CN112850387B - Elevator state acquisition and diagnosis system and method - Google Patents
Elevator state acquisition and diagnosis system and method Download PDFInfo
- Publication number
- CN112850387B CN112850387B CN202011630407.4A CN202011630407A CN112850387B CN 112850387 B CN112850387 B CN 112850387B CN 202011630407 A CN202011630407 A CN 202011630407A CN 112850387 B CN112850387 B CN 112850387B
- Authority
- CN
- China
- Prior art keywords
- data
- elevator
- server
- task
- brake
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003745 diagnosis Methods 0.000 title claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 41
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims description 46
- 238000004364 calculation method Methods 0.000 claims description 39
- 238000011156 evaluation Methods 0.000 claims description 37
- 238000001514 detection method Methods 0.000 claims description 12
- 238000000638 solvent extraction Methods 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 12
- 238000013526 transfer learning Methods 0.000 claims description 9
- 229910000831 Steel Inorganic materials 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000007619 statistical method Methods 0.000 claims description 6
- 239000010959 steel Substances 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000005192 partition Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
- B66B1/3492—Position or motion detectors or driving means for the detector
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/02—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/02—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions
- B66B5/16—Braking or catch devices operating between cars, cages, or skips and fixed guide elements or surfaces in hoistway or well
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mechanical Engineering (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
- Maintenance And Inspection Apparatuses For Elevators (AREA)
Abstract
The application discloses elevator state acquisition and diagnosis system and method, and the system comprises: at least one edge device and a server; each edge device is used for acquiring image data, elevator car motion data, elevator car position data and elevator brake coil current data in elevator shafts and elevator cars of a plurality of elevators, dividing the elevator data into edge end data and server end data according to a preset edge algorithm, performing preliminary early warning analysis on the image data, the motion data, the position data and the elevator brake coil current data according to the edge end data, and sending early warning analysis data and server end application to a server; and the server is used for receiving the early warning analysis data and the server data and carrying out deep analysis on the early warning analysis data according to the server data to obtain a deep analysis result. The timeliness and the accuracy of elevator monitoring early warning among the prior art have been improved.
Description
Technical Field
The application relates to the technical field of elevator fault diagnosis and safety monitoring, in particular to an elevator state acquisition and diagnosis system and method.
Background
The elevator is a necessary transportation tool of the current high-rise building, and belongs to special equipment which integrates multiple technologies. With the continuous improvement of the urbanization level of China, high-rise buildings and rail transit are more and more, the number of elevators is continuously multiplied, and the operation safety and reliability of the elevators have important influence on lives and properties of people. Because of the complexity of the elevator and the mutual correlation of the internal structure, the elevator inevitably has some potential safety hazards in the long-term use process, and serious faults sometimes bring loss of personnel and property, so that effective methods and means are urgently needed to predict and analyze the faults possibly occurring in the operation process of the elevator, and protective measures are made in advance through artificial advance control and intervention, so that the loss of the personnel and the property is greatly reduced. Therefore, how to effectively monitor and evaluate the reliability of the elevator and the safety of the running and using process is one of the key problems which people are trying to solve at present.
At present, a common elevator fault prediction and diagnosis method (PHM) generally obtains and collects various data generated in an elevator operation process through a sensor technology, and realizes detection, analysis, prediction and management of an elevator health state based on an intelligent algorithm and a model through operation means such as signal processing, data analysis and the like. Although the PHM can evaluate the reliability of the system under the actual life cycle condition and reduce the risk of system failure, because elevator faults have the characteristics of complexity, relevance, uncertainty and the like, some uncertain factors which cannot be mastered by a decision maker inevitably exist in the elevator use process, and generally expressed as performance reduction of equipment, equipment recession, wear of parts, running risk increase and the like. These factors are difficult to quantify by measurement and are often uncontrollable risks during elevator use, which can adversely affect elevator users. Therefore, the prior art cannot control the occurrence of the invisible factors or transparently present the invisible factors in advance in a pre-warning and forecasting manner, and further the elevator monitoring effect cannot meet the actual requirements.
Disclosure of Invention
The technical problem that this application was solved is: the effect of elevator monitoring is relatively poor in the prior art. In the scheme provided by the embodiment of the application, the edge device divides the image data, the motion data, the position data and the current data of the brake coil of the elevator brake into edge end processing data and server end processing data, carries out preliminary early warning analysis on the edge end processing data, sends early warning analysis data and the server end processing data to the server, and the server is used for receiving the early warning analysis data and the server end processing data and carrying out deep analysis on the early warning analysis data and the server end processing data to obtain a deep analysis result, namely, the edge device carries out early warning on possible faults of the elevator, and the server carries out deep analysis on the early warning data of the elevator fault, so that invisible factors of the elevator in the running process are generated or transparently presented, the early warning control is carried out in an early warning forecasting mode, and the elevator monitoring effect is improved.
In a first aspect, an elevator state collecting and diagnosing system provided in an embodiment of the present application includes: at least one edge device and a server; wherein,
each edge device is used for acquiring image data, elevator car motion data, elevator car position data and current data of a brake coil of an elevator brake in an elevator shaft and an elevator car of a plurality of elevators, dividing the image data, the motion data, the position data and the current data into edge end processing data and server end processing data according to a preset edge algorithm, analyzing the edge end processing data, performing fault early warning and unloading the server end processing data to a server;
and the server is used for receiving the server-side processing data and carrying out refined fault analysis according to the server-side processing data.
In the scheme provided by the embodiment of the application, the edge device divides the image data, the motion data, the position data and the current data of the brake coil of the elevator brake into edge end processing data and server end processing data, carries out preliminary early warning analysis on the edge end processing data, sends the early warning analysis data and the server end processing data to the server, and the server is used for receiving the early warning analysis data and the server end processing data and carries out deep analysis on the early warning analysis data and the server end processing data to obtain a deep analysis result, namely, the edge device carries out early warning on possible faults of the elevator and carries out deep analysis on the early warning data of the elevator fault through the server, so that invisible factors of the elevator fault in the running process of the elevator are presented or transparently presented, the fault is controlled in advance in a forecasting mode, and the elevator monitoring effect is improved.
Optionally, each of the edge devices comprises: the system comprises a first application division module, a first task scheduling module, a first task unloading module and a first task execution module; wherein,
the first application division module is used for dividing the complete elevator fault analysis application into a plurality of calculation layers according to a preset application division point, operating each calculation layer to determine the calculation cost and time delay of each calculation layer on the edge device, and dividing the elevator fault analysis application into an edge end application and a server end application according to the calculation cost and the time delay;
the first task scheduling module is configured to schedule the edge-side application from the first application partitioning module, and schedule first computation task information corresponding to the edge-side application to the first task execution module;
the first task unloading module is used for unloading second computing task information corresponding to the server-side application to the server;
the first task execution module is used for analyzing the image data, the motion data, the position data and the current data of the elevator brake band-type brake coil according to the first calculation task information and the preset edge algorithm and carrying out fault early warning.
Optionally, the first task execution module is specifically configured to:
determining a data set corresponding to each elevator in the multiple elevators, and performing clustering feasibility detection on the data set based on a preset Hopkins statistical method; if the clustering feasibility is achieved, clustering the data sets corresponding to the multiple elevators to obtain multiple groups of data; comparing any elevator in each group with data sets corresponding to other elevators in the same group to obtain a comparison result; the data set comprises machine types, working conditions, configuration parameters, image data in the elevator shaft and the elevator car, motion data of the elevator car, position data of the elevator car and current data of a band-type brake coil of the elevator brake;
carrying out safety evaluation on any elevator according to the comparison result to obtain a safety evaluation result, and judging whether any elevator has a fault or not according to the safety evaluation result;
and if the elevator brake current data exists, carrying out fault early warning on any elevator, and sending the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator to the server.
Optionally, the first task execution module is specifically configured to:
if any group does not have clustering feasibility, determining historical image data, motion data, position data and current data of a brake coil of an elevator brake of each elevator in any group; and comparing the current image data, the motion data, the position data and the current data of the brake coil of the elevator brake in any group with the historical image data, the motion data, the position data and the current data of the brake coil of the elevator brake to obtain a comparison result.
Optionally, the first task execution module is specifically configured to:
analyzing the vibration signals in the motion data to obtain digital vibration signals corresponding to vibration amplitude and vibration intensity, performing modal decomposition on the vibration signals according to a preset EMD algorithm to obtain complex signals, and performing fault early warning on a traction machine motor according to the digital vibration signals and the complex signals; or
Receiving image data in the elevator shaft, and determining state image data of the traction sheave and the steel wire rope at a preset visual angle according to the image data; extracting, comparing and identifying characteristic points according to the state image data and a preset machine vision algorithm, predicting the fault of a preset visual angle of the traction sheave according to the comparison and identification result, and sending the prediction result to the server so that the server performs fault early warning according to the prediction result; or
And receiving the current data of the brake coil of the elevator brake in real time, monitoring the current data of the brake coil of the elevator brake in real time to obtain a monitoring result, and performing fault early warning on the brake according to the monitoring result.
Optionally, the server includes: the system comprises a second application dividing module, a task receiving module, a resource monitoring module, a second task scheduling module and a second task executing module; wherein,
the second application division module is used for acquiring the preset application division points from each edge device, dividing the preset remote elevator operation and maintenance monitoring application into a plurality of calculation levels according to the preset application division points, operating each calculation level to determine the calculation cost and the time delay of each calculation level on the server, and sending the calculation cost and the time delay on the server to the first application division module;
the task receiving module is used for receiving the second computing task information and placing the second computing task in a preset task cache queue;
the resource monitoring module is used for monitoring the resources of the current server to obtain resource information and sending the resource information to the second task scheduling module;
the second task scheduling module is used for performing task scheduling from the task buffer queue according to the resource information and sending a scheduled task to the second task execution module;
the second task execution module is used for carrying out deep safety assessment on any elevator according to the scheduled task and the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator to obtain a deep safety assessment result.
Optionally, the second task execution module is specifically configured to:
and performing deep safety evaluation on any elevator according to the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator according to the scheduled task, the preset depth and the transfer learning algorithm to obtain a deep safety evaluation result.
Optionally, the method comprises the following steps: the system comprises a field layer, an edge layer, a network layer and a cloud computing layer; wherein,
the field layer comprises a plurality of field nodes, and the field nodes comprise controllers of a plurality of elevators and a data acquisition module;
the edge layer is used for receiving image data, elevator car motion data, elevator car position data and elevator brake coil current data in elevator shafts and elevator cars of the multiple elevators, which are sent by each field node in the field layer, performing real-time data analysis, state perception and fault early warning according to the image data, the motion data, the position data and the elevator brake coil current data, and sending data corresponding to the fault early warning to the cloud computing layer;
the network layer is used for connecting the edge layer and the cloud computing layer so as to enable data interaction between the edge layer and the cloud computing layer;
and the cloud computing layer is used for receiving data corresponding to the fault early warning, and performing deep analysis and safety evaluation on the data according to a preset deep neural network and a transfer learning algorithm.
In a second aspect, an elevator state collecting and diagnosing method provided in an embodiment of the present application is applied to the system according to the first aspect, and the method includes:
acquiring image data, elevator car motion data, elevator car position data and current data of a brake coil of an elevator brake in elevator shafts and elevator cars of a plurality of elevators;
respectively comparing the image data, the motion data and the position data of the plurality of elevators and the current data of the brake coil of the elevator brake to obtain comparison results, and judging whether any elevator has a fault or not according to the comparison results;
and if the elevator brake current data exists, carrying out fault early warning on any elevator, and sending the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator to the server.
Optionally, comparing the image data, the motion data and the position data of the plurality of elevators and the current data of the brake coils of the elevators to obtain comparison results respectively, includes:
determining a data set corresponding to each elevator in the plurality of elevators, and carrying out clustering feasibility detection on the data set based on a preset Hopkins statistical method; if the clustering feasibility is achieved, clustering the data sets corresponding to the multiple elevators to obtain multiple groups of data; comparing any elevator in each group with the data sets corresponding to other elevators in the same group to obtain a comparison result; wherein the data set comprises model, working condition, configuration parameters, image data in the elevator shaft and the elevator car, motion data of the elevator car, position data of the elevator car and current data of a band-type brake coil of the elevator brake;
comparing the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator in each group with the other elevators in the same group to obtain a comparison result;
carrying out safety evaluation on any elevator according to the comparison result to obtain a safety evaluation result, and judging whether any elevator has a fault or not according to the safety evaluation result;
and if the elevator brake current data exists, carrying out fault early warning on any elevator, and sending the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator to the server.
Optionally, if any elevator trouble is the hauler motor and the stopper trouble, carry out trouble early warning to any elevator, include:
analyzing the vibration signals in the motion data to obtain digital vibration signals corresponding to vibration amplitude and vibration intensity, performing modal decomposition on the vibration signals according to a preset EMD algorithm to obtain complex signals, and performing fault early warning on a traction machine motor according to the digital vibration signals and the complex signals; or
Receiving image data in the elevator shaft, and determining state image data of the traction sheave and the steel wire rope at a preset visual angle according to the image data; extracting, comparing and identifying characteristic points according to the state image data and a preset machine vision algorithm, predicting the fault of a preset visual angle of the traction sheave according to the comparison and identification result, and sending the prediction result to the server so that the server performs fault early warning according to the prediction result; or
And receiving the current data of the brake coil of the elevator brake in real time, monitoring the current data of the brake coil of the elevator brake in real time to obtain a monitoring result, and performing fault early warning on the brake according to the monitoring result.
Drawings
Fig. 1 is a schematic structural diagram of an elevator state acquisition and diagnosis system provided in an embodiment of the present application;
fig. 2 is a schematic structural diagram of an edge device according to an embodiment of the present disclosure;
fig. 3 is a schematic flow chart of safety evaluation of an edge device and a server in cooperation with an elevator according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a server according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an elevator state acquisition and diagnosis system partitioned from a software layer according to an embodiment of the present application;
fig. 6 is a schematic flow chart of an elevator state acquisition and diagnosis method provided in an embodiment of the present application.
Detailed Description
In the solutions provided in the embodiments of the present application, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to better understand the technical solutions of the present application, the following detailed descriptions are provided with accompanying drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and in a case of no conflict, the technical features in the embodiments and examples of the present application may be combined with each other.
Referring to fig. 1, an elevator state acquisition and diagnosis system provided in an embodiment of the present application includes: at least one edge device 1 and a server 2; wherein,
each edge device 1 is used for acquiring image data, elevator car motion data, elevator car position data and current data of a brake coil of an elevator brake in an elevator shaft and an elevator car of a plurality of elevators, dividing the image data, the motion data, the position data and the current data into edge end processing data and server end processing data according to a preset edge algorithm, analyzing the edge end processing data, performing fault early warning, and unloading the server end processing data to a server 2;
and the server 2 is used for receiving the server-side processing data and performing refined fault analysis according to the server-side processing data.
Specifically, in the solution provided in the embodiment of the present application, the server 2 may be a cloud server, and the server 2 and the at least one edge device 1 are connected through a wireless network or an ethernet network.
Referring to fig. 2, in a possible implementation, each of said edge devices 1 comprises: a first application dividing module 11, a first task scheduling module 12, a first task offloading module 13, and a first task execution module 14; wherein,
the first application dividing module 11 is configured to divide a complete elevator fault analysis application into multiple calculation levels according to a preset application partition point, run each calculation level to determine a calculation cost and a time delay of each calculation level on the edge device, and divide the elevator fault analysis application into an edge end application and a server end application according to the calculation cost and the time delay;
the first task scheduling module 12 is configured to schedule the edge-end application from the first application partitioning module, and schedule first computing task information corresponding to the edge-end application to the first task executing module 14;
the first task offloading module 13 is configured to offload second computing task information corresponding to the server-side application to the server 2;
the first task execution module 14 is configured to analyze the image data, the motion data, the position data, and the current data of the brake coil of the elevator brake according to the first calculation task information and the preset edge algorithm, and perform fault early warning.
Further, in a possible implementation manner, the first task execution module 14 is specifically configured to:
determining a data set corresponding to each elevator in the plurality of elevators, and carrying out clustering feasibility detection on the data set based on a preset Hopkins statistical method; if the clustering feasibility is achieved, clustering the data sets corresponding to the multiple elevators to obtain multiple groups of data; comparing any elevator in each group with the data sets corresponding to other elevators in the same group to obtain a comparison result; wherein the data set comprises model, working condition, configuration parameters, image data in the elevator shaft and the elevator car, motion data of the elevator car, position data of the elevator car and current data of a band-type brake coil of the elevator brake;
carrying out safety evaluation on any elevator according to the comparison result to obtain a safety evaluation result, and judging whether any elevator has a fault or not according to the safety evaluation result;
and if the elevator brake current data exists, carrying out fault early warning on any elevator, and sending the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator to the server.
Further, in a possible implementation manner, the first task execution module 14 is specifically configured to:
if any group does not have clustering feasibility, determining historical image data, motion data, position data and current data of a brake coil of an elevator brake of each elevator in any group; and comparing the current image data, the motion data, the position data and the current data of the brake coil of the elevator brake in any group with the historical image data, the motion data, the position data and the current data of the brake coil of the elevator brake to obtain a comparison result.
Specifically, in the solution provided in the embodiment of the present application, the edge device 1 is a computing device that provides computing, storage, and communication capabilities when installed in an elevator monitoring field area. The edge device portion is mainly composed of four modules: a first application dividing module 11, a first task scheduling module 12, a first task unloading module 13, and a first task executing module 14. These four modules cooperate to enable the edge device 1 to accomplish application partitioning, offloading computing tasks to the server 2, and scheduling and executing tasks on the local devices. The specific module functions are introduced as follows:
1. first application division module 11
Specifically, the first application partitioning module 11 on the edge device 1 obtains all the partitionable point information of the application from the preset partition point setting script file of the application, then performs pre-partitioning on the application at each partition point, partitions the complete application into a plurality of calculation layers, and obtains the calculation cost and the time delay of each calculation layer on the edge device 1 through operation. The module then obtains the computation cost and delay data at the server 2 and the network transmission delay for each computation layer by interacting with the application partitioning module at the server 2. Finally, the application is divided into two parts, namely an edge end and a server end by analyzing the data and selecting an optimal segmentation point with the aim of minimizing response time delay, wherein the former part runs locally on the edge device 1, and the latter part is unloaded to the server 2 for execution.
2. Second task scheduling Module 12
Specifically, the second task scheduling module 12 on the edge device 1 is configured to schedule the edge-side computing task divided by the first application dividing module 11 to be executed locally, and allocate the computing task scheduling to the first task executing module 14 for processing.
3. First task offload module 13
Specifically, the first task offloading module 13 of the edge device 1 is responsible for offloading the server-side computing task divided by the application to the server 2 for processing. This module splits task offloading into two parts: code and data. For a computing task, the task code is migrated first and then the input data for the task is unloaded. And the module is also responsible for receiving task calculation results returned from the server 2.
4. The first task execution module 14
Specifically, the first task execution module 14 on the edge device 1 is responsible for executing the edge computing task allocated by the first task scheduling module 12. The module also comprises one or more task performers, and similarly, two sub-modules are designed in the task performer module: and the general computation submodule and the AI computation submodule execute the two types of computation step by step according to the task configuration script to complete the whole computation task.
Further, the procedure of the first task execution module 14 for elevator fault warning is as follows: judging the feasibility of cluster clustering in the edge device 1, if the feasibility of clustering is achieved, performing cluster clustering and peer-to-peer comparison, performing similarity clustering on the elevators in the cluster, and automatically aggregating the elevators with similar functions and working conditions into a cluster; and if the clustering feasibility is not available, directly performing the next self-alignment detection. Secondly, the safety degree of each elevator is judged by comparing the elevator with the cluster or the difference of the historical characteristic trend data of the elevator. The specific implementation of the method is shown in fig. 3: step 1 is clustering feasibility judgment and cluster clustering: clustering is carried out according to variables (such as models, working conditions, configuration parameters and the like) related to the similarity of machines, wherein the clustering technology can adopt a K-means clustering algorithm, a density-based clustering algorithm (such as density-based clustering of applications with noise, DBSCAN), a model-based clustering algorithm (such as extrapolation-mapping, EM) and other algorithms to carry out integrated clustering, and the clustering tendency test is carried out by using Hopkins statistics to evaluate the feasibility of clustering. When the clustering feasibility is achieved, the clustering evaluation index S _ Dbw is preferably used for clustering evaluation, and the robustness of the clustering evaluation index to the adjustment parameters of interference items such as various noises and data sets with different densities is strong. And if the Hopkins statistic indicates that the clustering condition is not met, directly entering the step 2, and performing self-comparison according to the historical characteristic trend data. Step 2 is the local cluster fault detection, which includes: self-comparison detection is carried out according to self-historical characteristic trend data, and safety evaluation values are calculated by peer-to-peer comparison (characteristics of vibration, acceleration sensors and the like) of machines in the group, wherein the safety evaluation can adopt methods such as Euclidean distance, PCA-T2 (principal component analysis-T2 static) prediction technology and the like, or a plurality of methods are integrated to obtain better results.
Further, in a possible implementation manner, the first task execution module 14 is specifically configured to:
analyzing the vibration signals in the motion data to obtain digital vibration signals corresponding to vibration amplitude and vibration intensity, carrying out modal decomposition on the vibration signals according to a preset EMD algorithm to obtain complex signals, and carrying out fault early warning on a traction machine motor according to the digital vibration signals and the complex signals; or
Receiving image data in the elevator shaft, and determining state image data of the traction sheave and the steel wire rope at a preset visual angle according to the image data; extracting, comparing and identifying characteristic points according to the state image data and a preset machine vision algorithm, predicting the fault of a preset visual angle of the traction sheave according to the comparison and identification result, and sending the prediction result to the server so that the server performs fault early warning according to the prediction result; or
And receiving the current data of the brake coil of the elevator brake in real time, monitoring the current data of the brake coil of the elevator brake in real time to obtain a monitoring result, and performing fault early warning on the brake according to the monitoring result.
Specifically, in the solution provided in the embodiments of the present application, the elevator car motion data includes speed, acceleration, and vibration signals.
Referring to fig. 4, in one possible implementation, the server 2 includes: a second application dividing module 21, a task receiving module 22, a resource monitoring module 23, a second task scheduling module 24, and a second task executing module 25; wherein,
the second application dividing module 21 is configured to obtain the preset application dividing points from each edge device 1, divide a preset remote elevator operation and maintenance monitoring application into multiple calculation levels according to the preset application dividing points, operate each calculation level to determine the calculation cost and the time delay of each calculation level on the server 2, and send the calculation cost and the time delay of the server 2 to the first application dividing module 11;
the task receiving module 22 is configured to receive the second computing task information, and place the second computing task in a preset task buffer queue;
the resource monitoring module 23 is configured to monitor resources of the current server to obtain resource information, and send the resource information to the second task scheduling module 24;
the second task scheduling module 24 is configured to perform task scheduling from the task buffer queue according to the resource information, and send a scheduled task to the second task executing module 25;
the second task execution module 25 is configured to perform deep security assessment on any elevator according to the scheduled task and the image data, the motion data, the position data, and the elevator brake coil current data corresponding to any elevator, so as to obtain a deep security assessment result.
Further, in a possible implementation manner, the second task execution module 25 is specifically configured to:
and carrying out deep safety evaluation on any elevator according to the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator by the scheduled task, the preset depth and the transfer learning algorithm to obtain a deep safety evaluation result.
Specifically, in the solution provided in the embodiment of the present application, the server 2 is a high-performance server deployed in a cloud, and provides computation offload and cooperative computation services for the connected edge device 1. The server 2 mainly comprises a second application dividing module 21, a task receiving module 22, a resource monitoring module 23, a second task scheduling module 24, and a second task executing module 25. These modules work in concert to enable the server 2 to coordinate with the edge device 1 to accomplish application partitioning, monitor resource usage on the server, receive, schedule, execute computing tasks offloaded by the edge device 1, and extend to other servers. These modules are described in detail as follows:
(I) and (II) application dividing module 21
Specifically, for a monitoring application of remote elevator operation and maintenance, the second application partitioning module 21 on the server 2 first obtains an application partitioning point setting script file transmitted by the edge device 1, where the application partitioning point setting script file contains configuration information of all the partitionable points of an application. And then, pre-dividing the application, dividing the complete application into a plurality of computing layers according to the dividing points in the configuration file, and obtaining the computing time delay and cost of each computing layer on the server 2 through pre-operation. These information are finally sent to the first application partitioning module 11 on the edge device 1.
(II) task receiving module 22
Specifically, the task receiving module 22 is responsible for receiving the divided application server-side computing tasks unloaded by the edge device 1. The module receives the migrated task code first and then receives the offloaded task data. The module places the received computation task information in a task buffer queue and waits for the second task scheduling module 24 on the server 2 to perform scheduling execution. In addition, the module is also responsible for returning task computation results to the edge device 1 after the computation task is completed.
(III) resource monitoring module 23
Specifically, the resource monitoring module 23 is responsible for monitoring and collecting the usage status information of various computing resources on the server 2, including computing and communication resources, for the task scheduling module to use. Since the free resources available on the server 2 may change dynamically as the workload changes, this module needs to update the resource usage status information of the server 2 periodically. In addition, the module also needs to periodically collect resource usage and workload status information for neighboring edge devices or servers.
(IV) second task scheduling Module 24
In particular, the second task scheduling module 24 on the server 2 is mainly responsible for scheduling the computation tasks queued for processing in the task buffer queue. Which schedules tasks according to the current resource usage of the server 2 as provided by the resource monitoring module 23. If the task executor is idle at present, the task is distributed to the task executor to be processed; if all task performers are performing tasks and the remaining available resources on the server 2 can support the re-running of a task performer container instance, then the module will initiate a new task performer to process the task; if the load of the current server 2 is saturated, a scheme with short response delay is evaluated in the processes of unloading to other adjacent servers, uploading to a cloud server and locally waiting for processing to schedule the task.
A second application dividing module 21, a task receiving module 22, a resource monitoring module 23, a second task scheduling module 24, and a second task executing module 25; wherein,
(V) second task execution Module 25
Specifically, the second task execution module 25 is composed of a plurality of task performers, and in order to improve isolation of task execution, the module encapsulates the task performers by using a Docker container, and one task performer runs on one Docker container instance. Each task performer is responsible for processing the computing tasks assigned by the second task scheduling module 24. As shown in fig. 3, each task performer in the system architecture also includes two sub-modules for supporting general purpose computing and AI computing, respectively, and the two sub-modules perform the two types of computing step by step according to the task configuration script to complete the entire computing task.
Further, referring to fig. 5, partitioned from a software layer, in one possible implementation, the system includes: a field layer 51, an edge layer 52, a network layer 53, and a cloud computing layer 54; wherein,
the field layer 51 comprises a plurality of field nodes, and the field nodes comprise controllers of a plurality of elevators and a data acquisition module;
the edge layer 52 is configured to receive image data in elevator shafts and elevator cars, elevator car motion data, and elevator car position data of the multiple elevators, which are sent by each field node in the field layer 51, perform real-time data analysis, state sensing, and fault early warning according to the image data, the motion data, and the position data, and send data corresponding to the fault early warning to the cloud computing layer 54;
the network layer 53 is configured to connect the edge layer 52 and the cloud computing layer 54, so that data interaction is performed between the edge layer 53 and the cloud computing layer 54;
the cloud computing layer 54 is configured to receive data corresponding to the fault early warning, and perform deep analysis and security evaluation on the data according to a preset deep neural network and a transfer learning algorithm.
Specifically, referring to fig. 5, a structural schematic diagram of the elevator state collecting and diagnosing system provided in the embodiment of the present application, which is partitioned from a software layer, is shown. The function of each layer is briefly described below.
(1) The field layer 51: the layer connects field nodes such as: a controller of the elevator, an external sensor (such as vibration, acceleration, braking current, infrared and the like) or a conventional fault acquisition card and the like. These field nodes are connected to the edge devices of the edge layer 52 via the fieldbus/industrial ethernet.
(2) Edge layer 52: after receiving the data from the field layer 51, the elevator is subjected to real-time data analysis, state sensing, rapid fault diagnosis, safety evaluation and the like. The edge layer 52 is composed of network devices such as time sensitive network switches and the like, and each edge device with the functions of calculation, storage and communication is used as a node; each edge device is provided with control software for providing task scheduling and task execution capacity (storage, calculation and communication). After extraction, preprocessing and basic signal analysis of each characteristic signal are completed through the edge device nodes, abnormal elevators are found based on safety evaluation of cluster clustering and peer-to-peer comparison, and controller data and sensor data of the abnormal elevators are transmitted to the cloud computing layer 54 through wireless communication of the network layer by utilizing the narrow-band internet of things.
(3) The network layer 53: the network layer 53 is mainly a converged network formed by a wireless communication network and the internet, and plays a role in transmitting information acquired by the sensing layer.
(4) The cloud computing layer 54: after receiving detailed data of the abnormal machine sent by the edge layer 52 from the network layer 53, the layer performs deep data analysis on the abnormal machine by combining the computing power of the cloud server and utilizing technologies such as a deep neural network, a generative countermeasure network (GAN), transfer learning and the like, thereby realizing the evaluation of key components of the elevator and the safety condition of the whole machine; and sends information to the field layer 51 at the same time, providing accurate services for users, such as safety management, fault tracing, maintenance according to the situation, spare part prediction, and the like.
Further, in the solution provided in the embodiment of the present application, the cloud computing layer 54 mainly applies the deep learning frontier technique GAN and the transfer learning of the artificial intelligence algorithm to the deep security assessment. Specifically, the working principle of the cloud computing layer 54 is as follows:
1. the industrial elevators are various in types and different in working conditions, and different fault diagnosis models need to be established in the traditional technology when different elevator safety evaluations and diagnoses are performed. The method is based on the idea of domain adaptation (domain adaptation) in the fault diagnosis system, uses the domain adaptation, and introduces the transfer learning and the knowledge transfer as intermediate steps, so that when the originally trained model is transferred to a new elevator, the model does not need to be retrained, and the retraining of the model is avoided when the basic configuration state of the elevator is changed every time.
2. GAN is a model for generating data using a countermeasure method. The GAN is introduced to be applied to the field of elevator fault diagnosis based on the following three requirements.
1) And expanding the fault sample. Although elevator fault events occur from time to time, the elevator fault samples are very limited compared to normal data, and the sample imbalance problem is solved by expanding the samples by GAN.
2) And (4) abnormal value detection. GAN has been applied to anomaly detection. In the process of evaluating the safety of the elevator, the possible abnormal data only accounts for a small part of the total data, and the GAN is used for detecting abnormal values to prepare for further fault diagnosis.
3) And (5) semi-supervised learning. When the elevator is subjected to safety assessment and fault diagnosis, a large amount of data needs to be collected, the workload of marking samples is quite large, and a large amount of unlabeled samples can exist. And the semi-supervised learning is carried out by utilizing the GAN, and the elevator fault diagnosis is carried out under the condition that only a small number of marked samples exist, so that the method has better practical significance.
In the scheme provided by the embodiment of the application, the edge device 1 divides the image data, the motion data, the position data and the current data of the brake coil of the elevator brake into edge end processing data and server end processing data, carries out preliminary early warning analysis on the edge end processing data, sends the early warning analysis data and the server end processing data to the server 2, and the server 2 is used for receiving the early warning analysis data and the server end processing data and carries out deep analysis on the early warning analysis data and the server end processing data to obtain a deep analysis result, namely, the edge device 1 carries out early warning on possible faults of the elevator and carries out deep analysis on the early warning data of the elevator through the server 2, so that invisible factors of the elevator faults in the running process of the elevator are presented transparently, the early warning control is carried out in a mode of early warning and forecasting, and the elevator monitoring effect is improved.
Referring to fig. 6, an elevator state collecting and diagnosing method provided in an embodiment of the present application is applied to the system shown in fig. 1, and the method includes:
step 601, the edge device collects image data, elevator car motion data, elevator car position data and current data of a brake coil of an elevator brake in elevator shafts and elevator cars of a plurality of elevators.
And step 602, the edge device respectively compares the image data, the motion data, the position data and the current data of the brake coils of the elevator brakes to obtain comparison results.
Step 603, if the elevator is possible to exist, the edge device carries out fault early warning on any elevator, and the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator are sent to the server.
In one possible implementation manner, comparing the image data, the motion data, the position data and the current data of the brake coil of the elevator to obtain a comparison result respectively comprises the following steps:
determining a data set corresponding to each elevator in the plurality of elevators, and carrying out clustering feasibility detection on the data set based on a preset Hopkins statistical method; if the clustering feasibility is achieved, clustering the data sets corresponding to the multiple elevators to obtain multiple groups of data; comparing any elevator in each group with the data sets corresponding to other elevators in the same group to obtain a comparison result; wherein the data set comprises model, working condition, configuration parameters, image data in the elevator shaft and the elevator car, motion data of the elevator car, position data of the elevator car and current data of a band-type brake coil of the elevator brake;
comparing the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator in each group with other elevators in the same group to obtain a comparison result;
carrying out safety evaluation on any elevator according to the comparison result to obtain a safety evaluation result, and judging whether any elevator has a fault or not according to the safety evaluation result;
and if the elevator brake current data exists, carrying out fault early warning on any elevator, and sending the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator to the server.
In one possible implementation manner, if the failure of any elevator is a failure of a traction machine motor and a brake, performing failure early warning on any elevator includes:
analyzing the vibration signals in the motion data to obtain digital vibration signals corresponding to vibration amplitude and vibration intensity, performing modal decomposition on the vibration signals according to a preset EMD algorithm to obtain complex signals, and performing fault early warning on a traction machine motor according to the digital vibration signals and the complex signals; or
Receiving image data in the elevator shaft, and determining state image data of the traction sheave and the steel wire rope at a preset visual angle according to the image data; extracting, comparing and identifying characteristic points according to the state image data and a preset machine vision algorithm, predicting the fault of a preset visual angle of the traction sheave according to the comparison and identification result, and sending the prediction result to the server so as to enable the server to perform fault early warning according to the prediction result; or
And receiving the current data of the brake coil of the elevator brake in real time, monitoring the current data of the brake coil of the elevator brake in real time to obtain a monitoring result, and performing fault early warning on the brake according to the monitoring result.
Specifically, in the solution provided in the embodiment of the present application, the process of the edge device performing the fault early warning is described in detail in the elevator state collecting and diagnosing system shown in fig. 1, and is not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (9)
1. An elevator condition acquisition and diagnostic system, comprising: at least one edge device and a server; wherein,
each edge device is used for acquiring image data, elevator car motion data, elevator car position data and current data of a brake coil of an elevator brake in an elevator shaft and an elevator car of a plurality of elevators, dividing the image data, the motion data, the position data and the current data into edge end processing data and server end processing data according to a preset edge algorithm, analyzing the edge end processing data, performing fault early warning and unloading the server end processing data to a server;
the server is used for receiving the server-side processing data and carrying out refined fault analysis according to the server-side processing data;
each of the edge devices includes: the system comprises a first application division module, a first task scheduling module, a first task unloading module and a first task execution module; wherein,
the first application division module is used for dividing the complete elevator fault analysis application into a plurality of calculation layers according to a preset application division point, operating each calculation layer to determine the calculation cost and time delay of each calculation layer on the edge device, and dividing the elevator fault analysis application into an edge end application and a server end application according to the calculation cost and the time delay;
the first task scheduling module is configured to schedule the edge-side application from the first application partitioning module, and schedule first computation task information corresponding to the edge-side application to the first task execution module;
the first task unloading module is used for unloading second computing task information corresponding to the server-side application to the server;
the first task execution module is used for analyzing the image data, the motion data, the position data and the current data of the brake coil of the elevator brake and performing fault early warning according to the first calculation task information and the preset edge algorithm;
the first task execution module is specifically configured to:
determining a data set corresponding to each elevator in the plurality of elevators, and carrying out clustering feasibility detection on the data set based on a preset Hopkins statistical method; if the clustering feasibility is achieved, clustering the data sets corresponding to the multiple elevators to obtain multiple groups of data; comparing any elevator in each group with the data sets corresponding to other elevators in the same group to obtain a comparison result; the data set comprises machine types, working conditions, configuration parameters, image data in the elevator shaft and the elevator car, motion data of the elevator car, position data of the elevator car and current data of a band-type brake coil of the elevator brake;
carrying out safety evaluation on any elevator according to the comparison result to obtain a safety evaluation result, and judging whether any elevator has a fault or not according to the safety evaluation result;
and if the elevator brake current data is possible to exist, fault early warning is carried out on any elevator, and the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator are sent to the server.
2. The system of claim 1, wherein the first task execution module is specifically configured to:
if any group does not have clustering feasibility, determining historical image data, motion data, position data and current data of a brake coil of an elevator brake of each elevator in any group; and comparing the current image data, the motion data, the position data and the current data of the brake coil of the elevator brake in any group with the historical image data, the motion data, the position data and the current data of the brake coil of the elevator brake to obtain a comparison result.
3. The system of claim 2, wherein the first task execution module is specifically configured to:
analyzing the vibration signals in the motion data to obtain digital vibration signals corresponding to vibration amplitude and vibration intensity, performing modal decomposition on the vibration signals according to a preset EMD algorithm to obtain complex signals, and performing fault early warning on a traction machine motor according to the digital vibration signals and the complex signals; or
Receiving image data in the elevator shaft, and determining preset visual angle traction sheave and state image data of a steel wire rope according to the image data; extracting, comparing and identifying characteristic points according to the state image data and a preset machine vision algorithm, predicting the fault of a preset visual angle of the traction sheave according to the comparison and identification result, and sending the prediction result to the server so as to enable the server to perform fault early warning according to the prediction result; or
And receiving the current data of the brake coil of the elevator brake in real time, monitoring the current data of the brake coil of the elevator brake in real time to obtain a monitoring result, and performing fault early warning on the brake according to the monitoring result.
4. The system of any one of claims 1 to 3, wherein the server comprises: the system comprises a second application dividing module, a task receiving module, a resource monitoring module, a second task scheduling module and a second task executing module; wherein,
the second application division module is used for acquiring the preset application division points from each edge device, dividing the preset remote elevator operation and maintenance monitoring application into a plurality of calculation layers according to the preset application division points, operating each calculation layer to determine the calculation cost and the time delay of each calculation layer on the server, and sending the calculation cost and the time delay of the server to the first application division module;
the task receiving module is used for receiving the second computing task information and placing the second computing task in a preset task cache queue;
the resource monitoring module is used for monitoring the resources of the current server to obtain resource information and sending the resource information to the second task scheduling module;
the second task scheduling module is used for scheduling tasks from the task buffer queue according to the resource information and sending the scheduled tasks to the second task execution module;
the second task execution module is used for carrying out deep safety assessment on any elevator according to the scheduled task and the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator to obtain a deep safety assessment result.
5. The system of claim 4, wherein the second task execution module is specifically configured to:
and performing deep safety evaluation on any elevator according to the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator according to the scheduled task, the preset depth and the transfer learning algorithm to obtain a deep safety evaluation result.
6. The system of claim 5, comprising: the system comprises a field layer, an edge layer, a network layer and a cloud computing layer; wherein,
the field layer comprises a plurality of field nodes, and the field nodes comprise controllers of a plurality of elevators and a data acquisition module;
the edge layer is used for receiving image data, elevator car motion data, elevator car position data and elevator brake coil current data in elevator shafts and elevator cars of the multiple elevators, which are sent by each field node in the field layer, performing real-time data analysis, state perception and fault early warning according to the image data, the motion data and the position data, and sending data corresponding to the fault early warning to the cloud computing layer;
the network layer is used for connecting the edge layer and the cloud computing layer so as to enable data interaction between the edge layer and the cloud computing layer;
and the cloud computing layer is used for receiving data corresponding to the fault early warning, and performing deep analysis and safety evaluation on the data according to a preset deep neural network and a transfer learning algorithm.
7. An elevator state collection and diagnosis method applied to the system according to claim 6, comprising:
acquiring image data, elevator car motion data, elevator car position data and current data of a brake coil of an elevator brake in elevator shafts and elevator cars of a plurality of elevators;
respectively comparing the image data, the motion data, the position data and the current data of the brake coils of the elevator brakes to obtain comparison results, and judging whether any elevator has faults or not according to the comparison results;
and if the elevator brake current data is possible to exist, fault early warning is carried out on any elevator, and the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator are sent to the server.
8. The method of claim 7, wherein comparing the image data, the motion data, the position data, and the elevator brake coil current data for the plurality of elevators, respectively, to obtain a comparison result comprises:
determining a data set corresponding to each elevator in the multiple elevators, and performing clustering feasibility detection on the data set based on a preset Hopkins statistical method; if the clustering feasibility is achieved, clustering the data sets corresponding to the multiple elevators to obtain multiple groups of data; comparing any elevator in each group with the data sets corresponding to other elevators in the same group to obtain a comparison result; the data set comprises machine types, working conditions, configuration parameters, image data in the elevator shaft and the elevator car, motion data of the elevator car, position data of the elevator car and current data of a band-type brake coil of the elevator brake;
comparing the image data, the motion data, the position data and the current data of the brake coil of the elevator brake corresponding to any elevator in each group with other elevators in the same group to obtain a comparison result;
carrying out safety evaluation on any elevator according to the comparison result to obtain a safety evaluation result, and judging whether any elevator has a fault or not according to the safety evaluation result;
and if the elevator brake current data is possible to exist, fault early warning is carried out on any elevator, and the image data, the motion data, the position data and the elevator brake coil current data corresponding to any elevator are sent to the server.
9. The method of claim 8, wherein if the any elevator fault is a traction machine motor and brake fault, performing fault warning on the any elevator, comprising:
analyzing the vibration signals in the motion data to obtain digital vibration signals corresponding to vibration amplitude and vibration intensity, performing modal decomposition on the vibration signals according to a preset EMD algorithm to obtain complex signals, and performing fault early warning on a traction machine motor according to the digital vibration signals and the complex signals; or
Receiving image data in the elevator shaft, and determining state image data of a traction sheave and a steel wire rope at a preset visual angle according to the image data; extracting, comparing and identifying characteristic points according to the state image data and a preset machine vision algorithm, predicting the fault of a preset visual angle of the traction sheave according to the comparison and identification result, and sending the prediction result to the server so as to enable the server to perform fault early warning according to the prediction result; or
And receiving the current data of the brake coil of the elevator brake in real time, monitoring the current data of the brake coil of the elevator brake in real time to obtain a monitoring result, and performing fault early warning on the brake according to the monitoring result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011630407.4A CN112850387B (en) | 2020-12-31 | 2020-12-31 | Elevator state acquisition and diagnosis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011630407.4A CN112850387B (en) | 2020-12-31 | 2020-12-31 | Elevator state acquisition and diagnosis system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112850387A CN112850387A (en) | 2021-05-28 |
| CN112850387B true CN112850387B (en) | 2023-02-03 |
Family
ID=75999810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011630407.4A Active CN112850387B (en) | 2020-12-31 | 2020-12-31 | Elevator state acquisition and diagnosis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112850387B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113460843A (en) * | 2021-07-05 | 2021-10-01 | 江苏普瑞尔特控制工程有限公司 | Intelligent early warning system of escalator |
| CN114803743B (en) * | 2022-05-05 | 2022-11-01 | 桂林电子科技大学 | Group control method and system based on elevator comprehensive performance perception recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108483172A (en) * | 2018-02-28 | 2018-09-04 | 武汉大学 | A kind of Intelligent elevator car safety monitoring and evaluation system |
| CN108792871A (en) * | 2018-07-09 | 2018-11-13 | 闽江学院 | A kind of intelligent elevator monitoring system based on Internet of Things big data |
| CN110386530A (en) * | 2019-07-16 | 2019-10-29 | 浙江大学 | A kind of elevator monitoring systems and method towards fault diagnosis and safe early warning |
| CN110498311A (en) * | 2019-08-21 | 2019-11-26 | 日立电梯（中国）有限公司 | A kind of pre- diagnostic method of the brake force of elevator internal contracting brake and its device |
| CN111459670A (en) * | 2020-03-30 | 2020-07-28 | 中科边缘智慧信息科技（苏州）有限公司 | Method for performing cooperative processing at different levels of edge calculation |
| CN111835827A (en) * | 2020-06-11 | 2020-10-27 | 北京邮电大学 | Internet of things edge computing task unloading method and system |
-
2020
- 2020-12-31 CN CN202011630407.4A patent/CN112850387B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108483172A (en) * | 2018-02-28 | 2018-09-04 | 武汉大学 | A kind of Intelligent elevator car safety monitoring and evaluation system |
| CN108792871A (en) * | 2018-07-09 | 2018-11-13 | 闽江学院 | A kind of intelligent elevator monitoring system based on Internet of Things big data |
| CN110386530A (en) * | 2019-07-16 | 2019-10-29 | 浙江大学 | A kind of elevator monitoring systems and method towards fault diagnosis and safe early warning |
| CN110498311A (en) * | 2019-08-21 | 2019-11-26 | 日立电梯（中国）有限公司 | A kind of pre- diagnostic method of the brake force of elevator internal contracting brake and its device |
| CN111459670A (en) * | 2020-03-30 | 2020-07-28 | 中科边缘智慧信息科技（苏州）有限公司 | Method for performing cooperative processing at different levels of edge calculation |
| CN111835827A (en) * | 2020-06-11 | 2020-10-27 | 北京邮电大学 | Internet of things edge computing task unloading method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112850387A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| CN107589695B (en) | Train set fault prediction and health management system | |
| CN109102189B (en) | Electrical equipment health management system and method | |
| CN112850387B (en) | Elevator state acquisition and diagnosis system and method | |
| KR20180056900A (en) | Method for production control system using processing mining | |
| KR20180131246A (en) | Method for production control system through processing mining | |
| CN111124852A (en) | Fault prediction method and system based on BMC health management module | |
| CN115238915A (en) | Industrial equipment fault prediction and health monitoring system | |
| CN116187725B (en) | Forging equipment management system for forging automatic line | |
| CN115526375A (en) | Space flight equipment predictive maintenance system | |
| CN116880402A (en) | Intelligent factory cooperative control system and method thereof | |
| CN110059069A (en) | System and method for detecting and predicting the behavior of goal systems | |
| KR20210006832A (en) | Method and apparatus for machine fault diagnosis | |
| KR102269296B1 (en) | Data collection and analysis monitoring system and control method thereof | |
| KR20220032822A (en) | Method for estimating condition of elevator | |
| CN114760341B (en) | Intelligent control remote operation and maintenance platform and method for industrial internet equipment | |
| CN116258482A (en) | Method for automatically selecting maintenance scheme, server and electronic equipment | |
| CN115731073A (en) | Scheduling operation abnormity monitoring method based on service scene analysis | |
| CN114165430B (en) | Edge-computing-based computer pump health monitoring method, system, equipment and medium | |
| CN113168739B (en) | Method for checking at least one vehicle and electronic computing device | |
| CN114205190A (en) | Autonomous monitoring and coordinating method for Internet of things gateway | |
| Torikka | Predictive Maintenance Service Powered by Machine Learning and Big Data | |
| WO2021042233A1 (en) | Remote diagnosis system, apparatus and method for power tool | |
| Hu et al. | A semi-supervised method for digital twin-enabled predictive maintenance in the building industry | |
| CN117311283B (en) | Workshop running control intelligent monitoring method and system for preassembly body in heat exchanger |
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 |