CN115520741A - Elevator operation monitoring and early warning method and system based on neural network and storage medium - Google Patents
Elevator operation monitoring and early warning method and system based on neural network and storage medium Download PDFInfo
- Publication number
- CN115520741A CN115520741A CN202211310259.7A CN202211310259A CN115520741A CN 115520741 A CN115520741 A CN 115520741A CN 202211310259 A CN202211310259 A CN 202211310259A CN 115520741 A CN115520741 A CN 115520741A
- Authority
- CN
- China
- Prior art keywords
- fault
- elevator
- early warning
- neural network
- data
- 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.)
- Withdrawn
Links
Images
Classifications
-
- 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
- B66B5/0031—Devices monitoring the operating condition of the elevator system for safety reasons
-
- 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
- B66B5/04—Applications of checking, fault-correcting, or safety devices in elevators responsive to abnormal operating conditions for detecting excessive speed
Landscapes
- Maintenance And Inspection Apparatuses For Elevators (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The invention discloses an elevator operation monitoring and early warning method, system and storage medium based on a neural network, and relates to the technical field of elevator operation monitoring and early warning. The method comprises the following specific steps: collecting operation data in an elevator car in real time; preprocessing the operating data and extracting a characteristic vector; inputting the characteristic vector serving as an input vector into a trained fault state prediction model based on a neural network, and acquiring a state prediction result output by the fault state prediction model; and sending abnormal early warning information of different levels according to the state prediction result. The method can predict different elevator fault types through the construction of the neural network model, can be applied to elevators in various occasions, has high prediction precision and universality, can give an early warning before the elevator breaks down to avoid the failure, realizes early sensing of the elevator fault situation change, and improves the safety early warning capability.
Description
Technical Field
The invention relates to the technical field of elevator operation monitoring and early warning, in particular to an elevator operation monitoring and early warning method and system based on a neural network and a storage medium.
Background
With the increase of urban high-rise buildings, more and more elevators are put into operation. The elevator brings convenience to people, and meanwhile, the elevator fault also affects the life safety of people. In order to ensure safe and reliable operation of an elevator, in the prior art, safety protection is mainly performed on moving parts of the elevator through a physical safety device, for example, a speed limiter, when a steel wire rope of the elevator is disconnected, the steel wire rope can be automatically clamped to emergently stop the elevator in the original position to wait for rescue of technicians, a monitoring device is arranged on the elevator to monitor the operation condition of the elevator in real time, and alarm information is sent out in time after the elevator breaks down so that elevator managers can rescue in time. However, the monitoring method in the prior art can only respond passively when an accident occurs, and a fault occurs at this time, so that the time for people to rescue is very little in many cases, and damage cannot be prevented in time, so that a problem to be solved urgently is how to perform early warning before an elevator fault occurs to technicians in the field.
Disclosure of Invention
In view of this, the invention provides an elevator operation monitoring and early warning method and system based on a neural network, so as to solve the problems existing in the background technology.
In order to achieve the purpose, the invention adopts the following technical scheme: an elevator operation monitoring and early warning method based on a neural network comprises the following specific steps:
collecting operation data in an elevator car in real time;
preprocessing the operating data and extracting a feature vector;
inputting the characteristic vector serving as an input vector into a trained fault state prediction model based on a neural network, and obtaining a state prediction result output by the fault state prediction model;
and sending abnormal early warning information of different levels according to the state prediction result.
Optionally, the operation data includes real-time data and trigger data, and the real-time data includes temperature, pressure, acceleration data and acquisition time in the elevator car; the trigger data comprises the temperature, the pressure, the acceleration of the elevator running, the picture data in the car and the acquisition time extracted when the elevator is opened, closed and started and ended.
Optionally, the preprocessing the operation data includes performing normalization processing.
Optionally, the step of training the fault state prediction model includes:
collecting elevator fault related data, and performing fault classification definition through an expert according to the elevator fault related data, and performing sample marking;
taking the elevator fault related data and the sample marking data as data samples, and dividing the data samples into a training set and a testing set;
and constructing a convolutional neural network, and training the convolutional neural network by using the training set to obtain the fault state prediction model.
Optionally, the method further includes dividing the fault grade according to the state prediction result, and then sending out different abnormal early warning information according to different fault grades.
Optionally, the step of performing fault level division is: calculating health weight according to the state prediction result and a preset model; and determining the fault level of the elevator according to the health weight and a plurality of preset weight intervals.
By adopting the technical scheme, the method has the following beneficial technical effects: the targeted early warning is carried out according to different fault risk levels, the manpower can be reasonably configured, and the early warning efficiency is improved.
On the other hand, the elevator operation monitoring and early warning system based on the neural network comprises a data acquisition module, a preprocessing module, a fault prediction module and an early warning module which are sequentially connected; wherein the content of the first and second substances,
the data acquisition module is used for acquiring running data in the elevator car in real time;
the preprocessing module is used for preprocessing the operating data and extracting a characteristic vector;
the fault prediction module is used for inputting the characteristic vector serving as an input vector into a trained fault state prediction model based on a neural network and acquiring a state prediction result output by the fault state prediction model;
and the early warning module is used for sending abnormal early warning information of different grades according to the state prediction result.
Optionally, the system further comprises a fault level evaluation module, connected to the fault prediction module and the early warning module, and configured to perform fault level division according to the state prediction result.
Finally, a computer storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for monitoring and warning elevator operation based on a neural network.
Compared with the prior art, the invention discloses and provides an elevator operation monitoring and early warning method and system based on a neural network, and the method and system have the following beneficial technical effects: through the construction of the neural network model, the elevator fault types can be predicted according to different types, the prediction method can be applied to elevators in various occasions, the prediction precision is high, meanwhile, the universality is achieved, the early warning can be timely carried out before the elevator breaks down, the fault is avoided, the early sensing of the elevator fault situation change is realized, the safety early warning capability is improved, and the operation and maintenance cost of a protection system is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of the method of the present invention;
fig. 2 is a system configuration diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The embodiment of the invention discloses an elevator operation monitoring and early warning method based on a neural network, which comprises the following specific steps as shown in figure 1:
s1, acquiring running data in an elevator car in real time;
s2, preprocessing the operation data and extracting a feature vector;
s3, inputting the characteristic vector serving as an input vector into a trained fault state prediction model based on a neural network, and obtaining a state prediction result output by the fault state prediction model;
and S4, sending abnormal early warning information of different levels according to the state prediction result.
The operation data comprises real-time data and trigger data, and the real-time data comprises temperature, pressure, acceleration data and acquisition time in the elevator car; the triggering data comprises the temperature, the pressure, the acceleration of the elevator running, the picture data in the elevator car and the acquisition time extracted when the elevator is opened, closed and started and ended.
Further, the preprocessing of the operation data includes normalization processing.
Further, the step of training the fault state prediction model is as follows:
collecting elevator fault related data, and performing fault classification definition through experts according to the elevator fault related data to perform sample marking;
taking elevator fault related data and sample marking data as data samples, and dividing the data samples into a training set and a testing set;
and (3) constructing a convolutional neural network, and training the convolutional neural network by using a training set to obtain a fault state prediction model.
In this embodiment, the convolutional neural network is constructed to include three parts, the first part is an input part, the second part is an implicit layer part, and the third part is an output layer part. The input layer part only comprises one input layer, the hidden layer part comprises a plurality of hidden layers, and the output layer only comprises one fully-connected layer. The elevator fault related data is used as input, the fault type is used as output of the convolutional neural network, and the trained convolutional neural network outputs the prediction of the fault through an output layer. The other neural network layers except the first input layer are all linked with the previous neural network layer through an activation function, and the activation function selects a ReLU, a LeakyRelu, a Sigmoid or a tanh activation function.
Further, the collected elevator fault related data are classified, different categories represent different fault types, and the fault types are divided into three categories; the elevator car collision detection method comprises the following steps of respectively representing three elevator faults of people trapping, elevator overspeed and elevator car collision, wherein people trapping fault data are determined by picture data in the elevator car when the elevator is opened and closed; the elevator overspeed fault data is determined by the acceleration data of the elevator operation; the data of the top-rushing fault of the elevator car is determined by the temperature and the pressure in the elevator car.
Further, fault grade division is carried out according to the state prediction result, and different abnormal early warning information is sent out according to different fault grades.
The fault grade division method comprises the following steps: calculating health weight according to the state prediction result and a preset model; and determining the fault level of the elevator according to the health weight and the preset weight intervals.
Specifically, the fault grade of the elevator is divided into three grades, and a plurality of preset weight intervals corresponding to the first grade information to the third grade information are respectively a first weight interval to a third weight interval. The first weight interval is [0,0.3], the second weight interval is (0.3,0.6 ], and the third weight interval is (0.6,1.0 ].
The higher the grade is, the more serious the fault is, the more urgent the abnormal early warning information is, the first grade is in the first weight interval, and the abnormal early warning is general prompt information; and in the second weight interval, the abnormal early warning is general early warning information, and in the third weight interval, the abnormal early warning is important fault early warning.
The embodiment 2 of the invention provides an elevator operation monitoring and early warning system based on a neural network, which comprises a data acquisition module, a preprocessing module, a fault prediction module and an early warning module which are sequentially connected as shown in fig. 2; wherein the content of the first and second substances,
the data acquisition module is used for acquiring the running data in the elevator car in real time;
the preprocessing module is used for preprocessing the operation data and extracting the characteristic vector;
the fault prediction module is used for inputting the characteristic vector serving as an input vector into a trained fault state prediction model based on a neural network and acquiring a state prediction result output by the fault state prediction model;
and the early warning module is used for sending abnormal early warning information of different levels according to the state prediction result.
And the fault grade evaluation module is connected with the fault prediction module and the early warning module and is used for dividing the fault grade according to the state prediction result.
And finally, providing a computer storage medium, wherein a computer program is stored on the computer storage medium, and when the computer program is executed by a processor, the steps of the elevator operation monitoring and early warning method based on the neural network are realized.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. An elevator operation monitoring and early warning method based on a neural network is characterized by comprising the following specific steps:
collecting operation data in an elevator car in real time;
preprocessing the operating data and extracting a characteristic vector;
inputting the characteristic vector serving as an input vector into a trained fault state prediction model based on a neural network, and obtaining a state prediction result output by the fault state prediction model;
and sending abnormal early warning information of different levels according to the state prediction result.
2. The elevator operation monitoring and early warning method based on the neural network as claimed in claim 1, wherein the operation data comprises real-time data and trigger data, and the real-time data comprises temperature, pressure, acceleration data and acquisition time in the elevator car; the trigger data comprise the temperature and pressure in the elevator, the acceleration of the elevator operation, the picture data in the car and the acquisition time which are extracted when the elevator is opened and closed and starts and ends the operation.
3. The neural network-based elevator operation monitoring and early warning method as claimed in claim 1, wherein the preprocessing of the operation data comprises normalization processing.
4. The elevator operation monitoring and early warning method based on the neural network as claimed in claim 1, wherein the step of training the fault state prediction model comprises:
collecting elevator fault related data, and performing fault classification definition through an expert according to the elevator fault related data, and performing sample marking;
taking the elevator fault related data and the sample marking data as data samples, and dividing the data samples into a training set and a testing set;
and constructing a convolutional neural network, and training the convolutional neural network by using the training set to obtain the fault state prediction model.
5. The elevator operation monitoring and early warning method based on the neural network as claimed in claim 1, further comprising the steps of dividing fault grades according to the state prediction result, and sending out different abnormal early warning information according to different fault grades.
6. The elevator operation monitoring and early warning method based on the neural network as claimed in claim 5, wherein the step of fault grading is as follows: calculating health weight according to the state prediction result and a preset model; and determining the fault level of the elevator according to the health weight and a plurality of preset weight intervals.
7. An elevator operation monitoring and early warning system based on a neural network is characterized by comprising a data acquisition module, a preprocessing module, a fault prediction module and an early warning module which are sequentially connected; wherein, the first and the second end of the pipe are connected with each other,
the data acquisition module is used for acquiring the operation data in the elevator car in real time;
the preprocessing module is used for preprocessing the operating data and extracting a feature vector;
the fault prediction module is used for inputting the characteristic vector serving as an input vector into a trained fault state prediction model based on a neural network and acquiring a state prediction result output by the fault state prediction model;
and the early warning module is used for sending abnormal early warning information of different grades according to the state prediction result.
8. The elevator operation monitoring and early warning system based on the neural network as claimed in claim 7, further comprising a fault grade evaluation module connected with the fault prediction module and the early warning module for performing fault grade division according to the state prediction result.
9. A computer storage medium, characterized in that the computer storage medium has stored thereon a computer program which, when being executed by a processor, implements the steps of a neural network-based elevator operation monitoring and warning method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211310259.7A CN115520741A (en) | 2022-10-25 | 2022-10-25 | Elevator operation monitoring and early warning method and system based on neural network and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211310259.7A CN115520741A (en) | 2022-10-25 | 2022-10-25 | Elevator operation monitoring and early warning method and system based on neural network and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115520741A true CN115520741A (en) | 2022-12-27 |
Family
ID=84703941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211310259.7A Withdrawn CN115520741A (en) | 2022-10-25 | 2022-10-25 | Elevator operation monitoring and early warning method and system based on neural network and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115520741A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116873690A (en) * | 2023-09-06 | 2023-10-13 | 江苏省特种设备安全监督检验研究院 | Elevator safety monitoring data processing system |
-
2022
- 2022-10-25 CN CN202211310259.7A patent/CN115520741A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116873690A (en) * | 2023-09-06 | 2023-10-13 | 江苏省特种设备安全监督检验研究院 | Elevator safety monitoring data processing system |
| CN116873690B (en) * | 2023-09-06 | 2023-11-17 | 江苏省特种设备安全监督检验研究院 | Elevator safety monitoring data processing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111507489B (en) | Cloud-edge-coordinated amusement equipment fault prediction and health management system and method | |
| CN109800127A (en) | A kind of system fault diagnosis intelligence O&M method and system based on machine learning | |
| CN108569607B (en) | Elevator fault early warning method based on bidirectional gating cyclic neural network | |
| CN111445106B (en) | Safety control method and system for fault processing operation site of electricity acquisition equipment | |
| CN111651505B (en) | Equipment operation situation analysis and early warning method and system based on data driving | |
| CN111436944B (en) | Falling detection method based on intelligent mobile terminal | |
| CN111717753A (en) | Self-adaptive elevator fault early warning system and method based on multi-dimensional fault characteristics | |
| CN114330138A (en) | Fault diagnosis method and device and electronic equipment | |
| CN113962299A (en) | Intelligent operation monitoring and fault diagnosis general model for nuclear power equipment | |
| CN115520741A (en) | Elevator operation monitoring and early warning method and system based on neural network and storage medium | |
| CN113760670A (en) | Cable joint abnormity early warning method and device, electronic equipment and storage medium | |
| CN112990656A (en) | Health evaluation system and health evaluation method for IT equipment monitoring data | |
| CN112861071B (en) | High-speed rail traction system anomaly detection method based on depth self-coding | |
| CN114707401A (en) | Fault early warning method and device for signal system equipment | |
| CN116310940A (en) | Risk assessment method and system for running state of electromechanical equipment | |
| CN106379787B (en) | A kind of elevator early warning relief car | |
| CN114436087A (en) | Elevator passenger door-opening detection method and system based on deep learning | |
| CN113986893A (en) | Active early warning system and method based on generator car risk identification | |
| CN109858573A (en) | Truck neural network based is anti-to sling method | |
| CN109263650A (en) | Identify the method, apparatus and the vehicles of manpower intervention | |
| CN113987905A (en) | Escalator braking force intelligent diagnosis system based on deep belief network | |
| CN116679579A (en) | Digital twinning-based safety control method, device, equipment and medium | |
| CN114492636B (en) | Transformer winding state signal acquisition system | |
| CN113343176B (en) | Elevator equipment fault early warning method based on fuzzy comprehensive evaluation | |
| CN113581015B (en) | Safety early warning method and device for fuel cell system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221227 |