CN117786353A - System and method for high-speed real-time visual measurement of embedded bag making machine - Google Patents
System and method for high-speed real-time visual measurement of embedded bag making machine Download PDFInfo
- Publication number
- CN117786353A CN117786353A CN202311807214.5A CN202311807214A CN117786353A CN 117786353 A CN117786353 A CN 117786353A CN 202311807214 A CN202311807214 A CN 202311807214A CN 117786353 A CN117786353 A CN 117786353A
- Authority
- CN
- China
- Prior art keywords
- time
- making machine
- bag making
- measurement system
- speed real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 137
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000000007 visual effect Effects 0.000 title claims description 28
- 238000012545 processing Methods 0.000 claims abstract description 29
- 230000002159 abnormal effect Effects 0.000 claims description 62
- 238000012544 monitoring process Methods 0.000 claims description 44
- 238000011156 evaluation Methods 0.000 claims description 43
- 238000009826 distribution Methods 0.000 claims description 17
- 230000006698 induction Effects 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 14
- 238000012423 maintenance Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000007477 logistic regression Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses an embedded high-speed real-time vision measurement system and method for a bag making machine, and relates to the technical field of data processing.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an embedded high-speed real-time vision measurement system and method for a bag making machine.
Background
The high-speed real-time vision measuring system for bag making machine is a technological system for making high-speed real-time measurement and monitoring in the course of making bag machine, and the bag making machine is equipment for producing various kinds of plastic bags, paper bags or other packaging bags, and the vision measuring system is used for monitoring and ensuring that the parameters in the course of making bag meet quality standard.
The system is characterized in that dust, vibration, illumination and other environmental interference possibly exist on the operation site of the bag making machine, the performance of a traditional vision system can be affected, measurement inaccuracy is caused, and the stability of the vision measurement system of the bag making machine is further affected.
In order to solve the above-mentioned defect, a technical scheme is proposed.
Disclosure of Invention
The invention aims to provide a system and a method for embedding high-speed real-time vision measurement in a bag making machine, which are used for solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: the embedded high-speed real-time vision measurement system of the bag making machine comprises a signal acquisition module, an evaluation analysis module, a stability verification module and an early warning processing module;
the signal acquisition module is used for acquiring sensor state information and monitoring update efficiency information of the bag making machine embedded in the high-speed real-time vision measurement system in operation, and transmitting the sensor state information and the monitoring update efficiency information to the evaluation analysis module;
the evaluation analysis module is used for comprehensively analyzing the sensor state information and the monitoring update efficiency information, establishing a dynamic detection floating model, and calculating the identification floating index of the bag making machine embedded into the high-speed real-time vision measurement system through a logistic regression method;
the stability verification module is used for comparing the calculated identification floating index coefficient with a preset identification floating index, and classifying the running state of the embedded high-speed real-time vision measurement system of the bag making machine according to the comparison result;
the early warning processing module is used for carrying out early warning processing according to the signal type of the embedded high-speed real-time vision measurement system of the bag making machine.
Preferably, the sensor state information includes a sensing frequency real-time fluctuation coefficient and a gray level distribution drift coefficient, and the monitoring update efficiency information is an abnormal response evaluation coefficient.
Preferably, the method for calculating the real-time fluctuation coefficient of the induction frequency comprises the following steps:
s101, acquiring monitoring frequency of a bag making machine embedded high-speed real-time vision measurement system running in T time for a vision sensor capturing period, and calibrating the monitoring frequency of the bag making machine embedded high-speed real-time vision measurement system running in T time for the vision sensor capturing period to be Mr, wherein r is the number of the monitoring frequency of the bag making machine embedded high-speed real-time vision measurement system running in T time for the vision sensor capturing period, and r= {1,2,3 … e }, wherein e is a positive integer;
s102, acquiring a highest value of a capturing period of a visual sensor of the embedded high-speed real-time visual measurement system of the bag making machine, which operates in a time T, and calibrating the highest value of the capturing period of the visual sensor of the embedded high-speed real-time visual measurement system of the bag making machine, which operates in the time T, as Ca;
s103, the pair meetsExtracting the capturing period monitoring frequency of the visual sensor, which is operated in the T time, of the embedded high-speed real-time visual measurement system of the bag making machine, integrating the capturing period monitoring frequency into an overrun data set, numbering the overrun data set according to a time sequence of the capturing period monitoring frequency of the visual sensor, which is acquired in the T time by the embedded high-speed real-time visual measurement system of the bag making machine, wherein l is a data number, and l= {1,2,3 … k }, wherein k is a positive integer;
s104, calculating the real-time fluctuation coefficient of the induction frequency as the expression
Preferably, the gray level distribution drift coefficient calculating method comprises the following steps:
s201, acquiring gray pixel values of an image captured by a bag making machine embedded high-speed real-time vision measurement system in a T time, marking the total number of pixel units as Su, calculating the number of pixel units with gray values larger than or equal to 0 and smaller than 128 in the same captured image by taking the gray value of 128 as a limit, marking the number of pixel units with gray values larger than or equal to 0 and smaller than 128 in the same captured image as Lo, calculating the number of pixel units with gray values larger than or equal to 128 and smaller than or equal to 255 in the same captured image, and marking the number of pixel units with gray values larger than or equal to 128 and smaller than or equal to 255 in the same captured image as Ho, wherein o is the number of the image captured by the bag making machine embedded high-speed real-time vision measurement system in the T time, o= {1,2,3 … p }, and p is a positive integer;
s202, calculating expression of gray level distribution drift coefficient is
Preferably, the method for calculating the real-time fluctuation coefficient of the induction frequency comprises the following steps:
s301, setting a preset reference value for a comprehensive evaluation index of an image captured by a bag making machine embedded high-speed real-time vision measurement system in a time T, and calibrating the preset reference value of the comprehensive evaluation index as Ev, wherein Ev is larger than 1;
the index F is comprehensively evaluated, the value range is between 0 and 1, and indexes of the matching accuracy P and the recall R can be comprehensively considered;
s302, acquiring comprehensive evaluation indexes of the high-speed real-time vision measurement system embedded by the bag making machine in different time periods (the time in the time period is equal) in the T time, and calibrating the comprehensive evaluation indexes to Cx, wherein x represents the numbers of the comprehensive evaluation indexes of the high-speed real-time vision measurement system embedded by the user bag making machine in the game background in different time periods in the T time, and x= {1,2,3 … b }, and b is a positive integer;
the expression of the comprehensive evaluation index calculation is thatWherein P represents the matching accuracy and judgesThe accuracy rate refers to the proportion of the abnormal product which is actually judged to be the abnormal product by the high-speed real-time vision measurement system embedded in the bag making machine, and the calculation method comprises the following steps: matching accuracy = number of abnormal products correctly matched/number of all abnormal products determined, R represents recall, which refers to the ratio between the number of abnormal products correctly matched by the bag making machine embedded into the high-speed real-time vision measurement system and the number of all actual abnormal products, and the calculation method is as follows: recall = number of abnormal products correctly matched/number of all actual abnormal products;
s303, calculating an expression of the abnormal response evaluation coefficient as
Preferably, the method for calculating the identification floating index of the embedded high-speed real-time vision measurement system of the bag making machine by a logistic regression method comprises the following steps:
calculating the identification floating index Bf of the bag making machine embedded into the high-speed real-time vision measurement system, wherein the calculation expression is as followsWherein alpha, beta and gamma are proportional coefficients of real-time fluctuation coefficients, gray level distribution drift coefficients and abnormal response evaluation coefficients of the induction frequency respectively, and the alpha, beta and gamma are all larger than 0.
Preferably, the logic for classifying the signals of the running state of the embedded high-speed real-time vision measurement system of the bag making machine is as follows:
and (3) comparing the calculated identification floating index embedded into the high-speed real-time vision measurement system with a preset identification floating index threshold value, generating a maintenance signal if the calculated identification floating index is greater than or equal to the preset identification floating index, and generating a stable signal if the calculated identification floating index is smaller than the preset identification floating index.
Preferably, the logic for performing early warning processing according to the signal type of the embedded high-speed real-time vision measurement system of the bag making machine is as follows:
after receiving the maintenance signal, integrating a plurality of continuous identification floating index data embedded into the high-speed real-time vision measurement system by the bag making machine in the T time after the maintenance signal is generated to generate a data set, and calibrating the identification floating index in the data set to Hd, wherein d is the identification floating index number, namely d= {1,2,3 … h }, and h is a positive integer;
calculating standard deviations of a plurality of identification floating indexes in a data set, calibrating the standard deviations of the identification floating indexes as Pn, comparing the standard deviations of the identification floating indexes with a preset standard deviation threshold Pc of the identification floating indexes, and performing early warning processing according to comparison results, wherein the processing logic is as follows:
if Pn is greater than or equal to Pc, marking the embedded high-speed real-time vision measurement system of the bag making machine as a high risk level, and prompting a worker that the embedded high-speed real-time vision measurement system of the bag making machine has high error risk hidden danger and needs to be detected and maintained;
if Pn is smaller than Pc, marking the embedded high-speed real-time vision measurement system of the bag making machine as a low risk level, prompting staff that the embedded high-speed real-time vision measurement system of the bag making machine has low error risk hidden trouble, and not needing to carry out detection and maintenance.
An embedded high-speed real-time vision measurement method of a bag making machine comprises the following steps:
collecting sensor state information and monitoring update efficiency information of a bag making machine embedded in a high-speed real-time vision measurement system in operation;
comprehensively analyzing the sensor state information and the monitoring update efficiency information, establishing a dynamic detection floating model, and calculating an identification floating index of the bag making machine embedded into the high-speed real-time vision measurement system by a logistic regression method;
comparing the calculated identification floating index coefficient with a preset identification floating index, and classifying signals according to the comparison result, wherein the operation state of the bag making machine embedded into the high-speed real-time vision measurement system;
and carrying out early warning processing according to the signal type of the embedded high-speed real-time vision measurement system of the bag making machine.
In the technical scheme, the invention has the technical effects and advantages that:
according to the invention, the identification floating index of the embedded high-speed real-time vision measurement system of the bag making machine is detected, when the abnormality of the data processing stability and the real-time performance is found, the subsequent operation state of the embedded high-speed real-time vision measurement system of the bag making machine is comprehensively analyzed, the abnormal hidden danger is judged, and the early warning prompt is sent out, so that on one hand, the staff can conveniently sense the abnormal hidden danger phenomenon in time, the abnormal hidden danger is detected in advance, the occurrence of potential faults and abnormal early warning untimely risks caused by the stability reduction of the imaging effect is effectively prevented, and further, the system faults are effectively prevented, on the other hand, the staff can conveniently detect the operation state of the embedded high-speed real-time vision measurement system of the bag making machine, the detection management of the staff is facilitated, and the working efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a block diagram of a system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
Example 1
Referring to fig. 1, the invention relates to an embedded high-speed real-time vision measurement system of a bag making machine, which comprises a signal acquisition module, an evaluation analysis module, a stability verification module and an early warning processing module;
the signal acquisition module is used for acquiring sensor state information and monitoring update efficiency information of the bag making machine embedded in the high-speed real-time vision measurement system in operation, and transmitting the sensor state information and the monitoring update efficiency information to the evaluation analysis module;
the evaluation analysis module is used for comprehensively analyzing the sensor state information and the monitoring update efficiency information, establishing a dynamic detection floating model, and calculating the identification floating index of the bag making machine embedded into the high-speed real-time vision measurement system through a logistic regression method;
the stability verification module is used for comparing the calculated identification floating index coefficient with a preset identification floating index, and classifying the running state of the embedded high-speed real-time vision measurement system of the bag making machine according to the comparison result;
the early warning processing module is used for carrying out early warning processing according to the signal type of the embedded high-speed real-time vision measurement system of the bag making machine.
If the monitoring frequency of the high-speed real-time vision measurement system of the bag making machine to the image capturing period of the vision sensor is lower than the image capturing period of the vision sensor, the instantaneity and the stability of the high-speed real-time vision measurement system of the bag making machine can be adversely affected as follows:
the real-time performance is reduced: the monitoring frequency is lower than the image capturing period, which means that the system cannot respond to the change on the actual production line in time, so that the delay of the system in the process of detecting and adjusting the bag making machine is caused, and the requirement on the real-time property of the production line is reduced;
losing key information: the high speed bag making machine manufacturing process may involve fast moving objects, while low frequency monitoring may cause the system to miss image capture at critical moments, thereby losing part of critical information, which may affect accurate assessment of product quality by the system;
adjustment instability: because of the low monitoring frequency, the system may not accurately capture changes in the bag machine operation, resulting in instability in the adjustment intervention, which may make feedback and adjustment of the system less timely and accurate;
production line efficiency decreases: the problem that the system cannot timely detect the production line may result in increased rejection rate, reduced production efficiency, and increased processing cost for unqualified products.
The method for calculating the real-time fluctuation coefficient of the induction frequency comprises the following steps:
s101, acquiring monitoring frequency of a bag making machine embedded high-speed real-time vision measurement system running in T time for a vision sensor capturing period, and calibrating the monitoring frequency of the bag making machine embedded high-speed real-time vision measurement system running in T time for the vision sensor capturing period to be Mr, wherein r is the number of the monitoring frequency of the bag making machine embedded high-speed real-time vision measurement system running in T time for the vision sensor capturing period, and r= {1,2,3 … e }, wherein e is a positive integer;
it should be noted that, in the embodiment, the capturing period of the visual sensor in the bag making machine embedded high-speed real-time visual measurement system is set by a person skilled in the art according to the type of the film material, and the extrusion-cutting-forming speeds of the film materials are different from each other;
s102, acquiring a highest value of a capturing period of a visual sensor of the embedded high-speed real-time visual measurement system of the bag making machine, which operates in a time T, and calibrating the highest value of the capturing period of the visual sensor of the embedded high-speed real-time visual measurement system of the bag making machine, which operates in the time T, as Ca;
it should be noted that, the single-board machine monitoring tool assembly can be used for carrying out state analysis and monitoring on the embedded high-speed real-time vision measurement system of the bag making machine, the commonly used single-board machine monitoring tool assembly comprises HWiNFO, nagios, zabbix and the like, and the multi-dimensional data model can be used, or a label is defined for single-board machine operation data through a Z self-defined monitoring option, and the state data is recorded and stored through a time sequence;
s103, the pair meetsThe system is embedded with a high-speed real-time vision measurement system to extract the monitoring frequency of the capturing period of the vision sensor running in the T time and integrate the monitoring frequency into an overrun data set, and the system is embedded with the high-speed real-time vision measurement system to acquire the monitoring frequency in the T timeNumbering the overrun data set by a time sequence of monitoring frequency of a capturing period of the visual sensor, wherein l is a data number, and l= {1,2,3 … k }, wherein k is a positive integer;
s104, calculating the real-time fluctuation coefficient of the induction frequency as the expression
The expression of the real-time fluctuation coefficient of the induction frequency shows that the greater the real-time fluctuation coefficient of the induction frequency generated by the embedded high-speed real-time vision measurement system of the bag making machine in the T time is, the worse the running stability and the real-time performance of the embedded high-speed real-time vision measurement system of the bag making machine are, otherwise, the smaller the real-time fluctuation coefficient of the induction frequency generated by the embedded high-speed real-time vision measurement system of the bag making machine in the T time is, the better the running stability and the real-time performance of the embedded high-speed real-time vision measurement system of the bag making machine are;
the method comprises the steps of carrying out feature recognition on a captured image through a vision processing method, carrying out gray stretching recognition judgment on the captured image by a bag making machine embedded high-speed real-time vision measuring system to ensure the accuracy of vision processing, and judging whether the illumination of an operation environment influences the bag making machine embedded high-speed real-time vision measuring system to effectively monitor the production flow through the distribution range of gray elements in the captured image;
the effectiveness of the vision sensor is judged by calculating the gray level distribution drift coefficient, and the calculation method comprises the following steps:
s201, acquiring gray pixel values of an image captured by a bag making machine embedded high-speed real-time vision measurement system in a T time, marking the total number of pixel units as Su, calculating the number of pixel units with gray values larger than or equal to 0 and smaller than 128 in the same captured image by taking the gray value of 128 as a limit, marking the number of pixel units with gray values larger than or equal to 0 and smaller than 128 in the same captured image as Lo, calculating the number of pixel units with gray values larger than or equal to 128 and smaller than or equal to 255 in the same captured image, and marking the number of pixel units with gray values larger than or equal to 128 and smaller than or equal to 255 in the same captured image as Ho, wherein o is the number of the image captured by the bag making machine embedded high-speed real-time vision measurement system in the T time, o= {1,2,3 … p }, and p is a positive integer;
the gray level of the pixel units of the captured image is obtained through a state monitoring log of the visual sensor, the total number of the specific pixel units for dividing the gray level of the film material image is changed along with the size of a visual field of the visual sensor and the structural change of a bag making machine production line, and the total number of the specific gray level dividing pixel units is set by a person skilled in the art according to specific situations;
s202, calculating expression of gray level distribution drift coefficient is
The gray scale distribution drift coefficient calculation expression of the image captured by the bag making machine embedded high-speed real-time vision measurement system in the T time shows that the larger the gray scale distribution drift coefficient of the image captured by the bag making machine embedded high-speed real-time vision measurement system in the T time is, the worse the running stability of the bag making machine embedded high-speed real-time vision measurement system is, otherwise, the smaller the gray scale distribution drift coefficient of the image captured by the bag making machine embedded high-speed real-time vision measurement system in the T time is, the better the running stability of the bag making machine embedded high-speed real-time vision measurement system is;
the calculation method of the abnormal response evaluation coefficient is as follows:
s301, setting a preset reference value for a comprehensive evaluation index of an image captured by a bag making machine embedded high-speed real-time vision measurement system in a time T, and calibrating the preset reference value of the comprehensive evaluation index as Ev, wherein Ev is larger than 1;
it should be noted that, the preset reference value of the comprehensive evaluation index is a quantized specific reference value, no specific limitation is made here, ev is a value greater than 1, the comprehensive evaluation index, that is, the F value, has a value range between 0 and 1, and can comprehensively consider the indexes of the matching accuracy P and the recall R, and is used for measuring the judging capability of the bag making machine embedded high-speed real-time vision measuring system for anomaly detection, the high F value means that the bag making machine embedded high-speed real-time vision measuring system can accurately identify the anomaly product, avoid misjudging the normal product as the anomaly product, help to ensure that the detection processing of the bag making machine embedded high-speed real-time vision measuring system for the anomaly product is more accurately performed, improve the detection effect, and the high F value means that the recall rate of the bag making machine embedded high-speed real-time vision measuring system for the anomaly product is higher, and can effectively reduce error of error, so as to extract the true anomaly product;
s302, acquiring comprehensive evaluation indexes of the high-speed real-time vision measurement system embedded by the bag making machine in different time periods (the time in the time period is equal) in the T time, and calibrating the comprehensive evaluation indexes to Cx, wherein x represents the numbers of the comprehensive evaluation indexes of the high-speed real-time vision measurement system embedded by the user bag making machine in the game background in different time periods in the T time, and x= {1,2,3 … b }, and b is a positive integer;
the expression of the comprehensive evaluation index calculation is thatWherein, P represents the matching accuracy, the judging accuracy refers to the proportion of abnormal products actually judged to be abnormal products by embedding a high-speed real-time vision measuring system into a bag making machine, and the calculating method comprises the following steps: matching accuracy = number of abnormal products correctly matched/number of all abnormal products determined, R represents recall, which refers to the ratio between the number of abnormal products correctly matched by the bag making machine embedded into the high-speed real-time vision measurement system and the number of all actual abnormal products, and the calculation method is as follows: recall = number of abnormal products correctly matched/number of all actual abnormal products;
it should be noted that the number of abnormal products that are correctly matched refers to the number of abnormal products that are correctly identified and judged by the high-speed real-time vision measurement system embedded in the bag making machine, and the detected abnormal products are marked by the high-speed real-time vision measurement system embedded in the bag making machine or put into a database of abnormal product records, and the number of abnormal products that are correctly judged can be obtained by inquiring the number of abnormal product records;
the number of the abnormal products is that the bag making machine is embedded into the high-speed real-time vision measuring system to make the number of the abnormal products within a certain time range, wherein the number comprises real abnormal products and misjudged normal transactions, the bag making machine is embedded into the high-speed real-time vision measuring system to normally make classification marks on the transactions, or the abnormal judgment condition of the transactions is recorded in a log, and the abnormal judgment condition can be obtained by counting the number of the abnormal transactions marked;
the number of all actual abnormal products refers to the number of all abnormal products existing under the actual condition, and as the actual abnormal products are possibly caused by visual judgment errors, the embedded high-speed real-time visual measurement system of the bag making machine needs to interact with a production storage server or a database to acquire the number of the actual abnormal products;
s303, calculating an expression of the abnormal response evaluation coefficient as
According to the calculation expression of the abnormal response evaluation coefficient, the greater the abnormal response evaluation coefficient of the high-speed real-time vision measurement system embedded by the bag making machine is, the poorer the aging stability of the high-speed real-time vision measurement system embedded by the bag making machine is, which shows that the poorer the running stability and the real-time performance of the high-speed real-time vision measurement system embedded by the bag making machine are, otherwise, the smaller the abnormal response evaluation coefficient of the high-speed real-time vision measurement system embedded by the bag making machine is, the better the running stability and the real-time performance of the high-speed real-time vision measurement system embedded by the bag making machine are;
establishing a dynamic detection floating model, and performing mark classification on the running state of the embedded high-speed real-time vision measurement system of the bag making machine by a logistic regression method;
calculating the identification floating index Bf of the bag making machine embedded into the high-speed real-time vision measurement system, wherein the calculation expression is as followsWherein alpha, beta and gamma are proportional coefficients of real-time fluctuation coefficients, gray level distribution drift coefficients and abnormal response evaluation coefficients of the induction frequency respectively, and the alpha, beta and gamma are all larger than 0;
according to a calculation formula of the identification floating index, the larger the induction frequency real-time fluctuation coefficient of the bag making machine embedded high-speed real-time vision measurement system is, the larger the abnormal response evaluation coefficient is, the larger the gray distribution drift coefficient is, namely the smaller the identification floating index of the bag making machine embedded high-speed real-time vision measurement system is, the worse the stability of the bag making machine embedded high-speed real-time vision measurement system for data processing is, otherwise, the smaller the induction frequency real-time fluctuation coefficient of the bag making machine embedded high-speed real-time vision measurement system is, the smaller the abnormal response evaluation coefficient is, the smaller the gray distribution drift coefficient is, namely the larger the identification floating index of the bag making machine embedded high-speed real-time vision measurement system is, the better the stability of the bag making machine embedded high-speed real-time vision measurement system for data processing is;
the stability verification module is used for comparing the calculated identification floating index of the bag making machine embedded into the high-speed real-time vision measurement system with a preset identification floating index threshold value, generating a maintenance signal if the calculated identification floating index is larger than or equal to the preset identification floating index, and generating a stability signal if the calculated identification floating index is smaller than the preset identification floating index;
the early warning processing module performs processing strategy analysis according to the maintenance signal generated by the limit checking module, after receiving the maintenance signal generated by the limit checking module, the supervision decision module integrates a plurality of continuous identification floating index data embedded in the high-speed real-time vision measurement system by the bag making machine in the T time after the maintenance signal is generated to generate a data set, and the identification floating index in the data set is calibrated to Hd, wherein d is the identification floating index number, namely d= {1,2,3 … h }, and h is a positive integer;
calculating standard deviations of a plurality of identification floating indexes in a data set, calibrating the standard deviations of the identification floating indexes as Pn, comparing the standard deviations of the identification floating indexes with a preset standard deviation threshold Pc of the identification floating indexes, and performing early warning processing according to comparison results, wherein the processing logic is as follows:
if Pn is greater than or equal to Pc, marking the embedded high-speed real-time vision measurement system of the bag making machine as a high risk level, and prompting a worker that the embedded high-speed real-time vision measurement system of the bag making machine has high error risk hidden danger and needs to be detected and maintained;
if Pn is smaller than Pc, marking the embedded high-speed real-time vision measurement system of the bag making machine as a low risk level, prompting staff that the embedded high-speed real-time vision measurement system of the bag making machine has low error risk hidden trouble, and not needing to carry out detection and maintenance.
According to the invention, the identification floating index of the embedded high-speed real-time vision measurement system of the bag making machine is detected, when the abnormality of the data processing stability and the real-time performance is found, the subsequent operation state of the embedded high-speed real-time vision measurement system of the bag making machine is comprehensively analyzed, the abnormal hidden danger is judged, and the early warning prompt is sent out, so that on one hand, the staff can conveniently sense the abnormal hidden danger phenomenon in time, the abnormal hidden danger is detected in advance, the occurrence of potential faults and abnormal early warning untimely risks caused by the stability reduction of the imaging effect is effectively prevented, and further, the system faults are effectively prevented, on the other hand, the staff can conveniently detect the operation state of the embedded high-speed real-time vision measurement system of the bag making machine, the detection management of the staff is facilitated, and the working efficiency is improved.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the above-described method may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
Claims (9)
1. The embedded high-speed real-time vision measurement system of the bag making machine is characterized by comprising a signal acquisition module, an evaluation analysis module, a stability verification module and an early warning processing module;
the signal acquisition module is used for acquiring sensor state information and monitoring update efficiency information of the bag making machine embedded in the high-speed real-time vision measurement system in operation, and transmitting the sensor state information and the monitoring update efficiency information to the evaluation analysis module;
the evaluation analysis module is used for comprehensively analyzing the sensor state information and the monitoring update efficiency information, establishing a dynamic detection floating model, and calculating the identification floating index of the bag making machine embedded into the high-speed real-time vision measurement system through a logistic regression method;
the stability verification module is used for comparing the calculated identification floating index coefficient with a preset identification floating index, and classifying the running state of the embedded high-speed real-time vision measurement system of the bag making machine according to the comparison result;
the early warning processing module is used for carrying out early warning processing according to the signal type of the embedded high-speed real-time vision measurement system of the bag making machine.
2. The embedded high-speed real-time vision measurement system of a bag machine of claim 1, wherein the sensor status information includes an induction frequency real-time fluctuation coefficient and a gray scale distribution drift coefficient, and the monitoring update efficiency information is an abnormal response evaluation coefficient.
3. The embedded high-speed real-time vision measurement system of a bag making machine according to claim 1, wherein the method for calculating the real-time fluctuation coefficient of the induction frequency is as follows:
s101, acquiring monitoring frequency of a bag making machine embedded high-speed real-time vision measurement system running in T time for a vision sensor capturing period, and calibrating the monitoring frequency of the bag making machine embedded high-speed real-time vision measurement system running in T time for the vision sensor capturing period to be Mr, wherein r is the number of the monitoring frequency of the bag making machine embedded high-speed real-time vision measurement system running in T time for the vision sensor capturing period, and r= {1,2,3 … e }, wherein e is a positive integer;
s102, acquiring a highest value of a capturing period of a visual sensor of the embedded high-speed real-time visual measurement system of the bag making machine, which operates in a time T, and calibrating the highest value of the capturing period of the visual sensor of the embedded high-speed real-time visual measurement system of the bag making machine, which operates in the time T, as Ca;
s103, the pair meetsThe system is embedded into a high-speed real-time vision measurement system, and the monitoring frequency of the capturing period of a vision sensor running in the T time is extracted and integrated into an overrun data setCombining, numbering an overrun data set according to a time sequence of monitoring frequency of a capturing period of a visual sensor, which is acquired by a high-speed real-time visual measurement system embedded in a bag making machine in a T time, wherein l is a data number, and l= {1,2,3 … k }, wherein k is a positive integer;
s104, calculating the real-time fluctuation coefficient of the induction frequency as the expression
4. The embedded high-speed real-time vision measurement system of a bag making machine according to claim 1, wherein the calculation method of the gray level distribution drift coefficient is as follows:
s201, acquiring gray pixel values of an image captured by a bag making machine embedded high-speed real-time vision measurement system in a T time, marking the total number of pixel units as Su, calculating the number of pixel units with gray values larger than or equal to 0 and smaller than 128 in the same captured image by taking the gray value of 128 as a limit, marking the number of pixel units with gray values larger than or equal to 0 and smaller than 128 in the same captured image as Lo, calculating the number of pixel units with gray values larger than or equal to 128 and smaller than or equal to 255 in the same captured image, and marking the number of pixel units with gray values larger than or equal to 128 and smaller than or equal to 255 in the same captured image as Ho, wherein o is the number of the image captured by the bag making machine embedded high-speed real-time vision measurement system in the T time, o= {1,2,3 … p }, and p is a positive integer;
s202, calculating expression of gray level distribution drift coefficient is
5. The embedded high-speed real-time vision measurement system of a bag making machine according to claim 1, wherein the method for calculating the real-time fluctuation coefficient of the induction frequency is as follows:
s301, setting a preset reference value for a comprehensive evaluation index of an image captured by a bag making machine embedded high-speed real-time vision measurement system in a time T, and calibrating the preset reference value of the comprehensive evaluation index as Ev, wherein Ev is larger than 1;
the index F is comprehensively evaluated, the value range is between 0 and 1, and indexes of the matching accuracy P and the recall R can be comprehensively considered;
s302, acquiring comprehensive evaluation indexes of the high-speed real-time vision measurement system embedded by the bag making machine in different time periods (the time in the time period is equal) in the T time, and calibrating the comprehensive evaluation indexes to Cx, wherein x represents the numbers of the comprehensive evaluation indexes of the high-speed real-time vision measurement system embedded by the user bag making machine in the game background in different time periods in the T time, and x= {1,2,3 … b }, and b is a positive integer;
the expression of the comprehensive evaluation index calculation is thatWherein, P represents the matching accuracy, the judging accuracy refers to the proportion of abnormal products actually judged to be abnormal products by embedding a high-speed real-time vision measuring system into a bag making machine, and the calculating method comprises the following steps: matching accuracy = number of abnormal products correctly matched/number of all abnormal products determined, R represents recall, which refers to the ratio between the number of abnormal products correctly matched by the bag making machine embedded into the high-speed real-time vision measurement system and the number of all actual abnormal products, and the calculation method is as follows: recall = number of abnormal products correctly matched/number of all actual abnormal products;
s303, calculating an expression of the abnormal response evaluation coefficient to be F
6. The system for embedded high-speed real-time vision measurement of a bag machine according to claim 1, wherein the method for calculating the identification floating index of the embedded high-speed real-time vision measurement of the bag machine by a logistic regression method comprises the following steps:
calculating the identification floating index Bf of the bag making machine embedded into the high-speed real-time vision measurement system, wherein the calculation expression is as followsWherein alpha, beta and gamma are proportional coefficients of real-time fluctuation coefficients, gray level distribution drift coefficients and abnormal response evaluation coefficients of the induction frequency respectively, and the alpha, beta and gamma are all larger than 0.
7. The system of claim 1, wherein the logic for classifying the signals of the operating state of the system is:
and (3) comparing the calculated identification floating index embedded into the high-speed real-time vision measurement system with a preset identification floating index threshold value, generating a maintenance signal if the calculated identification floating index is greater than or equal to the preset identification floating index, and generating a stable signal if the calculated identification floating index is smaller than the preset identification floating index.
8. The embedded high-speed real-time vision measurement system of a bag making machine according to claim 1, wherein the logic for performing the early warning process according to the signal type of the embedded high-speed real-time vision measurement system of the bag making machine is:
after receiving the maintenance signal, integrating a plurality of continuous identification floating index data embedded into the high-speed real-time vision measurement system by the bag making machine in the T time after the maintenance signal is generated to generate a data set, and calibrating the identification floating index in the data set to Hd, wherein d is the identification floating index number, namely d= {1,2,3 … h }, and h is a positive integer;
calculating standard deviations of a plurality of identification floating indexes in a data set, calibrating the standard deviations of the identification floating indexes as Pn, comparing the standard deviations of the identification floating indexes with a preset standard deviation threshold Pc of the identification floating indexes, and performing early warning processing according to comparison results, wherein the processing logic is as follows:
if Pn is greater than or equal to Pc, marking the embedded high-speed real-time vision measurement system of the bag making machine as a high risk level, and prompting a worker that the embedded high-speed real-time vision measurement system of the bag making machine has high error risk hidden danger and needs to be detected and maintained;
if Pn is smaller than Pc, marking the embedded high-speed real-time vision measurement system of the bag making machine as a low risk level, prompting staff that the embedded high-speed real-time vision measurement system of the bag making machine has low error risk hidden trouble, and not needing to carry out detection and maintenance.
9. A method for measuring the embedded high-speed real-time vision of a bag making machine, which is realized by the embedded high-speed real-time vision measuring system of the bag making machine according to any one of claims 1 to 8, and is characterized by comprising the following steps:
collecting sensor state information and monitoring update efficiency information of a bag making machine embedded in a high-speed real-time vision measurement system in operation;
comprehensively analyzing the sensor state information and the monitoring update efficiency information, establishing a dynamic detection floating model, and calculating an identification floating index of the bag making machine embedded into the high-speed real-time vision measurement system by a logistic regression method;
comparing the calculated identification floating index coefficient with a preset identification floating index, and classifying signals according to the comparison result, wherein the operation state of the bag making machine embedded into the high-speed real-time vision measurement system;
and carrying out early warning processing according to the signal type of the embedded high-speed real-time vision measurement system of the bag making machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311807214.5A CN117786353A (en) | 2023-12-26 | 2023-12-26 | System and method for high-speed real-time visual measurement of embedded bag making machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311807214.5A CN117786353A (en) | 2023-12-26 | 2023-12-26 | System and method for high-speed real-time visual measurement of embedded bag making machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117786353A true CN117786353A (en) | 2024-03-29 |
Family
ID=90388634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311807214.5A Pending CN117786353A (en) | 2023-12-26 | 2023-12-26 | System and method for high-speed real-time visual measurement of embedded bag making machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117786353A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118466426A (en) * | 2024-05-31 | 2024-08-09 | 江苏三嘉三食品科技有限公司 | Artificial intelligence-based fermented glutinous rice steamed bread production process optimization control method |
| CN118572868A (en) * | 2024-04-28 | 2024-08-30 | 无锡市政公用新能源科技有限公司 | A photovoltaic storage and charging control system based on artificial intelligence |
-
2023
- 2023-12-26 CN CN202311807214.5A patent/CN117786353A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118572868A (en) * | 2024-04-28 | 2024-08-30 | 无锡市政公用新能源科技有限公司 | A photovoltaic storage and charging control system based on artificial intelligence |
| CN118466426A (en) * | 2024-05-31 | 2024-08-09 | 江苏三嘉三食品科技有限公司 | Artificial intelligence-based fermented glutinous rice steamed bread production process optimization control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117786353A (en) | System and method for high-speed real-time visual measurement of embedded bag making machine | |
| CN112508105B (en) | Fault detection and retrieval method for oil extraction machine | |
| CN116881745B (en) | Pressure transmitter abnormality monitoring method based on big data | |
| US12162056B2 (en) | Method and system for forming a stamped component using a stamping simulation model | |
| CN115409131B (en) | Production line abnormity detection method based on SPC process control system | |
| TW202012905A (en) | Method for monitoring cutting tool abrasion | |
| CN117689269B (en) | Fault tracing method for intelligent watch processing stage | |
| CN114664063B (en) | A device classification alarm method based on general indicator trend analysis | |
| CN107239066A (en) | A kind of Vertical Mill operation closed-loop control device and method based on data mining | |
| CN117556366B (en) | Data abnormality detection system and method based on data screening | |
| CN117826693A (en) | Intelligent oil depot monitoring and early warning system and method | |
| CN113029242B (en) | Fiber bragg grating sensor abnormity diagnosis method in structural health monitoring system | |
| CN112766301B (en) | Oil extraction machine indicator diagram similarity judging method | |
| CN117891159A (en) | Food processing control system and method based on big data | |
| CN114384872A (en) | Product development process quality comprehensive management and control system | |
| CN119168833B (en) | An intelligent supervision system and method for environmental monitoring quality control | |
| CN118275034B (en) | Intelligent anti-interference pressure transmitter | |
| CN118864464A (en) | An intelligent management system for textile handicrafts | |
| CN118938847A (en) | Wet wipes quality control system based on artificial intelligence | |
| CN114637645B (en) | Calibration method for sensor measurement data | |
| CN116976750A (en) | Product qualification rate detection method, device, equipment and storage medium | |
| CN118135234B (en) | A target extraction method based on cat's eye effect | |
| CN118801898B (en) | A compression processing method based on multi-source heterogeneous data fusion | |
| CN117420811B (en) | Production line quality monitoring method and system for automatic production | |
| CN119226867B (en) | A condition monitoring system for road anti-collision guardrail |
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 |