CN106586796B - A kind of escalator condition monitoring system and method - Google Patents
A kind of escalator condition monitoring system and method Download PDFInfo
- Publication number
- CN106586796B CN106586796B CN201611004666.XA CN201611004666A CN106586796B CN 106586796 B CN106586796 B CN 106586796B CN 201611004666 A CN201611004666 A CN 201611004666A CN 106586796 B CN106586796 B CN 106586796B
- Authority
- CN
- China
- Prior art keywords
- escalator
- state
- feature vector
- real
- monitoring
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B29/00—Safety devices of escalators or moving walkways
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B25/00—Control of escalators or moving walkways
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B27/00—Indicating operating conditions of escalators or moving walkways
Abstract
The invention discloses a kind of escalator condition monitoring system and methods, the system includes sensing subsystem, data acquisition subsystem and monitoring, diagnosing main system, sensing subsystem is for obtaining the status information of escalator in the process of running, data acquisition subsystem obtains corresponding preprocessed original state information for acquisition after being pre-processed to the status information of acquisition and stores, monitoring, diagnosing main system is for parsing preprocessed original state information, feature extraction processing is monitored on-line after obtaining real-time state feature vector, early warning and alarming processing, and historical failure data and/or expert knowledge library is combined to carry out self-learning type intelligent diagnostics and failure predication to state feature vector.Comprehensive on-line monitoring to escalator may be implemented in the present invention, and can accurately carry out intelligent diagnostics and failure predication, can be widely applied in the monitoring industry of escalator, moving sidewalk, elevator.
Description
Technical field
The present invention relates to the monitoring fields of escalator, more particularly to a kind of escalator condition monitoring system and side
Method can be used for monitoring babinet, lifting or the parallel transport people either run along rigid guideway along the step of line operation
The electromechanical equipment of member or cargo.
Background technology
Escalator (Escalator), also known as escalator, or automatic pedestrian's elevator, handrail elevator, Escalator, are one
Kind a large amount of upward or downward, continuous conveying passenger fixed electromechanical equipments with shuttling movement ladder road.It is usually used in subway, machine
The places such as field, station, office building, store, harbour.As shown in Figure 1, escalator is by drive system, terraced road system, handrail system
The compositions such as system, metal structure and electric control system, wherein drive system includes motor, speed reducer, drive chain and main driving
Axis etc., terraced road system include step, floor and fishback, broach, step chains and step chain tension device etc., and handrail system includes
Interior plate, skirtboard, cover board, handrail and hand strap driving device etc., metal structure refer to the metal parts of escalator, including lead
Rail and truss etc., electric control system include power supply, controller, driver and detecting signal unit etc..Because of escalator
Working environment be mainly the public place crowded at market, station etc., long operational time, load are big, and peak time is very
To frequent overload operation, after running for a long time, it inevitably will appear various failures.The appearance of failure not only shadow
The normal operation of escalator is rung, it is also possible to lead to safety accident, or even cause heavy economic losses or casualties.Closely
In the past few years, since failure is not found in time and the report of safety accident is caused to be seen repeatly not during escalator operation
It is fresh.It can be seen that the safety inspection and maintenance of escalator operation are very necessary.
Currently, mainly inspecting periodically two kinds of sides of maintenance and inspection after maintenance and failure to the safety detection method of escalator
Formula.Maintenance and inspection refer to being checked, being repaired again after escalator breaks down after failure, this only to one of failure
Relief measure, escalator cannot provide service in maintenance process, can bring inconvenient for use, economic loss etc., and because want
Prepare maintenance and repair parts in advance, larger financial burden can be brought.Though and regular Inspection and maintenance can be reduced and be helped automatically to a certain extent
The appearance of terraced failure, but its not only working service is of high cost, but also many failures are caused due to the improper of periodic maintenance
's.In addition, these safety inspection means largely rely on the experience level of the precision and reviewer of detecting instrument, it is difficult to
The operation conditions of escalator is accomplished to monitor in real time, failure can not be carried out according to the operation conditions of escalator timely pre-
Alert or alarm.Although existing also there are some methods for carrying out status monitoring to escalator in the art, such as passes through setting
Hall speed sensor, laser range sensor etc. acquire the operation conditions of passenger on escalator and are diagnosed automatically,
The operating status of escalator is detected by the way that mutual inductor is arranged, is acquired on escalator by the way that image capture module is arranged
Image recognition is carried out after image to determine whether the various modes such as being abnormal, existing these are monitored escalator
Mode is that do not have versatility, or only for automatic only for the monitoring of escalator or detecting and controlling for certain functions
Staircase operation certain parameter indexes, on-line monitoring state it is not comprehensive, or only monitoring function, do not have early warning and diagnostic function
Deng can not achieve comprehensive on-line checking, fault alarm, fault pre-alarming and the remote fault diagnosis etc. to escalator.
Invention content
In order to solve the above technical problems, the object of the present invention is to provide a kind of escalator condition monitoring systems, originally
The another object of invention is to provide a kind of escalator state monitoring method.
The technical solution adopted by the present invention to solve the technical problems is：
A kind of escalator condition monitoring system, including sensing subsystem, data acquisition subsystem and monitoring are examined
Disconnected main system, the sensing subsystem for obtaining the status information of escalator in the process of running, adopt by the data
Subsystem obtains corresponding preprocessed original state information for acquisition after being pre-processed to the status information of acquisition and stores,
The monitoring, diagnosing main system is for parsing preprocessed original state information, feature extraction processing obtain real-time state feature to
Monitored on-line after amount, early warning and alarming processing, and combine historical failure data and/or expert knowledge library to state feature to
Amount carries out self-learning type intelligent diagnostics and failure predication.
Further, the monitoring, diagnosing main system includes field monitoring alarm subsystem, communication subsystem and long-range monitoring
Diagnostic subsystem, the field monitoring alarm subsystem is for parsing preprocessed original state information, feature extraction processing obtains
It is monitored on-line, early warning and alarming processing, and real-time state feature vector is passed through logical after real-time state feature vector
Letter subsystem is sent to remote monitoring and diagnosis subsystem, and the remote monitoring and diagnosis subsystem is used to combine historical failure data
And/or expert knowledge library carries out self-learning type intelligent diagnostics and failure predication to state feature vector.
Further, the sensing subsystem includes at least one of lower sensor：
Vibrating sensor, at least one of rotary part, support member and guiding parts for obtaining escalator
The vibrational state of component；
Temperature sensor, for acquiring the working environment of escalator, rotary part, support member, electric control system
With the temperature of at least one of lubricant；
Infrared imaging sensor, at least one component in the drive system and electric control system for obtaining escalator
Two-dimension temperature state；
Sound transducer, electric control system, drive system, terraced road system and handrail system for obtaining escalator
At least one of component sound equipment state；
Staircase controller communication interface, the working condition of the electric control system for obtaining escalator, the work
State includes at least one following running state information：Operational mode, traffic direction, the speed of service, the safety of escalator are returned
At least one of road, inspection switch, cover plate switch, brake and failure code operating status；
Speed probe, at least one rotation in the drive system, terraced road system and handrail system for obtaining escalator
The rotating speed of shaft；
Electrical quantity sensor, instantaneous voltage, transient current and the instantaneous work(of the electric control system for obtaining escalator
Rate.
Further, the remote monitoring and diagnosis subsystem includes：
First state display module, the real-time status feature vector for showing escalator；
First alarm module, for according to the real-time status feature vector of escalator to the operation conditions of escalator into
Row early warning and alarm；
Analyzing and diagnosing module is parsed for the preprocessed original state information to escalator, feature extraction processing obtains in fact
When state feature vector, and historical failure data and/or expert knowledge library is combined to carry out self-learning type to state feature vector
Intelligent diagnostics and failure predication；
Data management module carries out real for the preprocessed original state information and/or real-time status feature vector to escalator
When storage, inquiry, delete or backup.
Further, the remote monitoring and diagnosis subsystem further includes dynamic analog module, and the dynamic analog module is used for
According to acquired preprocessed original state information, the operating status of escalator is simulated in real time, passes through image, sound, color, animation
And/or vibrational state, state of temperature, sound equipment state and the and/operating status of escalator is presented in the mode of text message.
Further, the field monitoring alarm subsystem includes main control module, the second state display module and the second alarm
Module, the main control module is for parsing the preprocessed original state information of escalator, feature extraction processing obtains in real time
State feature vector is simultaneously monitored in real time, and second state display module is used to show the real-time status feature of escalator
Vector, second alarm module be used for according to the real-time status feature vector of escalator to the operation conditions of escalator into
Row early warning and alarm.
Further, the status information includes at least one of following state：
The rotary part of escalator, the vibrational state of support member and guiding parts；
The working environment of escalator, the state of temperature of rotary part, support member, electric control system and lubricant；
The drive system of escalator and the two-dimension temperature state of electric control system；
The electric control system of escalator, the sound equipment state of drive system, terraced road system and handrail system；
The operational mode of escalator, traffic direction, the speed of service, safety return circuit, inspection switch, cover plate switch, braking
At least one of device and failure code operating status；
The rotating speed of at least one rotary shaft in the drive system of escalator, terraced road system and handrail system；
Instantaneous voltage, transient current and the instantaneous power of the electric control system of escalator.
The present invention solves another technical solution used by its technical problem：
A kind of escalator state monitoring method, including step：
S1, the status information of escalator in the process of running is obtained；
S2, the corresponding preprocessed original state information of acquisition is acquired after being pre-processed to the status information of acquisition；
S3, the preprocessed original state information of escalator is parsed, feature extraction processing obtain real-time state feature to
Monitored on-line after amount, early warning and alarming processing, and combine historical failure data and/or expert knowledge library to state feature to
Amount carries out self-learning type intelligent diagnostics and failure predication.
Further, the preprocessed original state information of escalator is parsed described in the step S3, feature extraction processing
The step of obtaining real-time state feature vector be specially：The preprocessed original state information of escalator is pre-processed successively,
After Fourier transformation, feature extraction and Fuzzy processing, extraction obtains real-time state feature vector.
Further, the combination historical failure data and/or expert knowledge library carry out self-learning type to state feature vector
It the step of intelligent diagnostics and failure predication, specifically includes：
S31, it is trained obtained neural network by using historical failure data state feature vector is examined
Disconnected reasoning, obtains multigroup failure diagnosis information corresponding with state feature vector；
S32, after being integrated using fuzzy theory operator to multigroup failure diagnosis information, preliminary diagnostic result is obtained；
S33, diagnostic result is obtained after being screened according to threshold value screening principle and maximum membership degree screening principle；
S34, in response to confirmation message input by user, judge whether diagnostic result is consistent with physical fault, if so, defeated
Terminate after going out diagnostic result, conversely, continuing to execute step S35；
S35, the diagnostic result is stored in special case searching associated with the neural network after training；
S36, judge whether the sum of special example in special case searching reaches predetermined threshold value, if so, re-starting god
Through network training, and reset special case searching.
Further, the historical failure data include failure diagnosis information and corresponding preprocessed original state information and/or
Line monitoring state, used described in the step S31 historical failure data be trained obtained neural network be by with
Under type training obtains：
S311, to preprocessed original state information and/or on-line monitoring state is pre-processed successively, Fourier transformation, feature carry
It takes with after Fuzzy processing, extraction obtains real-time state feature vector；
S312, the state feature vector that extraction obtains is examined as the input data of neural network, and by corresponding failure
After disconnected information is as the output data of neural network, neural network is trained.
Further, the real-time state feature vector includes vibration, sound, temperature and electricity feature, is specifically included：It drives
The rotational frequency of dynamic motor, vibration acceleration, the peak value of vibration velocity and vibration displacement, peak-to-peak value, root-mean-square value, maximum are square
Root, envelope and rumble spectrum；Wen Sheng, minimum temperature, maximum temperature and the change rate of temperature signal, the peak of acoustic signals
Value, mean value, root-mean-square value, crest factor, the kurtosis factor, envelope and frequency spectrum；Voltage, the instantaneous value of electric current and power, phase,
Mean value, root-mean-square value, maximum value, peak-to-peak value, fundamental wave and harmonic wave and three-phase current unbalance, voltage waveform radio-frequency component and
Current waveform radio-frequency component；The operational mode of escalator, traffic direction, the speed of service, safety return circuit, inspection switch, cover board
The operating status of at least one of switch, brake and failure code.
The beneficial effects of the invention are as follows：A kind of escalator condition monitoring system of the present invention, including sensing subsystem
System, data acquisition subsystem and monitoring, diagnosing main system, the sensing subsystem are being run for obtaining escalator
Status information in the process, the data acquisition subsystem is for acquisition acquisition pair after being pre-processed to the status information of acquisition
The preprocessed original state information answered simultaneously is stored, the monitoring, diagnosing main system for being parsed to preprocessed original state information, feature
Extraction process monitored on-line after obtaining real-time state feature vector, early warning and alarming processing, and combines historical failure number
According to and/or expert knowledge library self-learning type intelligent diagnostics and failure predication are carried out to state feature vector.This system may be implemented
To comprehensive on-line monitoring of escalator, and it can accurately carry out intelligent diagnostics and failure predication.
Another advantageous effect of beneficial effects of the present invention is：A kind of escalator state monitoring method, including step：S1、
Obtain the status information of escalator in the process of running；S2, acquisition pair is acquired after being pre-processed to the status information of acquisition
The preprocessed original state information answered；S3, the preprocessed original state information of escalator is parsed, the real-time shape of feature extraction processing acquisition
It is monitored on-line after state feature vector, early warning and alarming processing, and combines historical failure data and/or expert knowledge library to shape
State feature vector carries out self-learning type intelligent diagnostics and failure predication.Comprehensive online prison to escalator may be implemented in this method
It surveys, and can accurately carry out intelligent diagnostics and failure predication.
Description of the drawings
The invention will be further described with reference to the accompanying drawings and examples.
Fig. 1 is the structural schematic diagram of typical escalator；
Fig. 2 is a kind of electronic block diagrams of escalator condition monitoring system of the present invention；
Fig. 3 is the electronic block diagrams of the electric control system of typical escalator；
Fig. 4 be the present invention a kind of escalator state monitoring method in the topology diagram of BP neural network that uses；
Fig. 5 is the detail flowchart that fault diagnosis is carried out in the embodiment of the present invention two；
Reference numeral in Fig. 1：1, truss, 2, step, 3, broach, 4, floor and fishback, 5, skirtboard, 6, drive chain, 7,
Speed reducer, 8, motor, 9, step chains, 10, main drive shaft, 11, step chain tension device, 12, guide rail, 13, handrail driving
Device, 14, handrail, 15, interior plate, 16, console panel, 17, cover board.
Specific implementation mode
The embodiment of the present invention one
With reference to Fig. 2, the present invention provides a kind of escalator condition monitoring systems, including sensing subsystem, data
Acquisition subsystem and monitoring, diagnosing main system, the sensing subsystem are used to obtain escalator in the process of running
Status information, the data acquisition subsystem obtain corresponding original for acquisition after being pre-processed to the status information of acquisition
Status information is simultaneously stored, and the monitoring, diagnosing main system is for parsing preprocessed original state information, feature extraction is handled
Obtain monitored on-line after real-time state feature vector, early warning and alarming processing, and combine historical failure data and/or specially
Family's knowledge base carries out self-learning type intelligent diagnostics and failure predication to state feature vector.
It is further used as preferred embodiment, the data acquisition subsystem includes signal regulating device and data acquisition
Module, the signal regulating device obtain corresponding reset condition letter for acquisition after being pre-processed to the status information of acquisition
Breath, pretreatment include filtering, amplification and/or protocol analysis processing, and the data acquisition module is for obtaining after pretreatment
Preprocessed original state information is acquired, stores and/or forwards.
It is further used as preferred embodiment, the monitoring, diagnosing main system includes field monitoring alarm subsystem, leads to
Believe subsystem and remote monitoring and diagnosis subsystem, the field monitoring alarm subsystem is for solving preprocessed original state information
Analysis, feature extraction processing monitored on-line after obtaining real-time state feature vector, early warning and alarming processing, and will be real-time
State feature vector is sent to remote monitoring and diagnosis subsystem by communication subsystem, and the remote monitoring and diagnosis subsystem is used for
Self-learning type intelligent diagnostics and failure predication are carried out to state feature vector in conjunction with historical failure data and/or expert knowledge library.
Remote monitoring and diagnosis subsystem is arranged on the server.
It is further used as preferred embodiment, the communication subsystem passes through on-scene communication bus, cordless communication network
It is communicated at least one of internet communication mode.
It is further used as preferred embodiment, the sensing subsystem includes at least one in lower sensor
It is a：
Vibrating sensor, at least one of rotary part, support member and guiding parts for obtaining escalator
The vibrational state of component；Vibrational state includes in drive system ladder road system, handrail system and the metal structure of escalator
The vibration acceleration of at least one component, including at least one of the following：The support base of rotary part is axially and radially put down
In face in two mutually perpendicular directions at least one direction vibration acceleration；In the three-dimensional of support member and guiding parts
The vibration acceleration at least one direction.The rotary part of escalator refers to the rotor of motor, shaft coupling, braked wheel, driving
The portion that wheel, flywheel, gear, belt pulley, directive wheel, tensioning wheel, sprocket wheel, chain, rotary shaft and spindle nose etc. can rotate in operation
Part.Support member refers generally to the component that bearing, bearing block etc. mainly play a supportive role.Guiding parts refers mainly to guide rail and guide groove
Deng.
Temperature sensor, the temperature and/or rotary part of the working environment for acquiring escalator, support member, electricity
The temperature of at least one point of at least one of gas control system and lubricant component；
Infrared imaging sensor, at least one component in the drive system and electric control system for obtaining escalator
Two-dimension temperature state；
Sound transducer, electric control system, drive system, terraced road system and handrail system for obtaining escalator
At least one of component sound equipment state, i.e., in electric control system, drive system, terraced road system and handrail system at least
The sound equipment state that one component generates at runtime；
Staircase controller communication interface, the working condition of the electric control system for obtaining escalator, the work
State includes at least one following running state information：Operational mode, traffic direction, the speed of service, the safety of escalator are returned
At least one of road, inspection switch, cover plate switch, brake and failure code operating status；Staircase controller communication interface is
The working condition of the electric control system of escalator is obtained by live universal serial bus, the controller of electric control system is logical
It crosses universal serial bus and various working conditions is sent to staircase controller communication interface, staircase controller communication interface is forwarded to prison again
Survey diagnosis main system.As shown in figure 3, electric control system generally comprises power supply, controller, driver, brake, signal
The output end of detection unit, controller is connect by driver with brake, while passing through the electronic of driver and escalator
Machine connects, and the output end of detecting signal unit and the input terminal of controller connect, and power supply is simultaneously for being signal detection list
Member, controller and driver power supply.Detailed, detecting signal unit includes photosignal detection module, motion state detection mould
The output end of block and safety signal detection module etc., these modules is connect with the input terminal of controller.
Speed probe, at least one rotation in the drive system, terraced road system and handrail system for obtaining escalator
The rotating speed of shaft；
Electrical quantity sensor, instantaneous voltage, transient current and the instantaneous work(of the electric control system for obtaining escalator
Rate.
It is further used as preferred embodiment, the remote monitoring and diagnosis subsystem includes：
First state display module, the real-time status feature vector for showing escalator, can pass through digital information
And/or graphical information is shown；
First alarm module, for according to the real-time status feature vector of escalator to the operation conditions of escalator into
Row early warning and alarm；Alarm mode includes the modes such as sound alarm, color alarm, text output alarm；
Analyzing and diagnosing module is parsed for the preprocessed original state information to escalator, feature extraction processing obtains in fact
When state feature vector, and historical failure data and/or expert knowledge library is combined to carry out self-learning type to state feature vector
Intelligent diagnostics and failure predication；
Data management module carries out real for the preprocessed original state information and/or real-time status feature vector to escalator
When storage, inquiry, delete or backup.
Remote monitoring and diagnosis subsystem be used in conjunction with historical failure data and/or expert knowledge library to state feature vector into
Row self-learning type intelligent diagnostics and failure predication.
It is further used as preferred embodiment, the remote monitoring and diagnosis subsystem further includes dynamic analog module, institute
Dynamic analog module is stated for according to acquired preprocessed original state information, simulating the operating status of escalator in real time, passing through figure
The vibrational state, state of temperature, sound equipment state of escalator is presented in picture, sound, color, the mode of animation and/or text message
With with/operating status.
It is further used as preferred embodiment, the field monitoring alarm subsystem includes main control module, the second state
Display module and the second alarm module, the main control module for the preprocessed original state information of escalator is parsed, feature
Extraction process obtains real-time state feature vector and is monitored in real time, and second state display module is automatic for showing
The real-time status feature vector of staircase, second alarm module are used for the real-time status feature vector according to escalator to certainly
The operation conditions of dynamic staircase carries out early warning and alarm.
It is further used as preferred embodiment, the status information includes at least one of following state：
The rotary part of escalator, the vibrational state of support member and guiding parts；
The working environment of escalator, the state of temperature of rotary part, support member, electric control system and lubricant；
The drive system of escalator and the two-dimension temperature state of electric control system；
The electric control system of escalator, the sound equipment state of drive system, terraced road system and handrail system；
The operational mode of escalator, traffic direction, the speed of service, safety return circuit, inspection switch, cover plate switch, braking
At least one of device and failure code operating status；Here, the operational mode of escalator, traffic direction, the speed of service, safety
Circuit, inspection switch, cover plate switch, brake refer both to corresponding state, and mode of operation state includes that operation neutralizes two kinds of stopping
State, traffic direction state include uplink and downlink two states, and speed of service state includes positive and abnormal two states, peace
Full loop includes disconnecting and being closed two states, and inspection switch includes disconnecting and being closed two states, and cover board includes playing open and close
Two states are closed, brake includes opening and closing two states.
The rotating speed of at least one rotary shaft in the drive system of escalator, terraced road system and handrail system；
Instantaneous voltage, transient current and the instantaneous power of the electric control system of escalator.Pass through instantaneous voltage and wink
When the monitorings such as electric current, can identify electric fault and mechanical breakdown.
The status information of this monitoring system monitoring is more full and complete, can be many-sided, multi-angle to escalator
Carry out Failure detection and identification.
The embodiment of the present invention two
A kind of escalator state monitoring method, including step：
S1, the status information of escalator in the process of running is obtained；
S2, the corresponding preprocessed original state information of acquisition is acquired after being pre-processed to the status information of acquisition；
S3, the preprocessed original state information of escalator is parsed, feature extraction processing obtain real-time state feature to
Monitored on-line after amount, early warning and alarming processing, and combine historical failure data and/or expert knowledge library to state feature to
Amount carries out self-learning type intelligent diagnostics and failure predication.
It is further used as preferred embodiment, the preprocessed original state information of escalator is carried out described in the step S3
The step of parsing, feature extraction processing acquisition real-time state feature vector, it is specially：To the reset condition letter of escalator
Breath is pre-processed, successively after Fourier transformation, feature extraction and Fuzzy processing, extraction obtain real-time state feature to
Amount.
Preferred embodiment, the combination historical failure data and/or expert knowledge library are further used as to state spy
The step of sign vector carries out self-learning type intelligent diagnostics and failure predication, specifically includes：
S31, it is trained obtained neural network by using historical failure data state feature vector is examined
Disconnected reasoning, obtains multigroup failure diagnosis information corresponding with state feature vector；
S32, after being integrated using fuzzy theory operator to multigroup failure diagnosis information, preliminary diagnostic result is obtained；
S33, diagnostic result is obtained after being screened according to threshold value screening principle and maximum membership degree screening principle；Threshold value is sieved
It refers to being screened according to predetermined probabilities threshold value to select principle, if the possibility of certain diagnostic result is more than predetermined probabilities threshold value,
Think that the failure exists, otherwise it is assumed that being not present.Such as setting predetermined probabilities threshold value λ ∈ [0,1], such as λ=0.7, when generating certain
When the possibility of kind failure is more than λ, then it is assumed that there may be otherwise it is assumed that it is not possible that there are this failures for this failure.Maximum is subordinate to
Degree screening principle refers to that the size of the possibility generated according to failure carries out descending sort, and possibility the greater is taken to be tied as diagnosis
By.
S34, in response to confirmation message input by user, judge whether diagnostic result is consistent with physical fault, if so, defeated
Terminate after going out diagnostic result, conversely, continuing to execute step S35；
S35, the diagnostic result is stored in special case searching associated with the neural network after training；
S36, judge whether the sum of special example in special case searching reaches predetermined threshold value C, if so, re-starting god
Through network training, and reset special case searching.It is further used as preferred embodiment, the historical failure data includes failure
Diagnostic message and corresponding preprocessed original state information and/or on-line monitoring state, use historical failure described in the step S31
It is trained acquisition in the following manner that data, which are trained obtained neural network,：
S311, to preprocessed original state information and/or on-line monitoring state is pre-processed successively, Fourier transformation, feature carry
It takes with after Fuzzy processing, extraction obtains real-time state feature vector；
S312, the state feature vector that extraction obtains is examined as the input data of neural network, and by corresponding failure
After disconnected information is as the output data of neural network, neural network is trained.
Preferably, in the present embodiment, neural network uses BP neural network, and topological structure is as shown in figure 4, including input
Layer, hidden layer and output layer.Wherein, x1, x2···xnIt is the node of input layer, corresponding states feature vector, y1、y2、ymIt is
The node of output layer, corresponding failure diagnosis information, Wij indicate i-th of node of input layer to the company of j-th of node of hidden layer
Connect weights, Wjk indicates j-th of node of hidden layer to the connection weight of k-th of node of output layer.
In step S311, the process that Fuzzy processing is carried out to vibration data is as follows：Using rise half trapezoidal profile function come
It is normalized again after blurring.It is as follows to be blurred the formula specifically used：
In above formula, _ (Si) indicates that the feature vector obtained after Fuzzy processing, Soi indicate i-th of state feature vector
Standard amplitude when the normal operation of element respective frequencies section, SMi are threshold values corresponding with Soi, and Si is in vibration signals measured
The amplitude of i-th of frequency band.
The formula mode that normalized uses is as follows；
Xi indicates the real-time fault feature vector obtained after Fuzzy processing.It, can after being handled in the above manner
While considering failure degradation, to protrude the energy of major frequency components.
It is also to adopt in a similar manner to carry out Fuzzy processing to temperature data, voice data etc., differs only in formula
Symbol illustrates difference.The application repeats no more.
It is further used as preferred embodiment, real-time state feature vector includes that vibration, sound, temperature and electricity are special
Sign, specifically includes：The rotational frequency of driving motor, vibration acceleration, the peak value of vibration velocity and vibration displacement, peak-to-peak value,
Root value, maximum square value, envelope and rumble spectrum；Wen Sheng, minimum temperature, maximum temperature and the variation of temperature signal
Rate, peak value, mean value, root-mean-square value, crest factor, the kurtosis factor, envelope and the frequency spectrum of acoustic signals；Voltage, electric current and work(
Instantaneous value, phase, mean value, root-mean-square value, maximum value, peak-to-peak value, fundamental wave and harmonic wave and three-phase current unbalance, the electricity of rate
Corrugating radio-frequency component and current waveform radio-frequency component；Operational mode, traffic direction, the speed of service, the safety of escalator are returned
The operating status of at least one of road, inspection switch, cover plate switch, brake and failure code.
By taking vibration data as an example, the spectrogram of vibration signal reflects the vibration overall picture generated when mechanical equipment operation, respectively
The frequency domain character of kind failure is more clear, concentrates, is regular governed.It is former that different frequency components corresponds to different vibrations
Cause substantially may determine that vibration is former by analyzing the amplitude size of various frequencies and causing the major frequency components of vibration
Cause or failure.The amplitude of the score frequency multiplication of some frequencys multiplication and power frequency on usual spectrogram, has concentrated most of energy of vibration,
Embody various vibrational states.Thus the amplitude under these frequencies can be selected as fault signature.For example it chooses some and has
Representative harmonic component (10Hz~0.39X, 0.4X~0.49X, 0.51X~0.99X, 0.5X, 1X, 2X, 3X~5X,>5X,
Strange frequency multiplication) it is used as fault diagnosis feature vector.
On the basis of state feature vector based on vibration above-mentioned, sound, temperature and electricity feature, the present embodiment carries out
One detailed example of fault diagnosis is as shown in figure 5, its specific diagnostic process process is as follows：
First, by the various sensors of sensing subsystem detect the vibration of corresponding unit under test, sound, temperature and
Electric quantity signal.The signal detected is through excitation, amplification and analog/digital conversion signal condition, and then, execution is filtered step, carries
Take the filtering signal of predetermined frequency band corresponding with the natural frequency of unit under test.Hereafter, the number after being filtered is believed
Number execute characteristic extraction step, vibrated, the characteristic quantity of sound, temperature and electricity.The judgement provided by expert knowledge library is accurate
Then and boundary value, fault reference value, including the numerical value of characteristic quantity, envelope and spectral range are obtained by calculating；Fault reference value
The virtual value or peak value of the digital signal of measurement frequency spectrum data when can be arbitrary, or can be counted based on these values
It calculates.Following diagnosis is executed according to fault reference value：(1) judge whether the characteristic quantity of extraction is more than fault reference value.If it is：Refer to
Be out of order position and warning output.Otherwise：It is without exception.(2) whether judging characteristic amount exceeds fault reference envelope, if it is：It looks into
It looks for beyond the general maximum point of envelope, it is otherwise, without exception.After searching the maximum point general beyond envelope, judge to exceed envelope
The historical trend of general maximum point simultaneously calculates whether occurrence frequency is greater than the set value, if it is：Fault pre-alarming, otherwise：It is no different
Often.After fault pre-alarming, whether broken down according to user's input validation, if it is：It carries out failure logging and expert is written knows
Know library；Otherwise, without exception.
By taking vibrations of rotating components Characteristic Extraction as an example, the FFT based on rotational speed signal, which is calculated, to be obtained due to rotating part
The exception of part and the characteristic quantity generated, it may include：Bearing fault characteristics component F x (inner ring fault characteristic frequency fi, outer shroud failure
Characteristic frequency fo, rolling element fault characteristic frequency fbWith retainer fault characteristic frequency fc), the meshing fault feature point with gear
Measure the fault signature component F r of the rotating members such as fg, wheel (rotor unbalance misaligns, couples loosening).
Inner ring fault characteristic frequency fi=Zfo(1+dcosβ/D)/2；
Outer shroud fault characteristic frequency fo=Zfo(1-dcosβ/D)/2；
Rolling element fault characteristic frequency fb=foD/d[1-(dcosβ/D)2]/2；
Retainer fault characteristic frequency fc=fo(1-dcosβ/D)/2；
Wherein, fo(outer) circle rotary speed in expression, d indicate that rolling element diameter, D indicate rolling member pitch diameter, β tables
Show that contact angle [rad], Z indicate the number of rolling element.
The meshing fault characteristic frequency fg=Z of gear1N1/ 60 or fg=Z2N2/ 60, wherein N1Indicate the rotation of gear wheel
Number (unit is rev/min), N2Indicate the rotation number (unit is rev/min) of pinion gear, Z1Indicate the number of teeth of gear wheel, Z2Table
Show the number of teeth of pinion gear.
By taking the monitoring of escalator operation state characteristic quantity as an example, by obtain the operational mode of escalator, traffic direction,
The operating status of the speed of service, safety return circuit, inspection switch, cover plate switch, brake and failure code, tracking, record are automatic
Staircase operational mode (including it is standby, maintenance and it is automatic), traffic direction, the speed of service, safety return circuit, inspection switch, cover board
Switch, brake and failure code.Judge：(1) whether the speed of service is in allowable range, once exceed allowable range, alarm
Output；(2) whether safety return circuit disconnects, if so, according to the safety component that failure code judges to break down, alarm output；
(3) whether the step speed of service is corresponding consistent with driving motor steering with traffic direction, otherwise, is then judged as taking a turn for the worse and report
Alert output；(4) according to the speed of service of record and brake action time, under conditions of load is T, record escalator from
Travel at the uniform speed T0 at the time of starting braking, and the time Ts to escalator stop is adopted in conjunction with the rate curve V (t) of braking process
With even retarding method is segmented, the range ability of T0 → Ts, i.e. braking distance are calculated, judges braking distance whether in allowable range
It is interior, otherwise, alarm output.
In addition, according to the trouble-shooter and method for diagnosing faults of the present embodiment, signal processing is by miniature calculating
Mechanism is at therefore keeping signal processing unitized, and the small-sized formation of trouble-shooter may be implemented or module is formed.
It is to be illustrated to the preferable implementation of the present invention, but the invention is not limited to the implementation above
Example, those skilled in the art can also make various equivalent variations or be replaced under the premise of without prejudice to spirit of that invention
It changes, these equivalent modifications or replacement are all contained in the application claim limited range.
Claims (8)
1. a kind of escalator condition monitoring system, which is characterized in that including sensing subsystem, data acquisition subsystem with
And monitoring, diagnosing main system, the sensing subsystem is for obtaining the status information of escalator in the process of running, institute
It states data acquisition subsystem and obtains corresponding preprocessed original state information simultaneously for acquisition after being pre-processed to the status information of acquisition
It is stored, the monitoring, diagnosing main system is for parsing preprocessed original state information, feature extraction processing obtains in real time
It is monitored on-line after state feature vector, early warning and alarming processing, and combines expert knowledge library or combine historical failure number
According to and expert knowledge library, self-learning type intelligent diagnostics and failure predication are carried out to state feature vector；
The status information includes：
The rotary part of escalator, the vibrational state of support member and guiding parts；
The working environment of escalator, the state of temperature of rotary part, support member, electric control system and lubricant；
The electric control system of escalator, the sound equipment state of drive system, terraced road system and handrail system；
The status information further includes at least one of following state：
The drive system of escalator and the two-dimension temperature state of electric control system；
The operational mode of escalator, traffic direction, the speed of service, safety return circuit, inspection switch, cover plate switch, brake and
At least one of failure code operating status；
The rotating speed of at least one rotary shaft in the drive system of escalator, terraced road system and handrail system；
Instantaneous voltage, transient current and the instantaneous power of the electric control system of escalator；
Wherein, real-time state feature vector includes vibration, sound, temperature and electricity feature, is specifically included：Driving motor turns
Dynamic frequency, vibration acceleration, the peak value of vibration velocity and vibration displacement, peak-to-peak value, root-mean-square value, maximum square value, envelope
Line and rumble spectrum；Wen Sheng, minimum temperature, maximum temperature and the change rate of temperature signal, the peak values of acoustic signals, mean value,
Root value, crest factor, the kurtosis factor, envelope and frequency spectrum；It is voltage, the instantaneous value of electric current and power, phase, mean value, square
Root, maximum value, peak-to-peak value, fundamental wave and harmonic wave and three-phase current unbalance, voltage waveform radio-frequency component and current waveform are high
Frequency ingredient；The operational mode of escalator, traffic direction, the speed of service, safety return circuit, inspection switch, cover plate switch, brake
With the operating status of at least one of failure code.
2. a kind of escalator condition monitoring system according to claim 1, which is characterized in that the monitoring, diagnosing principal series
System includes that field monitoring alarm subsystem, communication subsystem and remote monitoring and diagnosis subsystem, the field monitoring alert subsystem
System is for parsing preprocessed original state information, feature extraction processing is supervised online after obtaining real-time state feature vector
Survey, early warning and alarming processing, and real-time state feature vector is sent to remote monitoring and diagnosis subsystem by communication subsystem
System, the remote monitoring and diagnosis subsystem are used in conjunction with expert knowledge library or combine historical failure data and expert knowledge library,
Self-learning type intelligent diagnostics and failure predication are carried out to state feature vector.
3. a kind of escalator condition monitoring system according to claim 1, which is characterized in that the sensing subsystem
System includes at least one of lower sensor：
Vibrating sensor, at least one of rotary part, support member and guiding parts for obtaining escalator component
Vibrational state；
Temperature sensor, working environment, rotary part, support member, electric control system and profit for acquiring escalator
The temperature of at least one of lubrication prescription；
Infrared imaging sensor, the two of at least one component in the drive system and electric control system for obtaining escalator
Tie up state of temperature；
Sound transducer, for obtaining in the electric control system of escalator, drive system, terraced road system and handrail system
The sound equipment state of at least one component；
Staircase controller communication interface, the working condition of the electric control system for obtaining escalator, the working condition
Including at least one following running state information：The operational mode of escalator, traffic direction, the speed of service, safety return circuit, inspection
Repair at least one of switch, cover plate switch, brake and failure code operating status；
Speed probe, at least one rotary shaft in the drive system, terraced road system and handrail system for obtaining escalator
Rotating speed；
Electrical quantity sensor, instantaneous voltage, transient current and the instantaneous power of the electric control system for obtaining escalator.
4. a kind of escalator condition monitoring system according to claim 2, which is characterized in that the remote monitoring and diagnosis
Subsystem includes：
First state display module, the real-time status feature vector for showing escalator；
First alarm module, it is pre- for being carried out to the operation conditions of escalator according to the real-time status feature vector of escalator
Alert and alarm；
Analyzing and diagnosing module is parsed for the preprocessed original state information to escalator, feature extraction processing obtains in real time
State feature vector, and combine expert knowledge library or combine historical failure data and expert knowledge library, to state feature vector
Carry out self-learning type intelligent diagnostics and failure predication；
Data management module, for escalator preprocessed original state information and/or real-time status feature vector deposited in real time
Storage, inquiry are deleted or are backed up.
5. a kind of escalator condition monitoring system according to claim 4, which is characterized in that the remote monitoring and diagnosis
Subsystem further includes dynamic analog module, and the dynamic analog module is used for according to acquired preprocessed original state information, real-time mould
The operating status of quasi- escalator, escalator is presented by way of image, sound, color, animation and/or text message
Vibrational state, state of temperature, sound equipment state and operating status.
6. a kind of escalator condition monitoring system according to claim 2, which is characterized in that the field monitoring alarm
Subsystem includes main control module, the second state display module and the second alarm module, and the main control module is used for escalator
Preprocessed original state information parsed, feature extraction processing obtains real-time state feature vector and is monitored in real time, described
Second state display module is used to show that the real-time status feature vector of escalator, second alarm module to be used for according to certainly
The real-time status feature vector of dynamic staircase carries out early warning and alarm to the operation conditions of escalator.
7. a kind of escalator state monitoring method, which is characterized in that including step：
S1, the status information of escalator in the process of running is obtained；
S2, the corresponding preprocessed original state information of acquisition is acquired after being pre-processed to the status information of acquisition；
S3, the preprocessed original state information of escalator is parsed, after the real-time state feature vector of feature extraction processing acquisition
It is monitored on-line, early warning and alarming processing, and combines expert knowledge library or combine historical failure data and expertise
Library carries out self-learning type intelligent diagnostics and failure predication to state feature vector；
The combination expert knowledge library or combination historical failure data and expert knowledge library, carry out certainly state feature vector
It the step of learning type intelligent diagnostics and failure predication, specifically includes：
S31, be trained by using historical failure data obtained neural network to state feature vector carry out diagnosis push away
Reason obtains multigroup failure diagnosis information corresponding with state feature vector；
S32, after being integrated using fuzzy theory operator to multigroup failure diagnosis information, preliminary diagnostic result is obtained；
S33, diagnostic result is obtained after being screened according to threshold value screening principle and maximum membership degree screening principle；
S34, in response to confirmation message input by user, judge whether diagnostic result is consistent with physical fault, if so, output examine
Terminate after disconnected result, conversely, continuing to execute step S35；
S35, the diagnostic result is stored in special case searching associated with the neural network after training；
S36, judge whether the sum of special example in special case searching reaches predetermined threshold value, if so, re-starting nerve net
Network training, and reset special case searching.
8. a kind of escalator state monitoring method according to claim 7, which is characterized in that described in the step S3
The preprocessed original state information of escalator is parsed, feature extraction processing obtain real-time state feature vector the step of,
Specially：The preprocessed original state information of escalator is pre-processed successively, Fourier transformation, feature extraction and Fuzzy processing
Afterwards, extraction obtains real-time state feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611004666.XA CN106586796B (en) | 2016-11-15 | 2016-11-15 | A kind of escalator condition monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611004666.XA CN106586796B (en) | 2016-11-15 | 2016-11-15 | A kind of escalator condition monitoring system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106586796A CN106586796A (en) | 2017-04-26 |
| CN106586796B true CN106586796B (en) | 2018-09-14 |
Family
ID=58591049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611004666.XA Active CN106586796B (en) | 2016-11-15 | 2016-11-15 | A kind of escalator condition monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106586796B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3823922B1 (en) * | 2018-07-19 | 2022-08-31 | Inventio AG | Method and device for monitoring a person transport installation using a registration device and a digital doppelgänger |
Families Citing this family (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3180765A1 (en) | 2013-03-29 | 2019-11-21 | Jvckenwood Corporation | Picture decoding device, picture decoding method and picture decoding program |
| CN107194053B (en) * | 2017-05-16 | 2020-10-20 | 歌拉瑞电梯股份有限公司 | Intelligent elevator control system operation fault prediction method |
| CN107271170B (en) * | 2017-07-12 | 2019-05-31 | 西安因联信息科技有限公司 | A kind of automatic diagnosis method and system of mechanical equipment fault type |
| CN107324196A (en) * | 2017-07-24 | 2017-11-07 | 合肥星袖机械科技有限公司 | A kind of Autonomous test safety protective escalator device |
| BR112020008866A2 (en) * | 2017-12-14 | 2020-10-20 | Inventio Ag | process and device for monitoring the status of a people transport facility using a digital doppelganger |
| CN108147257B (en) * | 2017-12-26 | 2019-12-31 | 杭州西奥电梯有限公司 | Attitude control system of elevator car |
| CN108238538B (en) * | 2017-12-28 | 2020-09-04 | 北京市地铁运营有限公司地铁运营技术研发中心 | Fault monitoring method and fault monitoring system of escalator |
| CN115352988A (en) * | 2017-12-29 | 2022-11-18 | 通力电梯有限公司 | Escalator monitoring system, escalator monitoring method, sound data collection device and clamp used for escalator monitoring device |
| CN107973206A (en) * | 2017-12-29 | 2018-05-01 | 通力电梯有限公司 | Escalator lubricating status monitors system and the sound collection means for it |
| CN110412967B (en) * | 2018-04-27 | 2021-05-25 | 万洲电气股份有限公司 | Industrial production line fault diagnosis system and method |
| CN112119027B (en) * | 2018-06-27 | 2022-05-31 | 因温特奥股份公司 | Method for detecting a fault in an elevator and elevator control |
| WO2020016016A1 (en) * | 2018-07-19 | 2020-01-23 | Inventio Ag | Method and device for monitoring a state of a passenger transport system using a digital double |
| CN109655106A (en) * | 2018-07-30 | 2019-04-19 | 杭州哲达科技股份有限公司 | One kind being used for running device Ankang real-time monitoring system |
| CN109324599B (en) * | 2018-09-27 | 2021-04-02 | 蔚来(安徽)控股有限公司 | Method, apparatus, device and medium for determining mechanical failure and compensating for mechanical failure |
| CN109218114B (en) * | 2018-11-12 | 2021-06-08 | 西安微电子技术研究所 | Decision tree-based server fault automatic detection system and detection method |
| CN109626193B (en) * | 2019-01-23 | 2020-05-12 | 广东省特种设备检测研究院珠海检测院 | Bypass variable frequency escalator fault detection method |
| CN109948914B (en) * | 2019-03-05 | 2020-12-11 | 清华大学 | Dynamic risk analysis method for escalator of rail transit junction based on characteristic quantity |
| CN110104533A (en) * | 2019-05-28 | 2019-08-09 | 上海交通大学 | The fault finding system and method for escalator or moving sidewalk |
| CN110517245B (en) * | 2019-08-20 | 2021-09-07 | 北京远舢智能科技有限公司 | Mechanical equipment fault diagnosis system |
| US11548764B2 (en) * | 2019-11-15 | 2023-01-10 | Otis Elevator Company | Selective wireless escalator data acquisition |
| US11292697B2 (en) * | 2019-11-15 | 2022-04-05 | Otis Elevator Company | Frequency analytics of components using internet of things sensor and sensor location on escalators |
| CN111256814A (en) * | 2020-03-13 | 2020-06-09 | 天津商业大学 | Tower monitoring system and method |
| CN111392538A (en) * | 2020-03-17 | 2020-07-10 | 浙江新再灵科技股份有限公司 | Elevator comprehensive fault early warning method based on multi-dimensional Internet of things atlas big data |
| CN111348535B (en) * | 2020-03-18 | 2021-08-27 | 上海应用技术大学 | Health state monitoring system and method for escalator used in rail transit station |
| CN111650919B (en) * | 2020-05-14 | 2021-09-14 | 中铁第四勘察设计院集团有限公司 | Multi-dimensional monitoring escalator fault prediction and health management method and system |
| CN111650918A (en) * | 2020-05-14 | 2020-09-11 | 中铁第四勘察设计院集团有限公司 | Vertical elevator full-life cycle operation safety monitoring system |
| CN111562096B (en) * | 2020-05-14 | 2022-07-19 | 中铁第四勘察设计院集团有限公司 | Real-time online health state monitoring system of escalator |
| CN111874786B (en) * | 2020-06-19 | 2022-08-30 | 日立电梯（广州）自动扶梯有限公司 | Operation control method and device for carrying equipment, operation control equipment and medium |
| CN112561280B (en) * | 2020-12-09 | 2023-04-18 | 中铁第四勘察设计院集团有限公司 | Equipment fault prediction method based on self-learning convergence fault knowledge base and application thereof |
| CN112905672A (en) * | 2021-04-14 | 2021-06-04 | 江苏普瑞尔特控制工程有限公司 | Fault diagnosis expert analysis system |
| CN113705924B (en) * | 2021-09-07 | 2023-10-13 | 华能威海发电有限责任公司 | Intelligent diagnosis method and system for thermal control equipment |
| CN114923107B (en) * | 2022-05-05 | 2024-04-05 | 广州广日电梯工业有限公司 | Escalator lubrication control method and device based on Internet of things and cluster analysis |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5344797B2 (en) * | 2007-03-13 | 2013-11-20 | 東芝エレベータ株式会社 | Remote monitoring system with variable function of escalator |
| JP5559305B2 (en) * | 2009-04-20 | 2014-07-23 | オーチス エレベータ カンパニー | Automatic adjustment of parameters for safety devices |
| JP5879214B2 (en) * | 2012-06-27 | 2016-03-08 | 株式会社日立製作所 | Abnormality diagnosis method, abnormality diagnosis device, and passenger conveyor equipped with abnormality diagnosis device |
| CN104891319A (en) * | 2015-05-15 | 2015-09-09 | 江南嘉捷电梯股份有限公司 | Energy-saving escalator or passenger conveyor and running control method thereof |
| CN205158082U (en) * | 2015-11-05 | 2016-04-13 | 杭州冷倍冠科技有限公司 | Moving staircase control system |
-
2016
- 2016-11-15 CN CN201611004666.XA patent/CN106586796B/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3823922B1 (en) * | 2018-07-19 | 2022-08-31 | Inventio AG | Method and device for monitoring a person transport installation using a registration device and a digital doppelgänger |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106586796A (en) | 2017-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106586796B (en) | A kind of escalator condition monitoring system and method | |
| CN106006344B (en) | Staircase On-line Fault early warning system and method for diagnosing faults | |
| CN109001649B (en) | Intelligent power supply diagnosis system and protection method | |
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN105800413B (en) | Elevator failure diagnosis device and method | |
| CN107247230B (en) | Rotary motor state monitoring method based on support vector machine and data driving | |
| CN107271170B (en) | A kind of automatic diagnosis method and system of mechanical equipment fault type | |
| CN105692383B (en) | Elevator failure diagnosis device, method and controller | |
| US6694286B2 (en) | Method and system for monitoring the condition of an individual machine | |
| CN110002329B (en) | A kind of escalator on-line monitoring early warning system and method based on cloud platform | |
| CN110766277B (en) | Health assessment and diagnosis system and mobile terminal for nuclear industry field | |
| CN102192825A (en) | User interface system and method for diagnosing a rotating machine condition not based upon prior measurement history | |
| CN104176613B (en) | The abnormity diagnostic system of passenger conveyors | |
| CN107884214B (en) | A kind of train EEF bogie unit failure multi-parameter comprehensive decision-making technique and device | |
| CN109613428A (en) | It is a kind of can be as system and its application in motor device fault detection method | |
| CN107144303A (en) | A kind of fault detection system of mineral electromechanical equipment, method and device | |
| EP2665925A1 (en) | A method for diagnostic monitoring of a wind turbine generator system | |
| CN104266841A (en) | Fault diagnosis device and diagnosis method of diesel engine | |
| CN112213131B (en) | Rotary machine overhauls and fault diagnosis analog system | |
| CN108238538A (en) | The fault monitoring method and fault monitoring system of a kind of escalator | |
| CN106494960A (en) | A kind of lift running safety monitoring and initial failure early warning system and method | |
| CN109444575A (en) | Motor driving system runs health state evaluation system and method | |
| CN107844067A (en) | A kind of gate of hydropower station on-line condition monitoring control method and monitoring system | |
| Leonidovich et al. | The development and use of diagnostic systems and estimation of residual life in industrial electrical equipment | |
| CN110044616A (en) | A kind of railway locomotive bearing and gear failure diagnosing method and diagnostic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |