CN117132266A - Block chain-based automobile service security guarantee method and system - Google Patents
Block chain-based automobile service security guarantee method and system Download PDFInfo
- Publication number
- CN117132266A CN117132266A CN202311384622.4A CN202311384622A CN117132266A CN 117132266 A CN117132266 A CN 117132266A CN 202311384622 A CN202311384622 A CN 202311384622A CN 117132266 A CN117132266 A CN 117132266A
- Authority
- CN
- China
- Prior art keywords
- fault
- sensor
- abnormal
- automobile
- ith
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 230000002159 abnormal effect Effects 0.000 claims abstract description 190
- 230000005856 abnormality Effects 0.000 claims abstract description 110
- 230000008859 change Effects 0.000 claims abstract description 28
- 230000006870 function Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 239000000758 substrate Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Abstract
The invention relates to the technical field of electric digital data processing, in particular to an automobile service security assurance method and system based on a block chain. The method comprises the steps of obtaining data of each sensor of a fault automobile as participation data; according to the change of the participation data, the abnormal degree of each sensor is obtained, and abnormal sensors are screened out; obtaining the similarity degree of the same abnormal sensor between any two fault automobiles, and clustering to obtain each performance of the participation data of the same abnormal sensor corresponding to each fault; and obtaining the influence degree according to the number and the abnormality degree of the abnormality sensors in each performance condition, determining the abnormality characteristic value of each abnormality sensor corresponding to each fault, and predicting the possible fault type of the automobile. According to the invention, the type of the possible faults of the automobile is accurately and efficiently predicted according to the abnormal characteristic values of each abnormal sensor corresponding to each fault, and the accuracy of the fault detection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to an automobile service security assurance method and system based on a block chain.
Background
The block chain technology is a distributed database technology, and provides safer and more reliable guarantee for automobile service through the characteristics of decentralization, non-tampering, traceability and the like.
When the automobile data are collected, each item of data of the automobile is obtained in real time through each sensor and stored, when the automobile breaks down, maintenance personnel can conveniently conduct investigation according to the real-time sensor data, but because various automobile equipment and various system types exist, the corresponding sensor data are different, meanwhile, certain correlation exists among the data of each sensor, therefore, in the maintenance process, the data of each sensor are analyzed and checked, the fault of the automobile is deduced, the automobile fault detection efficiency is reduced, and meanwhile the fault monitoring accuracy is reduced.
Disclosure of Invention
In order to solve the technical problems that the efficiency of automobile fault detection is reduced and the accuracy of fault monitoring is reduced due to the analysis of data of each sensor of an automobile, the invention aims to provide an automobile service safety guarantee method and system based on a block chain, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for guaranteeing safety of a vehicle service based on a blockchain, the method including the steps of:
acquiring data of a fault automobile at each moment of each sensor in a preset time period as participation data;
according to the change of the participation data, the abnormal degree of each sensor in each fault automobile corresponding to each fault is obtained, and the abnormal sensor in each fault automobile corresponding to each fault is screened out;
according to participation data and abnormality degrees of the same type of abnormality sensor between any two fault automobiles corresponding to each fault, obtaining the similarity degree of the same type of abnormality sensor between any two fault automobiles corresponding to each fault;
clustering the same type of abnormal sensors corresponding to each fault according to the similarity, and taking the obtained cluster as each expression condition of participation data of the same type of abnormal sensors corresponding to each fault;
according to the number and the abnormality degree of the abnormality sensors in each performance situation of the participation data of each abnormality sensor corresponding to each fault, obtaining the influence degree of each performance situation, and determining the abnormality characteristic value of each abnormality sensor corresponding to each fault;
and predicting the possible fault type of the automobile according to the abnormal characteristic value.
Further, the method for obtaining the abnormality degree comprises the following steps:
taking any one sensor of a certain fault automobile corresponding to a certain fault as a target sensor;
fitting predicted normal data of the target sensor when the fault automobile normally runs within a preset time period;
acquiring the difference between the participation data and the predicted normal data of the target sensor at each time in a preset time period, and taking the difference as a residual error value at each time;
acquiring the difference between the participation data of the target sensor at each time and the participation data of the target sensor at the next adjacent time, and taking the difference as a trend change value at each time;
and acquiring the abnormality degree of the target sensor in the fault automobile corresponding to the fault according to the residual value and the trend change value of the target sensor at each moment.
Further, the calculation formula of the abnormality degree is:
in the method, in the process of the invention,the degree of abnormality of the jth sensor in the kth fault automobile corresponding to the ith fault; t is the total number of times of collecting participation data of a jth sensor in a kth fault automobile corresponding to an ith fault in a preset time period;the residual error value of a jth sensor in a kth fault automobile corresponding to the ith fault at a t moment in a preset time period is obtained; />The method comprises the steps that the maximum residual error value of a jth sensor in a kth fault automobile corresponding to an ith fault in a preset time period is obtained; />The trend change value of a jth sensor in a kth fault automobile corresponding to an ith fault at a t moment in a preset time period is obtained; />The trend change value of the jth sensor in the kth fault automobile corresponding to the ith fault at the jth moment in the preset time period is obtained; l is a first preset number; norm is a normalization function; />As a function of absolute value.
Further, the method for acquiring the abnormal sensor comprises the following steps:
when the abnormality degree of the sensor is larger than a preset abnormality degree threshold, the sensor is an abnormality sensor in the fault automobile corresponding to the corresponding fault.
Further, the method for obtaining the similarity degree comprises the following steps:
acquiring a similarity value of participation data of the same abnormal sensor between any two fault automobiles corresponding to each fault through an image matching technology, and taking the similarity value as a first similarity value;
acquiring differences of the degree of abnormality of the same type of abnormality sensor between any two fault automobiles corresponding to each fault as first differences;
and obtaining the similarity degree of the same abnormal sensor between any two fault automobiles corresponding to the same fault according to the first similarity value and the first difference.
Further, the calculation formula of the similarity degree is as follows:
in the method, in the process of the invention,the similarity degree of the ith abnormal sensor between the a-th fault automobile and the b-th fault automobile corresponding to the ith fault; />Is a first similarity value; />The degree of abnormality of the ith abnormality sensor in the ith fault car corresponding to the ith fault; />The degree of abnormality of the ith abnormality sensor in the ith fault car corresponding to the ith fault; e is a natural constant; norm is a normalization function; />As a function of absolute value.
Further, the calculation formula of the influence degree is as follows:
in the method, in the process of the invention,the influence degree of the h expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault; />The total number of the abnormal sensors in the h expression situation of the participation data of the ith abnormal sensor corresponding to the ith fault; />The total number of the ith abnormal sensors corresponding to the ith fault; />The mean value of the abnormality degree of the abnormal sensor in the h expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault; />The total number of each performance situation of the participation data of the ith abnormal sensor corresponding to the ith fault; />The mean value of the abnormality degree of the abnormal sensor in the x-th expression of the participation data of the u-th abnormal sensor corresponding to the i-th fault; />Is a second preset constant, greater than 0; />As a function of absolute value.
Further, the method for acquiring the abnormal characteristic value comprises the following steps:
for any abnormal sensor corresponding to any fault, obtaining the influence degree of each performance condition of the abnormal sensor;
taking the performance condition corresponding to the maximum influence degree as a target performance condition;
and acquiring the average value of the abnormality degree of each abnormal sensor in the target performance condition as the abnormal characteristic value of the abnormal sensor corresponding to the fault.
Further, the method for predicting the possible fault type of the automobile according to the abnormal characteristic value comprises the following steps:
acquiring the difference between the abnormality degree of each sensor of the automobile to be tested and the abnormality characteristic value of each fault type corresponding to the same abnormality sensor as a second difference;
and taking the fault type corresponding to the smallest second difference as the possible fault type of the automobile to be tested.
In a second aspect, another embodiment of the present invention provides a blockchain-based automotive service security system, the system comprising: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any one of the methods described above when executing the computer program.
The invention has the following beneficial effects:
according to the change of the participation data, the abnormal degree of each sensor in each fault automobile corresponding to each fault is obtained, the abnormal sensor in each fault automobile corresponding to each fault is screened out, and only the abnormal sensor is analyzed, so that the efficiency is improved; according to participation data and degree of abnormality of the same type of abnormality sensor between any two fault automobiles corresponding to each fault, the similarity degree of the same type of abnormality sensor between any two fault automobiles corresponding to each fault is obtained, whether the participation data of the same type of abnormality sensor are identical to the performance of the same type of fault is determined, each performance of the participation data of each type of abnormality sensor corresponding to each fault is determined, therefore, the same type of abnormality sensor corresponding to each fault is clustered according to the similarity degree, the obtained cluster is used as each performance of the participation data of the same type of abnormality sensor corresponding to each fault, the number of abnormality sensors and degree of abnormality in each performance of the participation data are analyzed, the influence degree of each performance is obtained, the abnormal characteristic value of each type of abnormality sensor corresponding to each fault is accurately determined, and the type of fault possibly occurring in the automobile is accurately and efficiently predicted according to the abnormal characteristic value. According to the invention, through analyzing the performance of the abnormal sensor data of the fault automobile with known fault types, the abnormal characteristic value of each abnormal sensor corresponding to each fault is determined, and then the fault type of the automobile to be detected is determined by directly comparing the abnormal degree of each sensor of the automobile to be detected with the abnormal characteristic value of the corresponding abnormal sensor, so that the efficiency and accuracy of fault detection are improved, and maintenance personnel can maintain in time.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a block chain-based method for guaranteeing the safety of an automobile service according to an embodiment of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a block chain-based automobile service security guarantee method according to the invention, which is specific to the implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the block chain-based automobile service security assurance method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of a block chain-based automobile service security assurance method according to an embodiment of the invention is shown, the method includes the following steps:
step S1: and acquiring data of the fault automobile at each moment of each sensor in a preset time period as participation data.
Specifically, data of each sensor in each preset time period of M faulty automobiles in a maintenance service factory is obtained through a blockchain and used as participation data. In the embodiment of the invention, M is set to be 1000, the preset time period is set to be the time period from the fault automobile to the previous month of the maintenance service factory, the time interval between every two adjacent moments of each sensor is 1 second, and an operator can set the size of M, the time period of the preset time period and the time interval according to actual conditions without limitation.
Classifying M fault automobiles according to fault types, analyzing participation data of sensors in each fault automobile corresponding to each fault type, acquiring abnormal sensors in each fault automobile corresponding to each fault, analyzing participation data of the same abnormal sensor corresponding to each fault, and further acquiring abnormal characteristic values of each abnormal sensor corresponding to each fault, namely, each sensor. Analyzing the data of each sensor of the automobile to be tested, obtaining the abnormal degree of each sensor of the automobile to be tested, comparing the abnormal characteristic value of each sensor corresponding to each fault, accurately and efficiently determining the fault type of the automobile to be tested, and facilitating the maintenance of the maintainer accurately.
Step S2: according to the change of the participation data, the abnormality degree of each sensor in each fault automobile corresponding to each fault is obtained, and the abnormal sensors in the fault automobiles corresponding to each fault are screened out.
Specifically, a faulty automobile may have multiple faults, and one fault in a faulty automobile may correspond to multiple sensors. Because the types and the systems of the fault automobiles are different, the reasons for the same faults generated by different fault automobiles are different, and therefore, the types of the corresponding response sensors in different fault automobiles corresponding to the same faults are different. According to the embodiment of the invention, the abnormal degree of each sensor in each fault automobile corresponding to each fault is obtained by analyzing the participation data of each sensor in each fault automobile, so that the abnormal sensor corresponding to each fault in each fault automobile is determined.
Preferably, the method for obtaining the degree of abnormality is as follows: taking any one sensor of a certain fault automobile corresponding to a certain fault as a target sensor; fitting predicted normal data of the target sensor when the fault automobile normally runs within a preset time period; acquiring the difference between the participation data and the predicted normal data of the target sensor at each time in a preset time period, and taking the difference as a residual error value at each time; acquiring the difference between the participation data of the target sensor at each time and the participation data of the target sensor at the next adjacent time, and taking the difference as a trend change value at each time; and acquiring the abnormality degree of the target sensor in the fault automobile corresponding to the fault according to the residual value and the trend change value of the target sensor at each moment.
As an example, taking the jth sensor in the kth fault automobile corresponding to the ith fault as an example, the jth sensor is the target sensor. According to the data of each moment of the jth sensor when the kth fault automobile normally runs recorded in the block chain, the predicted normal data of the jth sensor when the kth fault automobile normally runs in a preset time period are fitted, namely, when the kth fault automobile does not fail, the data of the jth sensor in each moment in the preset time period are fitted. And acquiring the absolute value of the difference value between the participation data and the predicted normal data of the jth sensor at each time in a preset time period, namely the residual value at each time. For example, the absolute value of the difference between the participation data of the jth sensor at the t moment in the preset time period and the predicted normal data of the fitted jth sensor at the t moment in the preset time period is obtained, and the absolute value is the residual value at the t moment. And acquiring a difference value between the participation data of the jth sensor at each time in a preset time period and the participation data of the jth sensor at the next adjacent time, namely, a trend change value at each time. Wherein, no trend change value exists at the last moment in the preset time period. The embodiment of the invention respectively acquires the absolute difference value of the trend change value of the jth sensor at each moment in a preset time period and the first preset number of adjacent trend change values after the corresponding moment, and takes the absolute difference value as trend difference and the average value of the trend difference as the overall trend difference at each moment. In the embodiment of the present invention, the first preset number is set to 5, and the practitioner can set the size of the first preset number according to the actual situation, which is not limited herein. For example, the absolute difference value of the trend change value of the jth sensor at the t time in the preset time period and the trend change value of the jth sensor at 5 times adjacent to the jth time after the jth time period is obtained respectively, wherein the absolute difference value is the trend difference, and the average value of the trend difference is the integral trend difference of the jth sensor at the t time in the preset time period. When the jth sensor in the kth fault automobile does not have 5 adjacent moments after the t moment in the preset time period, only obtaining the average value of the trend variation value of the jth sensor at the t moment in the preset time period and the trend variation value at each moment after the t moment, namely the overall trend variation at the t moment. For example, when there are 3 trend change values of the jth sensor in the kth fault automobile after the t moment in the preset time period, the average value of the trend difference between the trend change value at the t moment and the 3 trend change values after the t moment is obtained respectively, that is, the overall trend difference of the jth sensor at the t moment in the preset time period. When the jth sensor in the kth fault automobile is the last moment in the t moment in the preset time period, the integral trend difference of the jth sensor at the t moment in the preset time period is defaulted to be 1. According to the residual value and the trend change value of the jth sensor in the kth fault automobile corresponding to the ith fault at each moment in a preset time period, the calculation formula for the degree of abnormality of the jth sensor in the kth fault automobile corresponding to the ith fault is obtained as follows:
in the method, in the process of the invention,the degree of abnormality of the jth sensor in the kth fault automobile corresponding to the ith fault; t is the total number of times of collecting participation data of a jth sensor in a kth fault automobile corresponding to an ith fault in a preset time period;the residual error value of a jth sensor in a kth fault automobile corresponding to the ith fault at a t moment in a preset time period is obtained; />The method comprises the steps that the maximum residual error value of a jth sensor in a kth fault automobile corresponding to an ith fault in a preset time period is obtained; />The trend change value of a jth sensor in a kth fault automobile corresponding to an ith fault at a t moment in a preset time period is obtained; />The trend change value of the jth sensor in the kth fault automobile corresponding to the ith fault at the jth moment in the preset time period is obtained; l is a first preset number, and the embodiment of the invention is 5; norm is a normalization function; />As a function of absolute value; />Is a trend difference; />Is the overall trend difference.
It should be noted that the number of the substrates,the larger the j-th sensor is, the more abnormal the participation data of the j-th sensor at the t-th time within the preset time period is, the more likely the abnormality is, the +.>The bigger the->The larger; trend difference->The larger the difference between the participation data of the jth sensor at the t time in the preset time period and the participation data of the adjacent time period is, the more likely the participation data of the jth sensor at the t time in the preset time period is abnormal, the overall trend difference is->The larger the size of the container,the larger; thus (S)>The larger the participation data of the jth sensor is, the more abnormal the participation data of the jth sensor is, and the jth sensor is more likely to be an abnormal sensor corresponding to the ith fault in the kth fault automobile. Wherein (1)>The value of (2) is in the range of 0 to 1.
And according to a method for acquiring the degree of abnormality of the jth sensor in the kth fault automobile corresponding to the ith fault, acquiring the degree of abnormality of each sensor in each fault automobile corresponding to each fault.
And analyzing the degree of abnormality of each sensor in each fault automobile corresponding to each fault, and determining the abnormal sensor corresponding to each fault in each fault automobile.
Preferably, the method for acquiring the abnormal sensor is as follows: when the abnormality degree of the sensor is larger than a preset abnormality degree threshold, the sensor is an abnormality sensor in the fault automobile corresponding to the corresponding fault. In the embodiment of the invention, the preset abnormality degree threshold is set to 0.7, and the operator can set the preset abnormality degree threshold according to the actual situation, which is not limited herein. When the degree of abnormality of the jth sensor in the kth fault automobile corresponding to the ith fault is greater than a preset threshold value of the degree of abnormality, the jth sensor is the abnormal sensor in the kth fault automobile corresponding to the ith fault, namely the jth sensor is the abnormal sensor corresponding to the ith fault in the kth fault automobile. So far, the abnormal sensor corresponding to each fault in each fault automobile is obtained.
Step S3: and obtaining the similarity degree of the same abnormal sensor between any two fault automobiles corresponding to each fault according to the participation data and the abnormality degree of the same abnormal sensor between any two fault automobiles corresponding to each fault.
Specifically, the same type of fault occurs for a plurality of reasons, so that the types of the abnormal sensors in the fault automobiles corresponding to the same fault may be different, and even if the types of the abnormal sensors in the fault automobiles corresponding to the same fault are the same, the participation data of the abnormal sensors in the different fault automobiles may be different. The changes of the participation data of the same type of abnormal sensors in the fault automobiles corresponding to the faults caused by the same reasons are similar, so that the different performance conditions of the participation data of the same type of abnormal sensors in the fault automobiles corresponding to each fault are further obtained by calculating the similarity degree of the same type of abnormal sensors between any two fault automobiles corresponding to the same faults, namely, each possible reason for each fault occurrence is caused, and further, the abnormal characteristic value of each abnormal sensor corresponding to each fault is determined, so that the fault type possibly occurring in the automobile to be tested is conveniently determined.
Preferably, the method for obtaining the similarity degree is as follows: acquiring a similarity value of participation data of the same abnormal sensor between any two fault automobiles corresponding to each fault through an image matching technology, and taking the similarity value as a first similarity value; acquiring differences of the degree of abnormality of the same type of abnormality sensor between any two fault automobiles corresponding to each fault as first differences; and obtaining the similarity degree of the same abnormal sensor between any two fault automobiles corresponding to the same fault according to the first similarity value and the first difference. The image matching technology is the prior art, and will not be described in detail.
As an example, taking a ith abnormal sensor between an a-th fault automobile corresponding to an ith fault and a b-th fault automobile as an example, acquiring a similarity value between participation data of the ith abnormal sensor in the a-th fault automobile corresponding to the ith fault and participation data of the ith abnormal sensor in the b-th fault automobile corresponding to the ith fault, namely a first similarity value, through an image matching technology. And acquiring the absolute value of the difference between the degree of abnormality of the ith abnormal sensor in the ith fault automobile corresponding to the ith fault and the degree of abnormality of the ith abnormal sensor in the ith fault automobile corresponding to the ith fault, namely the first difference. According to a first similarity value and a first difference between a ith fault automobile corresponding to the ith fault and a ith abnormal sensor in a b fault automobile, a calculation formula for obtaining the similarity degree of the ith abnormal sensor between the ith fault automobile corresponding to the ith fault and the ith abnormal sensor in the b fault automobile is as follows:
in the method, in the process of the invention,the similarity degree of the ith abnormal sensor between the a-th fault automobile and the b-th fault automobile corresponding to the ith fault; />Is a first similarity value; />The degree of abnormality of the ith abnormality sensor in the ith fault car corresponding to the ith fault; />The degree of abnormality of the ith abnormality sensor in the ith fault car corresponding to the ith fault; e is a natural constant; norm is a normalization function; />As a function of absolute value; />Is the first difference.
It should be noted that the number of the substrates,the larger the participation data of the ith abnormal sensor in the ith fault corresponding to the ith fault is, the more similar the participation data of the ith abnormal sensor in the ith fault corresponding to the ith fault is to the participation data of the ith abnormal sensor in the ith fault corresponding to the ith fault>The larger; first difference->The smaller the degree of abnormality of the ith abnormality sensor in the ith fault car corresponding to the ith fault is, the more similar the degree of abnormality of the ith abnormality sensor in the ith fault car is>The bigger the->The larger; thus (S)>The larger the data representing the participation data between the ith abnormal sensor in the ith fault automobile corresponding to the ith fault and the ith abnormal sensor in the ith fault automobile corresponding to the ith fault is, the more similar the data representing the participation data between the ith abnormal sensor in the ith fault automobile corresponding to the ith fault is, and the more the reason that the ith fault in the ith fault automobile and the ith fault in the ith fault automobile are generated is.
According to the method for obtaining the similarity degree of the u-th abnormal sensor between the a-th fault automobile and the b-th fault automobile corresponding to the i-th fault, obtaining the similarity degree of the same abnormal sensor between any two fault automobiles corresponding to each fault.
Step S4: and clustering the same type of abnormal sensors corresponding to each fault according to the similarity, and taking the obtained cluster as each expression condition of participation data of the same type of abnormal sensors corresponding to each fault.
Specifically, taking the similarity degree of the u-th abnormal sensor between any two fault automobiles corresponding to the i-th fault as an example, the embodiment of the invention uses the similarity degree of the u-th abnormal sensor between any two fault automobiles corresponding to the i-th fault as a clustering basis through a K-means clustering algorithm, and clusters all the u-th abnormal sensors corresponding to the i-th fault. The K-means clustering algorithm, the elbow method and the mode for evaluating the clustering result are all in the prior art, and are not described in detail. And taking the obtained cluster as each performance of the participation data of the ith abnormal sensor corresponding to the ith fault. I.e. the presence data of the anomaly sensors in each cluster vary similarly.
According to the method for acquiring each performance of the participation data of the ith abnormal sensor corresponding to the ith fault, acquiring each performance of the participation data of each abnormal sensor corresponding to each fault.
Step S5: and acquiring the influence degree of each performance condition according to the number and the abnormality degree of the abnormal sensors in each performance condition of the participation data of each abnormal sensor corresponding to each fault, and determining the abnormal characteristic value of each abnormal sensor corresponding to each fault.
Specifically, in order to timely predict the possible fault types of the automobile to be tested according to the data of each sensor of the automobile to be tested, the embodiment of the invention analyzes the number and the degree of abnormality of each abnormal sensor in each performance of the participation data of each abnormal sensor corresponding to each fault, and determines the overall data performance of each abnormal sensor corresponding to each fault, namely, obtains the abnormal characteristic value of each abnormal sensor corresponding to each fault.
As an example, taking each performance situation of the participation data of the ith abnormal sensor corresponding to the ith fault in step S4 as an example, the specific method is as follows:
(1) The degree of influence is obtained.
Taking the h expression situation of the participation data of the ith abnormal sensor corresponding to the ith fault as an example, namely taking the h cluster after the clustering of the ith abnormal sensor corresponding to the ith fault as an example, acquiring the total number of abnormal sensors in the h expression situation of the participation data of the ith abnormal sensor corresponding to the ith fault, and determining the association degree of the h expression situation of the participation data and the ith fault according to the association value by taking the ratio of the total number of the ith abnormal sensors corresponding to the ith fault as the association value; and acquiring the absolute value of the difference between the mean value of the abnormal degrees of the abnormal sensors in the h expression conditions of the participation data of the ith abnormal sensor corresponding to the ith fault and the mean value of the abnormal degrees of the abnormal sensors in other expression conditions of the participation data of the ith abnormal sensor, and taking the absolute value as an abnormal difference value. And acquiring the average value of the abnormal difference values as the overall abnormal value of the h expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault. According to the average value of the abnormal degree of the abnormal sensor in the h expression of the participation data of the ith abnormal sensor corresponding to the related value, the overall abnormal value and the ith fault, the calculation formula for obtaining the influence degree of the h expression of the participation data of the ith abnormal sensor corresponding to the ith fault is as follows:
in the method, in the process of the invention,the effect of the h expression of the participation data of the ith abnormal sensor corresponding to the ith faultThe degree of ringing; />The total number of the abnormal sensors in the h expression situation of the participation data of the ith abnormal sensor corresponding to the ith fault; />The total number of the ith abnormal sensors corresponding to the ith fault; />The mean value of the abnormality degree of the abnormal sensor in the h expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault; />The total number of each performance situation of the participation data of the ith abnormal sensor corresponding to the ith fault; />The mean value of the abnormality degree of the abnormal sensor in the x-th expression of the participation data of the u-th abnormal sensor corresponding to the i-th fault; />Is a second preset constant, greater than 0; />As a function of absolute value; />Is the association value; />Is an abnormal difference value;is the overall outlier.
The embodiment of the method uses a second preset constantSetting up1, avoiding the denominator being 0, the practitioner can set a second preset constant +.>Is not limited herein.
It should be noted that the number of the substrates,the larger the association value +.>The larger the participation data representing the ith abnormal sensor corresponding to the ith fault is, the more likely the participation data representing the ith abnormal sensor is, the +.>The larger; />The larger the response of the h-th performance situation to the i-th fault, which indicates the participation data of the u-th abnormal sensor, the larger the ∈>The larger; overall outlier valueThe greater the abnormality degree of the abnormality sensor in the h-th expression of the participation data indicating the u-th abnormality sensor, the more closely to the generation of the i-th failure, the ++>The larger; thus (S)>The larger the participation data h-th performance of the u-th abnormal sensor is, the more likely the participation data h-th performance of the u-th abnormal sensor is the data performance of the corresponding u-th sensor when the i-th fault occurs.
According to the method for acquiring the influence degree of the h expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault, acquiring the influence degree of each expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault.
(2) And obtaining an abnormal characteristic value.
And selecting the maximum influence degree of each performance condition of the participation data of the ith abnormal sensor corresponding to the ith fault as a target influence degree, and taking the performance condition corresponding to the target influence degree as a target performance condition. And obtaining the average value of the abnormality degree of each abnormal sensor in the target performance condition, namely the abnormal characteristic value of the ith abnormal sensor corresponding to the ith fault. If the target influence level corresponds to a plurality of performance cases, one performance case is selected as the target performance case.
According to the method for acquiring the abnormal characteristic value of the ith abnormal sensor corresponding to the ith fault, acquiring the abnormal characteristic value of each abnormal sensor corresponding to each fault.
Step S6: and predicting the possible fault type of the automobile according to the abnormal characteristic value.
And taking the type of the sensor as a vertical axis and the fault type as a horizontal axis, and establishing a two-dimensional matrix, wherein the element corresponding to each horizontal and vertical axis is an abnormal characteristic value of the corresponding abnormal sensor corresponding to the fault. Thus, each fault may result in a most likely representation of the sensor data. When a sensor corresponding to a certain fault in the two-dimensional matrix is not an abnormal sensor, namely, the corresponding element in the two-dimensional matrix cannot be acquired, and at the moment, filling is carried out by 0. The u-th abnormality sensor is a u-th sensor.
According to the technical characteristics of the Internet of vehicles, the data of each sensor in a period of time are continuously monitored and stored in the running process of the vehicle. For any one automobile, when the automobile breaks down, the abnormal degree of each sensor in the automobile is obtained, the abnormal degree of each sensor is compared with the elements with the same longitudinal axis in the two-dimensional matrix in sequence, namely, the absolute value of the difference value of the abnormal degree of each sensor in the automobile and the elements with the same longitudinal axis in the two-dimensional matrix is obtained and is used as a second difference. The fault type corresponding to the smallest second difference is the fault type possibly occurring in the automobile. The method and the device have the advantages that the possible fault types of the automobile are accurately and efficiently determined, the automobile fault detection efficiency is improved, meanwhile, the fault monitoring accuracy is improved, and maintenance staff can maintain conveniently.
The present invention has been completed.
In summary, the embodiment of the invention acquires the data of each sensor of the faulty automobile as the participation data; according to the change of the participation data, the abnormal degree of each sensor is obtained, and abnormal sensors are screened out; obtaining the similarity degree of the same abnormal sensor between any two fault automobiles, and clustering to obtain each performance of the participation data of the same abnormal sensor corresponding to each fault; and obtaining the influence degree according to the number and the abnormality degree of the abnormality sensors in each performance condition, determining the abnormality characteristic value of each abnormality sensor corresponding to each fault, and predicting the possible fault type of the automobile. According to the invention, the type of the possible faults of the automobile is accurately and efficiently predicted according to the abnormal characteristic values of each abnormal sensor corresponding to each fault, and the accuracy of the fault detection efficiency is improved.
Based on the same inventive concept as the method embodiment, the embodiment of the invention also provides an automobile service security assurance system based on a block chain, which comprises the following steps: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps in the embodiment of the block chain-based automobile service safety guarantee method, such as the steps shown in fig. 1. The method for guaranteeing the safety of the automobile service based on the blockchain is described in detail in the above embodiments, and will not be described again.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. A blockchain-based automobile service security assurance method, characterized by comprising the following steps:
acquiring data of a fault automobile at each moment of each sensor in a preset time period as participation data;
according to the change of the participation data, the abnormal degree of each sensor in each fault automobile corresponding to each fault is obtained, and the abnormal sensor in each fault automobile corresponding to each fault is screened out;
according to participation data and abnormality degrees of the same type of abnormality sensor between any two fault automobiles corresponding to each fault, obtaining the similarity degree of the same type of abnormality sensor between any two fault automobiles corresponding to each fault;
clustering the same type of abnormal sensors corresponding to each fault according to the similarity, and taking the obtained cluster as each expression condition of participation data of the same type of abnormal sensors corresponding to each fault;
according to the number and the abnormality degree of the abnormality sensors in each performance situation of the participation data of each abnormality sensor corresponding to each fault, obtaining the influence degree of each performance situation, and determining the abnormality characteristic value of each abnormality sensor corresponding to each fault;
and predicting the possible fault type of the automobile according to the abnormal characteristic value.
2. The method for guaranteeing automobile service safety based on blockchain as claimed in claim 1, wherein the method for obtaining the abnormality degree is as follows:
taking any one sensor of a certain fault automobile corresponding to a certain fault as a target sensor;
fitting predicted normal data of the target sensor when the fault automobile normally runs within a preset time period;
acquiring the difference between the participation data and the predicted normal data of the target sensor at each time in a preset time period, and taking the difference as a residual error value at each time;
acquiring the difference between the participation data of the target sensor at each time and the participation data of the target sensor at the next adjacent time, and taking the difference as a trend change value at each time;
and acquiring the abnormality degree of the target sensor in the fault automobile corresponding to the fault according to the residual value and the trend change value of the target sensor at each moment.
3. The method for guaranteeing the safety of the automobile service based on the blockchain as claimed in claim 2, wherein the calculation formula of the abnormality degree is as follows:
in the method, in the process of the invention,the degree of abnormality of the jth sensor in the kth fault automobile corresponding to the ith fault; t is the total number of times of collecting participation data of a jth sensor in a kth fault automobile corresponding to an ith fault in a preset time period; />The residual error value of a jth sensor in a kth fault automobile corresponding to the ith fault at a t moment in a preset time period is obtained;the method comprises the steps that the maximum residual error value of a jth sensor in a kth fault automobile corresponding to an ith fault in a preset time period is obtained;trend change of the jth sensor in the kth fault automobile corresponding to the ith fault at the t moment in a preset time periodA value; />The trend change value of the jth sensor in the kth fault automobile corresponding to the ith fault at the jth moment in the preset time period is obtained; l is a first preset number; norm is a normalization function; />As a function of absolute value.
4. The method for guaranteeing automobile service safety based on blockchain as in claim 1, wherein the method for acquiring the anomaly sensor is as follows:
when the abnormality degree of the sensor is larger than a preset abnormality degree threshold, the sensor is an abnormality sensor in the fault automobile corresponding to the corresponding fault.
5. The method for guaranteeing the safety of the automobile service based on the blockchain as defined in claim 1, wherein the method for obtaining the similarity degree is as follows:
acquiring a similarity value of participation data of the same abnormal sensor between any two fault automobiles corresponding to each fault through an image matching technology, and taking the similarity value as a first similarity value;
acquiring differences of the degree of abnormality of the same type of abnormality sensor between any two fault automobiles corresponding to each fault as first differences;
and obtaining the similarity degree of the same abnormal sensor between any two fault automobiles corresponding to the same fault according to the first similarity value and the first difference.
6. The method for guaranteeing the safety of the automobile service based on the blockchain as in claim 5, wherein the calculation formula of the similarity degree is as follows:
in the method, in the process of the invention,the similarity degree of the ith abnormal sensor between the a-th fault automobile and the b-th fault automobile corresponding to the ith fault; />Is a first similarity value; />The degree of abnormality of the ith abnormality sensor in the ith fault car corresponding to the ith fault; />The degree of abnormality of the ith abnormality sensor in the ith fault car corresponding to the ith fault; e is a natural constant; norm is a normalization function; />As a function of absolute value.
7. The method for guaranteeing the safety of the automobile service based on the blockchain as in claim 1, wherein the calculation formula of the influence degree is as follows:
in the method, in the process of the invention,the influence degree of the h expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault; />The total number of the abnormal sensors in the h expression situation of the participation data of the ith abnormal sensor corresponding to the ith fault;/>the total number of the ith abnormal sensors corresponding to the ith fault; />The mean value of the abnormality degree of the abnormal sensor in the h expression condition of the participation data of the ith abnormal sensor corresponding to the ith fault; />The total number of each performance situation of the participation data of the ith abnormal sensor corresponding to the ith fault; />The mean value of the abnormality degree of the abnormal sensor in the x-th expression of the participation data of the u-th abnormal sensor corresponding to the i-th fault; />Is a second preset constant, greater than 0; />As a function of absolute value.
8. The method for guaranteeing automobile service safety based on block chain as claimed in claim 1, wherein the method for obtaining the abnormal characteristic value is as follows:
for any abnormal sensor corresponding to any fault, obtaining the influence degree of each performance condition of the abnormal sensor;
taking the performance condition corresponding to the maximum influence degree as a target performance condition;
and acquiring the average value of the abnormality degree of each abnormal sensor in the target performance condition as the abnormal characteristic value of the abnormal sensor corresponding to the fault.
9. The method for guaranteeing the safety of the automobile service based on the blockchain as claimed in claim 1, wherein the method for predicting the possible failure type of the automobile according to the abnormal characteristic value is as follows:
acquiring the difference between the abnormality degree of each sensor of the automobile to be tested and the abnormality characteristic value of each fault type corresponding to the same abnormality sensor as a second difference;
and taking the fault type corresponding to the smallest second difference as the possible fault type of the automobile to be tested.
10. A blockchain-based automotive service security system comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of a blockchain-based automotive service security method as claimed in any of the preceding claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311384622.4A CN117132266A (en) | 2023-10-25 | 2023-10-25 | Block chain-based automobile service security guarantee method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311384622.4A CN117132266A (en) | 2023-10-25 | 2023-10-25 | Block chain-based automobile service security guarantee method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117132266A true CN117132266A (en) | 2023-11-28 |
Family
ID=88860357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311384622.4A Pending CN117132266A (en) | 2023-10-25 | 2023-10-25 | Block chain-based automobile service security guarantee method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117132266A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014148294A (en) * | 2013-02-04 | 2014-08-21 | Denso Corp | Diagnostic device |
| CN113807547A (en) * | 2021-08-12 | 2021-12-17 | 江铃汽车股份有限公司 | Vehicle fault early warning method and system, readable storage medium and computer equipment |
| CN114414023A (en) * | 2021-12-30 | 2022-04-29 | 北京万集科技股份有限公司 | Sensor abnormality diagnosis method and device, and storage medium |
| CN114936675A (en) * | 2022-04-26 | 2022-08-23 | 国能朔黄铁路发展有限责任公司 | Fault early warning method and device, storage medium and electronic equipment |
| CN116502166A (en) * | 2023-04-28 | 2023-07-28 | 天宇正清科技有限公司 | Prediction method, device, equipment and medium based on other equipment data |
-
2023
- 2023-10-25 CN CN202311384622.4A patent/CN117132266A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014148294A (en) * | 2013-02-04 | 2014-08-21 | Denso Corp | Diagnostic device |
| CN113807547A (en) * | 2021-08-12 | 2021-12-17 | 江铃汽车股份有限公司 | Vehicle fault early warning method and system, readable storage medium and computer equipment |
| CN114414023A (en) * | 2021-12-30 | 2022-04-29 | 北京万集科技股份有限公司 | Sensor abnormality diagnosis method and device, and storage medium |
| CN114936675A (en) * | 2022-04-26 | 2022-08-23 | 国能朔黄铁路发展有限责任公司 | Fault early warning method and device, storage medium and electronic equipment |
| CN116502166A (en) * | 2023-04-28 | 2023-07-28 | 天宇正清科技有限公司 | Prediction method, device, equipment and medium based on other equipment data |
Non-Patent Citations (1)
| Title |
|---|
| 符修文;杨勇生;姚海庆;: "基于趋势相关性的传感器网络故障检测算法", 华中科技大学学报(自然科学版), no. 10 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7308385B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| JP7017861B2 (en) | Anomaly detection system and anomaly detection method | |
| US7539597B2 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| US8332337B2 (en) | Condition-based monitoring system for machinery and associated methods | |
| US20140365179A1 (en) | Method and Apparatus for Detecting and Identifying Faults in a Process | |
| AU2002246994A1 (en) | Diagnostic systems and methods for predictive condition monitoring | |
| KR102444442B1 (en) | System and method for diagnosing facility fault | |
| CN111709447A (en) | Power grid abnormality detection method and device, computer equipment and storage medium | |
| CN111474475B (en) | Motor fault diagnosis system and method | |
| CN110795309A (en) | Hierarchical software health management method and system for microsatellite | |
| CN110909822A (en) | Satellite anomaly detection method based on improved Gaussian process regression model | |
| KR102362159B1 (en) | Method for Fault Detection and Fault Diagnosis in Semiconductor Manufacturing Process | |
| CN109165242B (en) | Fault diagnosis and early warning method based on entropy sorting and space-time analysis | |
| CN110703214A (en) | Weather radar state evaluation and fault monitoring method | |
| CN114417699A (en) | Pump valve fault detection method | |
| KR102073810B1 (en) | Method and system for predicting the failure of naval ship propulsion system using machine learning | |
| CN115958990A (en) | V2G charging pile information diagnosis and safety protection method | |
| CN111314110B (en) | Fault early warning method for distributed system | |
| WO2020230422A1 (en) | Abnormality diagnosis device and method | |
| CN117113135A (en) | Carbon emission anomaly monitoring and analyzing system capable of sorting and classifying anomaly data | |
| CN117132266A (en) | Block chain-based automobile service security guarantee method and system | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN116907772A (en) | Self-diagnosis and fault source identification method and system of bridge structure monitoring sensor | |
| CN117150337A (en) | Chemical process fault diagnosis method based on triage system | |
| JPH0134330B2 (en) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |