CN117908498B - Workshop production monitoring system based on MBS - Google Patents
Workshop production monitoring system based on MBS Download PDFInfo
- Publication number
- CN117908498B CN117908498B CN202410308384.7A CN202410308384A CN117908498B CN 117908498 B CN117908498 B CN 117908498B CN 202410308384 A CN202410308384 A CN 202410308384A CN 117908498 B CN117908498 B CN 117908498B
- Authority
- CN
- China
- Prior art keywords
- product
- standard
- frame
- graph
- comprehensive
- 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.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 72
- 238000012544 monitoring process Methods 0.000 title claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000007689 inspection Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 39
- 238000000034 method Methods 0.000 claims description 28
- 230000006698 induction Effects 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000012797 qualification Methods 0.000 abstract description 2
- 238000013480 data collection Methods 0.000 abstract 1
- 125000004122 cyclic group Chemical group 0.000 description 6
- 238000007726 management method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a workshop production monitoring system based on MBS, which relates to the technical field of monitoring systems and comprises a monitoring center, wherein the monitoring center is connected with a data acquisition module, a data preprocessing module, a data processing module and a comprehensive analysis module; the comprehensive video information of the workshop is collected through a data collection module, and a product parameter library is constructed; processing the product parameter library in a data preprocessing module to obtain a standard parameter drawing library; frame extraction is carried out on the collected comprehensive video information in a data processing module to obtain an input image frame, and a circulating extraction layer is arranged to carry out smooth extraction on the input image frame to obtain a characteristic product image; the comprehensive analysis module performs pattern comparison on the characteristic product graph and the standard parameter graph library to obtain a matched product graph, and performs repeated comparison on the obtained characteristic product graph and the matched product graph to obtain a disqualified product; greatly improves the quality inspection speed of workshop products, optimizes the production quality, and improves the consistency and qualification rate of the products.
Description
Technical Field
The invention relates to the technical field of monitoring systems, in particular to a workshop production monitoring system based on MBS.
Background
Workshop production monitoring is a method or system for monitoring and managing the production process of a manufacturing workshop in real time, and the method helps enterprises to know the production condition, discover and solve potential problems in time and optimize and control the production process by collecting, analyzing and displaying production data and indexes and tracking the equipment state and the production progress in real time. MBS is a software system for enterprise manufacturing management and control, and the application of MBS to workshop production can provide more comprehensive, accurate and comprehensive information, coordinate and manage on-site production activities to improve production efficiency, quality and on-time delivery performance.
However, shop production monitoring also has some drawbacks: the data acquisition may be affected by equipment failure, sensor problems or human operation, etc., resulting in the accuracy and integrity of the data being affected; the collection and analysis of large quantities of production data can lead to data overload problems, making efficient data analysis difficult, requiring appropriate algorithms and tools for data processing; therefore, the intelligent monitoring device has important theoretical and practical significance in intelligent monitoring of workshop production.
How to process the collected workshop comprehensive video information by using a monitoring system technology to obtain a characteristic product graph, and comparing the obtained characteristic product graph with a constructed standard parameter graph library in a repeated mode to obtain an unqualified product, wherein the unqualified product is obtained by matching production line nodes of the unqualified product, so that abnormal nodes are problems which need to be solved; for this purpose, a workshop production monitoring system based on MBS is now provided.
Disclosure of Invention
The aim of the invention can be achieved by the following technical scheme:
the workshop production monitoring system based on the MBS comprises a monitoring center, wherein the monitoring center is connected with a data acquisition module, a data preprocessing module, a data processing module and a comprehensive analysis module;
the data acquisition module is used for acquiring comprehensive video information of a workshop and constructing a product parameter library;
the process for collecting the comprehensive video information by the data collecting module comprises the following steps:
Acquiring a production line of a workshop, and setting sampling inspection nodes according to production equipment in the production line;
The method comprises the steps of setting an MBS acquisition end, carrying out communication connection on the set MBS acquisition end and a production line, and acquiring comprehensive video information of a workshop through the MBS acquisition end;
marking the time for collecting the comprehensive video information as the capturing time, and associating the obtained capturing time with the comprehensive video information;
Acquiring product data of the MBS end, and marking a production product corresponding to the product data as a standard production sample;
And constructing a product parameter library according to the obtained standard sample, and uploading the product data of the standard sample to the product parameter library.
The process for obtaining the standard parameter gallery comprises the following steps:
Dividing and splitting the standard sample according to the set sampling node and the standard sample to obtain a standard sub-pattern, and associating the obtained standard sub-pattern with the sampling node;
Carrying out graph standardization on the obtained standard sub-graph to obtain a standard sub-graph, carrying out edge capturing on the obtained standard sub-graph to obtain a standard element edge, inserting element identification points at the standard element edge to obtain a sub-graph edge point diagram, and setting identity points in the sub-graph edge point diagram;
And constructing a standard parameter gallery according to the obtained sub-pattern edge point diagram, and associating the obtained standard parameter gallery with the spot check node.
Carrying out frame extraction on the obtained comprehensive video information according to the obtained production line and the sampling inspection node to obtain a comprehensive frame picture, and obtaining a frame time point corresponding to the comprehensive frame picture according to the obtained capturing time;
Matching the obtained comprehensive frame picture with the sampling node to obtain a comprehensive frame picture corresponding to the sampling node, and associating the successfully matched comprehensive frame picture with the sampling node;
Sequencing the obtained frame time points according to a time sequence to obtain a frame time sequence;
and matching the obtained comprehensive frame pictures according to the obtained frame time sequence to obtain a frame picture sequence.
Setting an input standard according to the obtained sub-pattern edge point diagram, carrying out size specification on the obtained frame picture sequence according to the obtained input standard to obtain a coordination picture frame, and marking the obtained coordination picture frame as an input picture frame;
setting a feature acquisition window according to the obtained coordination frame, wherein the feature acquisition window comprises a window size and a window number;
setting a circulation processing layer according to the obtained window size and window number, and uploading the obtained characteristic acquisition window and input image frames to the circulation processing layer;
and smoothly extracting the obtained characteristic acquisition window and the input image frame to obtain a characteristic product image.
The process for smoothly extracting the obtained characteristic acquisition window and the input image frame comprises the following steps:
Selecting one point in an input image frame as a starting point, placing the obtained characteristic acquisition window at the starting point, marking the corresponding region of the characteristic acquisition window in the input image frame as an extraction region, and convolving the obtained extraction region with the characteristic acquisition window to obtain an interval image frame;
Sliding the characteristic acquisition window in the input image frame in a translation way to reach the next extraction area, and convolving with the extraction area to obtain an interval image frame until all the extraction areas of the input image frame are convolved with the characteristic acquisition window;
And combining the obtained interval image frames according to the obtained input image frames to obtain combined image frames, and setting edge induction points and identity recognition points for the combined image frames to obtain a characteristic product image.
Acquiring a spot check node associated with a characteristic product graph, carrying out identity matching on identity points of a sub-pattern edge spot diagram of a standard parameter graph library associated with the spot check node and identity recognition points of the characteristic product graph, and marking the successfully matched sub-pattern edge spot diagram as a matched product graph;
The obtained characteristic product graph and the matching product graph are subjected to repeated comparison to obtain induction point deviation;
Setting a threshold interval according to the obtained standard sample, comparing the obtained sensing point deviation with the threshold interval to obtain an unqualified product, marking a sampling inspection node corresponding to the unqualified product as an abnormal node, and sending an abnormal alarm to a monitoring center for early warning.
Compared with the prior art, the invention has the beneficial effects that: constructing a product parameter library according to the collected comprehensive video information, and processing the product parameter library to obtain a standard parameter drawing library;
frame extraction is carried out on the acquired comprehensive video information to obtain a comprehensive frame picture, an input standard is set to carry out size specification on the comprehensive frame picture to obtain an input image frame, a feature acquisition window and a circulating extraction layer are set, the obtained feature acquisition window and the input image frame are smoothly extracted in the circulating extraction layer to obtain a combined image frame, and an edge induction point and an identity recognition point are set according to the obtained combined image frame to obtain a feature product image; the size of the produced product can be determined through the set edge induction points, so that the produced product can be conveniently compared with a standard parameter chart library, whether the produced product is qualified or not is determined, the product identification accuracy is improved, and the manual detection operation is reduced;
Comparing the characteristic product graph with a standard parameter graph library to obtain a matched product graph, comparing the obtained characteristic product graph with the matched product graph in a repeated mode to obtain sensing point deviation, setting a threshold interval, and comparing the obtained sensing point deviation with the threshold interval to obtain a disqualified product; greatly improves the quality inspection speed of workshop products, optimizes the production quality, and improves the consistency and qualification rate of the products.
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 drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the workshop production monitoring system based on the MBS comprises a monitoring center, wherein the monitoring center is connected with a data acquisition module, a data preprocessing module, a data processing module and a comprehensive analysis module;
the data acquisition module is used for acquiring comprehensive video information of a workshop, and the specific process comprises the following steps:
Acquiring a production line of a workshop, and marking the acquired production line as i, wherein i=1, 2,3, … …, v1 and v1 are positive integers;
It should be further noted that, in the implementation process, the production line refers to that various production devices, procedures and operations are orderly connected to form a continuous production flow, that is, the production line includes a plurality of production devices;
Setting a sampling node according to production equipment in a production line, and marking the set sampling node as j, wherein j=1, 2,3, … …, v2 and v2 are positive integers;
setting an MBS acquisition end;
It should be further noted that, in the specific implementation process, the MBS collecting end is a part of an MBS system, the MBS system is used for coordinating and managing production activities of workshops, and the MBS collecting end is in communication connection with a production line of the workshops, so that information docking between a production plan, order management, execution plan, material management and equipment data included in the MBS collecting end and the production line is facilitated, the production line obtains product data information related to the MBS collecting end and a production product, and production operation is performed according to the obtained product data information, so as to obtain the product;
The acquired MBS acquisition end is in communication connection with the production line, and acquires the comprehensive video information of the workshop through the MBS acquisition end, wherein the acquired comprehensive video information is particularly the video information of the whole workshop production line, and covers the video information of the whole workshop;
marking the time for collecting the comprehensive video information as the capturing time, and associating the obtained capturing time with the comprehensive video information;
acquiring product data of an MBS end, wherein the product data comprises a product name, a product pattern, a product size and a production time length;
marking a production product corresponding to the product data as a standard production sample, and particularly marking a product pattern, a product size and a production time length of the standard production sample as a standard pattern, a standard size and a standard time length;
Further, product data of the MBS end are input before production, and a production line is used for producing according to the obtained standard production sample;
And constructing a product parameter library according to the obtained standard sample, and uploading the product data of the standard sample to the product parameter library.
The data preprocessing module is used for processing the obtained product parameter library to obtain a standard parameter drawing library, and the specific process comprises the following steps:
dividing and splitting the standard sample according to the obtained sampling node and the standard sample to obtain a standard sub-pattern, marking the obtained standard sub-pattern as a j-number standard sub-pattern, and associating the obtained standard sub-pattern with the sampling node;
It should be further noted that, in the implementation process, the division splitting is performed according to the standard pattern of the standard sample, so that the obtained standard sub-pattern is an element diagram, and the standard sub-pattern is obtained at each sampling node according to the standard sample, and the obtained standard sub-pattern is a production result of one sampling node, for example: a standard sample is manufactured and produced by a production line i=1, and a standard sub-pattern can be obtained at each sampling node through sampling nodes j=1 to sampling nodes j=v2 of the production line, for example, a number 3 standard sub-pattern can be obtained at sampling node j=3;
Sorting the standard time length according to the set sampling node, obtaining node time, and associating the obtained node time with the standard sub-pattern;
it should be further noted that, in the implementation process, the node time is the time when the standard sub-pattern passes through the sampling node, that is, the time point when the sampling node produces the standard sub-pattern;
carrying out graph standardization on the obtained standard sub-pattern to obtain a standardized sub-pattern;
further, the length and width of the obtained canonical sub-pattern are uniform with those of the standard pattern;
Capturing edges of the obtained standard sub-patterns to obtain standard element edges, inserting element identification points at the standard element edges to obtain sub-pattern edge point diagrams, and setting identity points in the sub-pattern edge point diagrams, wherein the identity points comprise product name information and are used for carrying out identity matching with produced products;
It should be further noted that, in the implementation process, the element identification point is used for performing feature matching with the standard sub-pattern, if matching is successful, the matched picture and the standard sub-pattern are the same element; in particular, the position of the inserted element recognition point is determined according to the standard pattern and the standard size, and the product size and shape of the standard sub-pattern can be obtained by obtaining the position of the element recognition point and the distance of the element recognition point at the corresponding position;
and constructing a standard parameter map library according to the obtained sub-pattern edge map, uploading the obtained sub-pattern edge map of the sampling node to the standard parameter map library, and associating the obtained standard parameter map library with the sampling node.
The data processing module is used for extracting information of the collected comprehensive video information to obtain a characteristic product graph, and the specific process comprises the following steps:
Carrying out frame extraction on the obtained comprehensive video information according to the obtained production line and the sampling inspection node to obtain a comprehensive frame picture, and obtaining a frame time point corresponding to the comprehensive frame picture according to the obtained capturing time;
Matching the obtained comprehensive frame picture with the sampling node to obtain a comprehensive frame picture corresponding to the sampling node, and associating the successfully matched comprehensive frame picture with the sampling node;
Sequencing the obtained frame time points according to a time sequence to obtain a frame time sequence;
matching the obtained comprehensive frame pictures according to the obtained frame time sequence to obtain a frame picture sequence;
setting input standards according to the obtained sub-pattern edge point diagram, wherein the input standards comprise a length standard, a width standard and a channel number standard;
It should be further noted that, in the implementation process, the channel number standard indicates the dimension of the input video, and the channel indicates the color information of each pixel point, and in this embodiment, the channel number standard is 3; the length standard and the width standard together form the pixel requirement of the picture, and if the resolution of the input picture is required to be clearer, the length standard and the width standard are increased to increase the definition of the picture;
Performing size specification on the obtained frame picture sequence according to the obtained input standard to obtain a coordination picture frame, and marking the obtained coordination picture frame as an input picture frame;
Setting a feature acquisition window according to the obtained coordination frame, wherein the feature acquisition window comprises a window size and a window number, and the window size comprises a window length, a window width and a window shape;
It should be further noted that, in the implementation process, the feature collection window is a matrix including a plurality of elements, the interior of the window is composed of elements, and element feature extraction is performed on the input image frame through the elements in the window; the window size determines the corresponding range of the characteristic acquisition window sliding in the input image frame, for example, the window size is 2×2, 3×6, 5×5, and the window shape can be square or round;
specifically, the number of windows is in direct proportion to the definition of the input picture, namely, the more the number of windows is, the more the features of the obtained picture are after element feature extraction is carried out on the input picture frame through the feature acquisition window;
setting a circulation processing layer according to the obtained window size and window number, and uploading the obtained characteristic acquisition window and input image frames to the circulation processing layer;
Smoothly extracting the obtained characteristic acquisition window and the input image frame to obtain a characteristic product image;
the smooth extraction process comprises the following steps:
Selecting one point in an input image frame as a starting point, placing the obtained characteristic acquisition window at the starting point, marking the corresponding region of the characteristic acquisition window in the input image frame as an extraction region, and convolving the obtained extraction region with the characteristic acquisition window to obtain an interval image frame;
Further, the convolution is to convolve the elements in the feature collection window with the elements of the extraction region;
Sliding the characteristic acquisition window in the input image frame in a translation way to reach the next extraction area, and convolving with the extraction area to obtain an interval image frame until all the extraction areas of the input image frame are convolved with the characteristic acquisition window;
In particular, the next extraction region is adjacent to the previous convolved extraction region, but has no overlapping region, and if the remaining region does not meet a u extraction and elimination interval, overlapping convolution can be performed, so that the remaining part is convolved with the feature acquisition window;
combining the obtained interval image frames according to the obtained input image frames to obtain combined image frames;
It should be further noted that in the specific implementation process, there may be multiple cyclic extraction layers, after the current cyclic extraction layer performs smooth extraction to obtain a combined image frame, the obtained combined image frame is uploaded to the next cyclic extraction layer, and is used as an input image frame to perform translational sliding again to obtain the combined image frame, so that the feature definition of the obtained combined image frame is higher than the feature definition of the previous feature extraction layer, and therefore, if the feature picture with the largest feature definition is desired, a corresponding number of feature extraction layers needs to be set, the cyclic cut-off condition corresponds to the number of cyclic extraction layers, and the combined image frame obtained by the last cyclic extraction layer is the finally required feature image;
Setting edge induction points and identity recognition points according to the obtained combined image frames, and marking the combined image frames with the edge induction points as characteristic product images;
It should be further noted that, in the specific implementation process, the identity recognition point is used for matching the product identity of the feature product graph, namely, the product name, and the identity matching can be performed through the production process in the integrated video information to obtain the product name.
The comprehensive analysis module is used for comparing and analyzing the characteristic product graph with a standard parameter graph library to obtain an unqualified product, and performing node matching on the unqualified product to obtain an abnormal node, and the specific process comprises the following steps:
obtaining a sampling node associated with the characteristic product graph, and performing pattern matching on the obtained characteristic product graph and a standard parameter graph library associated with the sampling node to obtain a matched product graph;
it should be further noted that, in the implementation process, the pattern matching process includes:
Carrying out identity matching on the identity recognition points of the obtained characteristic product graph and the identity points of the sub-pattern edge point graph, and marking the sub-pattern edge point graph successfully matched as a matched product graph;
The obtained characteristic product graph and the matching product graph are subjected to repeated comparison to obtain induction point deviation;
The coincidence comparison is to perform coincidence fixation on the center points of the characteristic product graph and the matching product graph, then perform coincidence correspondence on the edge induction points of the characteristic product graph and the element identification points of the matching product graph, if the edge induction points at the corresponding positions of the element identification points coincide, the edge induction points are qualified for production, if the edge induction points at the corresponding positions of the element identification points do not coincide, the sub-point deviation is obtained according to the obtained distance between the element identification points and the edge induction points, and all the sub-point deviations of the characteristic product graph are summed to obtain the induction point deviation;
further, the distance between the element identification point and the edge sensing point is the distance between the two points;
setting a threshold interval according to the obtained standard sample, and comparing the obtained sensing point deviation with the threshold interval;
It should be further noted that, in the specific implementation process, the threshold interval is set according to the standard pattern and standard size of the standard sample, and is used for judging whether the produced product is qualified, for example, the threshold interval is [0,0.03], if the deviation of the calculated sensing point is 0.0009, the product is qualified in the threshold interval, and if the deviation of the sensing point is 0.07, the product exceeds the threshold interval, namely, the product is unqualified;
If the deviation of the sensing points is not in the threshold value interval, the characteristic product graph is a disqualified product, the selective inspection node corresponding to the disqualified product is marked as an abnormal node, an abnormal alarm is sent to a monitoring center, and a workshop manager is informed to carry out safety inspection through the monitoring center.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (3)
1. The workshop production monitoring system based on the MBS comprises a monitoring center and is characterized in that the monitoring center is connected with a data acquisition module, a data preprocessing module, a data processing module and a comprehensive analysis module;
the data acquisition module is used for acquiring comprehensive video information of a workshop and constructing a product parameter library;
the data preprocessing module is used for processing the product parameter library to obtain a standard parameter drawing library;
The data processing module is used for carrying out frame extraction on the acquired comprehensive video information to obtain a comprehensive frame picture, setting an input standard to carry out size specification on the comprehensive frame picture to obtain an input image frame, setting a characteristic acquisition window and a circulating extraction layer, and carrying out smooth extraction on the obtained characteristic acquisition window and the input image frame in the circulating extraction layer to obtain a characteristic product image;
the comprehensive analysis module is used for comparing the obtained characteristic product graph with a standard parameter graph library to obtain a matched product graph, comparing the obtained characteristic product graph with the matched product graph in a repeated mode to obtain induction point deviation, setting a threshold interval, and comparing the obtained induction point deviation with the threshold interval to obtain an unqualified product;
the process for collecting the comprehensive video information by the data collecting module comprises the following steps:
Acquiring a production line of a workshop, and setting sampling inspection nodes according to production equipment in the production line;
The method comprises the steps of setting an MBS acquisition end, carrying out communication connection on the set MBS acquisition end and a production line, and acquiring comprehensive video information of a workshop through the MBS acquisition end;
marking the time for collecting the comprehensive video information as the capturing time, and associating the obtained capturing time with the comprehensive video information;
Acquiring product data of the MBS end, and marking a production product corresponding to the product data as a standard production sample;
Constructing a product parameter library according to the obtained standard sample, and uploading product data of the standard sample to the product parameter library;
The process for obtaining the standard parameter gallery comprises the following steps:
Dividing and splitting the standard sample according to the set sampling node and the standard sample to obtain a standard sub-pattern, and associating the obtained standard sub-pattern with the sampling node;
Carrying out graph standardization on the obtained standard sub-graph to obtain a standard sub-graph, carrying out edge capturing on the obtained standard sub-graph to obtain a standard element edge, inserting element identification points at the standard element edge to obtain a sub-graph edge point diagram, and setting identity points in the sub-graph edge point diagram;
Constructing a standard parameter gallery according to the obtained sub-pattern edge point diagram, and associating the obtained standard parameter gallery with the spot check node;
Carrying out frame extraction on the obtained comprehensive video information according to the obtained production line and the sampling inspection node to obtain a comprehensive frame picture, and obtaining a frame time point corresponding to the comprehensive frame picture according to the obtained capturing time;
Matching the obtained comprehensive frame picture with the sampling node to obtain a comprehensive frame picture corresponding to the sampling node, and associating the successfully matched comprehensive frame picture with the sampling node;
Sequencing the obtained frame time points according to a time sequence to obtain a frame time sequence;
matching the obtained comprehensive frame pictures according to the obtained frame time sequence to obtain a frame picture sequence;
setting an input standard according to the obtained sub-pattern edge point diagram, carrying out size specification on the obtained frame picture sequence according to the obtained input standard to obtain a coordination picture frame, and marking the obtained coordination picture frame as an input picture frame;
setting a feature acquisition window according to the obtained coordination frame, wherein the feature acquisition window comprises a window size and a window number;
setting a circulation processing layer according to the obtained window size and window number, and uploading the obtained characteristic acquisition window and input image frames to the circulation processing layer;
and smoothly extracting the obtained characteristic acquisition window and the input image frame to obtain a characteristic product image.
2. The MBS-based plant production monitoring system of claim 1 wherein the process of smoothly extracting the obtained feature collection window from the input frames comprises:
Selecting one point in an input image frame as a starting point, placing the obtained characteristic acquisition window at the starting point, marking the corresponding region of the characteristic acquisition window in the input image frame as an extraction region, and convolving the obtained extraction region with the characteristic acquisition window to obtain an interval image frame;
Sliding the characteristic acquisition window in the input image frame in a translation way to reach the next extraction area, and convolving with the extraction area to obtain an interval image frame until all the extraction areas of the input image frame are convolved with the characteristic acquisition window;
And combining the obtained interval image frames according to the obtained input image frames to obtain combined image frames, and setting edge induction points and identity recognition points for the combined image frames to obtain a characteristic product image.
3. The workshop production monitoring system based on MBS according to claim 2, wherein the sampling inspection node associated with the characteristic product graph is obtained, identity matching is carried out on the identity points of the sub-pattern edge point map of the standard parameter graph library associated with the sampling inspection node and the identity recognition points of the characteristic product graph, and the successfully matched sub-pattern edge point map is marked as a matched product graph;
The obtained characteristic product graph and the matching product graph are subjected to repeated comparison to obtain induction point deviation;
Setting a threshold interval according to the obtained standard sample, comparing the obtained sensing point deviation with the threshold interval to obtain an unqualified product, marking a sampling inspection node corresponding to the unqualified product as an abnormal node, and sending an abnormal alarm to a monitoring center for early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410308384.7A CN117908498B (en) | 2024-03-18 | 2024-03-18 | Workshop production monitoring system based on MBS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410308384.7A CN117908498B (en) | 2024-03-18 | 2024-03-18 | Workshop production monitoring system based on MBS |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117908498A CN117908498A (en) | 2024-04-19 |
| CN117908498B true CN117908498B (en) | 2024-05-31 |
Family
ID=90692580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410308384.7A Active CN117908498B (en) | 2024-03-18 | 2024-03-18 | Workshop production monitoring system based on MBS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117908498B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190093875A (en) * | 2018-02-02 | 2019-08-12 | (주)더블유비에스(Wbs) | Integrated production process management system using standard data and method of manufacturing process management using the system |
| CN111401154A (en) * | 2020-02-29 | 2020-07-10 | 同济大学 | Accurate delivery transparentization auxiliary operation device of commodity circulation based on AR |
| CN112925279A (en) * | 2021-01-30 | 2021-06-08 | 重庆简华科技有限公司 | Fault comprehensive analysis system based on MES system |
| CN114202248A (en) * | 2022-01-13 | 2022-03-18 | 浙江工企信息技术股份有限公司 | Production management method and system based on MES intelligent manufacturing |
| CN114999090A (en) * | 2022-05-25 | 2022-09-02 | 佛山市顺德区智安通电子有限公司 | Intelligent safety production monitoring and early warning system based on AI video image analysis |
| CN117544416A (en) * | 2023-12-28 | 2024-02-09 | 东莞本凡网络技术有限公司 | Intelligent internet of things abnormal flow prediction system |
| CN117573764A (en) * | 2024-01-16 | 2024-02-20 | 三明市脉源数字文化创意有限公司 | Audio and video monitoring method and system based on 5G communication technology |
-
2024
- 2024-03-18 CN CN202410308384.7A patent/CN117908498B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190093875A (en) * | 2018-02-02 | 2019-08-12 | (주)더블유비에스(Wbs) | Integrated production process management system using standard data and method of manufacturing process management using the system |
| CN111401154A (en) * | 2020-02-29 | 2020-07-10 | 同济大学 | Accurate delivery transparentization auxiliary operation device of commodity circulation based on AR |
| CN112925279A (en) * | 2021-01-30 | 2021-06-08 | 重庆简华科技有限公司 | Fault comprehensive analysis system based on MES system |
| CN114202248A (en) * | 2022-01-13 | 2022-03-18 | 浙江工企信息技术股份有限公司 | Production management method and system based on MES intelligent manufacturing |
| CN114999090A (en) * | 2022-05-25 | 2022-09-02 | 佛山市顺德区智安通电子有限公司 | Intelligent safety production monitoring and early warning system based on AI video image analysis |
| CN117544416A (en) * | 2023-12-28 | 2024-02-09 | 东莞本凡网络技术有限公司 | Intelligent internet of things abnormal flow prediction system |
| CN117573764A (en) * | 2024-01-16 | 2024-02-20 | 三明市脉源数字文化创意有限公司 | Audio and video monitoring method and system based on 5G communication technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117908498A (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921105B (en) | Method and device for identifying target number and computer readable storage medium | |
| CN109685075A (en) | A kind of power equipment recognition methods based on image, apparatus and system | |
| CN112149513A (en) | Industrial manufacturing site safety helmet wearing identification system and method based on deep learning | |
| CN101739556A (en) | Method for automatically identifying number of steel billet | |
| CN109684986B (en) | Vehicle analysis method and system based on vehicle detection and tracking | |
| CN113284154B (en) | Steel coil end face image segmentation method and device and electronic equipment | |
| EP3123393B1 (en) | Method for the optical detection of symbols | |
| CN112801965A (en) | Sintering belt foreign matter monitoring method and system based on convolutional neural network | |
| DE112019000093T5 (en) | Discrimination device and machine learning method | |
| CN113223041A (en) | Method, system and storage medium for automatically extracting target area in image | |
| CN112802027A (en) | Target object analysis method, storage medium and electronic device | |
| CN117908498B (en) | Workshop production monitoring system based on MBS | |
| CN113570587A (en) | Photovoltaic cell broken grid detection method and system based on computer vision | |
| CN112634259A (en) | Automatic modeling and positioning method for keyboard keycaps | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN114596243A (en) | Defect detection method, device, equipment and computer readable storage medium | |
| CN111815594A (en) | Reinforcing steel bar detection method and related equipment and device | |
| CN114549444A (en) | Cross-camera target detection and tracking system and method | |
| CN114519799A (en) | Real-time detection method and system for multi-feature seat state | |
| CN114202720A (en) | System and method for detecting number of eggs in real time based on target recognition | |
| CN114332630A (en) | Multi-stage accurate screening fruit tree pest and disease monitoring system and method | |
| CN113837178A (en) | Deep learning-based automatic positioning and unified segmentation method for meter of transformer substation | |
| CN112861724A (en) | Traditional Chinese medicine identification system | |
| CN113505776A (en) | Intelligent identification method and device for gas meter reading | |
| CN104964989A (en) | Method and system for visual inspection of photovoltaic module |
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 |