CN114414023A

CN114414023A - Sensor abnormality diagnosis method and device, and storage medium

Info

Publication number: CN114414023A
Application number: CN202111670325.7A
Authority: CN
Inventors: 郝杰鹏; 韩青山; 汪广业; 王平
Original assignee: Beijing Wanji Technology Co Ltd
Current assignee: Beijing Wanji Technology Co Ltd
Priority date: 2021-12-30
Filing date: 2021-12-30
Publication date: 2022-04-29

Abstract

The invention provides a sensor abnormity diagnosis method, a device and a storage medium, wherein the method comprises the following steps: acquiring weight related information of a target vehicle through a vehicle-mounted sensor carried by the target vehicle; under the condition that the weight-related information of a plurality of acquisition moments is determined to be acquired, similarity analysis is carried out on the weight-related information of the plurality of acquisition moments acquired in N sampling periods, and whether the vehicle-mounted sensor is abnormal or not is judged, wherein N is larger than or equal to 1, so that the problems that the vehicle-mounted weighing sensor cannot be monitored and managed in real time, the vehicle-mounted sensor cannot be identified to be abnormal and the like in the prior art are solved.

Description

Sensor abnormality diagnosis method and device, and storage medium

Technical Field

The invention relates to the field of vehicle-mounted weighing, in particular to a sensor abnormity diagnosis method and device and a storage medium.

Background

The traditional vehicle overrun overload detection is carried out when a vehicle passes through a weighing detection station, the weighing detection station cannot cover the whole road network, and the overloaded vehicle is easy to bypass the escape inspection.

In the face of the defects of the weighing detection station, a vehicle-mounted dynamic weighing system is generated, namely, the weight of the vehicle is obtained through the vehicle-mounted dynamic weighing system to judge whether the vehicle is overrun and overloaded. However, due to the characteristics of multiple installation and wide distribution of the vehicle-mounted weighing system, effective supervision is difficult to carry out after the vehicle-mounted weighing system is generally installed and calibrated. Some overrun overload vehicles cause the measurement result of the vehicle-mounted weighing system to be abnormal by means of destroying the sensor, changing the normal stress of the measurement area and the like, so that the monitoring is avoided.

Aiming at the problems that the vehicle-mounted weighing sensor cannot be monitored and managed in real time and the abnormality of the vehicle-mounted sensor is identified in the related art, an effective technical scheme is not provided.

Disclosure of Invention

The embodiment of the invention provides a sensor abnormity diagnosis method and device and a storage medium, which are used for at least solving the problems that the vehicle-mounted weighing sensor cannot be monitored and managed in real time, the abnormity of the vehicle-mounted sensor cannot be identified and the like in the related technology.

According to an embodiment of the present invention, there is provided a sensor abnormality diagnosis method including: acquiring weight related information of a target vehicle through a vehicle-mounted sensor carried by the target vehicle; and under the condition that the weight-related information of a plurality of acquisition moments is determined to be acquired, carrying out similarity analysis on the weight-related information of the plurality of acquisition moments acquired in N sampling periods, and judging whether the vehicle-mounted sensor is abnormal, wherein N is more than or equal to 1.

In an exemplary embodiment, in a case where it is determined that weight-related information at a plurality of collection times has been acquired, performing similarity analysis on the weight-related information at the plurality of collection times obtained in N sampling periods to determine whether the vehicle-mounted sensor is abnormal includes: performing cluster analysis on weight related information obtained at a plurality of acquisition moments in each sampling period to determine whether abnormal data exists; when the weight-related information obtained at a plurality of collection times has abnormal data, it is determined that the vehicle-mounted sensor has abnormality.

In an exemplary embodiment, in a case where it is determined that weight-related information at a plurality of collection times has been acquired, performing similarity analysis on the weight-related information at the plurality of collection times obtained in N sampling periods to determine whether the vehicle-mounted sensor is abnormal includes: determining weight related information obtained at the plurality of collection moments in each sampling period to obtain a variation trend between each vehicle-mounted sensor at each collection moment in each sampling period; and when the variation trend is abnormal, judging that the vehicle-mounted sensor mounted on the target vehicle is abnormal.

In an exemplary embodiment, the analyzing the weight-related information at the multiple collection times obtained in N sampling periods for correlation to determine whether the vehicle-mounted sensor is abnormal includes: determining a first relative relationship between the plurality of on-board sensors within a current sampling period, wherein the first relative relationship comprises a weight increment or a weight change rate; and under the condition that the change between the two first relative relations meets a preset first judgment condition, determining that abnormal data exist in the current sampling period, and judging that the vehicle-mounted sensor is abnormal.

In an exemplary embodiment, the analyzing the weight-related information at the multiple collection times obtained in N sampling periods for correlation to determine whether the vehicle-mounted sensor is abnormal includes: determining a second relative relationship between the plurality of vehicle-mounted sensors in the current sampling period; wherein the second relative relationship comprises one of a mean, a variance, and a standard deviation of any type of data in the weight-related information; determining a second relative relation between the vehicle-mounted sensors in the N-1 sampling periods according to the weight related information in the N-1 sampling periods adjacent to the current sampling period; wherein N is a positive integer; and under the condition that the change of the second relative relationship in the previous sampling period and the change of the second relative relationship in the N-1 sampling periods meet a preset second judgment condition, judging that the vehicle-mounted sensor is abnormal.

In an exemplary embodiment, the weight-related information includes at least one of: weight data, displacement data, pressure data.

In an exemplary embodiment, the cluster analysis of the weight-related information obtained at a plurality of sampling moments in each sampling period includes: for the same vehicle-mounted sensor, determining the maximum reachable distance between the neighborhood of each sampling moment and the sampling moment; determining the local reachable density of the sampling points in each sampling interval at other sampling moments within the range of the maximum reachable distance according to the maximum reachable distance; determining a target ratio of the local reachable density of each data point in the neighborhood corresponding to each data point contained in each sampling interval to the local reachable density of each data point; and adding the target ratio corresponding to each data point in the signal data corresponding to the weight related information and dividing the sum by the total number of the data points in the signal data to obtain a target factor value corresponding to each data point in the signal data.

In one exemplary embodiment, the onboard sensor includes at least one of: weighing sensor, pressure sensor, displacement sensor, micro-deformation sensor, foil gage, capacitance sensor.

According to another embodiment of the present invention, there is provided a sensor abnormality diagnostic apparatus including: the system comprises an acquisition module, a control module and a display module, wherein the acquisition module is used for acquiring weight related information of a target vehicle through a vehicle-mounted sensor carried by the target vehicle; the judging module is used for carrying out similarity analysis on the weight related information of the multiple collection moments obtained in N sampling periods under the condition that the weight related information of the multiple collection moments is determined to be obtained, and judging whether the vehicle-mounted sensor is abnormal or not, wherein N is larger than or equal to 1.

In an exemplary embodiment, the determining module is further configured to perform cluster analysis on the weight-related information obtained at multiple collection moments in each sampling period, and determine whether abnormal data exists; when the weight-related information obtained at a plurality of collection times has abnormal data, it is determined that the vehicle-mounted sensor has abnormality.

In an exemplary embodiment, the determining module is further configured to determine weight-related information obtained at the multiple collection times in each sampling period, and obtain a variation trend between each vehicle-mounted sensor at each collection time in each sampling period; and when the variation trend is abnormal, judging that the vehicle-mounted sensor mounted on the target vehicle is abnormal.

In an exemplary embodiment, the determining module is further configured to determine a first relative relationship between the plurality of vehicle-mounted sensors in the current sampling period, wherein the first relative relationship includes a weight increment or a weight change rate; and under the condition that the change between the two first relative relations meets a preset first judgment condition, determining that abnormal data exist in the current sampling period, and judging that the vehicle-mounted sensor is abnormal.

In an exemplary embodiment, the determining module is further configured to determine a second relative relationship between the plurality of vehicle-mounted sensors in the current sampling period; wherein the second relative relationship comprises one of a mean, a variance, and a standard deviation of any type of data in the weight-related information; determining a second relative relation between the vehicle-mounted sensors in the N-1 sampling periods according to the weight related information in the N-1 sampling periods adjacent to the current sampling period; wherein N is a positive integer; and under the condition that the change of the second relative relationship in the previous sampling period and the change of the second relative relationship in the N-1 sampling periods meet a preset second judgment condition, judging that the vehicle-mounted sensor is abnormal.

In an exemplary embodiment, the determining module further includes: the clustering unit is used for determining the maximum reachable distance between the neighborhood of each sampling moment and the sampling moment for the same vehicle-mounted sensor; determining the local reachable density of the sampling points in each sampling interval at other sampling moments within the range of the maximum reachable distance according to the maximum reachable distance; determining a target ratio of the local reachable density of each data point in the neighborhood corresponding to each data point contained in each sampling interval to the local reachable density of each data point; and adding the target ratio corresponding to each data point in the signal data corresponding to the weight related information and dividing the sum by the total number of the data points in the signal data to obtain a target factor value corresponding to each data point in the signal data.

According to a further embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.

According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.

According to the invention, the weight related information of the target vehicle is obtained through the vehicle-mounted sensor carried by the target vehicle; under the condition that the weight-related information at multiple collection moments is determined to be acquired, similarity analysis is carried out on the weight-related information at the multiple collection moments acquired in N sampling periods, and whether the vehicle-mounted sensor is abnormal or not is judged, wherein N is larger than or equal to 1, namely, whether the operation of the vehicle-mounted sensor carried by the current target vehicle is abnormal or not is determined through analyzing the weight-related information uploaded by the vehicle-mounted sensor and received by a vehicle-mounted weighing system, so that the problems that the vehicle-mounted weighing sensor cannot be monitored and managed in real time, the vehicle-mounted sensor is identified to be abnormal and the like in the prior art can be solved, the accuracy and effectiveness of the weighing system of the target vehicle for detecting the vehicle weight information are improved, and the condition that the target vehicle provided with the abnormal sensor cannot be monitored in time is avoided.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 is a block diagram of a hardware configuration of a computer terminal of a sensor abnormality diagnosis method according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method of diagnosing sensor anomalies according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a vehicle sensor-based monitoring system according to an alternative embodiment of the present invention;

fig. 4 is a block diagram of the structure of a sensor abnormality diagnostic apparatus according to an embodiment of the present invention.

Detailed Description

The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.

The method provided by the embodiment of the application can be executed in a computer terminal or a similar operation device of an equipment terminal. Taking the example of the computer terminal running on the computer terminal, fig. 1 is a hardware structure block diagram of the computer terminal of the sensor abnormality diagnosis method according to the embodiment of the present invention. As shown in fig. 1, the computer terminal may include one or more (only one shown in fig. 1) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and in an exemplary embodiment, may also include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the computer terminal. For example, the computer terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration with equivalent functionality to that shown in FIG. 1 or with more functionality than that shown in FIG. 1.

The memory 104 may be used to store a computer program, for example, a software program and a module of application software, such as a computer program corresponding to the sensor abnormality diagnosis method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to a computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

In the present embodiment, a sensor abnormality diagnosis method is provided, and fig. 2 is a flowchart of a sensor abnormality diagnosis method according to an embodiment of the present invention, the flowchart including the steps of:

step S202, acquiring weight related information of a target vehicle through a vehicle-mounted sensor carried by the target vehicle;

optionally, the vehicle-mounted sensor may be disposed on a suspension of the vehicle, or a load-bearing point on the vehicle is pointed out, so as to collect a change in weight of the vehicle through the vehicle-mounted sensor, and output corresponding sensor signal data, where the sensor signal data corresponds to weight-related information of the target vehicle.

And step S204, under the condition that the weight-related information of a plurality of acquisition moments is determined to be acquired, carrying out similarity analysis on the weight-related information of the plurality of acquisition moments acquired in N sampling periods, and judging whether the vehicle-mounted sensor is abnormal, wherein N is more than or equal to 1.

Through the steps, the weight related information of the target vehicle is obtained through a vehicle-mounted sensor carried by the target vehicle; under the condition that the weight-related information at multiple collection moments is determined to be acquired, similarity analysis is carried out on the weight-related information at the multiple collection moments acquired in N sampling periods, and whether the vehicle-mounted sensor is abnormal or not is judged, wherein N is larger than or equal to 1, namely, whether the operation of the vehicle-mounted sensor carried by the current target vehicle is abnormal or not is determined through analyzing the weight-related information uploaded by the vehicle-mounted sensor and received by a vehicle-mounted weighing system, so that the problems that the vehicle-mounted weighing sensor cannot be monitored and managed in real time, the vehicle-mounted sensor is identified to be abnormal and the like in the prior art can be solved, the accuracy and effectiveness of the weighing system of the target vehicle for detecting the vehicle weight information are improved, and the condition that the target vehicle provided with the abnormal sensor cannot be monitored in time is avoided.

In short, due to the fact that the target vehicle is different in corresponding running conditions under different states and environments, and further different differences exist in the weight related information of the target vehicle determined according to the vehicle-mounted sensor, in order to improve the accuracy of identification and judgment, clustering analysis is conducted on the weight related information obtained at multiple collection moments in the same sampling period, the variation of the weight related information is maintained within a preset error, abnormal data exist in the weight related information obtained at the multiple collection moments, and the fact that the vehicle-mounted sensor of the target vehicle is abnormal can be quickly determined.

Optionally, determining weight-related information obtained at a plurality of acquisition moments in each sampling period to obtain a real-time state of the vehicle-mounted sensor at each acquisition moment in each sampling period; and when the change between the two real-time states of the same vehicle-mounted sensor exceeds a first threshold value, determining that the change trend between the vehicle-mounted sensors is abnormal, and judging that the vehicle-mounted sensor carried on the current target vehicle is abnormal.

It can be understood that a plurality of vehicle-mounted sensors may exist on a target vehicle at the same time, in order to better monitor the plurality of vehicle-mounted sensors, under the condition that the vehicle-mounted sensors of the target vehicle are determined to be abnormal, weight-related information obtained by the plurality of vehicle-mounted sensors at a plurality of collection moments in each sampling period is analyzed, a target relative relationship between the plurality of vehicle-mounted sensors at each collection moment in each sampling period is determined, when the target relative relationship corresponding to any two vehicle-mounted sensors in the plurality of vehicle-mounted sensors is abnormal, that is, a change between two target relative relationships exceeds a first threshold value, it indicates that the vehicle-mounted sensors determine that the weight-related information exceeds a normal threshold value between the vehicle-mounted sensors, and one vehicle-mounted sensor in the plurality of vehicle-mounted sensors on the target vehicle is necessarily abnormal.

For example, in general, the rate of change of the signal of the on-board sensor should be within a certain range (usually a slow change process, so the rate of change is small) during the loading and unloading of the vehicle. However, if the vehicle-mounted sensor is artificially damaged, the signal change rate of the vehicle-mounted sensor may exceed the normal range (normally, the change rate is large because of a large change in a short time), and thus, it is possible to quickly identify an abnormality of the vehicle-mounted sensor mounted on the target vehicle.

It can be understood that the first judgment condition is to better identify a first relative relationship between the plurality of vehicle-mounted sensors and whether the first relative relationship exceeds a preset standard relative relationship between the plurality of vehicle-mounted sensors, and when the first relative relationship is greater than the preset standard relative relationship, it indicates that an abnormal sensor exists between the plurality of vehicle-mounted sensors; when the first relative relation is smaller than or equal to a preset standard relative relation, the fact that the abnormality existing among the plurality of vehicle-mounted sensors meets a preset error is shown, and an abnormal sensor does not exist among the plurality of vehicle-mounted sensors. It should be noted that the first relative relationship may be a mean, a variance, a ratio, and the like of any type of data in the weight-related information, that is, determined data or values that can be visually compared with the plurality of vehicle-mounted sensors in the current sampling period.

Namely, because the weight related information determined by the vehicle-mounted sensor can have large changes among different sampling periods, in order to be more accurate when the vehicle-mounted sensor is judged to be abnormal, the weight related information in N sampling periods adjacent to the current sampling period is determined, and the second relative relationship of the same vehicle-mounted sensor among different sampling periods is further compared, so that the misjudgment that the vehicle-mounted sensor has abnormality due to sudden changes of the weight related information recorded by the vehicle-mounted sensor is eliminated. And then, the first relative relation and the second relative relation are comprehensively considered, so that more precise judgment of the abnormality of the vehicle-mounted sensor is realized.

For example, in general, the signal change rates of the on-board sensors mounted on the vehicle are close, for example, all on-board sensor signals increase at an approximate rate when loading and all on-board sensor signals decrease at an approximate rate when unloading. However, when some vehicle-mounted sensors are damaged, the proportion of the change of the damaged vehicle-mounted sensor signal is obvious.

For example, for a data point α and an abnormal data point β which are conventional in a sensor, distances between two points, namely dianance (α, β) and dianance (β, α), are consistent, but similar nodes are not included in K-neighborhood of the abnormal data point as far as possible due to the distance, so that whether a corresponding sampling point is an abnormal data node to be confirmed can be quickly determined by determining a difference in local reachable density between adjacent sampling points in signal data, and further analysis and determination are performed.

Optionally, the K-neighbor distance d (p, o) of any node p in the sensor data set is first obtained, and the K-distance of any point in the sampling interval is calculated, that is, the nearest previous K neighbor points from the point, | nk (p) | ≧ K, the neighborhood of the kth distance can be obtained according to the K-neighbor distance, and the maximum reachable distance, rech-distance, in the data field is obtained in the set_k(p, o) ═ max { k-distance (o), d (p, o) }; and then the relationship between the two nodes is evaluated through the local reachable density:

local outlier factors are expressed for an arbitrary node p as follows,

calculating an outlier factor of each sampling point, wherein the closer the ratio in the data is to 1, the higher the probability that the data of the point and the central point are in one class is, and conversely, the larger the value is, the more possible the point becomes an abnormal data point; all nodes are evaluated in the mode and are originally evaluatedTaking the average value of the regular data in the set as the threshold value F of the data_oIf there is a value greater than the data, it is highly likely that there is an irrational operation on the current data, possibly alerting the remote control platform of the abnormal data point.

Optionally, the signal data output by the vehicle-mounted signal may also be directly identified, so as to determine whether the vehicle-mounted sensor is abnormal, specifically: acquiring signal data in a vehicle-mounted weighing system carried by a target vehicle, wherein the signal data is a data set uploaded by a vehicle-mounted sensor received by the vehicle-mounted weighing system in a running state, the vehicle-mounted sensor is arranged on the target vehicle, and the vehicle-mounted sensor comprises at least one of the following components: the device comprises a weighing sensor, a pressure sensor, a displacement sensor, a micro-deformation sensor, a strain gauge and a capacitance sensor; determining a target factor value corresponding to each data point in the signal data, wherein the target factor value is used for indicating the possibility that each data point and the signal data are in the same data class; the target factor and the preset threshold value are compared to determine whether the signal data has abnormal data points, namely, whether the operation of the vehicle-mounted sensor attached to the vehicle-mounted weighing system of the current target vehicle is abnormal is determined by analyzing the weight-related information uploaded by the vehicle-mounted sensor received by the vehicle-mounted weighing system, so that the problems that the vehicle-mounted weighing sensor cannot be monitored and managed in real time, the vehicle-mounted sensor is identified to be abnormal and the like in the prior art can be solved, the accuracy and the effectiveness of the weighing system of the target vehicle for detecting the vehicle weight information are improved, and the situation that the target vehicle provided with the abnormal sensor cannot be monitored in time is avoided.

In an exemplary embodiment, the target factor is compared with a preset threshold to determine whether there is an abnormal data point in the signal data, and the method further includes: determining that an abnormal data point exists in the current signal data under the condition that the target factor value is larger than a preset threshold value; and determining that no abnormal data point exists in the current signal data under the condition that the target factor value is smaller than or equal to a preset threshold value.

It is understood that by calculating the outlier factor (corresponding to the target factor value in the embodiment of the present invention) of each sample point, the closer the ratio in the data is to 1, the more likely the probability of the data of the point and the center point being in one class is, and conversely, the greater the value, the more likely the data is to be an abnormal data point. All the nodes are evaluated in the mode, the average value of the conventional data is obtained in the data original set of the vehicle-mounted weighing system in the normal operation state and serves as the threshold value of the data, if the average value is larger than the value of the data, unreasonable operation on the current data is highly possible, and the remote control platform is possibly alarmed for abnormal data points.

In an exemplary embodiment, determining that there is an abnormal data point in the current signal data when the target factor value is greater than a preset threshold value includes: counting the number of abnormal data points in the signal data; and under the condition that the abnormal number is larger than the preset number, summarizing the abnormal data points into an abnormal data set, and generating early warning information carrying the abnormal data set, wherein the early warning information is used for reminding a target object to verify a vehicle-mounted weighing system of the target vehicle.

That is, when the vehicle weighing system is in a stage abnormality, for example, the target object is adjusted in a certain period of time, so that the vehicle weighing system displays normal data no matter what kind of data is output by the corresponding vehicle-mounted sensor, and the sensor is adjusted to be normal after the period of time, so that in order to accurately monitor the above situation, the early warning information of the target vehicle is generated according to the abnormal data point and the occurrence time of the abnormal data point, so that the target vehicle can be monitored whenever there is an abnormality.

In an exemplary embodiment, when the abnormal number is greater than a preset number, the abnormal data points are collected into an abnormal data set, and after the warning information carrying the abnormal data set is generated, the method further includes: determining a communication quality of the target vehicle; under the condition that the communication quality is smaller than a target transmission rate, storing the early warning information in a data storage space of a vehicle-mounted weighing system carried by the target vehicle; and uploading the early warning information to a data management center corresponding to the target vehicle under the condition that the communication quality is greater than the target transmission rate.

In short, because the communication quality of the target vehicle may change in real time during the driving process, in order to monitor the early warning information of the target vehicle in a poor communication quality or no communication state, the communication quality of the target vehicle is monitored in real time, and then the accurate recording of the early warning information in different communication states is realized, so that subsequent searching or management and calibration of a vehicle-mounted sensor of the target vehicle have certain data reference.

In an exemplary embodiment, before determining the target factor value corresponding to each data point in the signal data, the method further includes: dividing the signal data into a plurality of sampling intervals through a preset sampling period; acquiring a sampling point in each sampling interval of the plurality of sampling intervals, wherein the sampling point is any point on the sampling interval, and the sampling interval comprises: a plurality of data points; and determining a plurality of target data points within the Kth distance from the sampling point as the neighborhood of the sampling point.

It can be understood that, in order to improve the analysis efficiency of the signal data, the signals acquired from the vehicle-mounted weighing system are subjected to interval division, and then a part of the signal data corresponding to a time period with a high abnormal frequency can be preferentially determined, so that the monitoring of the vehicle-mounted weighing system can be adjusted according to actual conditions.

In an exemplary embodiment, after determining a plurality of target data points within a kth distance from the sample point as a neighborhood of the sample point, the method further comprises: determining the maximum reachable distance between the neighborhood of the sampling point and the sampling point; and determining the local reachable density of the sampling point in each sampling interval to other data points in the maximum reachable distance range according to the maximum reachable distance.

In one exemplary embodiment, determining a target factor value corresponding to each data point in the signal data comprises: determining a target ratio of the local reachable density of the data point in the neighborhood corresponding to each data point to the local reachable density of each data point; and adding the target ratio corresponding to each data point in the signal data and dividing the sum by the total number of the data points in the signal data to obtain a target factor value corresponding to each data point in the signal data.

In an exemplary embodiment, the anomaly analysis of the signal data by a target algorithm includes: dividing the signal data into a plurality of sampling intervals through a preset sampling period; determining a sampling point in each of the plurality of sampling intervals, wherein the sampling point is used for indicating a data node to be analyzed in the signal data, the sampling point is any point on the sampling interval, and the sampling interval comprises: a plurality of data nodes.

In one exemplary embodiment, after determining the sampling points in each of the plurality of sampling intervals, the method further comprises: determining a neighborhood of the sampling point over a sampling interval, wherein the neighborhood is used for indicating a set of a plurality of target data nodes within a Kth distance from the sampling point; determining the maximum reachable distance of the sampling point according to the neighborhood; and determining the local reachable density of all data nodes in the maximum reachable distance range.

In an exemplary embodiment, after determining the local reachable densities corresponding to all data nodes within the maximum reachable distance range, the method further comprises: acquiring a preset standard local reachable density corresponding to the target vehicle, and determining a difference value between the local reachable density and the preset standard local reachable density; determining the sampling point as a normal data node under the condition that the difference value between the local reachable density and a preset standard local reachable density is smaller than a first preset threshold value; and under the condition that the difference value between the local reachable density and the preset standard local reachable density is larger than a first preset threshold value, determining the sampling point as an abnormal data node to be confirmed.

In an exemplary embodiment, after determining the sampling point to be an abnormal data node, the method further includes: determining an outlier factor of the abnormal data node to be confirmed, wherein the outlier factor is used for indicating an average of a ratio of a local reachable density of a neighborhood point of the abnormal data node to be confirmed to the local reachable density of the abnormal data node to be confirmed; determining a difference between the value of the outlier factor and a target value; and under the condition that the difference exceeds a second preset threshold value, determining the abnormal data node to be confirmed as an abnormal data point, wherein the abnormal data point is used for indicating that the vehicle-mounted sensor has abnormal operation.

In order to better understand the process of the sensor abnormality diagnosis method, the flow of the sensor abnormality diagnosis method is described below with reference to several alternative embodiments.

For a better understanding of the application scenarios of the alternative embodiments of the present invention, reference will now be made to the relevant contents.

Optionally, a common detection mode corresponding to the vehicle-mounted weighing mode is as follows: when the vehicle load is different, the leaf spring can generate different deformations, so that the deformation of the leaf spring when the vehicle is stressed can be analyzed, the relationship between the deformation of the leaf spring and the vehicle load is established, and the vehicle load is finally obtained.

Basic principle of a vehicle-mounted vehicle load mass dynamic weighing system: during vehicle travel, the weight of the vehicle is borne primarily by the suspension. For a truck, most of suspension systems of the truck are leaf spring suspensions, and deformation of a leaf spring can be changed greatly along with different loading capacity, so that in a vehicle-mounted dynamic weighing system, the load of the truck can be indirectly measured by measuring the variation of the leaf spring. The weighing sensor can convert the weight signal into a measurable electric signal for output, is the front end of the weighing system, and provides an important basis for subsequent display, storage, control and the like.

Optionally, the vehicle-mounted weighing sensor can be divided into five types according to different load testing methods: wheel load detection, single suspension detection, air suspension, pressure sensor, and balanced spring suspension. The vehicle-mounted weighing sensors of the types have certain advantages, but when the sensors are additionally arranged or modified, a carriage needs to be disassembled, the workload is large, and the sensors need to bear the continuous alternating load in the running process of the vehicle, such as the sensor is easily overloaded and damaged when the vehicle runs on uneven roads, loads and unloads goods, and vehicle collision and the like.

As an optional implementation mode, the optional weighing method of the load weighing system comprises the following steps:

(1) the column type weighing sensor is arranged at the contact position of the axle and the steel plate spring and is fixed by a riding bolt, and the output of the weighing sensor is the spring load mass. The weighing method has high precision and good stability; however, the installation process is very complicated, the height of the column type weighing sensor is more than 40mm at present, and the stability of the vehicle body can be seriously influenced by installing the column type weighing sensor.

(2) The linear displacement sensors are arranged at two ends of the plate spring, and are used for indirectly measuring the spring load mass by detecting the horizontal displacement change of the vehicle plate spring. The protection work of the sensor pull rope by adopting the method is very difficult, and the sensor pull rope is easy to be damaged artificially or naturally.

(3) The capacitance sensor is arranged between the vehicle frame and the vehicle axle, and the spring load mass is measured by detecting the vertical displacement change of the vehicle leaf spring.

(4) And a strain sensor is arranged on the surface of the steel plate spring, and the sprung mass is indirectly measured by detecting the strain on the surface of the steel plate spring.

(5) A pressure sensor is arranged in the tire, and the wheel load mass is indirectly obtained by detecting the tire pressure. This method is greatly affected by environmental factors.

In an optional embodiment of the invention, the invention mainly provides an abnormity monitoring method for a vehicle-mounted weighing system, which comprises the steps of firstly, acquiring a sensor signal of the vehicle-mounted weighing system by a sensor signal acquisition module; then the abnormity analysis module identifies system operation abnormity by utilizing an abnormity analysis algorithm according to the sensor signal and sends an analysis result to the abnormity early warning module; and after the abnormity early warning module receives the analysis result sent by the abnormity analysis module, if the result is abnormal, early warning information is generated and sent to the supervision platform. The monitoring device can monitor the running condition of the vehicle-mounted weighing system, and can effectively detect and early warn the abnormality of the vehicle-mounted weighing system caused by human or non-human reasons.

Optionally, fig. 3 is a schematic structural diagram of a monitoring system corresponding to a vehicle-mounted sensor according to an alternative embodiment of the present invention, which is specifically as follows:

the sensor signal acquisition module 32: collecting sensor signals of a vehicle-mounted weighing system, wherein the sensor signals comprise a weighing sensor, a pressure sensor, a displacement sensor and the like which are used for the vehicle-mounted weighing system;

the anomaly analysis module 34: according to the sensor signal, an anomaly analysis algorithm is utilized to identify system operation anomaly, and an analysis result is sent to an anomaly early warning module;

the anomaly early warning module 36: generating early warning information and sending the early warning information to a supervision platform;

optionally, whether the vehicle-mounted sensor is abnormal or not is judged by the following methods.

Judging whether a sensor signal exceeds a normal threshold value or not;

the output signal of the sensor is normally within its range or in a certain interval depending on the actual reasonable loading conditions of the vehicle. When a sensor fails or is artificially damaged, the output signal of the sensor is obviously abnormal.

Judging whether the change rate of the sensor signal exceeds a normal threshold value;

typically, the rate of change of the sensor signal should be within a certain range (typically a slow change process, so the rate of change is small) during loading and unloading of the vehicle. However, when artificially corrupted, the rate of change of the sensor signal will be outside the normal range (usually a large change in a short time, and therefore a large rate of change). In order to eliminate the condition of the dump truck, the state of the cargo box needs to be detected by matching with an inclinometer.

Judging the signal change proportion of the sensor;

typically, the rate of change of signals from on-board sensors mounted on a vehicle is close, e.g., all sensor signals increase in approximate proportion when loaded and all sensor signals decrease in approximate proportion when unloaded. However, when some sensors are in a corrupted sensor, it is often the case that the rate of change of the corrupted sensor signal will be significant.

Optionally, the Outlier detection is performed on the output signal of the sensor by an LOF (local Outlier Factor, LOF for short) algorithm, and the specific steps are as follows:

step 1, firstly, obtaining K-neighbor distance d (p, o) of any node p in a sensor data set, and calculating K-distance of any point in the sampling interval, namely the nearest front K neighbor points from the point, | Nk (p) | not less than K,

step 2, according to the K-neighbor distance, the neighborhood of the K-th distance can be obtained, and the maximum reachable distance, rech-distance, in the data domain is obtained in the set_k(p,o)＝max{k-distance(o),d(p,o)}；

That is, for the data point α and the abnormal data point β, which are conventional in the sensor, the euclidean distance between the two points, namely the dianance (α, β) and the dianance (β, α) distances, are consistent, but since the K-neighborhood of the abnormal data point contains no similar node as far as possible due to the distance, the relationship between the two nodes is evaluated by the local reachable density as follows:

the local outlier factor for any node p is expressed as follows, the outlier factor of each sampling point is calculated, and when the ratio of the data is closer to 1, the probability that the data of the point and the central point are in one class is higher, and conversely, when the value is higher, the probability that the data of the point and the central point are abnormal data points is higher.

All nodes are evaluated in the mode, and the average value of the conventional data in the original set is obtained as the threshold value F of the data_oIf there is a value greater than the data, it is highly likely that there is an irrational operation on the current data, possibly alerting the remote control platform of the abnormal data point.

In summary, according to the optional embodiment of the present invention, by collecting the sensor signal of the vehicle-mounted weighing system, the sensor signal includes a weighing sensor, a pressure sensor, a displacement sensor and the like used for the vehicle-mounted weighing system; identifying whether the operation of the vehicle-mounted weighing system is abnormal or not by using an abnormal analysis algorithm according to the sensor signal, and sending an analysis result to an abnormal early warning module; under the condition that the abnormality of the vehicle-mounted weighing system is determined, the abnormality early warning module generates early warning information and sends the early warning information to the supervision platform, so that the running condition of the vehicle-mounted weighing system is monitored, and the abnormality of the vehicle-mounted weighing system caused by human or non-human reasons can be effectively detected and early warned in real time.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

In this embodiment, a sensor abnormality diagnosis apparatus is further provided, and the apparatus is used to implement the above embodiments and preferred embodiments, and the description of the apparatus is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 4 is a block diagram showing the structure of a sensor abnormality diagnosis apparatus according to an embodiment of the present invention, as shown in fig. 4, the apparatus including:

an obtaining module 52, configured to obtain, through an on-vehicle sensor mounted on a target vehicle, weight-related information of the target vehicle;

the determining module 54 is configured to, under the condition that it is determined that the weight-related information at multiple collection times is obtained, perform similarity analysis on the weight-related information at multiple collection times obtained in N sampling periods, and determine whether the vehicle-mounted sensor is abnormal, where N is greater than or equal to 1.

By the device, the weight related information of the target vehicle is acquired through the vehicle-mounted sensor carried by the target vehicle; under the condition that the weight-related information at multiple collection moments is determined to be acquired, similarity analysis is carried out on the weight-related information at the multiple collection moments acquired in N sampling periods, and whether the vehicle-mounted sensor is abnormal or not is judged, wherein N is larger than or equal to 1, namely, whether the operation of the vehicle-mounted sensor carried by the current target vehicle is abnormal or not is determined through analyzing the weight-related information uploaded by the vehicle-mounted sensor and received by a vehicle-mounted weighing system, so that the problems that the vehicle-mounted weighing sensor cannot be monitored and managed in real time, the vehicle-mounted sensor is identified to be abnormal and the like in the prior art can be solved, the accuracy and effectiveness of the weighing system of the target vehicle for detecting the vehicle weight information are improved, and the condition that the target vehicle provided with the abnormal sensor cannot be monitored in time is avoided.

local outlier factors are expressed for an arbitrary node p as follows,

calculating an outlier factor of each sampling point, wherein the closer the ratio in the data is to 1, the higher the probability that the data of the point and the central point are in one class is, and conversely, the larger the value is, the more possible the point becomes an abnormal data point; all nodes are evaluated in the mode, and the average value of the conventional data in the original set is obtained and used as the threshold value F of the data_oIf there is a value greater than the data, it is highly likely that there is an irrational operation on the current data, possibly alerting the remote control platform of the abnormal data point.

It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.

Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.

In an exemplary embodiment, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:

s1, acquiring weight related information of a target vehicle through a vehicle-mounted sensor mounted on the target vehicle;

s2, under the condition that the weight-related information of a plurality of acquisition moments is determined to be acquired, carrying out similarity analysis on the weight-related information of the plurality of acquisition moments acquired in N sampling periods, and judging whether the vehicle-mounted sensor is abnormal, wherein N is larger than or equal to 1.

In an exemplary embodiment, in the present embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.

In an exemplary embodiment, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.

In an exemplary embodiment, in the present embodiment, the processor may be configured to execute the following steps by a computer program:

In an exemplary embodiment, for specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation manners, and details of this embodiment are not described herein again.

It will be apparent to those skilled in the art that the various modules or steps of the invention described above may be implemented using a general purpose computing device, which may be centralized on a single computing device or distributed across a network of computing devices, and in one exemplary embodiment may be implemented using program code executable by a computing device, such that the steps shown and described may be executed by a computing device stored in a memory device and, in some cases, executed in a sequence different from that shown and described herein, or separately fabricated into individual integrated circuit modules, or multiple ones of them fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A sensor abnormality diagnosis method characterized by comprising:

acquiring weight related information of a target vehicle through a vehicle-mounted sensor carried by the target vehicle;

and under the condition that the weight-related information of a plurality of acquisition moments is determined to be acquired, carrying out similarity analysis on the weight-related information of the plurality of acquisition moments acquired in N sampling periods, and judging whether the vehicle-mounted sensor is abnormal, wherein N is more than or equal to 1.

2. The method for diagnosing the abnormality of the sensor according to claim 1, wherein the analyzing the weight-related information at the plurality of collection times obtained in the N sampling periods in a correlated manner to determine whether the vehicle-mounted sensor is abnormal includes:

performing cluster analysis on the weight-related information obtained at the plurality of acquisition moments in each sampling period to determine whether abnormal data exists;

and when the weight-related information obtained at the plurality of acquisition times has abnormal data, judging that the vehicle-mounted sensor has abnormality.

3. The method for diagnosing the abnormality of the sensor according to claim 1, wherein the analyzing the weight-related information at the plurality of collection times obtained in the N sampling periods in a correlated manner to determine whether the vehicle-mounted sensor is abnormal includes:

determining weight related information obtained at the plurality of collection moments in each sampling period to obtain a variation trend between each vehicle-mounted sensor at each collection moment in each sampling period;

and when the variation trend is abnormal, judging that the vehicle-mounted sensor mounted on the target vehicle is abnormal.

4. The method for diagnosing the abnormality of the sensor according to claim 1, wherein the analyzing the weight-related information at the plurality of collection times obtained in the N sampling periods in a correlated manner to determine whether the vehicle-mounted sensor is abnormal includes:

determining a first relative relationship between the plurality of on-board sensors within a current sampling period, wherein the first relative relationship comprises a weight increment or a weight change rate;

and under the condition that the change between the two first relative relations meets a preset first judgment condition, determining that abnormal data exist in the current sampling period, and judging that the vehicle-mounted sensor is abnormal.

5. The method for diagnosing the abnormality of the sensor according to claim 1, wherein the analyzing the weight-related information at the plurality of collection times obtained in the N sampling periods in a correlated manner to determine whether the vehicle-mounted sensor is abnormal includes:

determining a second relative relationship between the plurality of vehicle-mounted sensors in the current sampling period; wherein the second relative relationship comprises one of a mean, a variance, and a standard deviation of any type of data in the weight-related information;

determining a second relative relation between the vehicle-mounted sensors in the N-1 sampling periods according to the weight related information in the N-1 sampling periods adjacent to the current sampling period; wherein N is a positive integer;

and under the condition that the change of the second relative relationship in the previous sampling period and the change of the second relative relationship in the N-1 sampling periods meet a preset second judgment condition, judging that the vehicle-mounted sensor is abnormal.

6. The sensor abnormality diagnostic method according to claim 1, characterized in that the weight-related information includes at least one of: weight data, displacement data, pressure data.

7. The method for diagnosing abnormality of a sensor according to claim 2, wherein the performing cluster analysis on the weight-related information obtained at a plurality of sampling timings in each sampling period includes:

for the same vehicle-mounted sensor, determining the maximum reachable distance between the neighborhood of each sampling moment and the sampling moment;

determining the local reachable density of the sampling points in each sampling interval reaching other sampling moments within the maximum reachable distance range according to the maximum reachable distance;

determining a target ratio of the local reachable density of the data point in the neighborhood corresponding to each data point contained in each sampling interval to the local reachable density of each data point;

and adding the target ratio corresponding to each data point in the signal data corresponding to the weight related information and dividing the sum by the total number of the data points in the signal data to obtain a target factor value corresponding to each data point in the signal data.

8. The sensor abnormality diagnostic method according to claim 1, characterized in that the vehicle-mounted sensor includes at least one of: weighing sensor, pressure sensor, displacement sensor, micro-deformation sensor, foil gage, capacitance sensor.

9. A sensor abnormality diagnostic device characterized by comprising:

the system comprises an acquisition module, a control module and a display module, wherein the acquisition module is used for acquiring weight related information of a target vehicle through a vehicle-mounted sensor carried by the target vehicle;

the judging module is used for carrying out similarity analysis on the weight related information of the multiple collection moments obtained in N sampling periods under the condition that the weight related information of the multiple collection moments is determined to be obtained, and judging whether the vehicle-mounted sensor is abnormal or not, wherein N is larger than or equal to 1.

10. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to carry out the method of any one of claims 1 to 8 when executed.