CN108776452B - Special equipment field maintenance monitoring method and system - Google Patents
Special equipment field maintenance monitoring method and system Download PDFInfo
- Publication number
- CN108776452B CN108776452B CN201810511921.2A CN201810511921A CN108776452B CN 108776452 B CN108776452 B CN 108776452B CN 201810511921 A CN201810511921 A CN 201810511921A CN 108776452 B CN108776452 B CN 108776452B
- Authority
- CN
- China
- Prior art keywords
- maintenance
- data
- field
- project
- special 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.)
- Active
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 469
- 238000012544 monitoring process Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 99
- 230000008569 process Effects 0.000 claims abstract description 30
- 230000003993 interaction Effects 0.000 claims abstract description 25
- 238000013480 data collection Methods 0.000 claims abstract description 9
- 230000003068 static effect Effects 0.000 claims description 44
- 230000002159 abnormal effect Effects 0.000 claims description 36
- 230000006870 function Effects 0.000 claims description 30
- 238000001514 detection method Methods 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 15
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 5
- 230000033001 locomotion Effects 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 abstract description 13
- 230000000694 effects Effects 0.000 abstract description 9
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000012549 training Methods 0.000 abstract description 5
- 238000007689 inspection Methods 0.000 description 9
- 208000024891 symptom Diseases 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000008531 maintenance mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/048—Monitoring; Safety
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of special equipment maintenance, in particular to a special equipment field maintenance monitoring method and system, which comprises the following steps: A1) synchronizing the file data of the target special equipment to the field equipment; A2) starting maintenance project monitoring, starting field data collection by field equipment, identifying a running maintenance project, judging whether the running maintenance project is a maintenance project with a correct flow, if so, continuing to collect the field data until the maintenance project is finished, and if not, sending a warning and restarting the step; A3) and the field device performs data interaction with the big data server. The substantial effects of the invention are as follows: 1. project level monitoring can be performed on the maintenance process, the analysis amount of monitoring data is reduced, and the monitoring efficiency is improved; 2. and a set field data acquisition project is added in the maintenance project monitoring, and training data is provided for the neural network model.
Description
Technical Field
The invention relates to the technical field of equipment maintenance, in particular to a special equipment field maintenance monitoring method and system.
Background
The special equipment refers to boilers, pressure vessels, pressure pipelines, elevators, hoisting machinery, passenger transport ropeways, large-scale amusement facilities and special motor vehicles in fields which are safe to life and have high dangerousness. When the special equipment breaks down, the personal injury of uncertain personnel is easily caused, and the death accident of the personnel can be caused seriously. Therefore, it is necessary to ensure safe and stable operation of the special equipment. Therefore, the country has strict regulations on various special equipment in three links of production, use, inspection and detection, and implements whole-course supervision and mandatory maintenance. At present, the quality inspection of special equipment in the production stage is more perfect. However, the special equipment maintenance mechanism in China has many problems, and the later use and maintenance inspection links are weak. At present, 80% of failures and accidents of special equipment are caused by inadequate later maintenance. At present, the main problem of limiting the maintenance quality of special equipment is that the service level and the service quality of maintenance personnel are different. The phenomena of false maintenance, no output of force and the like in the maintenance work are very serious, so that the special equipment almost runs without maintenance for a long time, and the potential safety hazard is very large. Therefore, methods and products for supervising field maintenance gradually appear in the market. In the existing products, the most mature scheme is that a certain supervision effect is achieved by positioning and maintaining the positions of operators through a GPS and recording the audio and video in the whole process, but a large amount of subsequent audio and video manual analysis and supervision are needed, the labor investment is huge, and the effect is very little. Therefore, there is an urgent need to develop an effective and targeted maintenance monitoring method.
Chinese patent CN 203366378U, published 2013, 12 and 25, a special equipment mobile maintenance system, which comprises a server, a management terminal, a front-end processor, a router, an Internet of things intelligent terminal and a handheld printer; the server is respectively connected with the management terminal and the front-end processor in a wireless network mode, the router is respectively connected with the front-end processor and the intelligent terminal of the Internet of things in a wireless network mode, and the handheld printer is connected to the intelligent terminal of the Internet of things through a short-distance wireless communication technology; the intelligent terminal of the Internet of things is provided with an identity verification module, an electronic tag automatic identification module, a positioning module and a field data entry module. Adopt the utility model discloses can realize that special equipment dimension protects the electron of work and send an order, dimension and protect personnel authentication, dimension and protect functions such as real-time supervision of work, improved the efficiency of special equipment dimension and protected the work and to dimension and protect staff's supervision dynamics. Although the system can carry out identity verification and electronic order distribution on maintenance personnel and can carry out character entry, sound entry and image entry on site, supervision lacks pertinence, a large amount of useless information is generated in the maintenance process, and the problems that supervision is not in place still exist and analysis cannot be timely processed and analyzed in the later period.
Chinese patent CN 105173929 a, published 2015, 12/23, elevator data collection system and method of operation thereof includes: the elevator data collection terminal is used for collecting the running state data of the elevator and sending the running state data to the data background server, wherein the running state data comprises one or more of the following data: running speed, oscillation amplitude, braking capacity, fault signals and maintenance data; the data background server is used for analyzing and storing the running state data to generate an elevator database; and sending the data in the elevator database to terminal equipment corresponding to the elevator, wherein the terminal equipment comprises one or more of the following components: terminal equipment of a supervision agency of the elevator, terminal equipment of a maintenance unit of the elevator and terminal equipment of an elevator owner. The invention can collect the running state data of the elevator, analyze and arrange the running state data, and provide the analyzed and arranged running state data for each relevant department of the elevator, thereby facilitating the management and control of the elevator by each relevant department of the elevator. The elevator monitoring system can judge whether the whole elevator is abnormal or not through sensor data, but cannot indicate which parts of the elevator have the abnormality or the faults, and cannot provide effective reference for elevator maintenance. The data collection is only used for message distribution, and the data collection is not targeted.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: at present, an effective monitoring method is lacked for field maintenance of special equipment, and the technical problem that the maintenance quality is difficult to guarantee due to poor monitoring precision is solved. The method and the system for monitoring the field maintenance of the special equipment have high monitoring accuracy and can carry out project-level maintenance monitoring.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a special equipment field maintenance monitoring method is suitable for a monitoring system comprising a big data server and field equipment, and comprises the following steps: A1) synchronizing the file data of the target special equipment to the field equipment; A2) starting maintenance project monitoring, starting field equipment to collect field data, identifying an ongoing maintenance project by the field equipment according to the collected field data, judging whether the ongoing maintenance project is a maintenance project with a correct flow according to target special equipment archive data, if so, continuing to collect the field data until the maintenance project is finished, and if not, sending a warning and restarting the step; A3) and the field device performs data interaction with the big data server. The field device has video recording, man-machine interaction, storage and operation functions. Project maintenance field data acquired by field equipment are specifically triggered to be started and finished, so that the amount of useless information is greatly reduced, subsequent analysis and supervision are very convenient, and the deterrent effect of field monitoring on maintenance personnel can be effectively improved. In the process of acquiring the field data, the field equipment simultaneously identifies the maintenance project, bears part of the subsequent analysis work, further lightens the workload of the subsequent field data analysis and supervision, and improves the supervision deterrence and supervision effect.
Preferably, the target special equipment archive data includes identification information of the target special equipment and an identification feature set of the maintenance project. The identification information can allow the field device to mark the field information of a plurality of special devices, the maintenance of the special devices can be processed simultaneously, and the accuracy and efficiency of identifying the maintenance project by the field device can be improved through the maintenance project identification feature set.
Preferably, the identification feature set of the maintenance project comprises a device feature set and a maintenance action feature set. The equipment feature set is used for identifying whether the maintenance personnel are located at the correct maintenance project part, and the maintenance action feature set can judge whether the maintenance personnel are performing maintenance actions and whether the maintenance actions are unreasonable.
Preferably, the device feature set includes a device static feature set and a device running dynamic feature set. Whether maintenance personnel are located at the correct maintenance position or not and whether the characteristic equipment components are damaged or not can be judged through the equipment static characteristic set. The equipment operation dynamic feature set can judge whether the maintenance personnel perform dynamic inspection when performing maintenance projects which need dynamic inspection.
In the technical scheme, the extraction of the static characteristics mainly comprises the following steps: the static pattern is obtained, the characteristic points in the static pattern are extracted, the characteristic points in the static pattern are compared with the standard static characteristic points of the set project to be maintained, and the current static characteristic meeting the requirement is determined as the standard static characteristic of the maintenance project, in the technical scheme, the static pattern is instantly finished, the comparison of the static characteristic points can be quickly finished after the input of the static pattern is finished, when the maintenance project is started, whether the current maintenance personnel reach the correct position for maintenance or not can be judged through the static characteristic points, namely, the maintenance arrival rate known in the industry is monitored, after the current maintenance personnel are judged to be in place in a very short time, the static characteristic can be used as the standard static characteristic for extracting the dynamic characteristic, the current static characteristic can be further analyzed when the dynamic characteristic is extracted, generally speaking, when the dynamic feature extraction is completed, the further analysis of the static features can be completed, and some preliminary maintenance data or results of the current maintenance project can be obtained; in practical application, when the maintenance staff use the system, only the field equipment is needed to be used for photographing and recording videos, and when the videos are recorded, some preliminary maintenance data or results of the current maintenance project can be obtained, so that the preliminary maintenance data or results can be obtained without changing the maintenance process by combining the work process of the original maintenance staff; according to the technical scheme, the data extracted by the static features are reasonably utilized, and on one hand, the data are used as the features of the maintenance project identification to monitor the arrival rate of maintenance personnel; on the other hand, the static feature extraction data is judged to be the time axis reference point extracted by the dynamic feature, so that the overall time is saved, the working process of the original maintenance personnel is combined, and the maintenance process is not changed; finally, the static characteristics are used for preliminary judgment of project maintenance, and the static characteristics are used as the reference static characteristics for extraction of dynamic characteristics, so that the accuracy of field monitoring data is improved.
Preferably, the method for starting the monitoring of the maintenance project comprises the following steps: B1) the method comprises the following steps that field equipment collects field data and intermittently extracts the characteristics of the collected field data; B2) comparing the field data characteristics with the identification characteristic sets of all the maintenance projects, if the identification characteristic set of at least one maintenance project is matched with the field data characteristics, starting the monitoring of the maintenance projects, and otherwise, executing the step B1 again; B3) and merging the field data between the successful matching and the last matching of the successful matching into the field data of the maintenance project, and marking the data which is successfully matched. In the maintenance process, the maintenance personnel can reduce the operation burden of the maintenance personnel by adopting the mode of automatically identifying the field data and starting the maintenance project monitoring when the hands of the maintenance personnel are busy or stained with dirt.
Preferably, the field information includes maintenance personnel voice and/or image information. In the process of field data identification, personnel identity identification can be carried out simultaneously, for example, when sounds with two different voiceprint characteristics are detected or a picture of an irrelevant person appears in picture display interaction, marking is carried out and a maintenance person is prompted to operate according to a maintenance procedure.
Preferably, the method for the field device to identify an ongoing maintenance project comprises the steps of: C1) extracting the characteristics of the field data; C2) and C1, comparing the field data features with the identification feature sets of all the maintenance items, if the identification feature set of one maintenance item is matched with the field data features, taking the maintenance item as an ongoing maintenance item, and otherwise, re-executing the step C1.
Preferably, the field data is a field image and/or a field video, the characteristics of the field data are image color block contour characteristics, and the identification feature set of the maintenance project is an image color block contour feature set formulated according to a maintenance project rule.
Preferably, the target special device archive data includes a maintenance item table, before performing data interaction with the big data server, the field device determines whether the current maintenance completes all maintenance items according to the maintenance item table, if so, performs data interaction with the big data server, and if not, performs step a 2. When the maintenance task is more than one maintenance item, whether maintenance items are omitted or the maintenance items are in wrong sequence can be judged according to the item table, the later data analysis and supervision work is undertaken, and the monitoring strength and effect are improved.
Preferably, the target special equipment archive comprises target special equipment sensor monitoring data, and the maintenance project table is formulated according to the sensor monitoring data and/or target special equipment maintenance regulations. When the sensor detects an abnormality or a fault, related maintenance items can be automatically added or marked, and if the related maintenance items are marked as key maintenance items, maintenance personnel are prompted to perform key maintenance inspection.
Preferably, the target special equipment archive comprises target special equipment sensor monitoring data and a sensor monitoring data analysis result, and when the sensor monitoring data is in a normal range and is long enough, relevant maintenance task items in the next maintenance task are removed.
Preferably, the sensor comprises a sensor owned by the target specific device and/or an additional sensor. The special equipment can be monitored more finely by additionally arranging the sensor, more accurate fault or abnormal prediction can be obtained, and maintenance personnel can be guided to improve the maintenance efficiency. A large number of sensor data samples which are owned and/or added are obtained and serve as data bases for artificial intelligence model learning after being marked artificially, artificial intelligence training is conducted, fault monitoring capacity is improved, workload of maintenance and detection personnel is reduced, and a foundation is provided for automatic special equipment maintenance and fault early warning of follow-up introduced artificial intelligence.
Preferably, the method for creating the maintenance item table comprises the following steps: and tracking sensor monitoring data, and when fault characteristics are detected, taking the maintenance items related to the faults as a maintenance item table according to the maintenance rule sequence of the target special equipment.
Preferably, the method for creating the maintenance item table comprises the following steps: and (4) formulating a maintenance project table according to the maintenance regulation of the target special equipment, tracking the monitoring data of the sensor, and marking the maintenance projects related to the abnormality when the abnormal characteristics are detected.
Preferably, the target special equipment archive comprises historical maintenance data, and the maintenance project table is made according to the historical maintenance data and/or target special equipment maintenance rules. When the historical maintenance data is abnormal, the related maintenance items are independently formulated into a maintenance task once or marked in the next maintenance task, and the maintenance personnel are prompted to perform key maintenance and inspection.
Preferably, the method for creating the maintenance item table comprises the following steps: and tracking historical maintenance data, and when the fault characteristics are detected, taking the maintenance items related to the fault as a maintenance item table according to the maintenance rule sequence of the target special equipment.
Preferably, the method for creating the maintenance item table comprises the following steps: and (4) formulating a maintenance project table according to the maintenance regulation of the target special equipment, tracking historical maintenance data, and marking the maintenance projects related to the abnormity when the abnormal characteristics are detected.
Preferably, the method for establishing the fault characteristics of the sensor monitoring data comprises the following steps: setting a simulation fault on the special equipment, and reading data of the sensor as a fault characteristic of the sensor data.
Preferably, the method for establishing the abnormal characteristics of the sensor monitoring data comprises the following steps: and (4) setting interference factors on the special equipment, and reading data of the sensor as abnormal characteristics of the sensor data.
Preferably, the method for detecting the abnormal feature by monitoring the data by the tracking sensor comprises the following steps: and if the detected sensor data accords with the abnormal characteristics or exceeds the corrected value of the average value of the historical monitoring data according to the trend function, judging that the sensor monitoring data accords with the abnormal characteristics.
Preferably, the method for detecting the fault characteristic and the abnormal characteristic of the history maintenance data comprises the following steps: establishing a neural network model, providing historical maintenance data marked with fault or abnormal information by manpower for the neural network model to learn, and importing the maintenance data to be identified into the neural network model to identify fault characteristics or abnormal characteristics.
Preferably, when the quantity of the accumulated sample data reaches a set value, the neural network model automatically adds a plurality of set characteristic value nodes, and the set characteristic value nodes are manually set when the neural network model is built. The characteristic value setting nodes are used for learning when the data samples are learned, but do not participate in the judgment of the result when the number of the sample data does not reach the set value, and a plurality of characteristic value setting nodes all participate in the judgment of the result when the number of the sample data reaches the set value.
Preferably, the maintenance data comprises standard field data and added field data, the standard field data is field data acquired by field equipment in a maintenance process of a maintenance project established according to a maintenance regulation of the special equipment, and the added field data is field data acquired by a field data acquisition project set according to a fault symptom and/or a fault sign of the special equipment.
Preferably, when the maintenance project is finished, the field device judges whether the quality of the finished maintenance project reaches the standard according to the field data, if so, the maintenance project is marked as reaching the standard, and if not, a signal is sent out and the maintenance project is restarted. Whether the maintenance project reaches the standard or not is analyzed through the field data, and part of later-stage field data analysis and monitoring work is undertaken, so that the monitoring effect is improved.
Preferably, the target special equipment archive comprises a maintenance project verification feature set, and the method for judging whether the quality of the finished maintenance project reaches the standard by the field equipment according to the field data comprises the following steps: D1) setting up field data acquisition add-on projects according to the maintenance projects; D2) judging whether the finished maintenance project belongs to a background judgment project, if so, marking that the maintenance project reaches the standard, otherwise, entering a step D3, wherein the background judgment project is manually set according to the complexity of the maintenance project, and the quality of the maintenance project reaches the standard by a big data server; D3) extracting the field data characteristics acquired by the field data acquisition add-on project, comparing the field data characteristics with the maintenance project verification characteristic set, marking that the maintenance project reaches the standard if the matched characteristics exist, and sending a signal and restarting the maintenance project if the matched characteristics do not exist. The field equipment has limited computing capability, so that whether the simple maintenance project reaches the standard or not can be judged, and the complex maintenance project is judged by the big data server.
Preferably, the method for establishing the verification feature set of the maintenance project comprises the following steps: and performing data acquisition of the additional field data acquisition project in the normally running special equipment, and extracting the characteristics of the field data acquired by the additional field data acquisition project to serve as a maintenance project verification characteristic set.
Preferably, the field data collection of the additional field data collection item includes field data collection before the maintenance item starts and after the maintenance item ends. By acquiring the field data before and after the project maintenance and comparing the field data, the difficulty of whether the maintenance project reaches the standard can be reduced, the data jump errors of different specifications can be offset, and the data sample can be used as a data sample for training the artificial intelligent model.
Preferably, the maintenance data comprises standard field data and added field data, the standard field data is field data acquired by field equipment in a maintenance process of a maintenance project established according to a maintenance regulation of the special equipment, and the added field data is field data acquired by a field data acquisition project set according to a fault symptom and/or a fault sign of the special equipment.
Preferably, when the field device performs data interaction with the big data server, the collected field data and the marking information of the field data are uploaded to the big data server; the marking information comprises target special equipment identification information, a maintenance project result and a maintenance result; and the big data server updates the file of the target special equipment and generates a health report and a fault prediction of the special equipment according to the latest file.
A special equipment field maintenance monitoring system is suitable for the special equipment field maintenance monitoring method, and comprises a big data server and field equipment; the big data server executes the following steps: D1) storing the archive data of the target special equipment; D2) after the maintenance is finished, data interaction is carried out with the field equipment; the field device performs the steps of: E1) before maintenance, target special equipment archive data are sent to field equipment; E2) starting maintenance project monitoring, starting field equipment to collect field data, identifying an ongoing maintenance project by the field equipment according to the collected field data, judging whether the ongoing maintenance project is a maintenance project with a correct flow according to target special equipment archive data, if so, continuing to collect the field data until the maintenance project is finished, and if not, sending a warning and restarting the step; E3) and after the maintenance is finished, the field device performs data interaction with the big data server. The field device has the function of acquiring one or more of on-site audio, video and images, and the field device has the functions of displaying, storing and operating.
The substantial effects of the invention are as follows: 1. project level monitoring can be performed on the maintenance process, the analysis amount of monitoring data is reduced, and the monitoring accuracy and efficiency are improved; 2. and a set field data acquisition project is added in the maintenance project monitoring, so that training data is provided for the neural network model, and the follow-up monitoring accuracy is further improved.
Drawings
FIG. 1 is a diagram of a maintenance project monitoring system.
FIG. 2 is a flow chart of a maintenance project monitoring method.
Wherein: 100. the system comprises a big data server, 200, a field device, 201, a data interaction module, 202, a processor, 203, a memory, 204, an audio recording module, 205, a video recording module, 206 and a display module.
Detailed Description
The following provides a more detailed description of the present invention, with reference to the accompanying drawings.
As shown in fig. 1, the structure of the maintenance project monitoring system includes a big data server 100 and a field device 200, where the field device 200 includes a processor 202, a memory 203, a data exchange module 201, an audio recording module 204, a video recording module 205, and a display module 206, the data exchange module 201 is connected to the big data server 100, and the data exchange module 201, the memory 203, the audio recording module 204, the video recording module 205, and the display module 206 are all connected to the processor 202. Wherein the display module 206 may be replaced by a language prompt module. The big data server 100 performs the following steps: D1) storing the archive data of the target special equipment; D2) after the maintenance is finished, data interaction is carried out with the field device 200; the field device 200 performs the following steps: E1) before the maintenance starts, target special equipment archive data is sent to the field equipment 200; E2) starting maintenance project monitoring, starting field equipment 200 to collect field data, identifying an ongoing maintenance project by the field equipment 200 according to the collected field data, judging whether the ongoing maintenance project is a maintenance project with a correct flow according to target special equipment archive data, if so, continuing to collect the field data until the maintenance project is finished, and if not, sending a warning and restarting the step; E3) after the maintenance is completed, the field device 200 performs data interaction with the big data server 100.
As shown in fig. 2, a flow chart of a maintenance project monitoring method includes the following steps: A1) synchronizing the target specific device profile data to the field device 200; A2) starting maintenance project monitoring, starting field equipment 200 to collect field data, identifying an ongoing maintenance project by the field equipment 200 according to the collected field data, judging whether the ongoing maintenance project is a maintenance project with a correct flow according to target special equipment archive data, if so, continuing to collect the field data until the maintenance project is finished, and if not, sending a warning and restarting the step; A3) the field device 200 interacts with the big data server 100.
The target special equipment archive data comprises identification information of the target special equipment and an identification feature set of the maintenance project. The identification feature set of the maintenance project comprises a device feature set and a maintenance action feature set. The device feature set includes a device static feature set and a device operational dynamic feature set.
The method for starting the maintenance project monitoring is started through non-contact human-computer interaction. The non-contact human-computer interaction is one or the combination of more than two of sound input interaction, scene recognition interaction and video recognition interaction. The method for monitoring the scene recognition interactive opening maintenance project comprises the following steps: B1) the field device 200 collects field data and intermittently extracts the characteristics of the collected field data; B2) comparing the field data characteristics with the identification characteristic sets of all the maintenance projects, if the identification characteristic set of at least one maintenance project is matched with the field data characteristics, starting the monitoring of the maintenance projects, and otherwise, executing the step B1 again; B3) and merging the field data between the successful matching and the last matching of the successful matching into the field data of the maintenance project, and marking the data which is successfully matched.
The method by which field device 200 identifies an ongoing maintenance project includes the steps of: C1) extracting the characteristics of the field data; C2) and C1, comparing the field data features with the identification feature sets of all the maintenance items, if the identification feature set of one maintenance item is matched with the field data features, taking the maintenance item as an ongoing maintenance item, and otherwise, re-executing the step C1.
The target special device archive data comprises a maintenance project table, before the field device 200 performs data interaction with the big data server 100, whether the current maintenance completes all maintenance projects according to the maintenance project table is judged, if yes, data interaction is performed with the big data server 100, and if not, the step A2 is executed. If other projects are not completed in the maintenance task after the maintenance of the elevator car door opening/closing project is finished, the field device 200 prompts a maintenance worker to maintain the next project.
The target special equipment archive comprises target special equipment sensor monitoring data, and the maintenance project table is formulated according to the sensor monitoring data and/or target special equipment maintenance regulations. The target special equipment archive comprises target special equipment sensor monitoring data, and when the sensor monitoring data are in a normal range and are long enough, relevant maintenance task items in the next maintenance task are removed. The sensor comprises a sensor of the target special equipment and/or an additional sensor. The method for making the maintenance project table comprises the following steps: and tracking sensor monitoring data, and when fault characteristics are detected, taking the maintenance items related to the faults as a maintenance item table according to the maintenance rule sequence of the target special equipment. The method for making the maintenance project table comprises the following steps: and (4) formulating a maintenance project table according to the maintenance regulation of the target special equipment, tracking the monitoring data of the sensor, and marking the maintenance projects related to the abnormality when the abnormal characteristics are detected.
The target special equipment archive comprises historical maintenance data, and the maintenance project table is formulated according to the historical maintenance data and/or the maintenance regulations of the target special equipment. When the historical maintenance data is abnormal, the related maintenance items are independently formulated into a maintenance task once or marked in the next maintenance task, and the maintenance personnel are prompted to perform key maintenance and inspection. In the first embodiment, if the monitoring data of the speed sensor arranged on the car door is abnormal, the car door opening/closing maintenance items are marked for key maintenance. And (3) extracting car door opening/closing characteristics from the uploaded maintenance data to obtain a car door opening/closing function curve, marking car door opening/closing maintenance items if the car door opening/closing function curve function jumps beyond a threshold value after maintenance is finished, and prompting maintenance personnel to perform key maintenance inspection.
The method for making the maintenance project table comprises the following steps: and tracking historical maintenance data, and when the fault characteristics are detected, taking the maintenance items related to the fault as a maintenance item table according to the maintenance rule sequence of the target special equipment. The method for making the maintenance project table comprises the following steps: and (4) formulating a maintenance project table according to the maintenance regulation of the target special equipment, tracking historical maintenance data, and marking the maintenance projects related to the abnormity when the abnormal characteristics are detected.
The method for establishing the fault characteristics of the sensor monitoring data comprises the following steps: setting a simulation fault on the special equipment, and reading data of the sensor as a fault characteristic of the sensor data. The method for establishing the abnormal characteristics of the sensor monitoring data comprises the following steps: and (4) setting interference factors on the special equipment, and reading data of the sensor as abnormal characteristics of the sensor data.
The method for detecting the abnormal features by monitoring data by the tracking sensor comprises the following steps: and if the detected sensor data accords with the abnormal characteristics or exceeds the corrected value of the average value of the historical monitoring data according to the trend function, judging that the sensor monitoring data accords with the abnormal characteristics.
The detection method of the fault characteristics and the abnormal characteristics of the historical maintenance data comprises the following steps: establishing a neural network model, providing historical maintenance data marked with fault or abnormal information by manpower for the neural network model to learn, and importing the latest maintenance data into the neural network model to identify fault characteristics or abnormal characteristics.
The maintenance data includes standard field data and added field data, the standard field data is field data acquired by the field device 200 in the maintenance process of the maintenance project established according to the maintenance regulation of the special device, and the added field data is field data acquired by the field data acquisition project set according to the fault symptom and/or fault sign of the special device.
When the maintenance project is completed, the field device 200 judges whether the quality of the completed maintenance project reaches the standard according to the field data, if so, the maintenance project is marked as having reached the standard, and if not, a signal is sent out and the maintenance project is restarted. Whether the maintenance project reaches the standard or not is analyzed through the field data, and part of later-stage field data analysis and monitoring work is undertaken, so that the monitoring effect is improved.
The target special equipment file comprises a maintenance project verification feature set, and the method for judging whether the quality of the finished maintenance project reaches the standard or not by the field equipment 200 according to the field data comprises the following steps: D1) setting up field data acquisition add-on projects according to the maintenance projects; D2) judging whether the finished maintenance project belongs to a background judgment project, if so, marking that the maintenance project reaches the standard, otherwise, entering a step D3, wherein the background judgment project is manually set according to the complexity of the maintenance project, and the quality of the maintenance project reaches the standard by the big data server 100; D3) extracting the field data characteristics acquired by the field data acquisition add-on project, comparing the field data characteristics with the maintenance project verification characteristic set, marking that the maintenance project reaches the standard if the matched characteristics exist, and sending a signal and restarting the maintenance project if the matched characteristics do not exist. The field device 200 has limited computing power, and can perform judgment on whether a simpler maintenance project reaches the standard or not, and a complex maintenance project is judged by the big data server 100.
The method for establishing the verification feature set of the maintenance project comprises the following steps: and performing data acquisition of the additional field data acquisition project in the normally running special equipment, and extracting the characteristics of the field data acquired by the additional field data acquisition project to serve as a maintenance project verification characteristic set.
The field data acquisition of the field data acquisition project is additionally arranged and comprises the field data acquisition before the maintenance project is started and after the maintenance project is finished. By collecting the field data before and after the project maintenance and comparing the field data, the difficulty of whether the maintenance project reaches the standard can be reduced, the data jump errors of different specifications can be counteracted, meanwhile, the field data can be used as a data sample for training an artificial intelligence model, and the field data before the project is started can be manually marked and then used as a data sample for learning a neural network model for fault prediction.
The maintenance data includes standard field data and added field data, the standard field data is field data acquired by the field device 200 in the maintenance process of the maintenance project established according to the maintenance regulation of the special device, and the added field data is field data acquired by the field data acquisition project set according to the fault symptom and/or fault sign of the special device.
When the field device 200 performs data interaction with the big data server 100, uploading the collected field data and the marking information of the field data to the big data server 100; the marking information comprises identification information of the target special equipment, a maintenance project result and a maintenance result; the big data server 100 updates the target special equipment archive and generates a health report and a fault prediction of the special equipment according to the latest archive.
In the first embodiment, the maintenance of the open/close of the elevator car door is taken as an example, and the maintenance of the open/close of the elevator car door is performed according to the following method: e1, storing at least the following data of the target special equipment on the big data server 100 as the archive data of the target special equipment: a) the system comprises an elevator model, b) the model of an elevator car door, c) image characteristic data of the car door, d) image characteristic data of a device related to the opening/closing of the car door, e) a speed curve of a normal car door switch, f) a normal movement speed curve of the device related to the opening/closing of the car door (in a function form or a parameter form of a function), g) data of an acceleration sensor installed on the car door, h) a fault pre-judgment result of a big data server 100 (judgment made by data returned by the site), i) last maintenance time, a maintenance result and a device replacement record; wherein the image characteristic data comprises: the shape of the door, the relative ratio of the door edge length, the color and texture of the door, whether the door is symmetrical along the middle during opening/closing, the shape of the doorframe, the relative ratio of the door edge length, and the color and texture of the doorframe; e2, after the maintenance worker carries the field device 200 to a target special device, a voice control command or a gesture command is sent, the maintenance project monitoring of whether the car door is normally opened or closed is started, namely, the field device 200 starts the video input module 205 to input a field image, meanwhile, the processor 202 extracts the characteristics of the input image information, the characteristics of the image information are the current static characteristics of the car door and are compared with the image characteristic data in the downloaded file number of the target special device, whether the maintenance device of the maintenance worker is the car door of the current maintenance target elevator is judged, if yes, the verification is passed, the current static characteristics are determined to be the standard static characteristics of the current maintenance project, and if not, an error prompt is sent and the step is restarted; e3, the maintenance personnel sends out a command of 'detecting the opening of the car door' through sound or gestures, the field device 200 starts recording video and carries out maintenance item identification, whether the maintenance personnel is carrying out maintenance of the car door opening item is judged, the processor collects static characteristics of set frames (or each frame, the setting mode is determined manually) in the maintenance image information and associates the static characteristics with the maintenance time, the associated static characteristics are compared with the reference static characteristics to obtain the dynamic characteristics of the current car door maintenance, through extracting the set parameters in the dynamic characteristics, a speed curve (which can be in a function form or a parameter form of the function, the form is adapted to the archive data) of the car door in the car door opening process is obtained, the speed curve is compared with the downloaded archive data, whether the car door opening process is normal is judged according to the difference degree of the function, the judgment can be in a form of attaching to the function, the comparison may be performed in the form of a threshold comparison or a weighted function comparison, the comparison in the form of a threshold is the simplest, and the field device 200 sends out a "detection normal" if it can be determined to be normal within the threshold range, otherwise, a "detection abnormal" signal if it exceeds the threshold range; when a maintenance worker sends a command of detecting car door closing through sound or gestures, the field device 200 starts recording video and performs maintenance item identification, judges whether the maintenance worker is performing car door closing item maintenance, collects a speed curve of the car door in the car door closing process and compares the speed curve with downloaded archive data (the method is the same as the above content and is not repeated), judges whether the car door closing process is normal, if so, the field device 200 sends 'detection normal', otherwise, sends 'detection abnormal'; e4, after the maintenance project is completed, the acceleration sensor installed on the car door uploads the collected data to the big data server 100 in real time, the big data server 100 compares the previous data or state, such as door opening and closing function, acceleration and speed curve, and meanwhile, the video data recorded by the field device 200 is also uploaded to the big data server 100; the big data server 100 updates the archive data of the target special equipment; if the big data server 100 finds that the sensor data is abnormal before maintenance, judging whether the signs disappear according to the sensor data after maintenance or the field data collected in the maintenance process, if not, submitting an artificial mark, and classifying the marked data into an effective sample as sample data for subsequent neural network learning judgment, wherein the sample data source for the neural network learning also comprises a maintenance example which is marked by the artificial and does not have a fault; the failure pre-judgment result of the big data server 100 is comprehensively judged by a neural network according to a) the model of the elevator, b) the model of the elevator car door, c) the image characteristic data of the car door, d) the image characteristic data of the device related to the opening/closing of the car door, e) the speed curve of the normal car door switch, f) the normal movement speed curve of the device related to the opening/closing of the car door (in a functional form or a parameter form of a function), g) the data of an acceleration sensor installed on the car door, i) the last maintenance time, the maintenance result and the device replacement record. The construction of the neural network refers to the existing maintenance neural network; as an improvement, when the quantity of the accumulated sample data reaches a set value, the neural network model automatically adds a plurality of set characteristic value nodes, the set characteristic value nodes are set manually when the neural network model is built, the set characteristic value nodes are learned when the data sample is learned, but the set characteristic value nodes do not participate in the judgment of the result when the quantity of the sample data does not reach the set value, and the set characteristic value nodes participate in the judgment of the result when the quantity of the sample data reaches the set value.
In the second embodiment, the project maintenance of the hauling wheel of the hoisting machinery is carried out by adopting the field maintenance monitoring according to the following method: f1, storing the following data of the target special equipment on the big data server 100 as the archive data of the target special equipment: a) the model of the hoisting machinery, b) the model of the dragging wheel, c) the image characteristic data of the dragging wheel, d) the image characteristic data of a device related to the operation of the dragging wheel, e) the speed curve of the normal operation of the dragging wheel, f) the normal motion speed curve of the device related to the operation of the dragging wheel, f) the fault pre-judgment result of the big data server 100, g) the last maintenance time, the maintenance result and the device replacement record; wherein the image characteristic data comprises: the method comprises the following steps of (1) completely or partially but at least two of dragging wheel color, dragging wheel texture, the number of corners of the polygonal dragging wheel outline, the corner smoothness of the polygonal dragging wheel outline and the relative positions of the corners of the polygonal outline; the speed curve of the normal operation of the dragging wheel comprises an angular speed and angular acceleration curve during dragging and an angular speed and angular acceleration curve of the dragging wheel during braking; f2, after the maintenance worker carries the field device 200 to the target special device, the field device 200 compares the collected field image information with the static characteristics of the pull wheel maintenance item in the downloaded archive data by collecting the field image information and extracting the field image static characteristics (which can be collected and extracted in connection with the field image characteristics or intermittently collected and extracted), if the field image static characteristics are matched with the static characteristics of the pull wheel maintenance item, the maintenance item monitoring is started, the field device 200 starts the video input module 205 to input the field image, meanwhile, the processor 202 extracts the characteristics of the input image information, the characteristics of the image information are the static characteristics of the pull wheel and are compared with the image characteristic data in the downloaded archive number of the target special device, whether the maintenance device of the maintenance worker is the pull wheel of the maintenance target crane is judged, if the maintenance device is the pull wheel of the maintenance target crane, the verification is prompted to pass, and the current static characteristics are determined as the reference static characteristics of the maintenance item, otherwise, sending out an error prompt and restarting the step; f3, the field device 200 intermittently records the video and extracts the dynamic characteristics, compares the dynamic characteristics with the downloaded file data (the dynamic characteristic extraction method is the same as the first embodiment), when the extracted item maintenance dragged by the field dynamic information dragging wheel is matched, judges that the maintenance personnel is maintaining the item dragged by the dragging wheel, the field device 200 starts recording and collects the angular velocity curve in the dragging wheel dragging process to be compared with the downloaded file data (the angular velocity curve can be in a function form or a parameter form of a function, and the form is suitable for the file data), judges whether the dragging wheel dragging process is normal, if the angular velocity curve is normal, the field device 200 sends out 'detection normal', otherwise, sends out 'detection abnormal', when the dynamic characteristics of the field information are matched with the dynamic characteristics of the downloaded detection dragging wheel brake, judges that the maintenance personnel is maintaining the item maintenance of the dragging wheel brake, the field device 200 starts recording and collects the velocity curve of the dragging wheel in the dragging wheel brake process and the downloaded file number According to the comparison, whether the brake process of the dragging wheel is normal or not is judged, if so, the field device 200 sends out 'detection normal', otherwise, sends out 'detection abnormal', the judgment method is the same as that of the first embodiment, and is not repeated; f4, after the maintenance project is completed, the angular velocity and angular acceleration sensors installed on the dragging wheel upload the collected data to the big data server 100 in real time, the big data server 100 compares the previous data or state, and meanwhile, the video data recorded by the field device 200 is also uploaded to the big data server 100; the big data server 100 updates the archive data of the target special equipment; if the big data server 100 finds that the sensor data is abnormal before maintenance, whether the symptom disappears is judged according to the sensor data after maintenance or the field data collected in the maintenance process, if the symptom does not disappear, a manual mark is submitted, and the marked data is classified into an effective sample to be used as sample data for subsequent neural network learning judgment.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (16)
1. A special equipment field maintenance monitoring method is suitable for a monitoring system comprising a big data server and field equipment and is characterized in that,
the method comprises the following steps:
A1) synchronizing the file data of the target special equipment to the field equipment;
A2) starting maintenance project monitoring, starting field equipment to collect field data, identifying an ongoing maintenance project by the field equipment according to the collected field data, judging whether the ongoing maintenance project is a maintenance project with a correct flow according to target special equipment archive data, if so, continuing to collect the field data until the maintenance project is finished, and if not, sending a warning and restarting the step;
A3) the field device and the big data server perform data interaction;
the maintenance items performed in the step A2) are the maintenance of the opening/closing items of the elevator car door,
the maintenance of the opening/closing project of the elevator car door is carried out according to the following method:
e1, storing at least the following data of the target special equipment on the big data server as the archive data of the target special equipment: a) the system comprises an elevator model, b) a model of an elevator car door, c) image characteristic data of the car door, d) image characteristic data of a device related to the opening/closing of the car door, e) a speed curve of a normal car door switch, f) a normal movement speed curve of the device related to the opening/closing of the car door, g) data of an acceleration sensor installed on the car door in a function form or a parameter form of a function, h) a fault pre-judging result of a big data server, judgment performed by data returned on site, i) last maintenance time, a maintenance result and device replacement record; wherein the image characteristic data comprises: the shape of the door, the relative ratio of the door edge length, the color and texture of the door, whether the door is symmetrical along the middle during opening/closing, the shape of the doorframe, the relative ratio of the door edge length, and the color and texture of the doorframe;
e2, after the maintenance personnel carry the field equipment to the target special equipment, the maintenance item monitoring of whether the car door is normally opened or closed is started after a voice control instruction or a gesture instruction is sent, namely, the field equipment starts a video input module to carry out field image input, meanwhile, a processor of the field equipment extracts the characteristics of input image information, the characteristics of the image information are the current static characteristics of the car door and are compared with image characteristic data in downloaded target special equipment archives, whether a maintenance device of a maintenance worker is the car door of the current maintenance target elevator is judged, if yes, verification is prompted to be passed, the current static characteristics are determined to be the standard static characteristics of the current maintenance item, and if not, an error prompt is sent and the step is restarted;
e3, the maintenance personnel sends out a command of 'detecting the opening of the car door' through sound or gestures, the field device starts to record video and carries out maintenance item identification, whether the maintenance personnel is carrying out maintenance of the car door opening is judged, a processor of the field device collects set frames or each frame in the maintenance image information, the set mode is determined manually, the static characteristics are associated with the maintenance time, the associated static characteristics are compared with the reference static characteristics to obtain the dynamic characteristics of the current car door maintenance, the speed curve of the car door in the car door opening process is obtained through extracting the set parameters in the dynamic characteristics, the function mode or the parameter mode of the function is adapted to the file data and is compared with the downloaded file data, whether the car door opening process is normal is judged according to the difference degree of the function, the judgment can be in the mode of being subordinate to the function, the comparison can be carried out in a threshold value comparison mode or a weighting function comparison mode, the comparison in the threshold value mode is simplest, the field device sends a 'detection normal' signal if the field device can be determined to be normal within a threshold value range, and otherwise, a 'detection abnormal' signal is sent if the field device exceeds the threshold value range; when a maintenance worker sends a command of detecting car door closing through sound or gestures, the field device starts recording video and carries out maintenance project identification, judges whether the maintenance worker is carrying out car door closing project maintenance, simultaneously collects a speed curve of the car door in the car door closing process and compares the speed curve with downloaded file data to judge whether the car door closing process is normal, if so, the field device sends detection normal, otherwise, sends detection abnormal;
e4, after the maintenance project is completed, the acceleration sensor arranged on the car door uploads the collected data to the big data server in real time, the big data server compares the previous data or state, including door opening and closing functions, acceleration and speed curves, and meanwhile, video data recorded by the field equipment is also uploaded to the big data server; the big data server updates the file data of the target special equipment; if the big data server finds that the sensor data is abnormal before maintenance, judging whether the sign disappears according to the sensor data after maintenance or the field data collected in the maintenance process, if not, submitting an artificial mark, and classifying the marked data into an effective sample as the sample data of subsequent neural network learning judgment, wherein the sample data source of the neural network learning also comprises a maintenance example which is marked by the artificial and does not have a fault; the fault pre-judgment result of the big data server is judged by a neural network according to a) the model of the elevator, b) the model of the elevator car door, c) the image characteristic data of the car door, d) the image characteristic data of a device related to the opening/closing of the car door, e) the speed curve of a normal car door switch, f) the normal movement speed curve of the device related to the opening/closing of the car door in a function form or a parameter form of a function, g) the data of an acceleration sensor installed on the car door, i) the last maintenance time, the maintenance result and the device replacement record.
2. A special equipment field maintenance monitoring method according to claim 1,
the target special equipment archive data comprises identification information of the target special equipment and an identification feature set of the maintenance project.
3. A special equipment field maintenance monitoring method according to claim 2,
the identification feature set of the maintenance project comprises a device feature set and a maintenance action feature set.
4. A special equipment field maintenance monitoring method according to claim 3,
the device feature set comprises a device static feature set and a device running dynamic feature set.
5. A special equipment field maintenance monitoring method according to claim 2, 3 or 4,
the method for starting the maintenance project monitoring comprises the following steps:
B1) the method comprises the following steps that field equipment collects field data and intermittently extracts the characteristics of the collected field data;
B2) comparing the field data characteristics with the identification characteristic sets of all the maintenance projects, if the identification characteristic set of at least one maintenance project is matched with the field data characteristics, starting the monitoring of the maintenance projects, and otherwise, executing the step B1 again;
B3) and merging the field data between the successful matching and the last matching of the successful matching into the field data of the maintenance project, and marking the data which is successfully matched.
6. A special equipment field maintenance monitoring method according to claim 2, 3 or 4,
the method for identifying an ongoing maintenance project by the field device comprises the following steps:
C1) extracting the characteristics of the field data;
C2) and C1, comparing the field data features with the identification feature sets of all the maintenance items, if the identification feature set of one maintenance item is matched with the field data features, taking the maintenance item as an ongoing maintenance item, and otherwise, re-executing the step C1.
7. A special equipment field maintenance monitoring method according to claim 1 or 3,
the target special equipment archive data comprises a maintenance project table, before data interaction is carried out between the field equipment and the big data server, whether all maintenance projects are completed according to the maintenance project table or not is judged, if yes, data interaction is carried out between the field equipment and the big data server, and if not, the step A2 is executed.
8. A special equipment field maintenance monitoring method according to claim 7,
the target special equipment archive comprises target special equipment sensor monitoring data, and the maintenance project table is formulated according to the sensor monitoring data and/or target special equipment maintenance regulations.
9. A special equipment field maintenance monitoring method according to claim 8,
the method for making the maintenance project table comprises the following steps: and (4) formulating a maintenance project table according to the maintenance regulation of the target special equipment, tracking the monitoring data of the sensor, and marking the maintenance projects related to the abnormality when the abnormal characteristics are detected.
10. A special equipment field maintenance monitoring method according to claim 8,
the target special equipment archive comprises historical maintenance data, and the maintenance project table is formulated according to the historical maintenance data and/or target special equipment maintenance regulations.
11. The special equipment field maintenance monitoring method according to claim 10,
the method for making the maintenance project table comprises the following steps: and tracking historical maintenance data, and when the fault characteristics are detected, taking the maintenance items related to the fault as a maintenance item table according to the maintenance rule sequence of the target special equipment.
12. The special equipment field maintenance monitoring method according to claim 10,
the method for making the maintenance project table comprises the following steps: and (4) formulating a maintenance project table according to the maintenance regulation of the target special equipment, tracking historical maintenance data, and marking the maintenance projects related to the abnormity when the abnormal characteristics are detected.
13. A special equipment field maintenance monitoring method according to claim 1 or 3,
when the maintenance project is finished, the field equipment judges whether the quality of the finished maintenance project reaches the standard according to the field data, if so, the maintenance project is marked, and if not, a signal is sent out and the maintenance project is restarted.
14. The special equipment field maintenance monitoring method according to claim 13,
the target special equipment file comprises a maintenance project verification feature set, and the method for judging whether the quality of the finished maintenance project reaches the standard or not by the field equipment according to the field data comprises the following steps:
D1) setting up field data acquisition add-on projects according to the maintenance projects;
D2) judging whether the finished maintenance project belongs to a background judgment project, if so, marking that the maintenance project reaches the standard, otherwise, entering a step D3, wherein the background judgment project is manually set according to the complexity of the maintenance project, and the quality of the maintenance project reaches the standard by a big data server;
D3) extracting the field data characteristics acquired by the field data acquisition add-on project, comparing the field data characteristics with the maintenance project verification characteristic set, marking that the maintenance project reaches the standard if the matched characteristics exist, and sending a signal and restarting the maintenance project if the matched characteristics do not exist.
15. The special equipment field maintenance monitoring method according to claim 13,
the field data acquisition of the field data acquisition added project comprises field data acquisition before the maintenance project is started and after the maintenance project is finished.
16. A special equipment field maintenance monitoring system is suitable for the special equipment field maintenance monitoring method as claimed in claim 1,
the system comprises a big data server and a field device;
the big data server executes the following steps:
storing the archive data of the target special equipment,
after the maintenance is finished, data interaction is carried out with the field equipment;
the field device performs the steps of:
before the maintenance start the target specific device profile data is sent to the field device,
starting maintenance project monitoring, starting field data collection by the field equipment, identifying an ongoing maintenance project by the field equipment according to the collected field data, judging whether the ongoing maintenance project is a maintenance project with a correct flow according to the archive data of the target special equipment, if so, continuing to collect the field data until the maintenance project is finished, and if not, sending a warning and restarting the step,
and after the maintenance is finished, the field device performs data interaction with the big data server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810511921.2A CN108776452B (en) | 2018-05-25 | 2018-05-25 | Special equipment field maintenance monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810511921.2A CN108776452B (en) | 2018-05-25 | 2018-05-25 | Special equipment field maintenance monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108776452A CN108776452A (en) | 2018-11-09 |
| CN108776452B true CN108776452B (en) | 2021-05-28 |
Family
ID=64027828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810511921.2A Active CN108776452B (en) | 2018-05-25 | 2018-05-25 | Special equipment field maintenance monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108776452B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110197201A (en) * | 2019-04-25 | 2019-09-03 | 永大电梯设备（中国）有限公司 | A kind of elevator mainteinance 5S detection method and system |
| CN110271929A (en) * | 2019-06-14 | 2019-09-24 | 山东科技大学 | A kind of city elevator maintenance QA system based on big data driving |
| US20220111097A1 (en) * | 2020-07-15 | 2022-04-14 | Jeffrey Hassell | System and Method of Managing Requirements for Foodstuffs with Processing Line Changes |
| CN112699490B (en) * | 2021-01-04 | 2024-04-09 | 广州瑞修得信息科技有限公司 | Vehicle maintenance result verification method and device |
| CN113928947B (en) * | 2021-11-18 | 2023-05-23 | 浙江新再灵科技股份有限公司 | Elevator maintenance process detection method and device |
| CN117902417A (en) * | 2024-02-29 | 2024-04-19 | 尼得科康迪克电梯技术(无锡)有限公司 | Elevator safety control method, device, equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1847132A (en) * | 2005-03-24 | 2006-10-18 | 东芝电梯株式会社 | Elevator nonitoring system, elevator monitoring arrangement, and code signature |
| EP1814813A1 (en) * | 2004-11-09 | 2007-08-08 | Inventio AG | Maintenance method and device for an elevator or escalator installation |
| CN101226610A (en) * | 2007-12-21 | 2008-07-23 | 上海市特种设备监督检验技术研究院 | An Elevator Maintenance Management System Utilizing Radio Frequency Identification Technology |
| CN102992127A (en) * | 2011-09-09 | 2013-03-27 | 廊坊凯博建设机械科技有限公司 | System and method for supervising maintenance of elevator device |
| CN106682741A (en) * | 2016-11-16 | 2017-05-17 | 国网山东省电力公司青岛供电公司 | Equipment maintenance method and equipment maintenance device |
| CN207366967U (en) * | 2016-11-16 | 2018-05-15 | 国网山东省电力公司青岛供电公司 | A kind of maintenance system of equipment |
| CN104925606B (en) * | 2015-06-03 | 2018-06-15 | 成都纺织高等专科学校 | Elevator maintenance management system and method based on 4G networks |
-
2018
- 2018-05-25 CN CN201810511921.2A patent/CN108776452B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1814813A1 (en) * | 2004-11-09 | 2007-08-08 | Inventio AG | Maintenance method and device for an elevator or escalator installation |
| CN1847132A (en) * | 2005-03-24 | 2006-10-18 | 东芝电梯株式会社 | Elevator nonitoring system, elevator monitoring arrangement, and code signature |
| CN101226610A (en) * | 2007-12-21 | 2008-07-23 | 上海市特种设备监督检验技术研究院 | An Elevator Maintenance Management System Utilizing Radio Frequency Identification Technology |
| CN102992127A (en) * | 2011-09-09 | 2013-03-27 | 廊坊凯博建设机械科技有限公司 | System and method for supervising maintenance of elevator device |
| CN104925606B (en) * | 2015-06-03 | 2018-06-15 | 成都纺织高等专科学校 | Elevator maintenance management system and method based on 4G networks |
| CN106682741A (en) * | 2016-11-16 | 2017-05-17 | 国网山东省电力公司青岛供电公司 | Equipment maintenance method and equipment maintenance device |
| CN207366967U (en) * | 2016-11-16 | 2018-05-15 | 国网山东省电力公司青岛供电公司 | A kind of maintenance system of equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108776452A (en) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108776452B (en) | Special equipment field maintenance monitoring method and system | |
| CN110826538B (en) | An Abnormal Leaving Recognition System for Electric Power Business Hall | |
| CN110674772B (en) | Auxiliary system and method for intelligent safety management and control of electric power work site | |
| CN111445106B (en) | A safety control method and system for power collection equipment fault handling and operation site | |
| CN109298785A (en) | A man-machine joint control system and method for monitoring equipment | |
| WO2016004774A1 (en) | Rail transportation fault diagnosis method and system based on time series analysis | |
| CN109506963A (en) | A kind of intelligence train traction failure big data abnormality detection discrimination method | |
| CN113807240A (en) | Intelligent monitoring method of substation personnel clothing based on non-cooperative face recognition | |
| CN108515991B (en) | A detection system for standardized operation of receiving and dispatching trains | |
| CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
| CN112193959A (en) | Method and system for detecting abnormal sound of elevator | |
| CN110889339B (en) | Head and shoulder detection-based dangerous area grading early warning method and system | |
| CN110618635A (en) | Train cab operation specification monitoring system based on AI technology | |
| CN114037249A (en) | An electronic work ticket control system | |
| CN118430216B (en) | A multiple communication protocol smog early warning system for filling electric pile | |
| CN118334563A (en) | A method and system for detecting and analyzing abnormality of power equipment under monitoring environment | |
| CN111177468A (en) | A safety inspection method for unsafe behavior of laboratory personnel based on machine vision | |
| CN113191273A (en) | Oil field well site video target detection and identification method and system based on neural network | |
| CN118172693A (en) | Method for intelligently identifying illegal filling of liquefied gas cylinder through video | |
| CN113327404A (en) | Post fatigue state monitoring and warning system for air traffic controller | |
| CN111353465A (en) | Transformer substation personnel behavior analysis method and system based on deep learning technology | |
| CN117373478A (en) | Voiceprint recognition system for transformer | |
| CN117911953A (en) | An artificial intelligence power operation risk supervision and identification system and method | |
| CN114429677A (en) | Coal mine scene operation behavior safety identification and assessment method and system | |
| CN114819461A (en) | Power grid abnormal fault emergency disposal method and system based on artificial intelligence technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210916 Address after: 510000 901, 38 Huajing North Road, Tianhe District, Guangzhou City, Guangdong Province Patentee after: Li Zhitong Address before: 510000 901, 38 Huajing North Road, Tianhe District, Guangzhou City, Guangdong Province Patentee before: Li Zhitong Patentee before: Li Da |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220214 Address after: 310000 Room 408, building 5, No. 16 (Zhongda Ginza), Zhuantang science and technology economic block, Xihu District, Hangzhou City, Zhejiang Province Patentee after: Hangzhou QianShui Digital Technology Co.,Ltd. Address before: 510000 901, 38 Huajing North Road, Tianhe District, Guangzhou City, Guangdong Province Patentee before: Li Zhitong |