Mobile source off-site supervision method and system based on Internet of Things

Abstract

The present invention relates to the field of mobile source supervision technology, and in particular to an off-site supervision method and system for mobile sources based on the Internet of Things. The method comprises the steps of: obtaining a vehicle emission data sequence and a vehicle speed data sequence; determining the change characteristics of an emission data point or a speed data point, the change characteristics being used to characterize the data change situation on the left and right sides of the emission data point or the speed data point; determining the change credibility of the emission data point; using the modulus of a vector composed of the change characteristics and the change credibility of the emission data point as the intrinsic characteristics of the emission data point; determining the correlation strength between the emission data point and the speed data point; using the modulus of a vector composed of the change characteristics and the correlation strength of the speed data point as the extrinsic characteristics of the emission data point; obtaining an off-site supervision result of a mobile source by comparing the cosine similarity of the intrinsic characteristics and the extrinsic characteristics of the emission data point with a threshold, which can effectively improve the accuracy of the off-site supervision result of the mobile source.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile source supervision, and in particular to an off-site supervision method and system for mobile sources based on the Internet of Things. Background Art

[0002] With the increase in the number of mobile sources, mobile source pollution has become an important source of air pollution in large and medium-sized cities. Mobile source pollution mainly refers to vehicles that emit pollutants into the air. Pollutants not only endanger human health, but also affect climate change and ecosystem balance. Therefore, it is necessary to monitor and manage mobile source pollution.

[0003] At present, the monitoring and management of mobile source pollution is mainly carried out by monitoring the emission of vehicles. For example, the patent application document with the publication number CN114416839A discloses an integrated mobile source emission monitoring system. The system records the behaviors that do not meet the emission standards through the detection system through the violation processing module. The violation processing module monitors the emission of vehicles through the monitoring equipment through the motor vehicle pollution control, and the corresponding vehicles with illegal emissions are matched and recorded. It is possible to carry out all-weather, all-round, and full-life cycle emission monitoring of motor vehicles, thereby realizing efficient and stable control of dynamic vehicle exhaust pollution.

[0004] Although the above-mentioned existing technical solutions can achieve the supervision of mobile sources to a certain extent, in the process of manually recording behaviors that do not meet emission standards, there may be cases of artificial tampering of data to help vehicles meet emission standards. The tampered data is relatively similar to the real monitoring data. Conventional methods cannot distinguish such data, resulting in the inability to accurately obtain mobile source emission monitoring results.

[0005] Based on this, it is necessary to propose a method for off-site supervision of mobile sources to identify whether there is tampered data in the monitoring data. Summary of the invention

[0006] In order to solve the technical problem of how to identify whether there is tampered data in the monitoring data of mobile source emissions, the present invention provides an off-site supervision method and system for mobile sources based on the Internet of Things.

[0007] In a first aspect, the present invention provides an off-site supervision method for mobile sources based on the Internet of Things, which adopts the following technical solutions:

[0008] The off-site supervision method of mobile sources based on the Internet of Things includes the following steps:

[0009] Obtain a vehicle emission data sequence and a vehicle speed data sequence, wherein the emission data points in the vehicle emission data sequence and the speed data points in the vehicle speed data sequence correspond to each other one by one; determine the change characteristics of the emission data point or the speed data point, wherein the change characteristics are used to characterize the data change on the left and right sides of the emission data point or the speed data point; obtain the difference between the data value and the fitting value of the emission data point, determine the change credibility of the emission data point, wherein the change credibility is negatively correlated with the absolute value of the difference; use the vector composed of the change characteristics and the change credibility of the emission data point as the intrinsic characteristics of the emission data point; perform curve fitting on the vehicle emission data sequence and the vehicle speed data sequence respectively, use the ratio of the slope and the intercept of the obtained emission trend line and the speed trend line as the correlation index, determine the correlation strength of the emission data point and the speed data point, wherein the correlation strength is negatively correlated with the difference of the correlation index between the emission trend line and the speed trend line; use the vector composed of the change characteristics and the correlation strength of the speed data point as the extrinsic characteristics of the emission data point; obtain the off-site supervision result of the mobile source by comparing the cosine similarity of the intrinsic characteristics and the extrinsic characteristics of the emission data point with the threshold.

[0010] When implementing off-site supervision of mobile sources, the present invention obtains data changes in the emission data sequence, and takes into account that normal fluctuations within the emission data may affect the supervision results. Therefore, the credibility of the data changes is obtained by obtaining the residual ratio of the emission data points, and the intrinsic characteristics of the emission data points are accurately obtained based on this; on this basis, the present invention also takes into account the trend correlation between vehicle speed data and vehicle emission data over a period of time, and thus further obtains the trend correlation degree between the vehicle emission data sequence and the vehicle speed data sequence, and obtains the similarity between the two by combining the intrinsic and extrinsic characteristics of the emission data points for comparison, so that the emission data that does not conform to the emission data and speed change trend can be screened out, and the tampered emission data can be accurately identified, thereby accurately obtaining the off-site supervision results of mobile sources.

[0011] According to the Internet of Things-based off-site supervision method for mobile sources of the present invention, the obtaining of vehicle emission data sequences and vehicle speed data sequences also includes: collecting vehicle emission data and vehicle speed data through sensors, and preprocessing the vehicle emission data and vehicle speed data.

[0012] The present invention can effectively improve the overall quality of emission data and speed data by preprocessing the collected raw data, and prepare for subsequent data processing.

[0013] According to the Internet of Things-based off-site supervision method for mobile sources described in the present invention, the determination of the change characteristics of the emission data point or speed data point includes: obtaining the ratio of the difference between the data value of the emission data point or speed data point and the data point on the left and the data value of the emission data point or speed data point, recorded as a first ratio; using the absolute value of the first ratio as the fluctuation index of the emission data point or speed data point; obtaining the ratio of the difference between the fluctuation index of the data points on the left and right sides of the emission data point or speed data point and the fluctuation index of the emission data point or speed data point, recorded as a second ratio; using the absolute value of the second ratio as the change characteristic of the emission data point or speed data point.

[0014] The present invention takes into account that in a continuous data sequence, there will be a certain correlation between a data point and an adjacent data point. Therefore, by analyzing the data change between the current data point and the adjacent data point, the change characteristics of the data point can be accurately obtained, wherein the data point includes an emission data point or a speed data point.

[0015] According to the mobile source off-site supervision method based on the Internet of Things of the present invention, the change credibility of the emission data point satisfies the relationship:

[0016] ;

[0017] In the formula, represents the credibility of the change of the ith emission data point, represents the data value of the ith emission data point, represents the fitted value of the ith emission data point, represents the number of emission data points in the vehicle emission data sequence, represents the data value of the jth emission data point in the vehicle emission data sequence, represents the fitted value of the jth emission data point in the vehicle emission data series, represents the exponential function with base e, Represents the absolute value symbol.

[0018] The present invention takes into account that the smaller the fitting residual of the emission data point, the more it can represent the true state of the emission data series. Therefore, by obtaining the proportion of the fitting residual of the emission data point, the credibility of the change of the emission data point is obtained. The smaller the proportion of the fitting residual of the emission data point, the more real the data value of the emission data point is, and thus the intrinsic characteristics of the emission data point can be accurately obtained based on this.

[0019] According to the mobile source off-site supervision method based on the Internet of Things of the present invention, the correlation strength between the emission data point and the speed data point satisfies the relationship:

[0020] ;

[0021] In the formula, represents the correlation strength between the ith emission data point and the ith velocity data point, represents the slope of the emission trend line, represents the slope of the velocity trend line, represents the intercept of the emission trend line, represents the intercept of the velocity trend line, represents the shortest vertical distance from the ith emission data point to the emission trend line, represents the shortest vertical distance from the ith speed data point to the speed trend line, Represents the absolute value symbol.

[0022] According to the Internet of Things-based off-site supervision method for mobile sources described in the present invention, the off-site supervision result of the mobile source is obtained by comparing the cosine similarity of the intrinsic characteristics and extrinsic characteristics of the emission data point with a threshold, including: taking the cosine similarity of the intrinsic characteristics and extrinsic characteristics of the emission data point as a monitoring value, and taking the average of the monitoring values ​​of all emission data points in the vehicle emission data sequence as a threshold; if the monitoring value of the emission data point of the mobile source is greater than the threshold, the monitoring result of the emission data point is obtained as a tampered data point; if the monitoring value of the emission data point of the mobile source is not greater than the threshold, the monitoring result of the emission data point is obtained as a normal data point.

[0023] According to the Internet of Things-based off-site supervision method for mobile sources of the present invention, the monitoring result of the emission data point is a tampered data point, which further includes: marking and removing the tampered data point, and issuing an early warning; obtaining the missing position corresponding to the tampered data point in the vehicle emission data sequence, and interpolating at the missing position using an interpolation method to obtain a complete vehicle emission data sequence.

[0024] The present invention takes into account that tampered data points in emission data will affect the fairness and accuracy of mobile source supervision. Therefore, after detecting the tampered data, an early warning can be issued to remind staff to deal with the tampered data in a timely manner, thereby ensuring the fairness and accuracy of mobile source supervision.

[0025] In a second aspect, the present invention provides an off-site monitoring system for mobile sources based on the Internet of Things, which adopts the following technical solutions:

[0026] The mobile source off-site supervision system based on the Internet of Things includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the mobile source off-site supervision method based on the Internet of Things is implemented.

[0027] By adopting the above technical solution, the above-mentioned mobile source off-site supervision method based on the Internet of Things is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0028] The present invention has the following technical effects:

[0029] Based on the above technical solution, when implementing off-site supervision of mobile sources, the present invention obtains the data changes in the emission data sequence, and obtains the credibility of the data changes by obtaining the residual ratio of the emission data points, which can effectively avoid the influence of normal internal fluctuations on the supervision results, and thus accurately obtain the intrinsic characteristics of the emission data points based on this; on this basis, the present invention further obtains the trend correlation degree between the vehicle emission data sequence and the vehicle speed data sequence, and obtains the similarity between the two by combining the intrinsic and extrinsic characteristics of the emission data points for comparison, so that the emission data that does not match the emission data and speed change trends can be screened out, and the tampered emission data can be accurately identified, so as to accurately obtain the off-site supervision results of mobile sources. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0031] Figure 1 A flowchart of an off-site supervision method for mobile sources based on the Internet of Things is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0033] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0034] It should be noted that mobile source pollution mainly refers to vehicles that emit pollutants into the air. Pollutants not only harm human health, but also affect climate change and ecosystem balance. Therefore, it is necessary to monitor and manage mobile source pollution. However, in the process of manually recording behaviors that do not meet emission standards, there may be cases of artificial tampering of data to help vehicles meet emission standards. The tampered data is similar to the real monitoring data. Conventional methods cannot distinguish such data, resulting in the inability to accurately obtain mobile source emission monitoring results.

[0035] Based on this, in order to ensure the authenticity of the off-site supervision of mobile sources, the embodiment of the present invention discloses an off-site supervision method for mobile sources based on the Internet of Things, which obtains the emission data and speed data generated during the operation of the mobile source, deeply analyzes the correlation between the emission data and the speed data, and obtains the tampered data in the emission data according to the correlation and operation trend between the emission data and the speed data, thereby realizing the off-site supervision of the mobile source. Figure 1 As shown, Figure 1 A flowchart of an off-site supervision method for mobile sources based on the Internet of Things is provided in an embodiment of the present invention. The method specifically includes the following steps S1 to S6.

[0036] S1: Acquire a vehicle emission data sequence and a vehicle speed data sequence, wherein emission data points in the vehicle emission data sequence correspond to speed data points in the vehicle speed data sequence one by one.

[0037] It should be noted that in the process of identifying tampered data, real emission data usually has continuity, regularity and explainability. For example, the data changes of excessive emissions due to vehicle aging, poor maintenance, etc. are often consistent with the change law of the vehicle itself. Forged emission data show irregularity and difficulty in explanation. For example, the data suddenly improves without obvious reasons, or the data changes are inconsistent with the vehicle's own conditions. Therefore, over a period of time, the change characteristics of the real emission data have a certain correlation with the change characteristics of other corresponding parameters of the vehicle, while the tampered data does not have this correlation. For example, as the vehicle speed increases, the vehicle's combustion efficiency improves and pollutant emissions will decrease.

[0038] Based on this, the embodiment of the present invention obtains speed data that is correlated with vehicle emission data and analyzes the inherent rules between the two, thereby identifying tampered data in the emission data.

[0039] For example, in an embodiment of the present invention, obtaining a vehicle emission data sequence and a vehicle speed data sequence also includes: collecting vehicle emission data and vehicle speed data through sensors, preprocessing the vehicle emission data and vehicle speed data to obtain a vehicle emission data sequence and a vehicle speed data sequence, the vehicle emission data sequence includes multiple emission data points, and the vehicle speed data sequence includes multiple speed data points.

[0040] Specifically, in an embodiment of the present invention, a gas sensor can be arranged in the exhaust pipe of the vehicle to obtain the vehicle emission data generated during the vehicle driving process, and the vehicle speed data generated during the vehicle driving process can be obtained through remote sensing and telemetry technology, and the vehicle emission data and vehicle speed data can be uploaded to the mobile source off-site supervision platform; wherein, the collection time of the vehicle emission data and the vehicle speed data can be set to 1 hour, and the collection frequency can be set to 1Hz, and the collection time and collection frequency can be set according to actual needs.

[0041] It can be understood that the same sampling moment corresponds to an emission data point and a speed data point.

[0042] Based on the above steps, the vehicle speed data and the vehicle emission data can be obtained. In order to identify the tampered data from the vehicle emission data, the following steps can be continued.

[0043] S2: Determine the change characteristics of the emission data point or the speed data point, obtain the difference between the data value and the fitting value of the emission data point, and determine the change credibility of the emission data point.

[0044] It should be noted that vehicle emission data will have certain changing patterns at different times and under different operating conditions. By analyzing the data change characteristics of emission data points compared with surrounding data points, it can be determined whether it conforms to the expected changing pattern; among them, the change characteristics can be used to characterize the data changes on the left and right sides of emission data points or speed data points.

[0045] For example, in an embodiment of the present invention, when determining the change characteristics of an emission data point or a speed data point, the difference between the data value of the emission data point or the speed data point and the data point on the left and the ratio of the data value of the emission data point or the speed data point can be obtained, which is recorded as a first ratio; the absolute value of the first ratio is used as a fluctuation index of the emission data point or the speed data point; the ratio of the difference between the fluctuation indexes of the data points on the left and right sides of the emission data point or the speed data point and the fluctuation index of the emission data point or the speed data point is obtained, which is recorded as a second ratio; and the absolute value of the second ratio is used as the change characteristic of the emission data point or the speed data point.

[0046] It is understandable that in a continuous data sequence, there is usually a certain correlation or trend between adjacent data points. Therefore, the larger the second ratio is, the greater the data fluctuation between the emission data point or speed data point and the data points on the left and right sides, and the greater the corresponding change characteristics.

[0047] Based on the above steps, the change characteristics of each emission data point or speed data point can be obtained. However, in order to distinguish normal emission data changes from tampered data, it is necessary to further verify the change characteristics of each emission data point to obtain the change credibility of the emission data point.

[0048] Specifically, each emission data point in the vehicle emission data sequence is fitted using the least squares method to obtain the fitted value of the emission data point. The fitting residual between the fitted value and the actual value of the emission data point is used to obtain the proportion of the fitting residual of the emission data point in the fitting residuals of all emission data points in the vehicle emission data sequence, and the proportion is used as the continuous feature of the emission data point.

[0049] For example, in the embodiment of the present invention, the change credibility of the emission data point is negatively correlated with the absolute value of the difference between the data value of the emission data point and the fitting value; the change credibility of the emission data point can be determined by referring to the following relationship:

[0050] ;

[0051] In the formula, represents the credibility of the change of the ith emission data point, represents the data value of the ith emission data point, represents the fitted value of the ith emission data point, represents the number of emission data points in the vehicle emission data sequence, represents the data value of the jth emission data point in the vehicle emission data sequence, represents the fitted value of the jth emission data point in the vehicle emission data series, represents the exponential function with base e, Represents the absolute value symbol.

[0052] In the above formula, It represents the deviation between the fitted value and the actual value of the ith emission data point. The absolute value of the difference between the data value and the fitted value is the fitting residual. The smaller the fitting residual, the more accurate the prediction of the emission data point. When the fitting residual of the ith emission data point is significantly larger than that of other emission data points, the emission data point may be abnormal. The smaller the proportion of the fitting residual of the ith emission data point, the more the emission data point can reflect the actual situation of the emission data series.

[0053] S3: The vector composed of the change characteristics and change credibility of the emission data point is used as the intrinsic characteristics of the emission data point.

[0054] It can be understood that the vector composed of the change characteristics and change credibility of the emission data point can characterize the size of its intrinsic characteristics. The larger the change characteristics of the emission data point and the higher the change credibility of the emission data point, the greater the possibility that the emission data point is tampered with.

[0055] In this way, the embodiment of the present invention can more comprehensively evaluate the degree of deviation between the emission data point and the adjacent data points by obtaining the change characteristics and change credibility of the emission data point. Among them, the change characteristics reflect the change trend between the emission data point and the adjacent data points, and the change credibility measures the reliability of this trend. Combining the two as a vector of the intrinsic characteristics of the emission data point and expressing them in the form of a vector can facilitate data visualization and comparison, and can also obtain a comprehensive indicator that includes both the change trend and the change reliability.

[0056] After obtaining the intrinsic characteristics of each emission data point based on the above steps, the following steps can be continued.

[0057] S4: curve fitting is performed on the vehicle emission data series and the vehicle speed data series respectively, and the difference between the slopes of the obtained emission trend line and the speed trend line is used as a correlation index to determine the correlation strength between the emission data point and the speed data point.

[0058] It should be noted that by analyzing the data changes within the vehicle emission data sequence based on the above steps, the intrinsic characteristics of each emission data point can be obtained. However, the purpose of tampering with the data is often to make the data more in line with emission standards and closer to the actual emission data. Therefore, the real data and tampered data in the emission data cannot be directly distinguished only by the data changes within the vehicle emission data sequence.

[0059] In combination with the actual running speed of the vehicle, it is possible to verify whether the emission data matches the actual condition of the vehicle. If the emission data fluctuates drastically in a short period of time, but the running speed of the vehicle does not change significantly, it is highly likely that such data has been tampered with. Based on this, the embodiment of the present invention can obtain the speed data point corresponding to the emission data point, and obtain the external characteristics of the emission data point through the correlation strength between the two.

[0060] It should be further explained that the trend line obtained by fitting can reflect the expected trend of the data series, and the shortest vertical distance between the data point and its trend line reflects the relative outlier of the data point in the data series. Therefore, the more consistent the shortest vertical distance between the corresponding emission data point and speed data point and their trend line, the more consistent the relative outlier of the two data points, and the stronger the association between the two data points. In addition, the slopes between the trend lines of the data series can reflect the trend similarity between the data series. The closer the slopes, the higher the similarity between the data series in the trend direction. On this basis, the intercepts between the trend lines of the data series are further obtained. If the slopes between the trend lines are closer and the intercepts are closer, it means that the similarity between the fitting curves of the data series is higher and the association strength is higher. Among them, the association strength of the emission data point and the speed data point is negatively correlated with the association index of the emission trend line and the speed trend line.

[0061] Among them, the step of obtaining the trend line through curve fitting can be implemented by the existing technology, and the embodiment of the present invention will not be described in detail here.

[0062] For example, in the embodiment of the present invention, the correlation strength between the emission data point and the speed data point is determined, and the specific relationship can be as follows:

[0063] ;

[0064] In the formula, represents the correlation strength between the ith emission data point and the ith velocity data point, represents the slope of the emission trend line, represents the slope of the velocity trend line, represents the intercept of the emission trend line, represents the intercept of the velocity trend line, represents the shortest vertical distance from the ith emission data point to the emission trend line, represents the shortest vertical distance from the ith speed data point to the speed trend line, Represents the absolute value symbol.

[0065] In the above formula, It represents the ratio of the shortest vertical distance between the ith emission data point and the ith velocity data point. The closer this ratio is to 1, the more consistent the deviation between the ith emission data point and the ith velocity data point is.

[0066] It represents the correlation index between the emission trend line and the speed trend line. The smaller the value is, the closer the trends between the emission trend line and the speed trend line are.

[0067] After obtaining the correlation strength between the emission data points and the speed data points based on the above steps, the external characteristics of the emission data points can be characterized by the correlation strength.

[0068] S5: The vector composed of the change characteristics and correlation strength of the velocity data point is used as the external characteristics of the emission data point.

[0069] It can be understood that the vector composed of the change characteristics and correlation strength of the speed data point can represent the size of its external characteristics. The larger the change characteristics of the speed data point and the higher the correlation strength between the emission data point and the speed data point, the greater the possibility that the emission data point is tampered data.

[0070] In this way, the embodiment of the present invention can more comprehensively evaluate the degree of correlation between the emission data points and the speed data points by obtaining the change characteristics of the speed data points and the correlation strength between the emission data points and the speed data points. Combining the two as a vector of the external characteristics of the emission data points and expressing them in the form of a vector helps to more comprehensively understand the change characteristics of the vehicle emission behavior under different speed conditions.

[0071] S6: The off-site supervision results of mobile sources are obtained by comparing the cosine similarity of the intrinsic and extrinsic characteristics of the emission data points with the threshold.

[0072] It should be noted that, through the above steps, the intrinsic characteristics and extrinsic characteristics of the emission data points can be obtained respectively. The intrinsic characteristics of the emission data points can characterize the data changes within the vehicle emission data sequence, and the extrinsic characteristics of the emission data points can characterize the correlation between the vehicle emission data sequence and the vehicle speed data sequence. By comparing the similarity between the intrinsic characteristics and extrinsic characteristics of the emission data points, the off-site supervision results of mobile sources can be accurately obtained.

[0073] By way of example, in an embodiment of the present invention, the off-site supervision result of the mobile source is obtained by comparing the cosine similarity of the intrinsic and extrinsic characteristics of the emission data point with a threshold, including: taking the cosine similarity of the intrinsic and extrinsic characteristics of the emission data point as the monitoring value, and taking the average of the monitoring values ​​of all emission data points in the vehicle emission data sequence as the threshold; if the monitoring value of the emission data point of the mobile source is greater than the threshold, the monitoring result of the emission data point is a normal data point; if the monitoring value of the emission data point of the mobile source is not greater than the threshold, the monitoring result of the emission data point is a tampered data point.

[0074] It can be understood that when the cosine similarity between the intrinsic and extrinsic features of the emission data point is high, it means that the data features of the emission data point are consistent with the data features of the emission data sequence itself and the correlation with the speed data sequence. Therefore, the higher the cosine similarity between the intrinsic and extrinsic features of the emission data point, the higher the possibility that the emission data point is a normal data point and the lower the possibility that it is a tampered data point. Based on this, all the tampered data points in the emission data sequence can be obtained.

[0075] After all the tampered data points in the emission data sequence are obtained, the tampered data points may be modified in order to accurately obtain the true situation of the tampered data points in the emission data sequence in the subsequent process.

[0076] By way of example, in an embodiment of the present invention, the monitoring result of the emission data point is a tampered data point, which then includes: marking the tampered data point and removing it, and issuing an early warning; obtaining the missing position corresponding to the tampered data point in the vehicle emission data sequence, and using the interpolation method to interpolate at the missing position to obtain a complete vehicle emission data sequence.

[0077] Among them, obtaining the value corresponding to the missing position data point by interpolation can be achieved through existing technology, and the embodiment of the present invention will not be described in detail here.

[0078] For example, after obtaining a complete vehicle emission data sequence through interpolation, a common anomaly detection algorithm can be used to detect the real abnormal data and produce a corresponding detection report.

[0079] It can be seen that in the embodiment of the present invention, when implementing off-site supervision of mobile sources, a vehicle emission data sequence and a vehicle speed data sequence can be obtained, and the emission data points in the vehicle emission data sequence and the speed data points in the vehicle speed data sequence correspond to each other one by one; the change characteristics of the emission data points or the speed data points are determined, and the change characteristics are used to characterize the data changes on the left and right sides of the emission data points or the speed data points; the difference between the data value and the fitting value of the emission data point is obtained, and the change credibility of the emission data point is determined, and the change credibility is negatively correlated with the absolute value of the difference; the vector composed of the change characteristics and the change credibility of the emission data point is used as the intrinsic characteristics of the emission data point; the vehicle emission data sequence and the vehicle speed data sequence are respectively curve fitted, and the ratio of the slope and intercept of the obtained emission trend line and the speed trend line is used as the correlation index to determine the correlation strength of the emission data point and the speed data point, and the correlation strength is negatively correlated with the difference of the correlation index between the emission trend line and the speed trend line; the vector composed of the change characteristics and the correlation strength of the speed data point is used as the extrinsic characteristics of the emission data point; the off-site supervision result of the mobile source is obtained by comparing the cosine similarity of the intrinsic characteristics and the extrinsic characteristics of the emission data point with the threshold.

[0080] In this way, the embodiment of the present invention obtains the data changes in the emission data sequence, and obtains the credibility of the data changes by obtaining the residual ratio of the emission data points, and can accurately obtain the intrinsic characteristics of the emission data points based on this; on this basis, the embodiment of the present invention further obtains the trend correlation degree between the vehicle emission data sequence and the vehicle speed data sequence, so as to accurately obtain the external characteristics of the emission data points, and by combining the intrinsic characteristics and the external characteristics of the emission data points for comparison to obtain the similarity between the two, it is possible to accurately identify the tampered emission data, thereby accurately obtaining the off-site supervision results of the mobile source.

[0081] An embodiment of the present invention also discloses an off-site supervision system for mobile sources based on the Internet of Things, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an off-site supervision method for mobile sources based on the Internet of Things according to the present invention is implemented.

[0082] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0083] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0084] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0085] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. The off-site supervision method of mobile sources based on the Internet of Things is characterized by: include: Acquire a vehicle emission data sequence and a vehicle speed data sequence, wherein emission data points in the vehicle emission data sequence correspond to speed data points in the vehicle speed data sequence one by one; Determine a change feature of the emission data point or the speed data point, wherein the change feature is used to characterize a change in data on the left and right sides of the emission data point or the speed data point; Obtaining the difference between the data value of the emission data point and the fitting value, determining the change credibility of the emission data point, wherein the change credibility is negatively correlated with the absolute value of the difference; taking the vector composed of the change characteristics of the emission data point and the change credibility as the intrinsic characteristics of the emission data point; Performing curve fitting on the vehicle emission data series and the vehicle speed data series respectively, taking the ratio of the slope and intercept of the emission trend line and the speed trend line as the correlation index, determining the correlation strength of the emission data point and the speed data point, wherein the correlation strength is negatively correlated with the difference of the correlation index between the emission trend line and the speed trend line; taking the vector composed of the change characteristics of the speed data point and the correlation strength as the external characteristics of the emission data point; The off-site supervision result of the mobile source is obtained by comparing the cosine similarity of the intrinsic characteristics and extrinsic characteristics of the emission data points with the threshold.

2. The method for off-site supervision of mobile sources based on the Internet of Things according to claim 1 is characterized in that: The step of obtaining the vehicle emission data sequence and the vehicle speed data sequence also includes: The vehicle emission data and the vehicle speed data are collected by sensors, and the vehicle emission data and the vehicle speed data are preprocessed.

3. The method for off-site supervision of mobile sources based on the Internet of Things according to claim 1 is characterized in that: Determining the change characteristics of the emission data points or speed data points includes: Obtaining a ratio of a difference between the data value of the emission data point or speed data point and the data value of the left data point and the data value of the emission data point or speed data point, and recording it as a first ratio; taking an absolute value of the first ratio as a fluctuation index of the emission data point or speed data point; Obtain the ratio of the difference between the fluctuation indexes of the data points on the left and right sides of the emission data point or the speed data point to the fluctuation index of the emission data point or the speed data point, and record it as the second ratio; and use the absolute value of the second ratio as the change feature of the emission data point or the speed data point.

4. The method for off-site supervision of mobile sources based on the Internet of Things according to claim 1 is characterized in that: The credibility of the change of the emission data points satisfies the relationship: ； In the formula, represents the credibility of the change of the ith emission data point, represents the data value of the ith emission data point, represents the fitted value of the ith emission data point, represents the number of emission data points in the vehicle emission data sequence, represents the data value of the jth emission data point in the vehicle emission data sequence, represents the fitted value of the jth emission data point in the vehicle emission data series, represents the exponential function with base e, Represents the absolute value symbol.

5. The method for off-site supervision of mobile sources based on the Internet of Things according to claim 1 is characterized in that: The correlation strength between the emission data points and the speed data points satisfies the relationship: ； In the formula, represents the correlation strength between the ith emission data point and the ith velocity data point, represents the slope of the emission trend line, represents the slope of the velocity trend line, represents the intercept of the emission trend line, represents the intercept of the velocity trend line, represents the shortest vertical distance from the ith emission data point to the emission trend line, represents the shortest vertical distance from the ith speed data point to the speed trend line, Represents the absolute value symbol.

6. The method for off-site supervision of mobile sources based on the Internet of Things according to claim 1 is characterized in that: The off-site supervision result of the mobile source is obtained by comparing the cosine similarity of the intrinsic characteristics and the extrinsic characteristics of the emission data points with the threshold, including: Using the cosine similarity of the intrinsic characteristics and the extrinsic characteristics of the emission data point as a monitoring value, and using the average of the monitoring values ​​of all emission data points in the vehicle emission data sequence as a threshold; If the monitoring value of the emission data point of the mobile source is greater than the threshold, the monitoring result of the emission data point is obtained as a tampered data point; If the monitoring value of the emission data point of the mobile source is not greater than the threshold value, the monitoring result of the emission data point is obtained as a normal data point.

7. The method for off-site supervision of mobile sources based on the Internet of Things according to claim 6 is characterized in that: The monitoring result of obtaining the emission data point is a tampered data point, and then further comprising: The tampered data points are marked and then removed, and an early warning is issued; the missing positions corresponding to the tampered data points are obtained in the vehicle emission data sequence, and interpolation is performed at the missing positions using an interpolation method to obtain a complete vehicle emission data sequence.

8. The mobile source off-site supervision system based on the Internet of Things is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the off-site supervision method for mobile sources based on the Internet of Things according to any one of claims 1 to 7 is implemented.

Images