further configured to: concatenate the state parameters, the time sequence features of the quantized state values, and the time sequence features of the abnormal state values to obtain an input quantity; input the input quantity into a fourth neural network model that has been trained to obtain the operation state of the methanol vehicle.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the method of any one of claims 1-6.

9. An electronic device, comprising: Comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to execute the method of any one of claims 1-6.

Images