CN117252421A - Device and method for grading, maintaining and monitoring risk hidden trouble of large-scale amusement facility - Google Patents
Device and method for grading, maintaining and monitoring risk hidden trouble of large-scale amusement facility Download PDFInfo
- Publication number
- CN117252421A CN117252421A CN202311306793.5A CN202311306793A CN117252421A CN 117252421 A CN117252421 A CN 117252421A CN 202311306793 A CN202311306793 A CN 202311306793A CN 117252421 A CN117252421 A CN 117252421A
- Authority
- CN
- China
- Prior art keywords
- data
- risk
- module
- monitoring
- facility
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 title claims abstract description 41
- 238000012423 maintenance Methods 0.000 claims description 29
- 238000006073 displacement reaction Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 230000006378 damage Effects 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 238000003745 diagnosis Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 208000027418 Wounds and injury Diseases 0.000 claims description 7
- 208000014674 injury Diseases 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 4
- 238000007667 floating Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- NRNCYVBFPDDJNE-UHFFFAOYSA-N pemoline Chemical compound O1C(N)=NC(=O)C1C1=CC=CC=C1 NRNCYVBFPDDJNE-UHFFFAOYSA-N 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 16
- 238000004458 analytical method Methods 0.000 description 8
- 238000005457 optimization Methods 0.000 description 7
- 239000010410 layer Substances 0.000 description 6
- 238000012217 deletion Methods 0.000 description 5
- 230000037430 deletion Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 239000012790 adhesive layer Substances 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
- G06K17/0029—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device the arrangement being specially adapted for wireless interrogation of grouped or bundled articles tagged with wireless record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Engineering & Computer Science (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of large-scale amusement facilities, in particular to a method and a device for classifying, maintaining and monitoring risk hidden dangers of the large-scale amusement facilities.
Description
Technical Field
The invention relates to the technical field of large-scale amusement facilities, in particular to a method and a device for classifying, maintaining and monitoring risk hidden trouble of a large-scale amusement facility.
Background
In recent years, the living standard of people is increasingly improved, and the demands of people on recreation activities are also more and more vigorous. Parks taking large-scale amusement facilities as topics gradually enter entertainment lives of people, and the large-scale amusement equipment is more and more popular with tourists in various large-scale theme parks in China for several years due to the characteristics of surprise, stimulation and interestingness. However, because the development time of the large-scale recreation facility industry is short, the recreation facility is various in variety and complex in structure, almost all of the recreation facility is operated in the open air, is greatly influenced by the environment and the climate, and parts are extremely easy to age and damage due to sun-drying and rain-spraying, so that the life safety of tourists is influenced.
The large-scale recreation facility has the characteristics of various structures, complex movement forms, large number of participants and the like, and once the accident is light, equipment is damaged, and the personal safety is endangered. Safety research work for amusement rides is an important component of the amusement ride industry.
The analysis of the current research situation at home and abroad can find that the safety research of the large-scale recreation facilities is mainly carried out after-accident reason analysis, fault analysis and construction of a safety evaluation system, the research content is mainly concentrated on safety management in equipment use and analysis and evaluation after the accident, and the control of the real-time running state of the equipment and the research of pre-warning measures are lacking. There is still room for improvement in safety supervision of large amusement rides.
Disclosure of Invention
The invention provides a method and a device for classifying, maintaining and monitoring risk hidden dangers of a large-scale amusement facility, which are used for establishing an intelligent risk hidden danger classifying method, dynamically analyzing potential hazard parts in the maintenance and operation processes of the amusement facility and effectively managing daily management, state management and risk early warning of the amusement facility.
In order to achieve the purpose of the invention, the technical scheme adopted is as follows: the device comprises an Internet of things equipment module, a data preprocessing module, a risk hidden danger grading module and a maintenance monitoring early warning module, wherein the Internet of things equipment module comprises an RFID electronic tag, a data acquisition device and an RFID handheld terminal, the data preprocessing module processes missing values of data acquired by the Internet of things equipment module, the risk hidden danger grading module comprehensively analyzes and evaluates an index system by constructing an abnormal factor of the amusement facility based on deep learning, and realizes the prediction of the running condition of the amusement facility by combining equipment information of the Internet of things equipment module, and establishes a risk class table; the maintenance monitoring early warning module carries out classified evaluation of risk hidden danger, thereby evaluating the probability and severity of various injuries of the amusement facility and carrying out targeted maintenance.
As an optimization scheme of the invention, the RFID electronic tag is arranged on an amusement facility, and the data acquisition device comprises a displacement sensor, a wind speed sensor, a vibration volume sensor, a temperature sensor and a swinging displacement acquisition device.
As an optimization scheme of the invention, the device also comprises an indicator lamp, and if the severity of the risk hidden danger is low or negligible, a green light is turned on; if the severity of the risk hidden trouble is middle, a yellow lamp is turned on; and if the severity of the risk potential hazard is high, a red light is lighted.
In order to achieve the purpose of the invention, the technical scheme adopted is as follows: a method for classifying, maintaining and monitoring risk hidden trouble of a large-scale recreation facility comprises the following steps:
s1, an Internet of things equipment module comprises an RFID electronic tag, a data collector and an RFID handheld terminal, wherein the RFID handheld terminal identifies the RFID electronic tag arranged on an amusement facility, and the RFID electronic tag stores the code and risk hidden danger level of the amusement facility; the data acquisition device is used for acquiring parameter information of the recreation facility, wherein the parameter information comprises displacement, wind speed, vibration, temperature, angle and daily maintenance monitoring data;
s2, the data preprocessing module processes missing values of the data collected by the Internet of things equipment module;
s3, accurately predicting the data obtained in the step S2 by adopting a VFEDformer model, determining the fluctuation range of the accurately predicted data by utilizing a variation automatic encoder, judging the abnormal condition of the data in real time, and predicting the running condition of the amusement facility to form a risk category table, a risk injury degree table and a risk probability registration table;
s4, carrying out risk hidden danger grading evaluation by the maintenance monitoring early warning module, identifying the existing dangerous state, carrying out all-weather monitoring and targeted maintenance, carrying out supervision and inspection according to the health degree of the amusement facility, realizing real-time on-line monitoring of the operation state data of the amusement facility, recording the use problems, faults and abnormality of the amusement facility and fault and problem data, and actively giving an alarm.
As an optimization scheme of the present invention, in step S2, processing of missing values using a multiple interpolation method specifically includes:
s2-1, generating a set of interpolation values for each null value, wherein each value is used for interpolating missing values in a data set, and generating a plurality of complete data interpolation sets;
s2-2, each interpolation data set is subjected to statistical analysis by using a statistical method aiming at the complete data set;
s2-3, selecting results from each interpolation data set according to a scoring function to generate a final interpolation value.
1. As an optimization scheme of the invention, in the step S3, training by adopting the VFEDformer model comprises the following specific implementation steps:
input: time sequence data X of recreation facility 1 (t)，X 2 (t)，...，X m (t)；
And (3) outputting: predicting a model training result;
the encoder is defined as:
wherein:representing period items processed by the ith period/trend decomposition module of the layer I; l epsilon {1, …, N }, FEB is a frequency enhancement module, feedForward is a forward propagation module,>distribution parameters output by the encoder;
the encoder is defined as:
wherein:representing the period term processed by the ith period trend decomposition module by the first layer decoder,representing trend items processed by the ith period trend decomposition module of the first layer decoder, W I，i E (1, 2, 3) represents the i-th trend term +.>The final output of VFEDformer is +.>Will->Projecting back to the input dimension;
intra-encoder probability density network pass throughAnd (5) optimizing.
Note that: minimizing the KL divergence here means optimizing the probability distribution parameters (μ and σ) so that they are very similar to the probability distribution parameters of the target distribution.
As an optimization scheme of the present invention, in step S3, it is determined that the fluctuation range of the precisely predicted data is:
input: timing history data x= { X 1 ，x 2 ，...，x n A VA reconstruction probability threshold α based on X;
and (3) outputting: normal time sequence data floating range;
training by VFEDformer model to obtain X s Is a predicted optimum result of (1); inputting the optimal prediction result into a new VA model for abnormality diagnosis, and recording the maximum value and the minimum value of the time sequence with the score higher than alpha in VA to obtain [ delta max, delta min ]]And the average value of the time sequence data is marked as E, and the normal time sequence data fluctuation range [ delta max-E, E-delta min ] is obtained]If the predicted value exceeds the fluctuation range, the predicted value is considered to be abnormal, otherwise, the predicted value is normal.
As an optimization scheme of the invention, the monitoring device of the amusement facility is provided with the indicator light, and if the severity of the risk hidden trouble is low or negligible, a green light is turned on; if the severity of the risk hidden trouble is middle, a yellow lamp is turned on; and if the severity of the risk potential hazard is high, a red light is lighted.
The invention has the positive effects that: 1) According to the invention, RFID identification and sensor acquisition are introduced into the classification, maintenance, monitoring and management of risk hidden trouble of a large-scale amusement facility, and digital information of the amusement facility is comprehensively acquired and a digital model is constructed. Based on a time sequence data abnormity diagnosis model of deep learning, the collected time sequence data is accurately predicted, then a variation automatic encoder is utilized to determine the normal fluctuation range of the data, whether new input data is in the normal fluctuation range or not is compared, the abnormal condition of the time sequence data is judged in real time, potential hazard parts in the maintenance and operation processes of the amusement facility are dynamically analyzed, and safety guarantee is provided for enterprises, supervision departments and tourists. Finally, a risk hidden danger grading evaluation mechanism is established, so that large-scale recreation facilities in management are effectively monitored, the life and property safety of enterprises and tourists is guaranteed, industrial development is promoted, accidents caused by human deviation and equipment faults are reduced, and better economic and social benefits are achieved;
2) The invention grasps the data of the running environment, running state and the like of the recreation facility, establishes a set of intelligent risk hidden danger grading method, dynamically analyzes potential hazard components in the maintenance and running process of the recreation facility, and effectively manages daily management, state management and control and risk early warning of the recreation facility. The double prevention mechanism of the amusement facility implementation is pushed to realize the risk early warning work, and the use management of the amusement facility is continuously promoted;
drawings
For a clearer description of the technical solutions of embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and should not be considered limiting in scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art, wherein:
FIG. 1 is a schematic block diagram of the present invention;
FIG. 2 is a block diagram of a fixing plate;
FIG. 3 is a schematic block diagram of a monitoring device;
FIG. 4 is a flowchart of RFID electronic tag information binding;
FIG. 5 is a method of anomaly diagnosis of time series data on a play facility;
FIG. 6 is a schematic diagram of a fault diagnosis dataset model training flow.
Detailed Description
The present invention will be described in further detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the invention discloses a device for grading and maintaining and monitoring risk hidden dangers of a large-scale amusement facility.
The RFID electronic tag is arranged on the recreation facility, and the data acquisition device comprises a displacement sensor, a wind speed sensor, a vibration volume sensor, a temperature sensor and a swinging displacement acquisition device.
The device also comprises an indicator light, and if the severity of the risk hidden trouble is low or negligible, a green light is turned on; if the severity of the risk hidden trouble is middle, a yellow lamp is turned on; and if the severity of the risk potential hazard is high, a red light is lighted.
As shown in fig. 2 and 3, the apparatus further includes an information display terminal (display screen, mobile terminal, such as tablet, mobile phone), and a monitoring apparatus (the monitoring apparatus includes a data processing server, a power supply module, a processor module) provided in the monitoring room. The power supply module, the data acquisition device, the RFID electronic tag and the indicator lamp are arranged on the fixed plate. According to the data required to be collected by different types of amusement facilities, a corresponding data collector is selected, the fixed plate is installed, and the fixed plate is combined with an RFID electronic tag to collect various types of parameter information of the amusement facilities, such as displacement, vibration, temperature, angle, daily maintenance monitoring and other data.
The data processing server (called server for short) reads the collected data and transmits the data to the processor module, and the data collected by the data processing server is accurately predicted by adopting the VFEDformer model, so that the hidden trouble investigation and management and the risk grading management and control of the large-scale amusement facilities are realized, and the life and property safety of enterprises and tourists is ensured.
(1) Internet of things equipment module
The Internet of things equipment module comprises an RFID electronic tag, a data acquisition unit, an RFID handheld terminal and an information display terminal.
RFID electronic tag
The passive ultrahigh frequency electronic tag is provided with a single-sided adhesive layer, and data in the tag comprises amusement facility codes and risk hidden danger levels.
2. Data acquisition device
The data collector consists of sensors with different purposes, such as a displacement sensor, a wind speed sensor, a vibration volume collector, a swing displacement collector and the like, and according to different types and different purposes of the large-scale amusement facilities, different sensors are selected, so that corresponding parameter information of different large-scale amusement facilities can be obtained.
3. Information display terminal
The information display terminal comprises an intelligent display screen, a mobile terminal (such as PAD and a mobile phone) and an RFID handheld terminal, and is used for receiving/displaying data information related to the recreation facility. The RFID handheld terminal is an Android operating system and an eight-core processor, is provided with an optical distance sensor, a gravity sensor and a gyroscope, can realize a wide scanning range and a scanning distance of more than 10 meters, and supports a plurality of communication interface protocols such as a wireless wide area network, a wireless local area network, bluetooth, GPS and the like.
(2) RFID electronic tag and RFID handheld terminal
The RFID electronic tag has the characteristics of strong anti-interference capability, high reading efficiency, convenience in installation and use, capability of meeting the requirements of high dielectric constant materials on the electronic tag and the like, and is configured for amusement facilities, and the unique ID number of the tag can identify the amusement facilities, so that maintenance/supervision personnel can conveniently acquire facility related information at any time. The RFID handheld terminal can automatically collect tag information, so that information collection of the appliance is realized.
RFID tag information binding
As shown in fig. 4, in the label information binding process, an RFID handheld terminal is used to scan a code to identify an RFID electronic label, collect electronic label information (for example, a unique ID number of the label), fill in an amusement facility (information includes amusement facility name, code, type, model, specification, manufacturer, etc.) in a mobile terminal, attach the RFID electronic label to the amusement facility, complete bidirectional binding of the RFID electronic label and the amusement facility information, and enable a mobile terminal to synchronize binding information to a server, and simultaneously support related operations such as generation and maintenance, information registration, rechecking, collection, etc. of the electronic label.
(3) Data preprocessing module
1. Distributed data acquisition
The data collected by the Internet of things equipment module comprises non-terminal collected data and terminal collected data. The non-terminal acquisition data comprise static data such as recreation facility type data, attribute data, age data and the like, and non-static data such as recreation facility maintenance data, fault data, complaint data, public opinion data and the like. The non-terminal data is generally obtained through registration, uploading, network collection and other modes, and is stored in a structured and semi-structured form after offline processing. The terminal acquisition data are real-time data such as operation data, video data, environment data and the like acquired by the terminal equipment, and the acquired distributed nodes participate in real-time operation in the form of stream data. The collected data is collected and transmitted by using a main stream architecture mode of big data spark+streaming+flame+kafka, and is written into various data receivers.
2. Data preprocessing
According to a data deletion mechanism, the method can be divided into complete random deletion, random deletion and non-negligible deletion, and subjective data are processed by a deletion value, so that people influence the authenticity of the data; objective data, and interpolation method is adopted. The multiple interpolation method is mainly divided into three steps: (1) generating a set of possible interpolation values for each null value, the values reflecting the uncertainty of the non-responsive model; each value may be used to interpolate missing values in the data set, resulting in several complete data sets. (2) Each interpolated data set is statistically analyzed using statistical methods for the complete data set. (3) The results from each of the interpolated data sets are selected according to a scoring function (measuring the linear correlation between the two vectors, i.e. the covariance of the two vectors divided by their respective standard deviation product) to produce the final interpolated value.
(4) Risk hidden danger grading module
1. Device anomaly diagnostic model analysis
In the embodiment, the deep neural network is combined with reinforcement learning with decision-making capability, and the technology of sensing, decision-making or sensing and decision-making integration is realized in an end-to-end learning mode. Aiming at different detection abnormal targets, the method can be quickly adjusted and dynamically adapted. As shown in FIG. 5, the method for anomaly diagnosis of time series data on amusement facilities mainly comprises three parts, (1) training a fault diagnosis data set model for accurately obtaining a predicted value; (2) The target detection algorithm is used for determining the fluctuation range of the normal sample; (3) Inputting real-time test data, and carrying out online prediction and identification.
As shown in fig. 6, the specific process method of the embodiment is as follows:
(1) Predictive model training
Input: time sequence data X of recreation facility 1 (t)，X 2 (t)，...，X m (t)；
And (3) outputting: predicting a model training result;
let the dimension of the sequence data be D, then the input of the encoderThe encoder defines:
wherein the method comprises the steps ofA period term representing the arrival after the ith period/trend decomposition module (MOEDecomp) of the first layerThe encoder may have a multi-layer structure, FEB is a frequency enhancement module, and in the frequency enhancement module, if there is monitoring sequence data with length of m, the monitoring sequence data is set as X 1 (t)，X 2 (t)，...，X m (t) transforming X by Fourier transform i (t) conversion tom groups of data are transformed and combined into a matrix +.>Then sampling s-dimensional data from d-dimensional frequency domain data based on random sampling subject to Gaussian distribution to obtain +.>To complete one time of frequency domain data enhancement, the module contains learning parameter R. />Is a distributed parameter of the encoder output. Likewise, the decoder is defined as:
wherein the method comprises the steps ofRespectively are provided withRepresenting the period item and trend item, W of the first layer decoder processed by the ith period/trend decomposition module I，j I.e. (1, 2, 3) represents the i-th trend term +.>Is a projection operator of (a). The final output of VFEDformer is +.>Wherein->Projected back into the input dimension.
The frequency enhancement module, the full-connection network in the frequency domain attention and the feedforward network layer are provided with a parameter W which can be learned, and batch gradient descent optimization is carried out according to a mean square error (Mean Square Error). Intra-encoder probability density network pass throughAnd (5) optimizing.
(2) Determining fluctuation range
Input: timing history data x= { X 1 ，x 2 ，...，x n Reconstructing a probability threshold alpha based on VA (variable automatic encoder) obtained by X;
and (3) outputting: normal time sequence data floating range;
(1) training through a prediction model to obtain X s Is a result of the optimal prediction.
(2) And inputting the result into a new VA (variable automatic encoder) model for abnormality diagnosis, recording the maximum value and the minimum value of the time sequence with the score higher than alpha in the VA to obtain [ delta max, delta min ], and recording the average value of the time sequence data as E to obtain the normal time sequence data fluctuation range [ delta max-E, E-delta min ]. Wherein: the variance inference is abbreviated as VI, and is a deterministic approximate inference method.
(3) Real-time online prediction
Input: inputting time sequence data in real time;
and (3) outputting: and obtaining a predicted value of the time sequence data, and considering that the predicted value is abnormal if the predicted value exceeds the fluctuation range, otherwise, judging that the predicted value is normal.
2. Risk hidden danger grading method
And constructing an amusement facility abnormal factor comprehensive analysis and evaluation index system based on deep learning. And combining modeling simulation and equipment information extracted by the Internet of things equipment, inputting basic information, corresponding inspection and detection information, maintenance information, supervision and supervision information and the like of different large-scale amusement facilities, and predicting running conditions of the amusement facilities in different periods by using a prediction model. And extracting and analyzing each data characteristic by using a covariance matrix analysis, a correlation coefficient analysis and a regression analysis method according to the predicted value identified by the model, and intelligently adjusting each index weight. And establishing a risk category table in table 1, a risk injury degree table in table 2 and a risk probability grade table in table 3.
Table 1 risk category table
Table 2 risk injury level table
TABLE 3 risk probability level Table
| Probability level | Description of the invention |
| A-frequency | Is likely to occur frequently over the life of the vehicle |
| B-most likely | Several times during the service life are likely to occur |
| C-occasionally | Is likely to occur at least once during the life |
| D-very few | Not necessarily, but may occur over the life of the article |
| E-is unlikely to | Is unlikely to occur during the service life |
| F-impossible to | Probability is almost zero |
The indicator lights of the amusement facility monitoring device give warning in different colors according to the evaluation result, and if the severity of the risk hidden trouble is low or negligible, the green light is turned on; if the severity of the risk hidden trouble is 'medium', the yellow lamp is lighted; if the severity of the risk potential is "high", the red light is lit.
(5) Maintenance monitoring and early warning module
1. Auxiliary on-demand maintenance management
The risk potential hazard grading evaluation work is carried out, the safety risks existing in the using recreation facility are further identified and evaluated, the probability and the severity of various injuries occurring in the using recreation facility are further evaluated, the existing dangerous state is identified, and routine maintenance of the recreation facility is converted into all-weather monitoring and targeted maintenance. According to the operation evaluation condition, countermeasures are adopted in advance to carry out preventive maintenance, so that the possibility of faults of facilities can be effectively reduced, the use safety of the facilities is continuously enhanced, preventive safety management measures are enhanced, and the safety management level of related units on amusement facilities is continuously improved.
2. Amusement ride safety supervision/verification
The embodiment scores the health degree of each amusement facility, and according to the health degree scoring condition, the facility is divided into general supervision, tracking supervision, key supervision, special supervision and the like, so that differential supervision, high-score less supervision and low-score more supervision are implemented. Meanwhile, the amusement facilities with low scores are pushed to the inspection and detection mechanism, so that accurate supervision/inspection of the amusement facilities is realized, supervision/inspection resources are reasonably distributed, and supervision/inspection efficiency is improved.
3. Remote monitoring and early warning management
The running characteristics of the amusement facility are uploaded to a server through equipment, real-time online monitoring of equipment running state data is achieved based on the real state of the equipment analyzed by the embodiment, information monitoring of equipment using problems (safety belts are used for standardization), faults and anomalies (overspeed, top-rushing, insensitive action of a pneumatic valve and the like), fault and problem data (fault and problem times, occurrence positions) are recorded, and an alarm is actively sent out when the faults occur.
The equipment with good state is maintained according to the regulated time, and the equipment with poor state is repaired and maintained in time.
1. The RFID identification and sensor acquisition are introduced into the grading, maintenance and monitoring management of risk hidden trouble of a large-scale amusement facility for the first time, and the digital information of the amusement facility is comprehensively acquired and a digital model is constructed. The scheme includes RFID electronic tags, data acquisition devices (including displacement sensor, wind speed sensor, vibration volume acquisition device, swing displacement acquisition device etc.), indicator lamps (three colors are respectively red, yellow and green), information display terminals (display screen, tablet, mobile phone), and monitoring devices (including server, power supply module, processor module and reader module) arranged in the monitoring room.
2. The collected data is accurately predicted by adopting a VFEDformer model, a variation automatic encoder is utilized to determine the normal fluctuation range of the data, the abnormal condition of the time sequence data is judged in real time by comparing whether the new input data is in the normal fluctuation range, potential hazard parts in the maintenance and operation processes of the amusement facilities are dynamically analyzed, and the potential hazard investigation and management and risk grading control of the large amusement facilities are realized by power-assisted scenic spot management staff, so that the life and property safety of enterprises and tourists is ensured.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical solution of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (8)
1. The utility model provides a device of large-scale amusement facility risk hidden danger classification and maintenance monitoring which characterized in that: the device comprises an internet of things equipment module, a data preprocessing module, a risk hidden danger grading module and a maintenance monitoring and early warning module, wherein the internet of things equipment module comprises an RFID electronic tag, a data acquisition device and an RFID handheld terminal, the data preprocessing module processes missing values of data acquired by the internet of things equipment module, the risk hidden danger grading module comprehensively analyzes and evaluates an index system by constructing an amusement facility abnormal factor based on deep learning, and combines equipment information of the internet of things equipment module to realize prediction of the running condition of the amusement facility and establish a risk category grade table; the maintenance monitoring early warning module carries out classified evaluation of risk hidden danger, thereby evaluating the probability and severity of various injuries of the amusement facility and carrying out targeted maintenance.
2. The device for classifying and maintaining and monitoring risk potential hazards of large-scale amusement facilities according to claim 1, wherein the device comprises: the RFID electronic tag is arranged on an amusement facility, and the data acquisition device comprises a displacement sensor, a wind speed sensor, a vibration volume sensor, a temperature sensor and a swing displacement acquisition device.
3. The device for classifying and maintaining and monitoring risk potential hazards of large-scale amusement facilities according to claim 2, wherein the device comprises: the device also comprises an indicator light, and if the severity of the risk hidden danger is low or negligible, a green light is turned on; if the severity of the risk hidden trouble is middle, a yellow lamp is turned on; and if the severity of the risk potential hazard is high, a red light is lighted.
4. A method for classifying, maintaining and monitoring risk hidden trouble of a large-scale recreation facility is characterized by comprising the following steps: the method comprises the following steps:
s1, an Internet of things equipment module comprises an RFID electronic tag, a data collector and an RFID handheld terminal, wherein the RFID handheld terminal identifies the RFID electronic tag arranged on an amusement facility, and the RFID electronic tag stores the code and risk hidden danger level of the amusement facility; the data acquisition device is used for acquiring parameter information of the recreation facility, wherein the parameter information comprises displacement, wind speed, vibration, temperature, angle and daily maintenance monitoring data;
s2, the data preprocessing module processes missing values of the data collected by the Internet of things equipment module;
s3, accurately predicting the data obtained in the step S2 by adopting a VFEDformer model, determining the fluctuation range of the accurately predicted data by utilizing a variation automatic encoder, judging the abnormal condition of the data in real time, and predicting the running condition of the amusement facility to form a risk category table, a risk injury degree table and a risk probability registration table;
s4, carrying out risk hidden danger grading evaluation by the maintenance monitoring early warning module, identifying the existing dangerous state, carrying out all-weather monitoring and targeted maintenance, carrying out supervision and inspection according to the health degree of the amusement facility, realizing real-time on-line monitoring of the operation state data of the amusement facility, recording the use problems, faults and abnormality of the amusement facility and fault and problem data, and actively giving an alarm.
5. The method for classifying, maintaining and monitoring risk potential hazards of large-scale amusement facilities according to claim 4, wherein the method comprises the following steps: in step S2, the processing of the missing values using the multiple interpolation method specifically includes:
s2-1, generating a set of interpolation values for each null value, wherein each value is used for interpolating missing values in a data set, and generating a plurality of complete data interpolation sets;
s2-2, each interpolation data set is subjected to statistical analysis by using a statistical method aiming at the complete data set;
s2-3, selecting results from each interpolation data set according to a scoring function to generate a final interpolation value.
6. The method for classifying, maintaining and monitoring risk potential hazards of large-scale amusement facilities according to claim 4, wherein the method comprises the following steps: in step S3, training by using the VFEDformer model specifically includes the following steps:
input: time sequence data X of recreation facility 1 (t)，X 2 (t)，...，X m (t)；
And (3) outputting: predicting a model training result;
the encoder is defined as:
wherein:representing period items processed by the ith period/trend decomposition module of the layer I; l epsilon {1, …, N }, FEB is a frequency enhancement module, feedForward is a forward propagation module,>distribution parameters output by the encoder;
the encoder is defined as:
wherein:representing the period term processed by the ith period trend decomposition module by the first layer decoder,representing trend items processed by the ith period trend decomposition module of the first layer decoder, W l,i I.e. (1, 2, 3) represents the i-th trend term +.>The final output of VFEDformer is +.>Will->Projecting back to the input dimension;
intra-encoder probability density network pass throughAnd (5) optimizing.
7. The method for classifying, maintaining and monitoring risk potential hazards of large-scale amusement facilities according to claim 5, wherein the method comprises the following steps: in step S3, the fluctuation range of the precisely predicted data is determined as:
input: timing history data x= { X 1 ，x 2 ，...，x n A VA reconstruction probability threshold α based on X;
and (3) outputting: normal time sequence data floating range;
training by VFEDformer model to obtain X s Is a predicted optimum result of (1); inputting the optimal prediction result into a new VA model for abnormality diagnosis, and recording the maximum value and the minimum value of the time sequence with the score higher than alpha in VA to obtain [ delta max, delta min ]]And the average value of the time sequence data is marked as E, and the normal time sequence data fluctuation range [ delta max-E, E-delta min ] is obtained]If the predicted value exceeds the fluctuation range, the predicted value is considered to be abnormal, otherwise, the predicted value is normal.
8. The method for classifying, maintaining and monitoring risk potential hazards of large-scale amusement facilities according to claim 6, wherein the method comprises the following steps: the monitoring device of the recreation facility is provided with an indicator light, and if the severity of the risk hidden danger is low or negligible, a green light is turned on; if the severity of the risk hidden trouble is middle, a yellow lamp is turned on; and if the severity of the risk potential hazard is high, a red light is lighted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311306793.5A CN117252421A (en) | 2023-10-10 | 2023-10-10 | Device and method for grading, maintaining and monitoring risk hidden trouble of large-scale amusement facility |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311306793.5A CN117252421A (en) | 2023-10-10 | 2023-10-10 | Device and method for grading, maintaining and monitoring risk hidden trouble of large-scale amusement facility |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117252421A true CN117252421A (en) | 2023-12-19 |
Family
ID=89131142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311306793.5A Pending CN117252421A (en) | 2023-10-10 | 2023-10-10 | Device and method for grading, maintaining and monitoring risk hidden trouble of large-scale amusement facility |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117252421A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172926A (en) * | 2024-01-10 | 2024-06-11 | 广东智造乐园数字信息科技有限公司 | Intelligent monitoring and early warning method and device for intelligent paradise |
| CN118430218A (en) * | 2024-07-04 | 2024-08-02 | 四川才子软件信息网络有限公司 | Intelligent early warning system for intelligent scenic spots |
| CN118691443A (en) * | 2024-06-18 | 2024-09-24 | 中国标准化研究院 | Smart public service infrastructure management method based on QR code and RFID |
| CN119250790A (en) * | 2024-09-12 | 2025-01-03 | 广州金老金信息科技有限公司 | Safety risk assessment and monitoring system for amusement equipment based on artificial intelligence |
| CN119476748A (en) * | 2025-01-16 | 2025-02-18 | 吉林省橡果文化旅游发展有限公司 | An amusement park safety management information system |
-
2023
- 2023-10-10 CN CN202311306793.5A patent/CN117252421A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172926A (en) * | 2024-01-10 | 2024-06-11 | 广东智造乐园数字信息科技有限公司 | Intelligent monitoring and early warning method and device for intelligent paradise |
| CN118172926B (en) * | 2024-01-10 | 2024-08-16 | 广东智造乐园数字信息科技有限公司 | Intelligent monitoring and early warning method and device for intelligent paradise |
| CN118691443A (en) * | 2024-06-18 | 2024-09-24 | 中国标准化研究院 | Smart public service infrastructure management method based on QR code and RFID |
| CN118691443B (en) * | 2024-06-18 | 2025-04-15 | 中国标准化研究院 | Smart public service infrastructure management method based on QR code and RFID |
| CN118430218A (en) * | 2024-07-04 | 2024-08-02 | 四川才子软件信息网络有限公司 | Intelligent early warning system for intelligent scenic spots |
| CN119250790A (en) * | 2024-09-12 | 2025-01-03 | 广州金老金信息科技有限公司 | Safety risk assessment and monitoring system for amusement equipment based on artificial intelligence |
| CN119476748A (en) * | 2025-01-16 | 2025-02-18 | 吉林省橡果文化旅游发展有限公司 | An amusement park safety management information system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117252421A (en) | Device and method for grading, maintaining and monitoring risk hidden trouble of large-scale amusement facility | |
| US11938784B2 (en) | Health protection system for passengers on a train in a polluted indoor environment and method thereof | |
| CN107024331B (en) | A kind of neural network is to train motor oscillating online test method | |
| Chen et al. | Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions | |
| CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
| Cacciola et al. | Aspects about air pollution prediction on urban environment | |
| CN111784060B (en) | Urban community social security chain coupling risk evolution scenario conjecture method | |
| CN108197731A (en) | It is a kind of based on jointly trained telemetering motor vehicle tail and car test result coherence method | |
| CN116952654B (en) | Environment monitoring and early warning system for administrative supervision | |
| CN119721645A (en) | An early warning system for gas equipment | |
| CN114049134A (en) | A method for identifying fraudulent pollution source online monitoring data | |
| CN114613101A (en) | Intelligent hotel security system based on big data | |
| Rahman et al. | Deep learning model for railroad structural health monitoring via distributed acoustic sensing | |
| Albaji et al. | Investigation on machine learning approaches for environmental noise classifications | |
| CN118761021B (en) | A method and system for monitoring abnormal grain storage environment | |
| CN113135480B (en) | Elevator fault early warning method based on local and overall characteristics | |
| CN112990599B (en) | Urban emergency fire control optimization method based on emergency fire event similarity calculation | |
| CN119398512A (en) | A food safety risk assessment system based on big data analysis | |
| CN117952440B (en) | Chemical industry park production environment supervision method and system | |
| CN113449966B (en) | Gypsum board equipment inspection method and system | |
| CN120047136B (en) | Intelligent machine room operation and maintenance management method and device | |
| Albaji et al. | A Machine Learning for Environmental Noise Monitoring and Classification Using Matlab | |
| CN117688503B (en) | Electricity safety inspection system based on mobile terminal | |
| Li | Abnormal Detection and Intervention of Students' Campus Behavior Based on Spatiotemporal Series Model | |
| Ali Othman Albaji et al. | Investigation on Machine Learning Approaches for Environmental Noise Classifications |
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 |