CN117687290A - Stopwatch detection and evaluation method and system based on multi-source data - Google Patents
Stopwatch detection and evaluation method and system based on multi-source data Download PDFInfo
- Publication number
- CN117687290A CN117687290A CN202410146683.5A CN202410146683A CN117687290A CN 117687290 A CN117687290 A CN 117687290A CN 202410146683 A CN202410146683 A CN 202410146683A CN 117687290 A CN117687290 A CN 117687290A
- Authority
- CN
- China
- Prior art keywords
- stopwatch
- actual characteristic
- characteristic parameter
- matrix
- preset
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 96
- 238000011156 evaluation Methods 0.000 title claims abstract description 39
- 239000011159 matrix material Substances 0.000 claims abstract description 174
- 230000009467 reduction Effects 0.000 claims abstract description 63
- 238000003860 storage Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 29
- KJONHKAYOJNZEC-UHFFFAOYSA-N nitrazepam Chemical compound C12=CC([N+](=O)[O-])=CC=C2NC(=O)CN=C1C1=CC=CC=C1 KJONHKAYOJNZEC-UHFFFAOYSA-N 0.000 claims abstract description 15
- 238000010586 diagram Methods 0.000 claims description 55
- 238000000034 method Methods 0.000 claims description 28
- 230000002159 abnormal effect Effects 0.000 claims description 24
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The invention relates to the technical field of timer evaluation, in particular to a stopwatch detection and evaluation method and system based on multi-source data. Detecting a stopwatch to be detected based on a preset detection parameter control detection device, acquiring actual characteristic parameters fed back by the stopwatch to be detected, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on a random projection algorithm and a Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction; the coordinate information of each actual characteristic parameter in the target dimension is obtained from the final parameter matrix data after dimension reduction, the actual characteristic parameters are classified according to the coordinate information of each actual characteristic parameter in the target dimension, the actual characteristic parameters in each final actual characteristic parameter group are compared with the preset characteristic parameters of corresponding items, an evaluation report is generated, the robustness of the system and the accuracy of detection results can be effectively improved, and intelligent detection and evaluation of a stopwatch are realized.
Description
Technical Field
The invention relates to the technical field of timer evaluation, in particular to a stopwatch detection and evaluation method and system based on multi-source data.
Background
With the development of society and the progress of technology, stopwatches play a vital role in time measurement of various industries. Before the stopwatch leaves the factory, the stopwatch needs to be detected and evaluated in a factory, and in order to improve the accuracy and the robustness of the stopwatch detection, the multi-source data become the key direction of the stopwatch detection research. While traditional stopwatch detection methods may rely solely on image data, modern methods integrate information from multiple data sources such as images, sensors, etc., and this way of comprehensively utilizing data is expected to make algorithms more robust and adaptable to different environments and application scenarios. The existing stopwatch detection and evaluation method based on multi-source data has some technical defects, the multi-source data can face the problem of data inconsistency, the information mismatch can be caused by the differences of time stamps, units, sampling frequencies and the like among different data sources, and a large number of complex algorithms are needed for processing the multi-source data, so that the speed and reliability of stopwatch detection are reduced.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a stopwatch detection and evaluation method and system based on multi-source data.
The technical scheme adopted by the invention for achieving the purpose is as follows:
the invention discloses a stopwatch detection and assessment method based on multi-source data, which comprises the following steps:
s102: acquiring a stopwatch three-dimensional model diagram of a stopwatch to be measured, and importing the stopwatch three-dimensional model diagram into a characteristic database for pairing search to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be measured;
s104: the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained, and the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library;
s106: introducing a random projection algorithm and a Pelson correlation coefficient algorithm, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on the random projection algorithm and the Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction;
s108: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction, and classifying each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter class groups;
S110: comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain a comparison result; and evaluating the stopwatch to be tested according to the comparison result, and generating an evaluation report.
Further, in a preferred embodiment of the present invention, a three-dimensional model diagram of a stopwatch to be measured is obtained, and the three-dimensional model diagram of the stopwatch is imported into a feature database for pairing search, so as to obtain preset detection parameters and preset feature parameters of the stopwatch to be measured, which specifically are:
acquiring image information of a stopwatch to be measured, preprocessing the image information to obtain preprocessed image information, and constructing a stopwatch three-dimensional model diagram of the stopwatch to be measured based on the preprocessed image information;
acquiring sample three-dimensional model diagrams corresponding to stopwatches of different types through a big data network, and acquiring preset detection schemes corresponding to stopwatches of different types; the preset detection scheme comprises preset detection parameters of equipment for detecting various types of stopwatches through detection equipment and preset characteristic parameters of the stopwatches after the various types of stopwatches are detected;
constructing a database, and importing a sample three-dimensional model diagram, preset detection parameters and various preset characteristic parameters corresponding to various signal stopwatches into the database to obtain a characteristic database; and periodically updating the feature database;
Introducing an ICP algorithm, and calculating the coincidence degree between the stopwatch three-dimensional model diagram and each sample three-dimensional model diagram in the database based on the ICP algorithm to obtain a plurality of coincidence degrees;
and carrying out ascending sort processing on the multiple overlapping degrees, extracting the maximum overlapping degree, obtaining a sample three-dimensional model diagram corresponding to the maximum overlapping degree, and searching in the characteristic database according to the sample three-dimensional model diagram corresponding to the maximum overlapping degree to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be detected.
Further, in a preferred embodiment of the present invention, a random projection algorithm and a pearson correlation coefficient algorithm are introduced, and dimension reduction processing is performed on each actual characteristic parameter in the storage library based on the random projection algorithm and the pearson correlation coefficient algorithm, so as to obtain a final parameter matrix after dimension reduction, which specifically includes:
s202: collecting each actual characteristic parameter in a storage library into an actual characteristic parameter set, randomly generating an original matrix according to the actual characteristic parameter set, and defining the original matrix as X; wherein each row in the original matrix represents a parameter point, and each column represents a feature;
s204: determining a target dimension to which the actual characteristic parameter is mapped, and defining the target dimension as d; initializing a projection matrix, and defining the projection matrix as W; wherein the projection matrix is a D D is the original dimension of the actual characteristic parameter, and D is the target dimension;
s206: multiplying the original matrix with the projection matrix to obtain an initial parameter matrix after dimension reduction; a pearson correlation coefficient algorithm is introduced, and pearson correlation coefficients between feature pairs in the initial parameter matrix after the dimension reduction are calculated based on the pearson correlation coefficient algorithm;
s208: forming a correlation matrix by the calculated pearson correlation coefficients according to corresponding feature arrangement, and judging whether feature pairs with correlation exceeding a set threshold exist in the correlation matrix or not;
s210: if not, taking the initial parameter matrix after the dimension reduction as final parameter matrix data after the dimension reduction; if yes, repeating the steps S202-S208 until no feature pair with the correlation exceeding the set threshold exists in the correlation matrix, and taking the initial parameter matrix after the dimension reduction as final parameter matrix data after the dimension reduction.
Further, in a preferred embodiment of the present invention, coordinate information of each actual characteristic parameter in the target dimension is obtained from the final parameter matrix data after dimension reduction, and the actual characteristic parameters are classified according to the coordinate information of each actual characteristic parameter in the target dimension, so as to obtain a plurality of final actual characteristic parameter class groups, which specifically are:
S302: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction; initializing a plurality of parameter centers according to the number of items of each preset characteristic parameter, and calculating the mahalanobis distance between each actual characteristic parameter and each parameter center according to the coordinate information of each actual characteristic parameter in the target dimension;
s304: sorting the mahalanobis distance between each actual characteristic parameter and each parameter center in a descending order, sorting out the shortest mahalanobis distance, and classifying each actual characteristic parameter into the parameter center with the shortest mahalanobis distance in sequence; after the classification is finished, acquiring actual characteristic parameters attached to each parameter center to obtain a plurality of actual characteristic parameter class groups;
s306: introducing a contour coefficient algorithm, and calculating contour coefficients of each actual characteristic parameter group of the contour coefficient algorithm; comparing the contour coefficients of the actual characteristic parameter groups with preset values one by one;
s308: if the contour coefficient of a certain actual characteristic parameter group is larger than a preset value, the fact that singular parameters do not exist in the actual characteristic parameter group is indicated, and the actual characteristic parameter group is taken as a final actual characteristic parameter group to be output;
S310: if the contour coefficient of a certain actual characteristic parameter group is not greater than a preset value, indicating that singular parameters exist in the actual characteristic parameter group, calculating Euclidean distances between all actual characteristic parameters in the actual characteristic parameter group and the parameter center, and eliminating the actual characteristic parameter with the largest Euclidean distance in the actual characteristic parameter group; and then repeating the step S306 until the contour coefficient of the actual characteristic parameter group is larger than a preset value, and outputting the actual characteristic parameter group as a final actual characteristic parameter group.
Further, in a preferred embodiment of the present invention, the actual characteristic parameters in each final actual characteristic parameter group are compared with the preset characteristic parameters of the corresponding items to obtain a comparison result, which specifically includes:
constructing a first empty matrix and a second empty matrix, and respectively filling actual characteristic parameters in each final actual characteristic parameter group and preset characteristic parameters of corresponding items into the first empty matrix and the second empty matrix according to time stamps to obtain an actual characteristic parameter matrix and a preset characteristic parameter matrix;
calculating the similarity between each actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix through a cosine similarity algorithm; comparing the similarity between each actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix with the preset similarity;
If the similarity between a certain actual characteristic parameter matrix and a corresponding preset characteristic parameter matrix is larger than the preset similarity, indicating that the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix are highly overlapped, marking the actual characteristic parameter of a corresponding item of the actual characteristic parameter matrix, and marking the actual characteristic parameter of the item of the stopwatch to be measured as a normal characteristic parameter;
if the similarity between a certain actual characteristic parameter matrix and a corresponding preset characteristic parameter matrix is not greater than the preset similarity, indicating that the coincidence degree between the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix is low, marking the actual characteristic parameter of a corresponding item of the actual characteristic parameter matrix, and marking the actual characteristic parameter of the item of the stopwatch to be measured as an abnormal characteristic parameter.
Further, in a preferred embodiment of the present invention, the stopwatch to be measured is evaluated according to the comparison result, and an evaluation report is generated, specifically:
if all actual characteristic parameters in the stopwatch to be measured are normal characteristic parameters, judging the stopwatch to be measured as a qualified product, and generating a first evaluation report;
if one or more actual characteristic parameters exist in the stopwatch to be measured as abnormal characteristic parameters, carrying out characteristic extraction processing on the abnormal characteristic parameters to obtain characteristic information of the abnormal characteristic parameters;
Carrying out relevance analysis on each device in the stopwatch to be detected according to the characteristic information of the abnormal characteristic parameters, and analyzing to obtain relevance devices which have functional relevance with the abnormal characteristic parameters in the stopwatch to be detected;
judging whether the relevance device is a preset type device or not, if so, judging the stopwatch to be tested as a defective product, and generating a second evaluation report; if not, the stopwatch to be measured is judged to be a repairable product, the type and the position of the relevance device are marked, and a third evaluation report is generated according to the type and the position of the relevance device.
The second aspect of the invention discloses a stopwatch detection and assessment system based on multi-source data, the stopwatch detection and assessment system comprising a memory and a processor, the memory storing a stopwatch detection and assessment method program, when the stopwatch detection and assessment method program is executed by the processor, the steps are implemented as follows:
s102: acquiring a stopwatch three-dimensional model diagram of a stopwatch to be measured, and importing the stopwatch three-dimensional model diagram into a characteristic database for pairing search to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be measured;
s104: the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained, and the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library;
S106: introducing a random projection algorithm and a Pelson correlation coefficient algorithm, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on the random projection algorithm and the Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction;
s108: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction, and classifying each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter class groups;
s110: comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain a comparison result; and evaluating the stopwatch to be tested according to the comparison result, and generating an evaluation report.
The invention solves the technical defects existing in the background technology, and has the following beneficial effects: obtaining preset detection parameters and various preset characteristic parameters of the stopwatch to be detected by obtaining a stopwatch three-dimensional model diagram of the stopwatch to be detected and importing the stopwatch three-dimensional model diagram into a characteristic database for pairing search; the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained, and the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library; introducing a random projection algorithm and a Pelson correlation coefficient algorithm, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on the random projection algorithm and the Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction; acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction, and classifying each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter class groups; comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain a comparison result; and evaluating the stopwatch to be tested according to the comparison result, and generating an evaluation report. The method processes the multi-source data through a simple and effective algorithm, simplifies the data processing flow, can effectively improve the robustness of the system, improves the detection efficiency, can obtain data with high reliability, can improve the accuracy of the detection result, and realizes intelligent detection and evaluation of the stopwatch.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a first method of a multi-source data based stopwatch detection and assessment method;
FIG. 2 is a second method flow diagram of a multi-source data based stopwatch detection and assessment method;
FIG. 3 is a third method flow diagram of a multi-source data based stopwatch detection and assessment method;
FIG. 4 is a system block diagram of a multi-source data based stopwatch detection and assessment system.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present invention discloses a stopwatch detection and evaluation method based on multi-source data, comprising the following steps:
s102: acquiring a stopwatch three-dimensional model diagram of a stopwatch to be measured, and importing the stopwatch three-dimensional model diagram into a characteristic database for pairing search to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be measured;
s104: the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained, and the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library;
s106: introducing a random projection algorithm and a Pelson correlation coefficient algorithm, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on the random projection algorithm and the Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction;
s108: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction, and classifying each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter class groups;
S110: comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain a comparison result; and evaluating the stopwatch to be tested according to the comparison result, and generating an evaluation report.
The method processes the multi-source data through a simple and effective algorithm, simplifies the data processing flow, can effectively improve the system robustness and the detection efficiency, can obtain the data with high reliability, can improve the accuracy of the detection result, and realizes the intelligent detection and evaluation of the stopwatch.
Further, in a preferred embodiment of the present invention, a three-dimensional model diagram of a stopwatch to be measured is obtained, and the three-dimensional model diagram of the stopwatch is imported into a feature database for pairing search, so as to obtain preset detection parameters and preset feature parameters of the stopwatch to be measured, which specifically are:
acquiring image information of a stopwatch to be measured, preprocessing the image information to obtain preprocessed image information, and constructing a stopwatch three-dimensional model diagram of the stopwatch to be measured based on the preprocessed image information;
acquiring sample three-dimensional model diagrams corresponding to stopwatches of different types through a big data network, and acquiring preset detection schemes corresponding to stopwatches of different types; the preset detection scheme comprises preset detection parameters of equipment for detecting various types of stopwatches through detection equipment and preset characteristic parameters of the stopwatches after the various types of stopwatches are detected;
Constructing a database, and importing a sample three-dimensional model diagram, preset detection parameters and various preset characteristic parameters corresponding to various signal stopwatches into the database to obtain a characteristic database; and periodically updating the feature database;
introducing an ICP algorithm, and calculating the coincidence degree between the stopwatch three-dimensional model diagram and each sample three-dimensional model diagram in the database based on the ICP algorithm to obtain a plurality of coincidence degrees;
and carrying out ascending sort processing on the multiple overlapping degrees, extracting the maximum overlapping degree, obtaining a sample three-dimensional model diagram corresponding to the maximum overlapping degree, and searching in the characteristic database according to the sample three-dimensional model diagram corresponding to the maximum overlapping degree to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be detected.
Before the stopwatch to be detected is detected, the image information of the stopwatch to be detected is shot, and then a stopwatch three-dimensional model diagram is constructed according to the image information, so that the stopwatch three-dimensional model diagram is paired with a sample three-dimensional model diagram corresponding to the stopwatch of various types, and preset detection parameters and various preset characteristic parameters of the stopwatch to be detected are obtained through pairing. The preset detection parameters and various preset characteristic parameters of the stopwatch to be detected are obtained rapidly through a simple image processing and model pairing method, so that the detection equipment realizes full-automatic detection, one machine has multiple functions, the detection efficiency is improved effectively, and the intelligent degree of a factory is improved.
As shown in fig. 2, in a preferred embodiment of the present invention, a random projection algorithm and a pearson correlation coefficient algorithm are introduced, and the dimension reduction process is performed on each actual feature parameter in the storage library based on the random projection algorithm and the pearson correlation coefficient algorithm, so as to obtain a final parameter matrix after dimension reduction, which specifically is:
s202: collecting each actual characteristic parameter in a storage library into an actual characteristic parameter set, randomly generating an original matrix according to the actual characteristic parameter set, and defining the original matrix as X; wherein each row in the original matrix represents a parameter point, and each column represents a feature;
s204: determining a target dimension to which the actual characteristic parameter is mapped, and defining the target dimension as d; initializing a projection matrix, and defining the projection matrix as W; wherein the projection matrix is a DD is the original dimension of the actual characteristic parameter, and D is the target dimension;
s206: multiplying the original matrix with the projection matrix to obtain an initial parameter matrix after dimension reduction; a pearson correlation coefficient algorithm is introduced, and pearson correlation coefficients between feature pairs in the initial parameter matrix after the dimension reduction are calculated based on the pearson correlation coefficient algorithm;
S208: forming a correlation matrix by the calculated pearson correlation coefficients according to corresponding feature arrangement, and judging whether feature pairs with correlation exceeding a set threshold exist in the correlation matrix or not;
s210: if not, taking the initial parameter matrix after the dimension reduction as final parameter matrix data after the dimension reduction; if yes, repeating the steps S202-S208 until no feature pair with the correlation exceeding the set threshold exists in the correlation matrix, and taking the initial parameter matrix after the dimension reduction as final parameter matrix data after the dimension reduction.
After the preset detection parameters and each preset characteristic parameter of the stopwatch to be detected are obtained through pairing, the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained through each detection device (such as each sensor and each camera), the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library, and the characteristic parameters comprise response time, resolution, battery voltage, anti-interference performance, temperature stability and the like.
It should be noted that, because the acquired actual characteristic parameters are high-dimensional data, in order to improve the classification data of the subsequent data, the dimension reduction processing needs to be performed on the high-dimensional actual characteristic parameters in the storage library by using a random projection algorithm, so as to reduce the dimension of the data, improve the processing speed of the subsequent data and save the storage space of the data. Each element in the projection matrix can be randomly extracted from the preset probability distribution independently; in addition, if different features of the original parameters have different scales, normalization or normalization may be performed first to ensure that each feature contributes approximately equally to the dimension reduction. Because of the defect reason of the dimension reduction algorithm of the random projection algorithm, the problem of overhigh redundancy exists in the parameter matrix after dimension reduction, for example, in order to reduce the dimension in the dimension reduction process, information of some original data is lost, if the dimension after dimension reduction is overlow, insufficient representation of the information is possibly caused, and redundancy is introduced, therefore, after the initial parameter matrix after dimension reduction is obtained, whether the initial parameter matrix after dimension reduction has the problem of overhigh redundancy is further judged through a pearson correlation coefficient algorithm, specifically, if a feature pair with the correlation exceeding a set threshold exists in the correlation matrix, the problem of redundancy exists in the initial parameter matrix is indicated, and therefore, the original matrix needs to be randomly generated again, and dimension reduction processing is carried out on each actual feature parameter until the feature pair with the correlation exceeding the set threshold does not exist in the correlation matrix. Through the steps, the dimension reduction processing can be rapidly carried out on each actual characteristic parameter in the storage library, so that the operation efficiency of the system is improved, the robustness of the system is improved, the reliable high-final parameter matrix data is obtained, the data precision can be improved, and the accuracy of a detection result is improved.
As shown in fig. 3, in a further preferred embodiment of the present invention, coordinate information of each actual characteristic parameter in the target dimension is obtained from the final parameter matrix data after dimension reduction, and classification processing is performed on each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension, so as to obtain a plurality of final actual characteristic parameter clusters, which are specifically:
s302: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction; initializing a plurality of parameter centers according to the number of items of each preset characteristic parameter, and calculating the mahalanobis distance between each actual characteristic parameter and each parameter center according to the coordinate information of each actual characteristic parameter in the target dimension;
s304: sorting the mahalanobis distance between each actual characteristic parameter and each parameter center in a descending order, sorting out the shortest mahalanobis distance, and classifying each actual characteristic parameter into the parameter center with the shortest mahalanobis distance in sequence; after the classification is finished, acquiring actual characteristic parameters attached to each parameter center to obtain a plurality of actual characteristic parameter class groups;
s306: introducing a contour coefficient algorithm, and calculating contour coefficients of each actual characteristic parameter group of the contour coefficient algorithm; comparing the contour coefficients of the actual characteristic parameter groups with preset values one by one;
S308: if the contour coefficient of a certain actual characteristic parameter group is larger than a preset value, the fact that singular parameters do not exist in the actual characteristic parameter group is indicated, and the actual characteristic parameter group is taken as a final actual characteristic parameter group to be output;
s310: if the contour coefficient of a certain actual characteristic parameter group is not greater than a preset value, indicating that singular parameters exist in the actual characteristic parameter group, calculating Euclidean distances between all actual characteristic parameters in the actual characteristic parameter group and the parameter center, and eliminating the actual characteristic parameter with the largest Euclidean distance in the actual characteristic parameter group; and then repeating the step S306 until the contour coefficient of the actual characteristic parameter group is larger than a preset value, and outputting the actual characteristic parameter group as a final actual characteristic parameter group.
After the dimension reduction processing is performed on each actual characteristic parameter in the storage library, the mahalanobis distance between each actual characteristic parameter and each parameter center is calculated through a mahalanobis distance algorithm, and each actual characteristic parameter is sequentially classified into the parameter center with the shortest mahalanobis distance to obtain a plurality of actual characteristic parameter groups, wherein the same type of actual characteristic parameter is clustered in each actual characteristic parameter group, and if the temperature stability of the stopwatch to be measured in the detection time is clustered in a certain actual characteristic parameter. Invalid data, such as noise data, may exist in each actual characteristic parameter group due to the influence of factors such as the acquisition environment and the acquisition precision of each sensor. Therefore, after the actual feature parameter groups are obtained, the profile coefficient of each actual feature parameter group is calculated, so that the compactness of each actual feature parameter group is evaluated, specifically, if the profile coefficient of a certain actual feature parameter group is larger than a preset value, it is indicated that the compactness of the actual feature parameter group is good, it is indicated that no singular parameter (noise data) exists in the actual feature parameter group, and at the moment, the actual feature parameter group is output as a final actual feature parameter group. If the contour coefficient of a certain actual characteristic parameter group is not greater than a preset value, the fact that the compactness of the actual characteristic parameter group is poor is indicated, if the actual characteristic parameter group has singular parameters, the Euclidean distance between all actual characteristic parameters in the actual characteristic parameter group and the parameter center is calculated, and the actual characteristic parameter with the largest Euclidean distance is removed from the actual characteristic parameter group, so that noise data are screened out and removed; and then repeating the step S306 until the contour coefficient of the actual characteristic parameter group is larger than a preset value, and outputting the actual characteristic parameter group as a final actual characteristic parameter group. By the method, the actual characteristic parameters in the storage library can be rapidly classified, so that the actual characteristic parameters of different types are obtained, and the robustness of the system can be effectively improved.
Further, in a preferred embodiment of the present invention, the actual characteristic parameters in each final actual characteristic parameter group are compared with the preset characteristic parameters of the corresponding items to obtain a comparison result, which specifically includes:
constructing a first empty matrix and a second empty matrix, and respectively filling actual characteristic parameters in each final actual characteristic parameter group and preset characteristic parameters of corresponding items into the first empty matrix and the second empty matrix according to time stamps to obtain an actual characteristic parameter matrix and a preset characteristic parameter matrix;
calculating the similarity between each actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix through a cosine similarity algorithm; comparing the similarity between each actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix with the preset similarity;
if the similarity between a certain actual characteristic parameter matrix and a corresponding preset characteristic parameter matrix is larger than the preset similarity, indicating that the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix are highly overlapped, marking the actual characteristic parameter of a corresponding item of the actual characteristic parameter matrix, and marking the actual characteristic parameter of the item of the stopwatch to be measured as a normal characteristic parameter;
If the similarity between a certain actual characteristic parameter matrix and a corresponding preset characteristic parameter matrix is not greater than the preset similarity, indicating that the coincidence degree between the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix is low, marking the actual characteristic parameter of a corresponding item of the actual characteristic parameter matrix, and marking the actual characteristic parameter of the item of the stopwatch to be measured as an abnormal characteristic parameter.
It should be noted that, by constructing a first empty matrix and a second empty matrix in advance, the actual characteristic parameters in each final actual characteristic parameter group and the preset characteristic parameters of the corresponding items are respectively filled into the first empty matrix and the second empty matrix according to the time stamps, so as to obtain an actual characteristic parameter matrix and a preset characteristic parameter matrix. For example, the actual temperature stability of each acquisition time node in the detection time period is sequentially filled into the first empty matrix according to the time sequence to obtain an actual temperature stability parameter matrix, the preset temperature stability is similarly filled into the second empty matrix to obtain a preset temperature stability parameter matrix, and then the similarity, namely the coincidence ratio, of a certain actual characteristic parameter matrix and a corresponding preset characteristic parameter matrix is calculated, if the similarity between the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix is not greater than the preset similarity, the fact that the coincidence ratio between the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix is lower is indicated, the actual characteristic parameters of corresponding items of the actual characteristic parameter matrix are marked, and the actual characteristic parameters of the stopwatch to be detected are marked as abnormal characteristic parameters. And the like, judging whether the actual characteristic parameters of each item of the stopwatch to be measured are normal or not through the method.
Further, in a preferred embodiment of the present invention, the stopwatch to be measured is evaluated according to the comparison result, and an evaluation report is generated, specifically:
if all actual characteristic parameters in the stopwatch to be measured are normal characteristic parameters, judging the stopwatch to be measured as a qualified product, and generating a first evaluation report;
if one or more actual characteristic parameters exist in the stopwatch to be measured as abnormal characteristic parameters, carrying out characteristic extraction processing on the abnormal characteristic parameters to obtain characteristic information of the abnormal characteristic parameters;
carrying out relevance analysis on each device in the stopwatch to be detected according to the characteristic information of the abnormal characteristic parameters, and analyzing to obtain relevance devices which have functional relevance with the abnormal characteristic parameters in the stopwatch to be detected;
judging whether the relevance device is a preset type device or not, if so, judging the stopwatch to be tested as a defective product, and generating a second evaluation report; if not, the stopwatch to be measured is judged to be a repairable product, the type and the position of the relevance device are marked, and a third evaluation report is generated according to the type and the position of the relevance device.
After judging whether the actual characteristic parameters of the stopwatch to be measured are normal, if the actual characteristic parameters of the stopwatch to be measured are all normal characteristic parameters, judging the stopwatch to be measured as a qualified product, and generating a first evaluation report. If one or more actual characteristic parameters in the stopwatch to be measured are abnormal characteristic parameters, the existence of parameter abnormality in the stopwatch is indicated, at the moment, correlation analysis is carried out on all devices in the stopwatch to be measured according to the characteristic information of the abnormal characteristic parameters, and the correlation devices which are functionally associated with the abnormal characteristic parameters in the stopwatch to be measured are obtained through analysis, for example, when the timing accuracy parameters of the stopwatch are abnormal, the situation that a crystal oscillator element (an oscillator) is likely to be failed is indicated, namely the oscillator is the correlation device. And judging whether the relevance device is a preset type device, if so, judging the stopwatch to be tested as a defective product and generating a second evaluation report if the relevance device is not capable of being replaced or is extremely difficult to replace. If not, the stopwatch to be measured is judged to be a repairable product, the type and the position of the relevance device are marked, and a third evaluation report is generated according to the type and the position of the relevance device. The relevance device can be further evaluated according to the abnormal characteristic parameters of the stopwatch through the step, so that the fault is diagnosed, positioned and analyzed in the detection process, the subsequent overhaul efficiency of the fault stopwatch is improved, and the intelligent detection is realized.
Furthermore, the method comprises the following steps:
acquiring a lens image of a stopwatch to be measured, carrying out weighted average processing on the lens image information based on a weighted average method to obtain gray values of all preset node areas in the lens image, and constructing an actual gray matrix of the lens according to the gray values of all preset node areas in the lens image;
obtaining standard lens images of the stopwatch with different precision grades, generating standard gray matrixes of the stopwatch with different precision grades according to the standard lens images, constructing a knowledge graph, and importing the standard gray matrixes of the stopwatch with different precision grades into the knowledge graph;
acquiring the precision grade requirement of the current stopwatch to be measured, generating a search tag according to the precision grade requirement of the current stopwatch to be measured, and searching the knowledge graph based on the search tag to obtain a standard gray matrix of a lens in the current stopwatch to be measured;
calculating the similarity between an actual gray matrix of a lens in a stopwatch to be tested and a corresponding standard gray matrix based on a cosine similarity algorithm, and judging whether the similarity is larger than a preset similarity;
if the measured lens is larger than the measured lens, judging the lens of the current stopwatch to be a qualified lens; if the number of the pixels is not greater than the preset number, judging the lens of the stopwatch to be tested as a disqualified lens, acquiring the positions where the elements in the actual gray matrix and the corresponding standard gray matrix are not equal, and marking the defect positions of the disqualified lens according to the fact that the elements in the actual gray matrix and the corresponding standard gray matrix are not equal.
The lens is one of appearance components of the stopwatch, and the appearance quality of the lens is directly related to the overall appearance of the stopwatch. The detection ensures that the lens is free of blemishes, bubbles, cracks or other problems affecting the appearance. The method can detect the stopwatch lens, ensure that the quality, performance and appearance of the stopwatch lens meet manufacturing standards, and improve the overall quality and user experience of the product.
In addition, a stopwatch three-dimensional model diagram of the stopwatch to be measured is constructed based on the preprocessed image information, and the stopwatch three-dimensional model diagram specifically comprises the following steps:
s402: performing feature extraction processing on the preprocessed image information to obtain a plurality of feature points; introducing a K-means clustering algorithm, calculating Manhattan distances between all the characteristic points and cluster centers, and screening out the characteristic points with Manhattan distances larger than a preset distance to obtain screened characteristic points;
s404: randomly selecting a screened characteristic point as a construction origin, generating a three-dimensional coordinate system according to the construction origin, acquiring coordinate values of each screened characteristic point in the three-dimensional coordinate system, and generating a characteristic point coordinate set according to the coordinate values of each screened characteristic point;
s406: importing the characteristic point coordinate set into three-dimensional modeling software for model construction, and generating an initial stopwatch three-dimensional model diagram;
S408: decomposing the initial stopwatch three-dimensional model diagram based on a non-negative matrix decomposition algorithm to obtain a non-negative matrix, and searching whether elements smaller than a preset threshold exist in the non-negative matrix one by one;
s410: if not, outputting the initial stopwatch three-dimensional model diagram as a stopwatch three-dimensional model diagram, and repeating the steps S402-S408 until no element smaller than a preset threshold exists in the non-negative matrix.
It should be noted that, after the modeling software performs three-dimensional modeling, due to the self-defect problem of the feature extraction algorithm (such as the ORB algorithm, etc.), there may be a situation that an erroneous feature point is extracted, so that an incorrect geometry is created, and an inconsistency of connecting inaccurate vertices is created, thereby causing a topology problem of the three-dimensional model. By the method, whether the constructed three-dimensional model diagram has topological errors can be judged, so that the stopwatch three-dimensional model diagram with high reliability is obtained, and the pairing precision of the follow-up model is improved.
As shown in fig. 4, the second aspect of the present invention discloses a stopwatch detection and evaluation system based on multi-source data, the stopwatch detection and evaluation system comprising a memory 41 and a processor 62, the memory 41 storing a stopwatch detection and evaluation method program, when executed by the processor 62, implementing the steps of:
S102: acquiring a stopwatch three-dimensional model diagram of a stopwatch to be measured, and importing the stopwatch three-dimensional model diagram into a characteristic database for pairing search to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be measured;
s104: the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained, and the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library;
s106: introducing a random projection algorithm and a Pelson correlation coefficient algorithm, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on the random projection algorithm and the Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction;
s108: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction, and classifying each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter class groups;
s110: comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain a comparison result; and evaluating the stopwatch to be tested according to the comparison result, and generating an evaluation report.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. A stopwatch detection and assessment method based on multi-source data, comprising the steps of:
s102: acquiring a stopwatch three-dimensional model diagram of a stopwatch to be measured, and importing the stopwatch three-dimensional model diagram into a characteristic database for pairing search to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be measured;
s104: the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained, and the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library;
s106: introducing a random projection algorithm and a Pelson correlation coefficient algorithm, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on the random projection algorithm and the Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction;
S108: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction, and classifying each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter class groups;
s110: comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain a comparison result; and evaluating the stopwatch to be tested according to the comparison result, and generating an evaluation report.
2. The stopwatch detection and assessment method based on multi-source data according to claim 1, wherein a stopwatch three-dimensional model diagram of a stopwatch to be detected is obtained, and the stopwatch three-dimensional model diagram is imported into a feature database for pairing search, so as to obtain preset detection parameters and various preset feature parameters of the stopwatch to be detected, specifically:
acquiring image information of a stopwatch to be measured, preprocessing the image information to obtain preprocessed image information, and constructing a stopwatch three-dimensional model diagram of the stopwatch to be measured based on the preprocessed image information;
acquiring sample three-dimensional model diagrams corresponding to stopwatches of different types through a big data network, and acquiring preset detection schemes corresponding to stopwatches of different types; the preset detection scheme comprises preset detection parameters of equipment for detecting various types of stopwatches through detection equipment and preset characteristic parameters of the stopwatches after the various types of stopwatches are detected;
Constructing a database, and importing a sample three-dimensional model diagram, preset detection parameters and various preset characteristic parameters corresponding to various signal stopwatches into the database to obtain a characteristic database; and periodically updating the feature database;
introducing an ICP algorithm, and calculating the coincidence degree between the stopwatch three-dimensional model diagram and each sample three-dimensional model diagram in the database based on the ICP algorithm to obtain a plurality of coincidence degrees;
and carrying out ascending sort processing on the multiple overlapping degrees, extracting the maximum overlapping degree, obtaining a sample three-dimensional model diagram corresponding to the maximum overlapping degree, and searching in the characteristic database according to the sample three-dimensional model diagram corresponding to the maximum overlapping degree to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be detected.
3. The stopwatch detection and evaluation method based on multi-source data according to claim 1, wherein a random projection algorithm and a pearson correlation coefficient algorithm are introduced, and dimension reduction processing is performed on each actual characteristic parameter in a storage library based on the random projection algorithm and the pearson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction, specifically:
s202: collecting each actual characteristic parameter in a storage library into an actual characteristic parameter set, randomly generating an original matrix according to the actual characteristic parameter set, and defining the original matrix as X; wherein each row in the original matrix represents a parameter point, and each column represents a feature;
S204: determining a target dimension to which the actual characteristic parameter is mapped, and defining the target dimension as d; initializing a projection matrix, and defining the projection matrix as W; wherein the projection matrix is a DD is the original dimension of the actual characteristic parameter, and D is the target dimension;
s206: multiplying the original matrix with the projection matrix to obtain an initial parameter matrix after dimension reduction; a pearson correlation coefficient algorithm is introduced, and pearson correlation coefficients between feature pairs in the initial parameter matrix after the dimension reduction are calculated based on the pearson correlation coefficient algorithm;
s208: forming a correlation matrix by the calculated pearson correlation coefficients according to corresponding feature arrangement, and judging whether feature pairs with correlation exceeding a set threshold exist in the correlation matrix or not;
s210: if not, taking the initial parameter matrix after the dimension reduction as final parameter matrix data after the dimension reduction; if yes, repeating the steps S202-S208 until no feature pair with the correlation exceeding the set threshold exists in the correlation matrix, and taking the initial parameter matrix after the dimension reduction as final parameter matrix data after the dimension reduction.
4. The stopwatch detection and evaluation method based on multi-source data according to claim 1, wherein the coordinate information of each actual characteristic parameter in the target dimension is obtained from the final parameter matrix data after dimension reduction, and each actual characteristic parameter is classified according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter groups, specifically:
S302: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction; initializing a plurality of parameter centers according to the number of items of each preset characteristic parameter, and calculating the mahalanobis distance between each actual characteristic parameter and each parameter center according to the coordinate information of each actual characteristic parameter in the target dimension;
s304: sorting the mahalanobis distance between each actual characteristic parameter and each parameter center in a descending order, sorting out the shortest mahalanobis distance, and classifying each actual characteristic parameter into the parameter center with the shortest mahalanobis distance in sequence; after the classification is finished, acquiring actual characteristic parameters attached to each parameter center to obtain a plurality of actual characteristic parameter class groups;
s306: introducing a contour coefficient algorithm, and calculating contour coefficients of each actual characteristic parameter group of the contour coefficient algorithm; comparing the contour coefficients of the actual characteristic parameter groups with preset values one by one;
s308: if the contour coefficient of a certain actual characteristic parameter group is larger than a preset value, the fact that singular parameters do not exist in the actual characteristic parameter group is indicated, and the actual characteristic parameter group is taken as a final actual characteristic parameter group to be output;
S310: if the contour coefficient of a certain actual characteristic parameter group is not greater than a preset value, indicating that singular parameters exist in the actual characteristic parameter group, calculating Euclidean distances between all actual characteristic parameters in the actual characteristic parameter group and the parameter center, and eliminating the actual characteristic parameter with the largest Euclidean distance in the actual characteristic parameter group; and then repeating the step S306 until the contour coefficient of the actual characteristic parameter group is larger than a preset value, and outputting the actual characteristic parameter group as a final actual characteristic parameter group.
5. The method for detecting and evaluating a stopwatch based on multi-source data according to claim 1, wherein the comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain the comparison result comprises:
constructing a first empty matrix and a second empty matrix, and respectively filling actual characteristic parameters in each final actual characteristic parameter group and preset characteristic parameters of corresponding items into the first empty matrix and the second empty matrix according to time stamps to obtain an actual characteristic parameter matrix and a preset characteristic parameter matrix;
calculating the similarity between each actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix through a cosine similarity algorithm; comparing the similarity between each actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix with the preset similarity;
If the similarity between a certain actual characteristic parameter matrix and a corresponding preset characteristic parameter matrix is larger than the preset similarity, indicating that the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix are highly overlapped, marking the actual characteristic parameter of a corresponding item of the actual characteristic parameter matrix, and marking the actual characteristic parameter of the item of the stopwatch to be measured as a normal characteristic parameter;
if the similarity between a certain actual characteristic parameter matrix and a corresponding preset characteristic parameter matrix is not greater than the preset similarity, indicating that the coincidence degree between the actual characteristic parameter matrix and the corresponding preset characteristic parameter matrix is low, marking the actual characteristic parameter of a corresponding item of the actual characteristic parameter matrix, and marking the actual characteristic parameter of the item of the stopwatch to be measured as an abnormal characteristic parameter.
6. The method for detecting and evaluating the stopwatch based on the multi-source data according to claim 1, wherein the stopwatch to be tested is evaluated according to the comparison result, and an evaluation report is generated, specifically:
if all actual characteristic parameters in the stopwatch to be measured are normal characteristic parameters, judging the stopwatch to be measured as a qualified product, and generating a first evaluation report;
if one or more actual characteristic parameters exist in the stopwatch to be measured as abnormal characteristic parameters, carrying out characteristic extraction processing on the abnormal characteristic parameters to obtain characteristic information of the abnormal characteristic parameters;
Carrying out relevance analysis on each device in the stopwatch to be detected according to the characteristic information of the abnormal characteristic parameters, and analyzing to obtain relevance devices which have functional relevance with the abnormal characteristic parameters in the stopwatch to be detected;
judging whether the relevance device is a preset type device or not, if so, judging the stopwatch to be tested as a defective product, and generating a second evaluation report; if not, the stopwatch to be measured is judged to be a repairable product, the type and the position of the relevance device are marked, and a third evaluation report is generated according to the type and the position of the relevance device.
7. A multi-source data based stopwatch detection and assessment system comprising a memory and a processor, the memory having stored therein a stopwatch detection and assessment method program which when executed by the processor performs the steps of:
s102: acquiring a stopwatch three-dimensional model diagram of a stopwatch to be measured, and importing the stopwatch three-dimensional model diagram into a characteristic database for pairing search to obtain preset detection parameters and various preset characteristic parameters of the stopwatch to be measured;
s104: the detection equipment is controlled to detect the stopwatch to be detected based on the preset detection parameters, the actual characteristic parameters fed back by the stopwatch to be detected are obtained, and the actual characteristic parameters fed back by the stopwatch to be detected are conveyed to a storage library;
S106: introducing a random projection algorithm and a Pelson correlation coefficient algorithm, and performing dimension reduction processing on each actual characteristic parameter in a storage library based on the random projection algorithm and the Pelson correlation coefficient algorithm to obtain a final parameter matrix after dimension reduction;
s108: acquiring coordinate information of each actual characteristic parameter in a target dimension from the final parameter matrix data after dimension reduction, and classifying each actual characteristic parameter according to the coordinate information of each actual characteristic parameter in the target dimension to obtain a plurality of final actual characteristic parameter class groups;
s110: comparing the actual characteristic parameters in each final actual characteristic parameter group with the preset characteristic parameters of the corresponding items to obtain a comparison result; and evaluating the stopwatch to be tested according to the comparison result, and generating an evaluation report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410146683.5A CN117687290B (en) | 2024-02-02 | 2024-02-02 | Stopwatch detection and evaluation method and system based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410146683.5A CN117687290B (en) | 2024-02-02 | 2024-02-02 | Stopwatch detection and evaluation method and system based on multi-source data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117687290A true CN117687290A (en) | 2024-03-12 |
| CN117687290B CN117687290B (en) | 2024-04-12 |
Family
ID=90133779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410146683.5A Active CN117687290B (en) | 2024-02-02 | 2024-02-02 | Stopwatch detection and evaluation method and system based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117687290B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040049134A1 (en) * | 2002-07-02 | 2004-03-11 | Tosaya Carol A. | System and methods for treatment of alzheimer's and other deposition-related disorders of the brain |
| CN103118180A (en) * | 2013-01-17 | 2013-05-22 | 广东欧珀移动通信有限公司 | Mobile phone stopwatch control method and control device |
| CN107144291A (en) * | 2017-05-23 | 2017-09-08 | 维沃移动通信有限公司 | A kind of data processing method and mobile terminal |
| CN107590819A (en) * | 2017-08-03 | 2018-01-16 | 浙江工业大学 | A kind of river surface flow velocity method of estimation based on compressed sensing graphical analysis |
| US20180070823A1 (en) * | 2015-04-02 | 2018-03-15 | Cambridge Cognition Limited | Systems and methods for assessing cognitive function |
| US20200344303A1 (en) * | 2018-05-10 | 2020-10-29 | Sony Corporation | Transmission of sensor data from sensor devices |
| CN114611768A (en) * | 2022-02-24 | 2022-06-10 | 国网湖北省电力有限公司 | Power distribution network industry expansion matching capacity time sequence construction scale prediction method |
| CN117111434A (en) * | 2023-08-17 | 2023-11-24 | 湖南时空信安科技有限公司 | Clock performance evaluation method and device and terminal equipment |
| CN117272155A (en) * | 2023-09-20 | 2023-12-22 | 合肥工业大学 | Intelligent watch-based driver road anger disease detection method |
| CN117350028A (en) * | 2023-09-19 | 2024-01-05 | 贵州省疾病预防控制中心 | Mushroom dryer intelligent management method and system based on data processing |
-
2024
- 2024-02-02 CN CN202410146683.5A patent/CN117687290B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040049134A1 (en) * | 2002-07-02 | 2004-03-11 | Tosaya Carol A. | System and methods for treatment of alzheimer's and other deposition-related disorders of the brain |
| CN103118180A (en) * | 2013-01-17 | 2013-05-22 | 广东欧珀移动通信有限公司 | Mobile phone stopwatch control method and control device |
| US20180070823A1 (en) * | 2015-04-02 | 2018-03-15 | Cambridge Cognition Limited | Systems and methods for assessing cognitive function |
| CN107144291A (en) * | 2017-05-23 | 2017-09-08 | 维沃移动通信有限公司 | A kind of data processing method and mobile terminal |
| CN107590819A (en) * | 2017-08-03 | 2018-01-16 | 浙江工业大学 | A kind of river surface flow velocity method of estimation based on compressed sensing graphical analysis |
| US20200344303A1 (en) * | 2018-05-10 | 2020-10-29 | Sony Corporation | Transmission of sensor data from sensor devices |
| CN114611768A (en) * | 2022-02-24 | 2022-06-10 | 国网湖北省电力有限公司 | Power distribution network industry expansion matching capacity time sequence construction scale prediction method |
| CN117111434A (en) * | 2023-08-17 | 2023-11-24 | 湖南时空信安科技有限公司 | Clock performance evaluation method and device and terminal equipment |
| CN117350028A (en) * | 2023-09-19 | 2024-01-05 | 贵州省疾病预防控制中心 | Mushroom dryer intelligent management method and system based on data processing |
| CN117272155A (en) * | 2023-09-20 | 2023-12-22 | 合肥工业大学 | Intelligent watch-based driver road anger disease detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117687290B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112987675B (en) | Method, device, computer equipment and medium for anomaly detection | |
| CN111931806A (en) | Equipment fault diagnosis method and device for multi-sensor data fusion | |
| CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
| CN114090396A (en) | Cloud environment multi-index unsupervised anomaly detection and root cause analysis method | |
| CN112527604A (en) | Deep learning-based operation and maintenance detection method and system, electronic equipment and medium | |
| CN115801463B (en) | Industrial Internet platform intrusion detection method and device and electronic equipment | |
| CN114760098A (en) | CNN-GRU-based power grid false data injection detection method and device | |
| CN112766429A (en) | Method, device, computer equipment and medium for anomaly detection | |
| CN112529109A (en) | Unsupervised multi-model-based anomaly detection method and system | |
| CN112307827B (en) | Object recognition apparatus, system and method | |
| CN111767192A (en) | Service data detection method, device, equipment and medium based on artificial intelligence | |
| CN109033205B (en) | Aerospace test data checking device based on data input behavior analysis | |
| CN117687290B (en) | Stopwatch detection and evaluation method and system based on multi-source data | |
| CN116451081A (en) | Data drift detection method, device, terminal and storage medium | |
| CN116910526A (en) | Model training method, device, communication equipment and readable storage medium | |
| CN111091194A (en) | Operation system identification method based on CAVWB _ KL algorithm | |
| CN115460061A (en) | Health degree evaluation method and device based on intelligent operation and maintenance scene | |
| CN117236572B (en) | Method and system for evaluating performance of dry powder extinguishing equipment based on data analysis | |
| CN111798237B (en) | Abnormal transaction diagnosis method and system based on application log | |
| CN115757365A (en) | Multi-dimensional time sequence data anomaly detection method, model training method and device | |
| CN113255810A (en) | Network model testing method based on key decision logic design test coverage rate | |
| CN113627755A (en) | Test method, device, equipment and storage medium for intelligent terminal factory | |
| CN113705920A (en) | Generation method of water data sample set for thermal power plant and terminal equipment | |
| CN113495907A (en) | Product detection method, product detection device, computer device and storage medium | |
| CN113391256A (en) | Electric energy meter metering fault analysis method and system of field operation terminal |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |