CN117331802A - Middle-station data monitoring and analyzing system based on industrial Internet - Google Patents

Middle-station data monitoring and analyzing system based on industrial Internet Download PDF

Info

Publication number
CN117331802A
CN117331802A CN202311313656.4A CN202311313656A CN117331802A CN 117331802 A CN117331802 A CN 117331802A CN 202311313656 A CN202311313656 A CN 202311313656A CN 117331802 A CN117331802 A CN 117331802A
Authority
CN
China
Prior art keywords
data
image data
scene
original image
industrial equipment
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
Application number
CN202311313656.4A
Other languages
Chinese (zh)
Inventor
林昌平
柴振把
杨立新
倪明奇
刘月华
刘亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Zhenshan Technology Co ltd
Original Assignee
Zhejiang Zhenshan Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Zhenshan Technology Co ltd filed Critical Zhejiang Zhenshan Technology Co ltd
Priority to CN202311313656.4A priority Critical patent/CN117331802A/en
Publication of CN117331802A publication Critical patent/CN117331802A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3466—Performance evaluation by tracing or monitoring
    • G06F11/3476—Data logging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3452—Performance evaluation by statistical analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computer Hardware Design (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a middle data monitoring and analyzing system based on an industrial Internet, which relates to the technical field of data analysis and comprises a data acquisition module, a monitoring center, a data distribution module and an image analysis module; the data acquisition module is used for acquiring original image data of industrial equipment during operation through the productivity center; the data distribution module is used for extracting the characteristic value of the original image data to carry out distribution priority FY analysis, and sequencing the original image data according to the FY size to obtain a processing priority sequence of the original image data; the monitoring center is used for driving the image analysis module to sequentially perform identification analysis on the original image data according to the processing priority sequence, so that the data analysis efficiency is improved; the image analysis module is used for carrying out equipment state identification on the original image data by applying a convolutional neural network algorithm so that management personnel can check, analyze and manage the production process of the whole factory through the monitoring center, and the abnormal problems can be accurately positioned to assist in optimizing the resource configuration.

Description

Middle-station data monitoring and analyzing system based on industrial Internet
Technical Field
The invention relates to the technical field of data analysis, in particular to a middle-stage data monitoring and analyzing system based on an industrial Internet.
Background
Along with the rapid development of artificial intelligence technology, people are increasingly widely applied to the artificial intelligence technology, in the industrial field, people dynamically monitor production data in the industrial field in a mode of Internet of things and artificial intelligence, and further realize real-time monitoring of production states in the industry, ensure stable performance of industrial production and reduce corresponding defective rate in production results.
Most of production and manufacturing equipment runs independently and cannot be integrated with an enterprise information system, so that the production and processing information of an enterprise is isolated, the equipment state and the processing information can be reported only in a manual mode, and the accuracy and the timeliness are poor; the production process cannot be monitored and managed intuitively and vividly from the whole; in order to comprehensively know the real-time production condition of each workshop and greatly facilitate the real-time monitoring, fault diagnosis and investigation of the production process, a middle data monitoring and analyzing system based on the industrial Internet is provided.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a middle-stage data monitoring and analyzing system based on the industrial Internet.
To achieve the above objective, an embodiment according to a first aspect of the present invention provides an industrial internet-based middle-stage data monitoring and analyzing system, which includes a data acquisition module, a monitoring center, a data distribution module, an image analysis module, and an early warning module;
the data acquisition module is used for acquiring original image data of industrial equipment during operation through the productivity center and sending the original image data to the monitoring center in the form of a message; the original image data mainly comprises a three-dimensional digital model of industrial equipment and parameter data in the processing process;
the data distribution module is connected with the monitoring center and is used for extracting characteristic values of the original image data to carry out distribution priority FY analysis and sequencing the original image data according to the size of the distribution priority FY to obtain a processing priority sequence of the original image data;
the monitoring center is used for driving the image analysis module to sequentially perform identification analysis on the original image data according to the processing priority sequence; the image analysis module is used for carrying out equipment state identification on the original image data by applying a convolutional neural network algorithm; the method comprises the following steps:
compressing the original image data to obtain the processed light image data;
secondly, cutting and dividing the light-weight image data based on a rule defined or trained in advance; performing action recognition and scene recognition based on a conventional algorithm;
finally, performing image recognition by applying a convolutional neural network algorithm, recognizing the running state of industrial equipment based on training of the normal state, the abnormal state and the subdivision fault type in advance, and feeding back the recognition result to an early warning module;
the early warning module is used for prompting the identification on the monitoring center interface in a signal sign or text mode according to the identification result; the identification result includes whether the industrial equipment is normal or not and the corresponding fault type.
Further, the specific analysis steps of the data distribution module are as follows:
extracting characteristic values of original image data; the characteristic value comprises data quantity, data transmission distance and data transmission bandwidth; the data quantity, the data transmission distance and the data transmission bandwidth are marked as L1, L2 and L3 in sequence; calculating to obtain a calculation force load value Lt required for analyzing the original image data by using a formula lt=L1×a1+L2×a2+L3×a3, wherein a1, a2 and a3 are all preset coefficient factors;
acquiring industrial equipment corresponding to the original image data; collecting an instruction control record of the industrial equipment within a preset time period, wherein the instruction control record comprises an instruction type and an instruction control moment;
comparing and analyzing the instruction control moment of the industrial equipment with the instruction control moment of other industrial equipment, and calculating to obtain an instruction association index Zg of the industrial equipment;
counting the total times of faults of the industrial equipment as G1; and carrying out normalization processing on the calculated force load value, the instruction association index and the total number of faults, taking the values of the calculated force load value, the instruction association index and the total number of faults, and calculating by using a formula FY= (ZgXb1+G1×b2)/(LtXb 3) to obtain the distribution priority FY of the original image data, wherein b1, b2 and b3 are all preset coefficient factors.
Further, the specific calculation method of the instruction association index Zg is as follows:
marking other industrial equipment with the instruction control time difference within a preset value as instruction associated equipment by taking certain instruction control time of the industrial equipment as a center; counting the number of instruction association devices to be Dz; if Dz is greater than a preset quantity threshold value, marking the instruction control as instruction association control;
counting the total times of instruction control of the industrial equipment as ZK, and counting the times of instruction association control of the industrial equipment as association duty ratio Kb; counting the time difference between two adjacent instruction association control moments of the industrial equipment as an instruction association interval ZTi to obtain an association interval information group;
calculating standard deviation of the associated interval information group according to a standard deviation formula and marking the standard deviation as alpha; traversing the association interval information group, marking the maximum value as ZTmax, and marking the minimum value as ZTmin;
calculating to obtain a difference ratio Cb by using a formula Cb= (ZTmax-ZTmin)/(ZTmin+u), wherein u is a preset compensation coefficient; calculating to obtain a discrete value LS by using a formula LS=alpha×g1+Cb×g2, wherein g1 and g2 are preset coefficient factors;
obtaining an average value GW of the associated interval information group according to an average value calculation formula; using the formulaCalculating to obtain a spacing limit GF, wherein g3 and g4 are preset coefficient factors；
Calculating a command correlation index Zg of the industrial equipment by using a formula Zg=fX (ZKxg5+Kb xg6)/(GF xg 7), wherein g5, g6 and g7 are all preset coefficient factors; f is a preset equalization coefficient.
Further, two ways are used to acquire the original image data: the first mode is to read a productivity middle platform interface and acquire image data displayed by the interface; the second way is to acquire raw image data through a data interface provided by the MES/SCADA system.
Further, the lightweight image data is cut and segmented based on rules defined or trained in advance; performing action recognition and scene recognition based on a conventional algorithm; the method specifically comprises the following steps:
first, screenshot and classification: marking a plurality of scene interfaces of the acquired lightweight image data as a scene one, a scene two, a scene three, … and a scene N respectively; determining a position boundary of each scene in the screen based on the coordinates; the system automatically captures a screen once every set time t; then cutting the whole screen shot picture into a plurality of scene pictures according to the coordinate boundary of each scene, wherein the scene pictures are respectively a scene picture I, a scene picture II, a scene picture III, … and a scene picture N;
second, determining abnormal mark characteristics: the abnormal sign features are extracted based on the prior definition or training of a deep learning algorithm, and are classified according to a first scene picture, a second scene picture, a third scene picture, … and a N scene picture; wherein pictures of the same scene at different times are taken as a class.
Further, the abnormality flag feature is based on a definition in advance, specifically: corresponding abnormal mark features are set based on the features of the first scene, the second scene, the third scene, the … scene and the N scene respectively.
Further, the training extraction of the abnormal sign feature based on the deep learning algorithm specifically comprises the following steps:
forming an abnormal characteristic sample library by collecting a large amount of original image data of industrial equipment in various fault states; parameter optimization is carried out on the sample data, wherein the parameter optimization comprises the steps of sequentially carrying out epoch optimization, batch size optimization and neuron number optimization;
meanwhile, a machine learning algorithm is adopted to analyze the abnormal feature sample library, key feature parameters are extracted, and an abnormal feature classifier is obtained;
in addition, a deep learning algorithm is adopted, and the data set is trained on line, so that the system continuously acquires new information from the environment and automatically updates the abnormal feature classifier.
Compared with the prior art, the invention has the beneficial effects that:
drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a system block diagram of a system for monitoring and analyzing data of a middle station based on the industrial Internet.
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, 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.
As shown in FIG. 1, the middle data monitoring and analyzing system based on the industrial Internet comprises a data acquisition module, a monitoring center, a data distribution module, an image analysis module and an early warning module;
the data acquisition module is used for acquiring original image data of industrial equipment during operation through the productivity center and sending the original image data to the monitoring center for caching in a message form;
wherein, the original image data is acquired in two ways: the first mode is to read a productivity middle platform interface and acquire image data displayed by the interface; the second mode is to obtain the original image data through a data interface provided by an MES/SCADA system; the original image data mainly comprises a three-dimensional digital model of industrial equipment and parameter data in the processing process;
the data distribution module is connected with the monitoring center and is used for extracting characteristic values of the original image data to carry out distribution priority FY analysis, and the specific analysis steps are as follows:
extracting characteristic values of original image data; the characteristic value comprises data quantity, data transmission distance and data transmission bandwidth; the data quantity, the data transmission distance and the data transmission bandwidth are marked as L1, L2 and L3 in sequence; calculating a calculation force load value Lt required for analyzing original image data by using a formula Lt=L1×a1+L2×a2+L3×a3, wherein a1, a2 and a3 are all preset coefficient factors;
acquiring industrial equipment corresponding to the original image data; in a preset time period, acquiring an instruction control record of the industrial equipment, wherein the instruction control record comprises an instruction type and an instruction control moment;
comparing and analyzing the command control time of the industrial equipment with the command control time of other industrial equipment, and calculating to obtain a command association index Zg of the industrial equipment;
counting the total times of faults of industrial equipment as G1; normalizing the calculated force load value, the instruction association index and the total number of faults, taking the values of the normalized values, and calculating by using a formula FY= (ZgXb1+G1 Xb2)/(LtXb 3) to obtain the distribution priority FY of the original image data, wherein b1, b2 and b3 are all preset coefficient factors;
sorting the original image data according to the size of the allocation priority FY to obtain a processing priority sequence of the original image data; the data distribution module is used for feeding back the processing priority sequence of the original image data to the monitoring center;
the monitoring center is used for driving the image analysis module to sequentially perform identification analysis on the original image data according to the processing priority sequence, so that the data analysis efficiency is improved;
the image analysis module is used for carrying out equipment state identification on the original image data by applying a convolutional neural network algorithm (CNN), and specifically comprises the following steps:
compressing the original image data to obtain the processed light image data;
secondly, cutting and dividing the light-weight image data based on a rule defined or trained in advance; performing action recognition and scene recognition based on a conventional algorithm; the method specifically comprises the following steps:
first, screenshot and classification: marking a plurality of scene interfaces of the acquired lightweight image data as a scene one, a scene two, a scene three, … and a scene N respectively; determining a position boundary of each scene in the screen based on the coordinates; the system automatically captures a screen once every set time t; then cutting the whole screen shot picture into a plurality of scene pictures according to the coordinate boundary of each scene, wherein the scene pictures are respectively a scene picture I, a scene picture II, a scene picture III, … and a scene picture N;
second, determining abnormal mark characteristics: the abnormal sign features are extracted based on the prior definition or training of a deep learning algorithm, and are classified according to a first scene picture, a second scene picture, a third scene picture, … and a N scene picture; wherein pictures of the same scene at different times are taken as a class;
in this embodiment, the abnormality flag feature is based on a definition in advance, specifically: corresponding abnormal mark features are set on the basis of the features of the first scene, the second scene, the third scene, the … scene and the N scene respectively;
finally, performing image recognition by applying a convolutional neural network algorithm (CNN), recognizing the running state of the industrial equipment based on training of the normal state and the abnormal state (and subdivision fault types) in advance, and feeding back the recognition result to an early warning module;
the early warning module is used for prompting the identification on the interface of the monitoring center in a signal sign or character mode according to the identification result; the identification result comprises whether the industrial equipment is normal or not and the corresponding fault type;
in this embodiment, the training extraction of the abnormal marker feature based on the deep learning algorithm specifically includes:
forming an abnormal characteristic sample library by collecting a large amount of original image data of industrial equipment in various fault states; parameter optimization is carried out on the sample data, wherein the parameter optimization comprises the steps of sequentially carrying out epoch optimization, batch size optimization and neuron number optimization;
meanwhile, a machine learning algorithm is adopted to analyze the abnormal feature sample library, key feature parameters are extracted, and an abnormal feature classifier is obtained;
in addition, a deep learning algorithm is adopted, and a data set is trained on line, so that the system continuously acquires new information from the environment and automatically updates the abnormal feature classifier, and the purposes of improving the data utilization rate and the detection accuracy rate are achieved;
the further technical proposal is that: comparing and analyzing the command control time of the industrial equipment with the command control time of other industrial equipment, and calculating to obtain a command association index Zg of the industrial equipment, wherein the specific analysis steps are as follows:
taking a certain instruction control moment of industrial equipment as a center, and marking other industrial equipment with instruction control time difference within a preset value as instruction associated equipment; counting the number of instruction association devices to be Dz; if Dz is greater than a preset quantity threshold value, marking the instruction control as instruction association control;
counting the total times of instruction control of industrial equipment as ZK, and counting the times of instruction association control of the industrial equipment as association duty ratio Kb; counting the time difference between two adjacent instruction association control moments of the industrial equipment as an instruction association interval ZTi to obtain an association interval information group;
calculating standard deviation of the associated interval information group according to a standard deviation formula and marking the standard deviation as alpha; traversing the association interval information group, marking the maximum value as ZTmax, and marking the minimum value as ZTmin;
calculating to obtain a difference ratio Cb by using a formula Cb= (ZTmax-ZTmin)/(ZTmin+u), wherein u is a preset compensation coefficient; calculating to obtain a discrete value LS by using a formula LS=alpha×g1+Cb×g2, wherein g1 and g2 are preset coefficient factors;
obtaining an average value GW of the associated interval information group according to an average value calculation formula; using the formulaCalculating to obtain an interval limit value GF, wherein g3 and g4 are preset coefficient factors;
normalizing the total times of command control, the association duty ratio and the interval limit value, taking the values, and calculating by using a formula Zg=fX (ZKxg5+Kb xg6)/(GF xg 7) to obtain a command association index Zg of the industrial equipment, wherein g5, g6 and g7 are all preset coefficient factors; f is a preset equalization coefficient.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The working principle of the invention is as follows:
the middle station data monitoring and analyzing system based on the industrial Internet comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring original image data of industrial equipment during operation through a productivity middle station; the data distribution module is used for extracting characteristic values of the original image data to carry out distribution priority FY analysis; calculating according to the characteristic value of the original image data to obtain a calculation force load value Lt required by analyzing the original image data; then, according to the corresponding instruction control record of the industrial equipment, calculating to obtain an instruction association index Zg of the industrial equipment; calculating to obtain the distribution priority FY of the original image data by combining the calculated force load value, the instruction association index and the total times of faults; sorting the original image data according to the size of the allocation priority FY to obtain a processing priority sequence of the original image data; the monitoring center is used for driving the image analysis module to sequentially perform identification analysis on the original image data according to the processing priority sequence, so that the data analysis efficiency is improved;
the image analysis module is used for carrying out equipment state identification on the original image data by applying a convolutional neural network algorithm (CNN); firstly, compressing original image data to obtain processed light image data; secondly, cutting and dividing the light-weight image data based on a rule defined or trained in advance; performing action recognition and scene recognition based on a conventional algorithm; finally, performing image recognition by applying a convolutional neural network algorithm (CNN), and recognizing the running state of the industrial equipment based on training of the normal state and the abnormal state (and subdivision fault types) in advance; so that the manager can check, analyze and manage the production process of the whole factory through the monitoring center, and the abnormal problems can be accurately positioned to assist in optimizing the resource allocation.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
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 (7)

1. The middle data monitoring and analyzing system based on the industrial Internet is characterized by comprising a data acquisition module, a monitoring center, a data distribution module, an image analysis module and an early warning module;
the data acquisition module is used for acquiring original image data of industrial equipment during operation through the productivity center and sending the original image data to the monitoring center in the form of a message; the original image data mainly comprises a three-dimensional digital model of industrial equipment and parameter data in the processing process;
the data distribution module is connected with the monitoring center and is used for extracting characteristic values of the original image data to carry out distribution priority FY analysis and sequencing the original image data according to the size of the distribution priority FY to obtain a processing priority sequence of the original image data;
the monitoring center is used for driving the image analysis module to sequentially perform identification analysis on the original image data according to the processing priority sequence; the image analysis module is used for carrying out equipment state identification on the original image data by applying a convolutional neural network algorithm; the method comprises the following steps:
compressing the original image data to obtain the processed light image data;
secondly, cutting and dividing the light-weight image data based on a rule defined or trained in advance; performing action recognition and scene recognition based on a conventional algorithm;
finally, performing image recognition by applying a convolutional neural network algorithm, recognizing the running state of industrial equipment based on training of the normal state, the abnormal state and the subdivision fault type in advance, and feeding back the recognition result to an early warning module;
the early warning module is used for prompting the identification on the monitoring center interface in a signal sign or text mode according to the identification result; the identification result includes whether the industrial equipment is normal or not and the corresponding fault type.
2. The industrial internet-based center data monitoring and analyzing system according to claim 1, wherein the specific analyzing steps of the data distribution module are as follows:
extracting characteristic values of original image data; the characteristic value comprises data quantity, data transmission distance and data transmission bandwidth; the data quantity, the data transmission distance and the data transmission bandwidth are marked as L1, L2 and L3 in sequence; calculating to obtain a calculation force load value Lt required for analyzing the original image data by using a formula lt=L1×a1+L2×a2+L3×a3, wherein a1, a2 and a3 are all preset coefficient factors;
acquiring industrial equipment corresponding to the original image data; collecting an instruction control record of the industrial equipment within a preset time period, wherein the instruction control record comprises an instruction type and an instruction control moment;
comparing and analyzing the instruction control moment of the industrial equipment with the instruction control moment of other industrial equipment, and calculating to obtain an instruction association index Zg of the industrial equipment;
counting the total times of faults of the industrial equipment as G1; and carrying out normalization processing on the calculated force load value, the instruction association index and the total number of faults, taking the values of the calculated force load value, the instruction association index and the total number of faults, and calculating by using a formula FY= (ZgXb1+G1×b2)/(LtXb 3) to obtain the distribution priority FY of the original image data, wherein b1, b2 and b3 are all preset coefficient factors.
3. The industrial internet-based center data monitoring and analyzing system according to claim 2, wherein the specific calculation method of the instruction association index Zg is as follows:
marking other industrial equipment with the instruction control time difference within a preset value as instruction associated equipment by taking certain instruction control time of the industrial equipment as a center; counting the number of instruction association devices to be Dz; if Dz is greater than a preset quantity threshold value, marking the instruction control as instruction association control;
counting the total times of instruction control of the industrial equipment as ZK, and counting the times of instruction association control of the industrial equipment as association duty ratio Kb; counting the time difference between two adjacent instruction association control moments of the industrial equipment as an instruction association interval ZTi to obtain an association interval information group;
calculating standard deviation of the associated interval information group according to a standard deviation formula and marking the standard deviation as alpha; traversing the association interval information group, marking the maximum value as ZTmax, and marking the minimum value as ZTmin;
calculating to obtain a difference ratio Cb by using a formula Cb= (ZTmax-ZTmin)/(ZTmin+u), wherein u is a preset compensation coefficient; calculating to obtain a discrete value LS by using a formula LS=alpha×g1+Cb×g2, wherein g1 and g2 are preset coefficient factors;
obtaining an average value GW of the associated interval information group according to an average value calculation formula; using the formulaCalculating to obtain an interval limit value GF, wherein g3 and g4 are preset coefficient factors;
calculating a command correlation index Zg of the industrial equipment by using a formula Zg=fX (ZKxg5+Kb xg6)/(GF xg 7), wherein g5, g6 and g7 are all preset coefficient factors; f is a preset equalization coefficient.
4. The industrial internet-based center data monitoring and analysis system of claim 1, wherein the raw image data is obtained in two ways: the first mode is to read a productivity middle platform interface and acquire image data displayed by the interface; the second way is to acquire raw image data through a data interface provided by the MES/SCADA system.
5. The industrial internet-based center data monitoring and analyzing system according to claim 1, wherein the lightweight image data is cut and divided based on a rule defined or trained in advance; performing action recognition and scene recognition based on a conventional algorithm; the method specifically comprises the following steps:
first, screenshot and classification: marking a plurality of scene interfaces of the acquired lightweight image data as a scene one, a scene two, a scene three, … and a scene N respectively; determining a position boundary of each scene in the screen based on the coordinates; the system automatically captures a screen once every set time t; then cutting the whole screen shot picture into a plurality of scene pictures according to the coordinate boundary of each scene, wherein the scene pictures are respectively a scene picture I, a scene picture II, a scene picture III, … and a scene picture N;
second, determining abnormal mark characteristics: the abnormal sign features are extracted based on the prior definition or training of a deep learning algorithm, and are classified according to a first scene picture, a second scene picture, a third scene picture, … and a N scene picture; wherein pictures of the same scene at different times are taken as a class.
6. The industrial internet-based center data monitoring and analyzing system according to claim 5, wherein the abnormality flag feature is defined in advance, specifically: corresponding abnormal mark features are set based on the features of the first scene, the second scene, the third scene, the … scene and the N scene respectively.
7. The industrial internet-based center data monitoring and analyzing system according to claim 5, wherein the anomaly flag feature is extracted based on training of a deep learning algorithm, specifically:
forming an abnormal characteristic sample library by collecting a large amount of original image data of industrial equipment in various fault states; parameter optimization is carried out on the sample data, wherein the parameter optimization comprises the steps of sequentially carrying out epoch optimization, batch size optimization and neuron number optimization;
meanwhile, a machine learning algorithm is adopted to analyze the abnormal feature sample library, key feature parameters are extracted, and an abnormal feature classifier is obtained;
in addition, a deep learning algorithm is adopted, and the data set is trained on line, so that the system continuously acquires new information from the environment and automatically updates the abnormal feature classifier.
CN202311313656.4A 2023-10-11 2023-10-11 Middle-station data monitoring and analyzing system based on industrial Internet Pending CN117331802A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311313656.4A CN117331802A (en) 2023-10-11 2023-10-11 Middle-station data monitoring and analyzing system based on industrial Internet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311313656.4A CN117331802A (en) 2023-10-11 2023-10-11 Middle-station data monitoring and analyzing system based on industrial Internet

Publications (1)

Publication Number Publication Date
CN117331802A true CN117331802A (en) 2024-01-02

Family

ID=89276911

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311313656.4A Pending CN117331802A (en) 2023-10-11 2023-10-11 Middle-station data monitoring and analyzing system based on industrial Internet

Country Status (1)

Country Link
CN (1) CN117331802A (en)

Similar Documents

Publication Publication Date Title
CN111353413B (en) Low-missing-report-rate defect identification method for power transmission equipment
CN104992223A (en) Dense population estimation method based on deep learning
CN111505424A (en) Large experimental device power equipment fault diagnosis method based on deep convolutional neural network
CN108802041B (en) Method for rapidly changing small sample set of screen detection
CN110309967A (en) Prediction technique, system, equipment and the storage medium of customer service session grading system
CN112017204A (en) Tool state image classification method based on edge marker graph neural network
CN115660288A (en) Analysis management system based on internet big data
CN113988573A (en) Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system
CN115511367A (en) Intelligent quality management system of production line
CN116185757A (en) Intelligent monitoring system for energy consumption of machine room
CN114913129A (en) System for identifying and positioning laying defects of composite material
CN117114420B (en) Image recognition-based industrial and trade safety accident risk management and control system and method
CN115984158A (en) Defect analysis method and device, electronic equipment and computer readable storage medium
CN114067268A (en) Method and device for detecting safety helmet and identifying identity of electric power operation site
CN113077423A (en) Laser selective melting pool image analysis system based on convolutional neural network
KR20220105689A (en) System for determining defect of display panel based on machine learning model
CN115562191B (en) Industrial digital twin-based intelligent presumption analysis method for productivity center
CN115987692A (en) Safety protection system and method based on flow backtracking analysis
CN117331802A (en) Middle-station data monitoring and analyzing system based on industrial Internet
CN110855467B (en) Network comprehensive situation prediction method based on computer vision technology
CN113837178A (en) Deep learning-based automatic positioning and unified segmentation method for meter of transformer substation
US20190266403A1 (en) Server, method and wearable device for supporting maintenance of military apparatus based on binary search tree in augmented reality-, virtual reality- or mixed reality-based general object recognition
CN110569277A (en) Method and system for automatically identifying and classifying configuration data information
CN111930982A (en) Intelligent labeling method for power grid images
CN112968941B (en) Data acquisition and man-machine collaborative annotation method based on edge calculation

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