CN116969148A - Multi-dimensional linkage monitoring and processing method and system for faults of adhesive tape machine - Google Patents
Multi-dimensional linkage monitoring and processing method and system for faults of adhesive tape machine Download PDFInfo
- Publication number
- CN116969148A CN116969148A CN202311087810.0A CN202311087810A CN116969148A CN 116969148 A CN116969148 A CN 116969148A CN 202311087810 A CN202311087810 A CN 202311087810A CN 116969148 A CN116969148 A CN 116969148A
- Authority
- CN
- China
- Prior art keywords
- fault
- tape machine
- adhesive tape
- faults
- alarm
- 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
- 239000002390 adhesive tape Substances 0.000 title claims abstract description 79
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 50
- 238000004519 manufacturing process Methods 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 34
- 238000013499 data model Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 238000012423 maintenance Methods 0.000 claims description 13
- 239000000463 material Substances 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 238000009434 installation Methods 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 abstract description 6
- 238000003745 diagnosis Methods 0.000 abstract description 5
- 230000001419 dependent effect Effects 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 6
- 230000001276 controlling effect Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 239000003016 pheromone Substances 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 239000002243 precursor Substances 0.000 description 4
- 230000000903 blocking effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 241000257303 Hymenoptera Species 0.000 description 2
- 238000009529 body temperature measurement Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 206010020843 Hyperthermia Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036031 hyperthermia Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G15/00—Conveyors having endless load-conveying surfaces, i.e. belts and like continuous members, to which tractive effort is transmitted by means other than endless driving elements of similar configuration
- B65G15/30—Belts or like endless load-carriers
- B65G15/32—Belts or like endless load-carriers made of rubber or plastics
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/02—Control or detection
- B65G2203/0266—Control or detection relating to the load carrier(s)
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/04—Detection means
- B65G2203/042—Sensors
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a multi-dimensional linkage monitoring and processing method and system for faults of a tape machine, and belongs to the technical field of fault inspection. The invention constructs a fault detection method based on a rule judgment engine and a fault image recognition method based on machine vision and deep learning, realizes a multidimensional linkage monitoring and rechecking strategy of fault detection signals, video image recognition and manual intervention, and solves the problem that a tape machine is dependent on manual point inspection. The problems of single fault alarm channel and incomplete alarm information are solved by the methods of coordinate positioning, video screenshot and video recording and APP micro-message short message multi-channel pushing. The emergency linkage treatment is carried out on the faults by controlling the operation stop of the fault adhesive tape machine and controlling the on-site fault handling equipment. The Dijkstra algorithm and the ant colony algorithm are used for calculating the alternative production flow, so that the influence of fault shutdown on the production efficiency is reduced; through analysis of parameter trend and establishment of fault prediction model, intelligent diagnosis of the equipment is increased.
Description
Technical Field
The invention relates to the technical field of inspection of a tape machine, in particular to a multi-dimensional linkage monitoring and processing method and system for faults of the tape machine.
Background
With the advancement of intelligent manufacturing, industrial intelligent digitization is becoming more and more important, with intelligent digital management of devices, and intelligent monitoring of the status of devices becoming more and more important.
The adhesive tape machine is used as an important transportation tool for a raw material factory, a mine and the like of a metallurgical enterprise, and often causes faults such as deviation, slipping, blocking and the like due to long conveying distance, a plurality of links involved in a process, severe site environment and the like. The existing fault detection mode mainly comprises manual spot inspection, a fault detection sensor alarms, and a video picture can also be used as an auxiliary means for monitoring equipment conditions.
The fault detection sensor of the adhesive tape machine comprises, but is not limited to, a temperature measurement sensor, a slip detection sensor, an anti-blocking sensor, a deviation detection sensor and the like.
The temperature measuring sensor measures the temperature of the contact point of the driving roller and the adhesive tape in an infrared temperature measuring mode, and judges whether the adhesive tape is abnormally high or not by comparing the temperature of the contact point of the driving roller and the adhesive tape with the set temperature. The slip detection sensor detects the rotating speed of the driven roller, compares the rotating speed with the speed of the driving roller, and gives a slip alarm when the speeds are inconsistent. The anti-blocking sensor is provided with a chute blocking detection device at each chute of the transfer point of the belt conveyor. The detection switches of the deviation detection sensors are fixed on two sides of each machine frame of the adhesive tape machine through brackets, and under the condition that the adhesive tape machine normally operates, the swing rods of the deviation detection switches are kept at a certain distance from the edge lines of the adhesive tape, and the swing rods and the edge lines of the adhesive tape are in an orthogonal state; when the conveyer belt is deviated, the vertical stick on the switch is deflected due to the side pressure of the edge of the conveyer belt, and when the inclination degree exceeds the secondary action angle (heavy deviation fault), the deviation detection switch triggers an alarm.
In summary, the fault detection of the adhesive tape machine at present only depends on mutually independent manual inspection, fault detection sensor or video monitoring to monitor, and has the following problems: (1) The equipment points of the industrial production field are wide in multiple aspects, manual point inspection is difficult to cover the whole area, and the inspection results are different from person to person depending on experience judgment; (2) The failure alarm of the detection sensor lacks multidimensional linkage rechecking, the number of false alarms is related to the quality and maintenance frequency of the detection equipment, and the failure alarm accuracy is required to be improved; (3) The channel for fault alarm pushing is single, alarm information content is incomplete, and information such as accurate positions, real-time images and the like are not available; (4) The fault processing depends on the speed of manual reaction, so that emergency processing is difficult to be carried out on the fault condition in the first time, and the safety risk is easily enlarged; (5) After the adhesive tape machine fails, an alternative production scheme cannot be formulated in time, and the production efficiency is affected; (6) The fault post analysis is less, and the intelligent diagnosis of equipment is lacking.
Through retrieval, patent publication number CN110077803A, a centralized control system of a tape machine is disclosed; the application comprises a centralized control room on the ground and a plurality of adhesive tape machines installed under a mine, wherein a main industrial control machine and a standby industrial control machine are installed in the centralized control room, the main industrial control machine and the standby industrial control machine are all connected with a main station under the mine through Ethernet, the main station is connected with substations distributed beside each adhesive tape machine, a programmable control cabinet for locally controlling the adhesive tape machines is installed in each substation, a deviation sensor, a slipping sensor, a temperature sensor, a speed sensor, a smoke sensor and an emergency stop sensor are all installed on each adhesive tape machine, and the sensors on each adhesive tape machine are all connected to the corresponding programmable control cabinet. The application adopts a distributed control structure and has more perfect detection and protection functions, but the application focuses on fault detection, and the emergency treatment of fault conditions and the generation of alternative production schemes are not considered more.
Disclosure of Invention
1. Technical problem to be solved by the invention
In order to solve the problems, the invention provides a multi-dimensional linkage monitoring and processing method and a system for a fault of a tape machine, which can improve the fault alarm accuracy and enrich the fault alarm channel and alarm information; emergency linkage treatment is carried out on the faults, so that safety risks caused by the faults are reduced; meanwhile, the method calculates the alternative production flow, and reduces the influence of fault shutdown on the production efficiency.
2. Technical proposal
In order to achieve the above purpose, the technical scheme provided by the invention is as follows:
the invention relates to a multi-dimensional linkage monitoring and processing method for faults of a tape machine, which comprises the following steps:
s1, installing and accessing fault detection sensor signals, constructing a data model of the adhesive tape machine and a data model of the detection sensor in the system, and establishing corresponding positions and affiliations.
And S2, installing and accessing a high-definition video camera with a movable cradle head to acquire a video stream and control rights.
S3, calibrating the camera, and storing the corresponding relation between the camera shooting parameters and the position of the detection sensor; and establishing a geometric model of the imaging of the adhesive tape machine through the calibration value, and providing a calculation basis for an image recognition algorithm.
S4: and accessing related systems or equipment units, including a production flow decision system, a production control system, fault alarm equipment and the like.
S5, collecting, analyzing and processing signals of the fault detection sensor, including collecting, cleaning and storing original data and establishing a fault judgment rule engine to carry out fault judgment.
And S6, after triggering an alarm, controlling the high-definition video camera to focus on the fault alarm point, acquiring a video stream signal, capturing a screenshot and previewing in real time.
And S7, rechecking the fault by using an image recognition and deep learning algorithm, so as to confirm the alarm accuracy of the detection equipment.
And S8, if the video rechecks pass, starting a fault processing flow from S10. If the video rechecking is not passed, the user needs to manually confirm rechecking, the user confirms that the video rechecking is a fault, and the next step is to start a fault processing flow from S10; if the user considers that the error report is generated, the next step starts to detect the equipment fault self-checking flow from S9.
S9: the false alarm device performs self-checking, checks possible problems of network transmission, detection elements and the like related to the sensor, analyzes false alarm reasons and generates a maintenance work order of the sensor device.
S10: and integrating the related information of fault alarm, generating a maintenance work order of the tape machine, and pushing the fault alarm information to a user through a computer client, a mobile phone APP, a WeChat public platform and a mobile phone short message multi-channel.
S11: and emergency linkage treatment is adopted for the adhesive tape machine with faults, and the adhesive tape machine is controlled to stop running immediately. And controlling the on-site audible and visual alarm to give an alarm. For specific types of faults, such as high-temperature fire alarm, the system is linked with the on-site fire extinguishing device, and the fire extinguishing device is controlled to start operation.
S12, planning an alternative process of the original process. And (3) the key information of the production flow is searched and judged, the available tape machine equipment list is searched and judged, the Dijkstra algorithm and the ant colony algorithm are utilized to calculate the optimal path of the replacement flow, and after confirmation of a user, the replacement flow is started.
And S13, after the fault is ended, updating a fault diagnosis knowledge base, analyzing time domain, frequency spectrum and characteristic parameter trend, inputting data into a fault prediction model for training, and updating an alarm rule analysis engine.
3. Advantageous effects
Compared with the prior art, the technical scheme provided by the invention has the following remarkable effects:
according to the multi-dimensional linkage monitoring processing method for the faults of the adhesive tape machine, disclosed by the invention, the multi-dimensional linkage monitoring rechecking strategy of the fault detection signals, video image recognition and manual intervention of the adhesive tape machine is realized by constructing the fault detection method based on the rule judgment engine and the adhesive tape machine fault image recognition method based on the machine vision and the deep learning algorithm, the problem that the faults of the adhesive tape machine depend on manual point inspection is solved, and the fault detection alarm accuracy is improved. The problems of single fault alarm channel and incomplete alarm information are solved by the methods of coordinate positioning, video screenshot and video recording and APP micro-message short message multi-channel pushing. The emergency linkage treatment is carried out on the faults by a method for controlling the operation stop of the fault adhesive tape machine and controlling the on-site fault handling equipment, so that the problem of untimely fault handling measures is solved. The Dijkstra algorithm and the ant colony algorithm are used for calculating the alternative production flow, so that the influence of fault shutdown on the production efficiency is reduced; the intelligent diagnosis of the equipment is added through analysis of analysis time domain, frequency spectrum and characteristic parameter trend and establishment of a fault prediction model.
Drawings
FIG. 1 is a flow chart of a multi-dimensional linkage monitoring processing method for a fault of a tape machine.
Detailed Description
For a further understanding of the present invention, the present invention will be described in detail with reference to the drawings and examples.
Example 1
Referring to fig. 1, the method for multidimensional linkage monitoring and processing of faults of the adhesive tape machine in this embodiment comprises the following specific steps:
s1, according to the scale of an industrial field, the existing or installed fault detection sensors such as slipping, deviation, blocking and temperature measurement are utilized to collect the signals of the detection sensors distributed on the industrial field, and the signals are accessed into a low-distribution room nearby through optical fibers in a unified access mode, and then are forwarded to a system main server in a centralized manner through a convergence switch. And constructing a data model of the tape machine and a data model of the detection sensor in the system, and establishing corresponding positions and affiliations.
The "position" in the data model of the tape machine refers to the exact coordinates of each tape machine in the industrial site, and is usually represented by using geographic coordinates or a coordinate system inside the site. May be obtained by Global Positioning System (GPS) or other positioning technology. The taping machine may be subordinate to different production lines, production areas or work units. In the data model, a relationship between each adhesive tape machine and the production line, working area and the like to which each adhesive tape machine belongs can be established. In this way, the information of the tape machine in a specific production line or work area can be easily queried as required.
The "position" in the test sensor data model refers to the specific mounting position of each sensor relative to the taping machine. Including information about the orientation (e.g., left, right, top, bottom, etc.), relative height, angle, etc. of the sensor relative to the taping machine. Each sensor may be subordinate to a particular taping machine component or a particular monitoring task. The dependencies between each sensor and its monitored components of the tape machine are defined in a data model. For example, one temperature sensor may be slaved to the hot zone of the machine and one deflection sensor may be slaved to the positioning system of the machine.
S2, according to the industrial field scale, the existing or installed high-definition video camera with the movable cradle head is utilized, the video stream is accessed to a system main server in a direct connection or video system background interface mode, and the control authority of the video equipment is obtained.
And S3, calibrating the shooting angle and focal length (PTZ value) of the high-definition video camera. Storing the IP address and PTZ value of the video camera corresponding to each detection sensor into a detection sensor data model; and establishing a geometric model of camera imaging for each adhesive tape, determining the corresponding relation between the change amount of the adhesive tape edge position in the image and the actual measurement through calibration, and providing a theoretical calculation basis for image recognition algorithm execution.
And S4, connecting a related system or equipment with the fault detection and processing system of the adhesive tape machine to acquire necessary information and control capability. These systems or devices include production process decision-making systems (acquiring key production information such as starting points and ending points of material transportation, used tape machines, material transportation amount, etc. in the production process), production control systems (acquiring starting and stopping states and control authorities of the tape machines), and fault alarm devices (such as on-site audible and visual alarm lamps, fire extinguishing devices, etc.).
And (3) accessing a production flow decision system:
it is determined which key production information needs to be obtained from the production flow decision system, such as material transportation start point, end point, tape machine used, etc.
The process flow decision system is connected to the tape machine fault detection and handling system via a network connection using an appropriate communication protocol (e.g., HTTP, TCP/IP, etc.) or API interface.
Corresponding data parsing and transmission modules are developed to ensure that data extracted from the production flow decision system can be properly interpreted and utilized by the tape machine system.
And (3) accessing a production control system:
and determining the start-stop state, the control authority and other information of the adhesive tape machine to be acquired from the production control system.
And selecting a proper communication protocol or interface for connection according to the communication mode of the production control system. Common communication protocols include Modbus, OPC, and the like.
The data interaction module is developed to realize data exchange and control instruction transmission between the production control system and the tape machine fault detection and processing system.
And (3) accessing fault alarm equipment:
and identifying fault alarm equipment which needs to be accessed, such as on-site acousto-optic alarm lamps, fire extinguishing devices and the like.
And selecting a proper access method according to the characteristics and the communication mode of the fault alarm equipment. Steps such as hardware connections, signal conversion, and the like may be involved.
The communication between the fault alarm equipment and the tape machine system is ensured to realize real-time fault information transmission and response.
And S5, collecting, analyzing and processing signals of the fault detection sensor, including acquisition, cleaning, storage and rule judgment of the original data. Specifically, the method comprises the following steps:
s5-1: the detection sensor signals are acquired from the acquisition gateway to the system host server using acquisition protocols including, but not limited to, OPC, MODBUS, and the like.
S5-2: after the detection data are collected to the main server, data cleaning is started, and data are rechecked and checked. For incomplete data, using average, maximum, minimum, or probability estimates as appropriate instead of missing values; for error data, checking data values through a statistical method such as deviation analysis, regression equation or establishing a specific rule base, screening and correcting, and then storing; and for repeated data, checking and judging whether the records are equal or not through GUID, and merging and eliminating the same data.
S5-3, storing the cleaned data into a data warehouse according to the characteristics and types of the data, and storing the data which are continuous in data time, have the acquisition frequency as fast as the pressure, weight, temperature and the like acquired by the sensor into a time sequence database; the data point changes fast, the frequency of use is high and the data point is stored in the memory database; the collected data with fixed data structure is stored in a relational database.
And S5-4, constructing a rule engine module, accessing the data of the data warehouse into a rule engine, converting expert experience into logic alarm by utilizing logic compiling of the rule engine, performing real-time alarm judgment on the accessed data, and triggering business processing flows of different roles by combining alarm grades.
The logic compiling of the rule engine is utilized to convert expert experience into alarm logic which can be automatically executed, so that the real-time monitoring and processing of faults are realized. This process involves the following key steps:
configuration of the rules engine and rule definition:
an applicable rule engine, such as Drools, is selected for managing and executing the rules.
The fault type is defined, e.g. "hyperthermia", and the corresponding rules are built according to expert experience.
And (3) constructing rules:
for each fault type, a rule is created. For example, for a temperature that is too high, conditions may be defined: if the temperature sensor data exceeds a set threshold, an alarm is triggered.
Conditions and actions of rules define:
in the rules engine, conditions and corresponding actions are defined for each rule. The condition is a logical expression based on the sensor data and the action is an operation triggering an alarm and corresponding business process.
Data entry and rule matching:
the cleaned sensor data enters a rule engine to match defined rules one by one.
Assuming that the temperature sensor data shows a temperature of 100 ℃, the rules engine will check if the data meets the rule condition of excessive temperature.
Rule matching triggers an alarm:
since the data satisfies the rule condition, the rule engine triggers an alarm action, such as sending an alarm notification, for example: and sending a short message to maintenance personnel to remind the adhesive tape machine of abnormal temperature.
Triggering a business processing flow:
the rules engine may further trigger business process flows, such as generating a repair order. When the alarm is triggered due to the fact that the temperature is too high, the rule engine automatically generates a maintenance work order to instruct maintenance personnel to check and repair the problem.
Multi-rule linkage:
assuming another rule, an emergency shutdown is required if the temperature continues to rise and the duration exceeds a threshold.
The rules engine may examine a combination of conditions through multi-rule linkage. If the temperature continues to rise and the duration exceeds the threshold, the rules engine triggers an emergency shutdown operation.
Through the comprehensive process, expert experience can be converted into an actually executable logic rule, so that the system can automatically judge data and trigger corresponding alarm and processing. The method not only improves the accuracy of fault detection, but also accelerates the response and solving speed of the problems, and is beneficial to improving the production efficiency and the stability of the working flow.
And S6, after triggering an alarm, determining the fault position and type and corresponding IP address and PTZ value of the video camera by detecting the sensor data model. And controlling the high-definition video camera to focus on the fault alarm point by using the calibrated PTZ value, acquiring a video stream signal, capturing a picture according to a period, and playing the real-time preview of the fault point on the system.
And S7, rechecking the fault by using an image recognition and deep learning algorithm, so as to confirm the alarm accuracy of the detection equipment. Taking deviation fault as an example for explanation, the specific process is as follows:
s7-1, before the video image is subjected to algorithm processing, firstly, geometric transformation is carried out on the image, so that the position information of the edge of the adhesive tape is better determined. The geometric transformation comprises image translation, image mirror image transformation, image transposition, image scaling and rotation, and image ROI position selection, and when the acquired image is transformed, an external rectangular frame region containing a target position is selected, so that the interference of other regions on the target position information is reduced, and the processing speed of each frame of image is increased.
S7-2, noise reduction and enhancement treatment are carried out, because the adhesive tape runs in an open air environment and is greatly influenced by illumination change, a plurality of interference objects which are unfavorable for image processing are easily generated in the collected image, so that the image is subjected to filtering treatment, the influence of light change on the quality of a picture is reduced, and meanwhile, the geometric characteristics of all parts around the adhesive tape are weakened by using a filtering algorithm, and the geometric position information of the edge of the enhanced adhesive tape is highlighted.
S7-3, detecting and extracting geometric features of the edge of the adhesive tape. And (3) carrying out linear feature detection and extraction on the pre-processed ROI image by adopting an image processing algorithm, screening the extracted linear segments according to the characteristic that the linear slope and the length of the adhesive tape edge along the line in the ROI area are basically unchanged, fitting the obtained features, and identifying the position of the adhesive tape edge along the line in the running process in the detection image according to the fitted linear.
And S7-4, finally judging the deviation state of the adhesive tape. When the adhesive tape is deviated, one end moves towards the direction of the carrier roller, the other end moves towards the lowest point, at the moment, the relative distance between the edges of the adhesive tapes at two sides and the highest point of the carrier roller changes, the position of the adhesive tape at one side is detected in real time through image processing, then the position of the adhesive tape is combined with the detected highest point of the carrier roller, the pixel distance from the edge of the belt to the highest point of the carrier roller is calculated, the actual deviation distance is obtained through coordinate conversion, and the alarm is confirmed when the deviation distance exceeds a set threshold value.
And S8, if the video rechecks pass, starting a fault processing flow from S10. If the video rechecking is not passed, the user needs to manually confirm rechecking, the user confirms that the video rechecking is a fault, and the next step is to start a fault processing flow from S10; if the user considers that the error report is generated, the next step starts to detect the equipment fault self-checking flow from S9.
S9: according to the alarm value characteristics, the system checks the possible problems of network transmission, detection elements and the like related to the sensor, analyzes the false alarm reasons, generates a maintenance work order of the sensor equipment, hangs up the equipment signal to prevent false alarm again until a user confirms that the maintenance of the sensor equipment is completed, and the system re-accesses the equipment signal.
S10: and integrating relevant fault alarm information in the system, including the number of the fault tape, the fault type, the fault time, the fault type, the fault position, the geographic coordinates, the fault video screenshot and the like, and simultaneously generating a maintenance work order of the tape machine, and waiting for a user to carry out maintenance work and confirm. The fault alarm information is pushed to the user through a computer client, a mobile phone APP, a WeChat public platform and a mobile phone short message multichannel.
S11: emergency linkage treatment is adopted for the adhesive tape machine with faults, and an operation stopping signal is actively sent to the production control system, so that the adhesive tape machine is immediately stopped. Meanwhile, the on-site audible and visual alarm is controlled to give an alarm to remind operators of paying attention. For specific types of faults, such as high-temperature fire alarm, the system is linked with the on-site fire extinguishing device, and the fire extinguishing device is controlled to start operation.
S12, planning an alternative process of the original process. Firstly, acquiring key production information such as a material transportation starting point, a material transportation end point, a used tape machine, material transportation quantity and the like in a production process through a production process decision-making system; next, acquiring a currently unoperated, unoccupied and schedulable adhesive tape machine equipment list from a production control system; next, calculating an optimal path of the alternative flow by using a Dijkstra algorithm and an ant colony algorithm; finally, after confirmation by the user, a signal is sent to the production control system to start the alternative process.
The optimal path of the alternative flow is calculated by using the Dijkstra algorithm and the ant colony algorithm, so that a feasible standby flow can be quickly found when the failure of the adhesive tape machine occurs, and the continuity and the efficiency of production are ensured. The following is a detailed description of the operation steps of these two algorithms in this scenario:
dijkstra algorithm:
1. representation of the figures: the production flow is considered a directed graph in which nodes represent workstations or equipment and edges represent connections between workstations. Each side has a weight representing execution time or cost.
2. Starting and end point selection: and determining the starting point and the ending point related to the current failure of the adhesive tape machine. The starting point is a fault adhesive tape machine, and the end point is a target workstation or equipment.
3. Initializing distance and precursor: the distance from the start point to each node is initialized to infinity and the distance from the start point to the start point is 0. The precursor nodes for each node are recorded.
4. Traversing nodes: starting from the start point, all nodes are traversed. For each node, the distance to it is updated, and if a shorter path is found, the precursor is updated.
5. Determining the shortest path: and after traversing, backtracking according to the precursor node information to obtain the shortest path.
6. Alternative flow planning: and (3) formulating a standby flow according to the node sequence on the shortest path, so as to ensure that the workstation on the shortest path can be preferentially selected for production when a fault occurs.
Ant colony algorithm:
1. representation of the figures: the production flow is also considered as a directed graph, the nodes represent workstations or devices, and the sides are weighted.
2. Ant colony initialization: a group of virtual "ants" is initialized, each ant randomly selecting a starting point to start.
3. Ant path selection: each ant moves between nodes according to a certain strategy (such as probability), and a decision is made according to the weight of the edge and the concentration of the pheromone.
4. Updating the pheromone: after the ants pass through the path, the pheromone concentration of the edges on the path is updated, and more pheromones are obtained by the edges with shorter distance on the path.
5. Searching a global optimal path: and iterating the ant movement for a plurality of times, and gradually converging to a global optimal path through accumulation of pheromones.
6. Alternative flow planning: and (3) formulating a standby flow according to the paths after the ant algorithm converges, so that the optimal paths obtained by the ant algorithm can be selected for production when the adhesive tape machine fails.
In practical application, the algorithm parameters are adjusted and configured according to specific production flows, relations and weights among nodes. Both algorithms are methods for finding the optimal path, which algorithm is chosen depending on the actual requirements of the field.
And S13, after the user confirms that the fault is over, collecting and arranging fault data, combining a big data analysis algorithm, converging historical data of related equipment of the adhesive tape machine, analyzing trend of time domain, frequency spectrum and characteristic parameters through the fault information of the adhesive tape machine and expert experience, searching characteristic values or characteristic curves with high correlation, inputting the data into a fault prediction model for training, correcting through the expert to gradually improve the prediction accuracy, and simultaneously accessing the fault influence factors into a fault judgment rule engine for monitoring, so that intelligent diagnosis of equipment faults is realized.
Example 2
The multi-dimensional linkage monitoring and processing system for the faults of the adhesive tape machine of the embodiment executes the multi-dimensional linkage monitoring and processing method for the faults of the adhesive tape machine of the embodiment 1.
The invention and its embodiments have been described above by way of illustration and not limitation, and the invention is illustrated in the accompanying drawings as one of its embodiments and is not limited to the embodiments shown. Therefore, those skilled in the art, having benefit of this disclosure, will appreciate that other embodiments can be devised which do not depart from the gist of the invention.
Claims (10)
1. The multi-dimensional linkage monitoring and processing method for the faults of the adhesive tape machine is characterized by comprising the following steps:
step 1, installing and accessing fault detection sensor signals, and establishing a position and an affiliation of a tape machine and a detection sensor;
step 2, installing and accessing a camera, calibrating the camera, determining the corresponding relation between the camera parameters and the position of the detection sensor, and establishing a geometric model of the imaging of the adhesive tape machine through a calibration value;
step 3, accessing a related system or equipment unit, wherein the related system or equipment unit comprises a production flow decision system, a production control system and fault alarm equipment;
step 4, collecting, analyzing and processing signals of the fault detection sensor, and judging faults;
step 5, after triggering fault alarm, rechecking the fault, and if rechecking passes, starting a fault processing flow; if the rechecking is not passed, the user manually confirms the rechecking, the user confirms the fault and starts the fault processing flow; if the user considers that the error report is generated, the self-checking flow of detecting equipment faults is started.
2. The method for multi-dimensional linkage monitoring and processing of the faults of the adhesive tape machine according to claim 1 is characterized in that: the fault processing flow comprises the following steps:
(1) Integrating the fault alarm information, generating a maintenance work order of the adhesive tape machine, and pushing the fault alarm information to a user;
(2) Emergency linkage treatment is adopted for the adhesive tape machine with faults, the adhesive tape machine is controlled to stop running immediately and give an alarm, and for specific types of faults, the adhesive tape machine is linked with a field processing device to carry out fault emergency treatment;
(3) And planning an alternative process of the original process, and starting the alternative process after confirmation of a user.
3. The method for multidimensional linkage monitoring and processing of the faults of the adhesive tape machine according to claim 2 is characterized in that: the fault self-checking flow comprises the following steps: and analyzing the false alarm reason according to the alarm value characteristics, generating a maintenance work order of the sensor equipment, suspending the equipment signal to prevent false alarm again until a user confirms that the maintenance of the sensor equipment is finished, and re-accessing the equipment signal.
4. The method for multidimensional linkage monitoring and processing of faults of the adhesive tape machine according to claim 3, which is characterized in that: and carrying out video rechecking on the faults by using an image recognition and deep learning algorithm.
5. The multi-dimensional linkage monitoring and processing method for faults of the adhesive tape machine according to claim 2 or 4 is characterized in that: step (3) is to obtain key production information in the production process through a production process decision system, comprising: the starting point and the ending point of material transportation, a used tape machine and the material transportation quantity; acquiring a current unoperated, unoccupied and scheduling adhesive tape machine equipment list from the production control system; then calculating the optimal path of the alternative flow by using Dijkstra algorithm or ant colony algorithm; after confirmation by the user, a signal is sent to the production control system to start the alternative process.
6. The multi-dimensional linkage monitoring and processing method for faults of a tape machine according to claim 5 is characterized in that: step 1, constructing a data model of the adhesive tape machine and a data model of a detection sensor, wherein the position in the data model of the adhesive tape machine is the accurate coordinate of each adhesive tape machine in an industrial field; the subordinate relation in the data model of the adhesive tape machine is the subordinate relation between the adhesive tape machine and the production line, the working area or the working unit to which the adhesive tape machine belongs; detecting the position in the sensor data model as the specific installation position of each sensor relative to the tape machine; the dependencies in the sensor data model are detected as dependencies between each sensor and its monitored components of the tape machine.
7. The method for multidimensional linkage monitoring and processing of the faults of the adhesive tape machine according to claim 6 is characterized in that: step 4, collecting, analyzing and processing signals of the fault detection sensor, including acquisition, cleaning, storage and rule judgment of original data; when the rule judgment is carried out, a rule engine module is built, stored data are accessed into the rule engine, expert experience is converted into logic alarm by utilizing logic compiling of the rule engine, real-time alarm judgment is carried out on the accessed data, and service processing flows of different roles are triggered by combining alarm grades.
8. The method for multidimensional linkage monitoring and processing of faults of the adhesive tape machine according to claim 7, which is characterized in that: and 5, after triggering an alarm, determining the fault position and type and the corresponding IP address and PTZ value of the video camera by detecting the sensor data model, controlling the camera to focus on a fault alarm point by using the calibrated PTZ value, acquiring a video stream signal, capturing a picture according to a period, and playing a real-time preview of the fault point.
9. The multi-dimensional linkage monitoring and processing method for faults of the adhesive tape machine according to claim 8 is characterized in that: after the user confirms that the fault is over, collecting and arranging fault data, combining with big data analysis, converging historical data of relevant equipment of the tape machine, analyzing time domain, frequency spectrum and characteristic parameter trends through the fault information of the tape machine and expert experience, searching characteristic values or characteristic curves with big relativity, inputting the data into a fault prediction model for training, correcting through the expert, improving prediction accuracy, and simultaneously accessing the fault influence factors into a fault judgment rule engine for monitoring.
10. A multi-dimensional linkage monitoring processing system for faults of a tape machine is characterized in that: the system executes the multi-dimensional linkage monitoring processing method for the faults of the tape machine according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311087810.0A CN116969148A (en) | 2023-08-28 | 2023-08-28 | Multi-dimensional linkage monitoring and processing method and system for faults of adhesive tape machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311087810.0A CN116969148A (en) | 2023-08-28 | 2023-08-28 | Multi-dimensional linkage monitoring and processing method and system for faults of adhesive tape machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116969148A true CN116969148A (en) | 2023-10-31 |
Family
ID=88473149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311087810.0A Pending CN116969148A (en) | 2023-08-28 | 2023-08-28 | Multi-dimensional linkage monitoring and processing method and system for faults of adhesive tape machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116969148A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117302897A (en) * | 2023-11-23 | 2023-12-29 | 常州市传动输送机械有限公司 | Intelligent monitoring prevention and control method and system for belt conveyor |
-
2023
- 2023-08-28 CN CN202311087810.0A patent/CN116969148A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117302897A (en) * | 2023-11-23 | 2023-12-29 | 常州市传动输送机械有限公司 | Intelligent monitoring prevention and control method and system for belt conveyor |
| CN117302897B (en) * | 2023-11-23 | 2024-01-26 | 常州市传动输送机械有限公司 | Intelligent monitoring prevention and control method and system for belt conveyor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101730450B1 (en) | System for monitoring spot equipment using active black box and method therefor | |
| CN104590852B (en) | Belt based on laser ranging detects alarm system | |
| CN116969148A (en) | Multi-dimensional linkage monitoring and processing method and system for faults of adhesive tape machine | |
| CN111932709A (en) | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification | |
| CN107733905A (en) | A kind of detection method of industry control network unit exception flow | |
| CN112112629A (en) | Safety business management system and method in drilling operation process | |
| CN113381511A (en) | Online intelligent inspection system of transformer substation | |
| KR20220085125A (en) | Safety management system using unmanned detector | |
| KR102056564B1 (en) | Method And Apparatus for Managing Facility by using Machine Vision | |
| CN208732382U (en) | Elevator signal acquisition device and system | |
| CN111028452A (en) | Transformer substation foreign matter intrusion monitoring system and method | |
| KR102592291B1 (en) | System and method for monitoring unmanned-office using mobile robot | |
| CN102740112A (en) | Method for controlling equipment polling based on video monitoring system | |
| CN117977813B (en) | Remote intelligent inspection system for transformer substation | |
| CN114495312A (en) | Online inspection method, device, system and storage medium | |
| CN110430261A (en) | Detecting devices fault handling method and device | |
| Xie et al. | On‐line physical security monitoring of power substations | |
| CN109416863B (en) | Monitoring system for security technology | |
| CN116506278A (en) | Abnormal monitoring platform based on zabbix | |
| CN116316233A (en) | Intelligent substation inspection system, method, equipment and storage medium | |
| KR101996237B1 (en) | DEVICE AND PLATFORM FOR IoT SENSOR THROUGH DISTRIBUTED PROCESSING | |
| CN115100812A (en) | Intelligent security monitoring method, system and device and electronic equipment | |
| KR20120118339A (en) | Method for unmanned surveillance services | |
| CN114584979A (en) | Method and system for sniffing network behavior of mobile terminal user | |
| CN111245643B (en) | IT asset monitoring method and system |
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 |