CN112607555A - Training method and detection method of model for elevator guide rail state detection - Google Patents
Training method and detection method of model for elevator guide rail state detection Download PDFInfo
- Publication number
- CN112607555A CN112607555A CN202011325442.5A CN202011325442A CN112607555A CN 112607555 A CN112607555 A CN 112607555A CN 202011325442 A CN202011325442 A CN 202011325442A CN 112607555 A CN112607555 A CN 112607555A
- Authority
- CN
- China
- Prior art keywords
- elevator
- data
- guide rail
- real
- time
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B7/00—Other common features of elevators
- B66B7/12—Checking, lubricating, or cleaning means for ropes, cables or guides
- B66B7/1207—Checking means
- B66B7/1246—Checking means specially adapted for guides
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
- B66B1/3492—Position or motion detectors or driving means for the detector
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0037—Performance analysers
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
- Maintenance And Inspection Apparatuses For Elevators (AREA)
Abstract
The embodiment of the invention discloses a training method and a detection method of a model for detecting the state of an elevator guide rail. The method comprises the steps of obtaining elevator data of at least two dimensions of guide rail vibration information, elevator running speed and elevator position information at a plurality of moments, and training a preset neural network at least based on the elevator data at the plurality of moments. The guide rail plays a guiding role when the elevator runs, and simultaneously bears the impact of a car and the elevator during braking and the impact force of the safety tongs during emergency braking, so the running state of the guide rail can indirectly reflect the state of the whole elevator system.
Description
Technical Field
The invention relates to the technical field of elevator fault diagnosis, in particular to a training method, a detection system, a device, equipment and a storage medium of a model for elevator guide rail state detection.
Background
With the development of socio-economy, elevators have become common transportation tools in high-rise buildings, but safety accidents also happen occasionally.
At present, people have developed a great deal of research aiming at the safety monitoring of elevators, and the monitoring of traction machines and lift cars of the elevators is generally adopted. Because the elevator system is comparatively complicated, when the elevator moves, the running state of the elevator can not be comprehensively monitored only by monitoring the states of the traction machine and the lift car, so that the safety monitoring of the elevator has a leak, and the safety of the elevator can not be guaranteed.
Therefore, the safety monitoring method of the elevator at present has security holes, and the safety of the elevator cannot be guaranteed.
Disclosure of Invention
The embodiment of the invention provides a training method, a detection system, a device, equipment and a storage medium of a model for detecting the state of an elevator guide rail, which solve the problem of security holes in the prior technical scheme, ensure the safety of the elevator and improve the safety of the elevator.
In order to solve the technical problems, the invention comprises the following steps:
in a first aspect, a training method for a model for elevator guide rail condition detection is provided, the training method comprising:
obtaining elevator data at a plurality of moments, wherein the elevator data comprises data of at least two dimensions in guide rail vibration information, elevator running speed and elevator position information;
and training a preset neural network based on the elevator data at a plurality of moments.
In some implementations of the first aspect, training the preset neural network based on elevator data at a plurality of times further comprises:
fusing data of at least two dimensions in the elevator data at multiple moments to obtain fused data;
and training the preset neural network based on the fusion data.
In some implementations of the first aspect, fusing data of at least two dimensions in the elevator data at a plurality of times to obtain fused data, includes:
acquiring N elevator data of each dimension in elevator data of at least two dimensions;
the N elevator data of each dimension are fused into fused data of at least two dimensions.
In some implementations of the first aspect, obtaining N elevator data for each dimension of at least two dimensions of elevator data comprises:
and acquiring N elevator data of each of at least two dimensions from the elevator data at a plurality of moments in a sliding window mode.
In some implementations of the first aspect, fusing the N elevator data of each dimension into fused data of at least two dimensions includes:
carrying out normalization processing on the N elevator data of each dimension to obtain N normalized elevator data of each dimension;
and fusing the N normalized elevator data of each dimension into fused data of at least two dimensions.
In a second aspect, a method for detecting a state of an elevator guide rail is provided, the method comprising:
acquiring real-time elevator data at a plurality of moments, wherein the real-time elevator data comprises data of at least two dimensions in real-time guide rail vibration information, real-time elevator running speed and real-time elevator position information;
the method comprises the steps of calculating real-time elevator data by using a model to obtain state data of the elevator guide rail, wherein the model is obtained based on the first aspect and a training method in some implementation modes of the first aspect.
In a third aspect, a detection system for elevator guide rail condition is provided, the detection system comprising:
the guide rail vibration information acquisition equipment is used for acquiring real-time guide rail vibration information of the elevator at multiple moments;
the elevator running speed acquisition equipment is used for acquiring the real-time elevator running speeds at multiple moments;
the elevator position information acquisition equipment is used for acquiring real-time elevator position information at multiple moments;
a processor for calculating real-time elevator data comprising data of at least two dimensions of real-time guide rail vibration information, real-time elevator operation speed and real-time elevator position information using a model to obtain state data of the elevator guide rail, wherein the model is obtained based on the first aspect and the training methods in some implementations of the first aspect.
In some implementation manners of the third aspect, the processor is further configured to generate alarm information according to the state data when the state data meets a preset condition, and send the alarm information to the client, so that the client generates prompt information according to the alarm information.
In a fourth aspect, there is provided a training apparatus for a model for elevator guide rail condition detection, the training apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring elevator data at a plurality of moments, and the elevator data comprises data of at least two dimensions in guide rail vibration information, elevator running speed and elevator position information;
and the processing module is used for training the preset neural network based on the elevator data at a plurality of moments.
In some implementations of the fourth aspect, the processing module is further configured to fuse data of at least two dimensions in the elevator data at multiple times to obtain fused data; and training the preset neural network based on the fusion data.
In some implementations of the fourth aspect, the obtaining module is further configured to obtain N elevator data of each dimension from among the elevator data of at least two dimensions;
and the processing module is also used for fusing the N elevator data of each dimension into fused data of at least two dimensions.
In some implementations of the fourth aspect, the processing module is further configured to obtain N elevator data for each of the at least two dimensions from the elevator data at the plurality of times by means of a sliding window.
In some implementation manners of the fourth aspect, the processing module is further configured to perform normalization processing on the N elevator data of each dimension to obtain N normalized elevator data of each dimension; and fusing the N normalized elevator data of each dimension into fused data of at least two dimensions.
In a fifth aspect, there is provided a detection device for detecting a state of a guide rail of an elevator, the detection device comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring real-time elevator data at a plurality of moments, and the real-time elevator data comprises data of at least two dimensions in real-time guide rail vibration information, real-time elevator running speed and real-time elevator position information;
a processing module for calculating real-time elevator data using a model to obtain state data of the elevator guide rails, wherein the model is obtained based on the first aspect and the training method in some implementations of the first aspect.
In a sixth aspect, an electronic device is provided, which includes: a processor and a memory storing computer program instructions;
the computer program instructions, when executed by a processor, implement the first aspect and the training method in some implementations of the first aspect or the detection method of the second aspect.
In a seventh aspect, a computer storage medium is provided, which is characterized by having stored thereon computer program instructions, which, when executed by a processor, implement the first aspect and the training method in some implementations of the first aspect, or implement the detection method of the second aspect.
The embodiment of the invention provides a training method, a detection system, a device, equipment and a storage medium of a model for detecting the state of an elevator guide rail. The detection of the state of the guide rail of the elevator is realized by acquiring the vibration information of the guide rail, the running speed of the elevator and the position information of the elevator, and training the elevator data at a plurality of moments of at least two dimensions in the vibration information of the guide rail, the running speed of the elevator and the position information of the elevator through a neural network to obtain a model for detecting the state of the guide rail of the elevator. Therefore, the complex relation among the vibration of the guide rail, the position of the elevator in operation, the operation speed and the fault of the guide rail is identified, and the fault diagnosis and monitoring accuracy of the elevator guide rail is further improved. And because the guide rail plays a guiding role when the elevator operates, and simultaneously bears the impact of the elevator car and the elevator during braking and the impact force of the safety tongs during emergency braking, the operating state of the safety tongs can indirectly reflect the state of the whole elevator system, so the embodiment of the invention solves the problem of safety leak existing in the conventional elevator safety monitoring method by detecting the state of the guide rail of the elevator, and ensures the safety of the elevator.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a detection system for detecting the state of a guide rail of an elevator according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a training method for a model for elevator guide rail condition detection according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for detecting the state of an elevator guide rail according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a training device for a model for elevator guide rail state detection according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a detecting device for detecting the state of a guide rail of an elevator according to an embodiment of the present invention;
fig. 6 is a block diagram of a computing device provided by an embodiment of the invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
With the development of socio-economy, elevators have become common conveying tools on high-rise buildings, but safety accidents happen sometimes.
Because the artificial intelligence technology is rapidly developed in recent years, based on the background, the elevator safety monitoring system combining artificial intelligence and big data improves the monitoring efficiency and accuracy, and brings great promotion to the safe operation of the elevator.
However, currently, a safety monitoring system for an elevator generally monitors a hoisting machine and a car of the elevator. In addition, people judge the abnormal monitoring scheme of each part of the elevator based on single sensor data. Therefore, the safety monitoring method of the elevator at present has security holes, and the safety of the elevator cannot be guaranteed.
In order to solve the problems of security holes existing in the prior technical scheme and incapability of guaranteeing the safety of an elevator, the embodiment of the invention provides a training method, a detection system, a device, equipment and a storage medium for a model for detecting the state of an elevator guide rail. The detection of the state of the elevator guide rail is realized by obtaining elevator data at a plurality of moments of at least two dimensions in guide rail vibration information, elevator running speed and elevator position information and training a preset neural network based on the elevator data at the plurality of moments to obtain a model for detecting the state of the elevator guide rail. And because the guide rail plays a guiding role when the elevator operates, and simultaneously bears the impact of the elevator car and the elevator during braking and the impact force of the safety tongs during emergency braking, the operating state of the safety tongs can indirectly reflect the state of the whole elevator system, so the embodiment of the invention solves the problem of safety leak existing in the conventional elevator safety monitoring method by detecting the state of the guide rail of the elevator, and further ensures the safety of the elevator.
The technical solutions provided by the embodiments of the present invention are described below with reference to the accompanying drawings.
Since the training method of the model for elevator guide rail state detection and the detection method are implemented based on the detection system, the configuration of the detection system can be described first.
As shown in fig. 1, fig. 1 is a schematic structural diagram of a detection system for detecting a state of an elevator guide rail according to an embodiment of the present invention, where the detection system may include: a guide rail vibration information acquisition device 101, an elevator running speed acquisition device 102, an elevator position information acquisition device 103, a processor 104 and a client 105.
The guide rail vibration information acquisition device 101 can be used for acquiring real-time guide rail vibration information of an elevator at multiple moments.
The guide rail vibration information acquisition equipment can be vibration acceleration sensors arranged on the left guide rail and the right guide rail.
The elevator running speed acquisition device 102 may be used to acquire real-time elevator running speeds at a plurality of times.
Wherein, the elevator running speed acquisition equipment can be a three-axis acceleration sensor arranged on the top of the elevator car.
The elevator position information collecting device 103 can be used for collecting real-time elevator position information at multiple moments.
The elevator position information acquisition equipment can be an RFID sensor arranged at the top of an elevator car, and can acquire real-time elevator position information at multiple moments by reading preset floor information.
The processor 104 may be configured to calculate real-time elevator data including data for at least two dimensions of real-time guide rail vibration information, real-time elevator run speed, and real-time elevator position information using a model to obtain state data for the elevator guide rail, wherein the model is obtained based on the training method of fig. 2.
In addition, in order to prompt the user in time when the state data meets the preset condition, in an embodiment, the processor 104 may be further configured to generate alarm information according to the state data when the state data meets the preset condition, and send the alarm information to the client 105, so that the client generates prompt information according to the alarm information to prompt the user.
The elevator guide rail state detection system provided by the embodiment of the invention can respectively collect real-time guide rail vibration information, real-time elevator running speed and real-time elevator position information through the guide rail vibration information collection equipment, the running speed collection equipment and the floor data collection equipment, and then the processor calculates real-time elevator data comprising data of at least two dimensions in the real-time guide rail vibration information, the real-time elevator running speed and the real-time elevator position information according to the model obtained by the training method in figure 2 to obtain the state data of the elevator guide rail, so that the state of the elevator guide rail is detected. And because the guide rail plays a guiding role when the elevator operates, and simultaneously bears the impact of the elevator car and the elevator during braking and the impact force of the safety tongs during emergency braking, the operating state of the safety tongs can indirectly reflect the state of the whole elevator system, so the embodiment of the invention solves the problem of safety leak existing in the conventional elevator safety monitoring method by detecting the state of the guide rail of the elevator, and further ensures the safety of the elevator.
Fig. 2 is a schematic flow chart of a training method of a model for elevator guide rail state detection according to an embodiment of the present invention. The method execution subject can be a terminal device or a cloud device.
As shown in fig. 2, the training method of a model for elevator guide rail condition detection may include:
s201: elevator data at a plurality of times is acquired.
Wherein the elevator data may comprise data in at least two dimensions of guide rail vibration information, elevator travel speed and elevator position information.
Because the types of elevator data collected by different sensors are different, before a model for detecting the state of an elevator guide rail is trained according to the elevator data, the elevator data of each dimensionality needs to be preprocessed, so that the number of the data of each dimensionality is uniform and meets the calculation requirement.
In one embodiment, for the guide rail vibration information, since the guide rail vibration information is determined according to the guide rail acceleration, the sampling frequency of the guide rail acceleration is higher, and the amount of data collected in the same time length is larger. The rail acceleration includes vibration data of the left and right rails, and the sampling frequency and the sampling time of the left and right rails are the same, and the data lengths of the left and right rails are equal to each other. Therefore, for the guide rail vibration data, absolute values of the left and right guide rail vibration data can be respectively obtained to obtain the absolute size of the guide rail vibration data, and then corresponding points of the obtained left and right guide rail vibration data are averaged to be used as the final guide rail vibration data, so that the comprehensive guide rail vibration information can be reflected by a small amount of data.
Specifically, the vibration data of the left rail may be as shown in formula (1), and the vibration data of the right rail may be as shown in formula (2).
Wherein left _ vibration represents vibration data of the left rail,
representing vibration data of the left guide rail at the nth time; right _ vibration represents vibration data of the right rail,
and (3) representing vibration data of the right guide rail at the nth time.
According to the guide rail vibration data shown in the formula (1) and the formula (2), absolute values of the left and right guide rail data are respectively obtained to obtain absolute sizes of the guide rail vibration data, corresponding points of the obtained left and right guide rail vibration data are averaged, and the process of using the absolute sizes as the final guide rail vibration data can be shown in the formula (3).
Wherein combined _ vib represents the final data of the guide rail vibration, i.e. the guide rail vibration information; abs () represents an absolute value operation.
Through the calculation process of the formula (3), the comprehensive guide rail vibration information can be reflected by a small amount of data, and the calculation resources of a processor are saved.
In one embodiment, the preprocessing process may include, after elevator data of multiple dimensions including guide rail vibration information, elevator running speed, and elevator position information is acquired, filtering and filtering the data of each dimension according to the total number of the data of each dimension and a preset number of the data, so that the number of the data of each dimension is uniform and meets the calculation requirement, and fused data is obtained to facilitate subsequent calculation.
In the specific preprocessing process, the sliding distance of the sliding window, that is, the jump interval of the sliding window, may be determined according to the total number of the data of each dimension and the preset number of the data.
The process of determining the sliding distance may specifically be: and calculating the total number of data/a preset number of data of each dimension, wherein the preset number of data can be N, and then taking a maximum integer X not exceeding the value, wherein the integer X is used as a sliding distance.
After the sliding distance is determined, the sliding window can be determined according to the preset one-dimensional Gaussian filter function, the standard deviation of the preset one-dimensional Gaussian filter function and the number of elements (which is an odd number) preset by the sliding window.
The preset one-dimensional gaussian filter function can be shown as formula (4).
In equation (4), δ is a preset standard deviation, and the one-dimensional gaussian filter function is a probability density function of a normal distribution.
And then, determining a sliding window according to the preset number of elements, a preset one-dimensional Gaussian filter function and a preset standard deviation.
After the sliding window is determined, the data of each dimension can be calculated according to the sliding window and the moving distance, and the data of each dimension, the number of which is uniform and is N, after filtering is obtained.
In addition, because the numerical value of the floor data of the elevator may be relatively large, the floor data of the elevator which is uniform in quantity and filtered can be normalized by preprocessing the floor data of the elevator.
For example, the highest floor of the building is P, when the floor of the elevator is Q, the floor is normalized to obtain Q/P, and the Q/P is normalized floor data. The floor data of the elevator is processed twice, so that a floor data sequence which is uniform in quantity with other dimension data and has a numerical value of 0,1 can be obtained.
In a specific embodiment, the data of one elevator in a building with 33 floors can be preprocessed. The specific process can be data such as guide rail vibration information, elevator running speed, elevator position information and the like in the primary running process of the elevator. The reporting frequency of the guide rail vibration information, the elevator running speed and the elevator position information acquisition can be set to be 0.1s for uploading once, 100 original data are continuously acquired in the running process of the elevator, and the 100 original data can be shown in table 1.
TABLE 1
| Serial number | Left guide rail vibration | Vibration of right guide rail | Speed of elevator operation | Elevator position information (floor) |
| 1 | 0.1687514 | -0.3697556 | 0.176571 | 3 |
| 2 | -0.28387560 | 0.1789523 | 0.58571 | 3 |
| 3 | -0.11643124 | -0.4687514 | 0.61683 | 3 |
| … | … | … | … | .. |
| 100 | -0.09643177 | 0.2656534 | 0.06683 | 20 |
In the subsequent filtering process, the preset number N of data may be 30, the preset number of elements of the sliding window is 3, the standard deviation δ is 0.5, the coefficient of the sliding window is calculated as [0.63,1,0.63] according to the gaussian filter formula, and the result of rounding 100/30 is taken to determine that the sliding distance S of the sliding window is 3.
And then, calculating the vibration data of the left guide rail and the vibration data of the right guide rail in the table 1 according to a formula (3) to obtain the final vibration data of the guide rail, calculating the final vibration data of the guide rail, the running speed and the floor information according to the coefficient of a sliding window and the sliding distance to obtain N pieces of vibration information of the guide rail, N pieces of running speed and N pieces of position data of the elevator, and carrying out normalization processing on the position data of the elevator to obtain the final data shown in the table 2.
TABLE 2
| Serial number | Rail vibration information | Speed of elevator operation | Elevator position data (after normalization) |
| 1 | 0.2527 | 0.1471 | 0.12 |
| 2 | 0.2879 | 0.48571 | 0.32 |
| 3 | 0.2121 | 0.11683 | 0.46 |
| … | … | … | … |
| 30 | 0.0087 | 0.02683 | 0.60 |
After preprocessing the data of each dimension, fused data is obtained, and model training can be performed, that is, the step S202 is performed.
S202: and training a preset neural network to obtain a model at least based on the elevator data at a plurality of moments.
After the data preprocessing of S201, a data set may be constructed according to the preprocessed fusion data of the three dimensions, so as to train a preset neural network. Because the number of data for each dimension is uniform after the data for each dimension is preprocessed, in one embodiment, the data set may be [ N, N ].
The preset neural network is used for calculating the possibility of various faults of the guide rail, namely P (X | Y), Y represents the data set collected by one operation of the elevator, and X is the type of the fault of the elevator. Because the convolutional layer in the neural network has direction invariance, the features in the input data set can be automatically extracted, and therefore the failure type of the elevator can be determined by fusing multi-sensor data by adopting the neural network.
Because the neural network cannot accurately output the fault type through one-time calculation, the neural network can be trained by calculating a loss value through a loss function so as to obtain the neural network meeting the preset condition.
In the process of training the neural network, a data set can be calculated according to a preset neural network to obtain first state data, wherein the first state data refer to the fault type of the elevator obtained by the first calculation, and because the obtained fault type is larger than the real fault type of the elevator corresponding to the data set, namely, the real fault type is larger than the second state data, a loss value can be determined according to the difference value between the first state data and the second state data, and parameters of the neural network are updated according to the loss value until the neural network corresponding to the loss value meeting the preset condition is used as a model for detecting the state of the guide rail of the elevator when the loss value meets the preset condition.
The preset parameters of the neural network may be as shown in table 3.
TABLE 3
In table 3, for the preset parameters of the neural network to be updated in the neural network, as shown in table 3, the parameters of the neural network to be updated include parameters of a Linear rectification function (ReLU), parameters of a Batch Normalization (BN) layer, and partial parameters of a residual sum.
In addition, it should be noted that the second condition data may include at least one of a dynamic shoe imbalance, a rail deformation, and a normality. For the second state data, One-Hot encoding (One-Hot) processing can also be performed on the second state data.
In one embodiment, the loss function may be as shown in equation (5)
FL(pt)＝-αt(1-pt)γlog(pt) (5)
Wherein alpha istMay be a unit step function; ptIs a predictor of a data set; (1-P)t) Is the modulation factor; gamma is a set parameter for adjusting the steepness of the weight curve.
In addition, in the training process, an Adam gradient descent method can be adopted, the learning rate can be adaptively trained according to first-order momentum and second-order momentum, and when the loss value of the trained neural network meets a preset condition, the trained neural network is used as the model for detecting the state of the elevator guide rail to detect the state of the elevator guide rail. The preset condition may specifically mean that the loss value is smaller than a preset threshold.
According to the training method for the elevator guide rail state detection model provided by the embodiment of the invention, the model for the elevator guide rail state detection is obtained by acquiring the guide rail vibration information, the elevator running speed and the elevator position information and training the elevator data at a plurality of moments of at least two dimensions in the guide rail vibration information, the elevator running speed and the elevator position information through the neural network. The identification of complex relationships among the vibration of the guide rail, the position of the elevator in operation, the operation speed and the fault of the guide rail is realized, and the accuracy of fault diagnosis and monitoring of the elevator guide rail is further improved. And because the guide rail plays a guiding role when the elevator operates, and simultaneously bears the impact of the elevator car and the elevator during braking and the impact force of the safety tongs during emergency braking, the operating state of the safety tongs can indirectly reflect the state of the whole elevator system, so the embodiment of the invention solves the problem of safety leak existing in the conventional elevator safety monitoring method by detecting the state of the guide rail of the elevator, and ensures the safety of the elevator.
Fig. 3 is a flow chart of a method for detecting the state of an elevator guide rail according to an embodiment of the present invention.
The method may be implemented by a terminal device or a cloud device, as shown in fig. 3, and the method for detecting the state of the elevator guide rail may include:
s301: real-time elevator data at multiple times is obtained.
Wherein the real-time elevator data may include data for at least two dimensions of real-time rail vibration information, real-time elevator operating speed, and real-time elevator position information.
S302: and calculating the real-time elevator data by using the model to obtain the state data of the elevator guide rail.
Wherein the model is obtained based on the training method in fig. 2, and the state data includes at least one of dynamic unbalance of the guide shoe, deformation of the guide rail, and normality.
Specifically, the type probabilities of different faults can be obtained by calculating the elevator data by using the model, the fault corresponding to the maximum probability value is taken as the fault type, and the fault type is the state data of the elevator guide rail.
The method for detecting the state of the elevator guide rail provided by the embodiment of the invention uses a model for detecting the state of the elevator guide rail, which is obtained by training elevator data of a plurality of moments of at least two dimensions in guide rail vibration information, elevator running speed and elevator position information through a neural network in advance, to determine the state data of the elevator guide rail. The identification of complex relationships among the vibration of the guide rail, the position of the elevator in operation, the operation speed and the fault of the guide rail is realized, and the accuracy of fault diagnosis and monitoring of the elevator guide rail is further improved. And because the guide rail plays a guiding role when the elevator operates, and simultaneously bears the impact of the elevator car and the elevator during braking and the impact force of the safety tongs during emergency braking, the operating state of the safety tongs can indirectly reflect the state of the whole elevator system, so the embodiment of the invention solves the problem of safety leak existing in the conventional elevator safety monitoring method by detecting the state of the guide rail of the elevator, and ensures the safety of the elevator.
Corresponding to the embodiment of the training method of the model for detecting the state of the elevator guide rail, the embodiment of the invention also provides a training device of the model for detecting the state of the elevator guide rail.
Fig. 4 is a schematic structural diagram of a training device for a model for elevator guide rail state detection according to an embodiment of the present invention. As shown in fig. 4, the training apparatus may include:
the obtaining module 401 may be configured to obtain elevator data at a plurality of times.
The elevator data comprises data of at least two dimensions in guide rail vibration information, elevator running speed and elevator position information;
the processing module 402 may be configured to train a preset neural network based on elevator data at a plurality of times.
The processing module 402 may also be configured to fuse data of at least two dimensions in the elevator data at multiple times to obtain fused data; and training a preset neural network based on the fusion data.
The processing module 402 may further be configured to obtain N elevator data of each dimension from among the elevator data of at least two dimensions; fusing the N elevator data of each dimension into the fused data of at least two dimensions.
The processing module 402 may be further configured to obtain N elevator data of each of at least two dimensions from the elevator data at the multiple times in a sliding window manner.
The processing module 402 may also be configured to perform normalization processing on the N elevator data of each dimension to obtain N normalized elevator data of each dimension; fusing the normalized N elevator data of each dimension into the fused data of at least two dimensions.
It can be understood that each module in the training apparatus shown in fig. 4 has a function of implementing each step in fig. 2, and can achieve the corresponding technical effect, and for brevity, no further description is provided herein.
The training device for the elevator guide rail state detection model, provided by the embodiment of the invention, acquires guide rail vibration information, elevator running speed and elevator position information, and trains elevator data of at least two dimensions of the guide rail vibration information, the elevator running speed and the elevator position information at multiple moments through a neural network to obtain the elevator guide rail state detection model. The identification of complex relationships among the vibration of the guide rail, the position of the elevator in operation, the operation speed and the fault of the guide rail is realized, and the accuracy of fault diagnosis and monitoring of the elevator guide rail is further improved. And because the guide rail plays a guiding role when the elevator operates, and simultaneously bears the impact of the elevator car and the elevator during braking and the impact force of the safety tongs during emergency braking, the operating state of the safety tongs can indirectly reflect the state of the whole elevator system, so the embodiment of the invention solves the problem of safety leak existing in the conventional elevator safety monitoring method by detecting the state of the guide rail of the elevator, and ensures the safety of the elevator.
Corresponding to the embodiment of the detection method of the elevator guide rail state, the embodiment of the invention also provides a detection device of the elevator guide rail state.
Fig. 5 is a schematic structural diagram of a detecting device for detecting the state of an elevator guide rail according to an embodiment of the present invention. As shown in fig. 5, the apparatus for detecting the state of the elevator guide rails may include:
the obtaining module 501 may be configured to obtain real-time elevator data at multiple times.
The real-time elevator data comprises data of three dimensions of real-time guide rail acceleration, real-time running speed and real-time elevator position information.
The processing module 502 may be configured to calculate real-time elevator data using the model to obtain state data of the elevator guide rails.
Wherein the model is obtained based on the training method in fig. 2, and the state data includes at least one of dynamic unbalance of the guide shoe, deformation of the guide rail, and normality.
It can be understood that each module in the detection apparatus shown in fig. 5 has a function of implementing each step in fig. 3, and can achieve the corresponding technical effect, and for brevity, no further description is provided herein.
The detection device for the state of the elevator guide rail provided by the embodiment of the invention determines the state data of the elevator guide rail by using a model obtained by fusing and training the elevator data at a plurality of moments of at least two dimensions in the vibration information of the guide rail, the running speed of the elevator and the position information of the elevator in advance through a neural network. The identification of complex relationships among the vibration of the guide rail, the position of the elevator in operation, the operation speed and the fault of the guide rail is realized, and the accuracy of fault diagnosis and monitoring of the elevator guide rail is further improved. And because the guide rail plays a guiding role when the elevator operates, and simultaneously bears the impact of the elevator car and the elevator during braking and the impact force of the safety tongs during emergency braking, the operating state of the safety tongs can indirectly reflect the state of the whole elevator system, so the embodiment of the invention solves the problem of safety leak existing in the conventional elevator safety monitoring method by detecting the state of the guide rail of the elevator, and ensures the safety of the elevator.
Fig. 6 is a block diagram of a hardware architecture of a computing device according to an embodiment of the present invention. As shown in fig. 6, computing device 600 includes an input device 601, an input interface 602, a central processor 603, a memory 604, an output interface 605, and an output device 606. The input interface 602, the central processing unit 603, the memory 604, and the output interface 605 are connected to each other via a bus 610, and the input device 601 and the output device 606 are connected to the bus 610 via the input interface 602 and the output interface 605, respectively, and further connected to other components of the computing device 600.
Specifically, the input device 601 receives input information from the outside, and transmits the input information to the central processor 603 through the input interface 602; the central processor 603 processes input information based on computer-executable instructions stored in the memory 604 to generate output information, stores the output information temporarily or permanently in the memory 604, and then transmits the output information to the output device 606 through the output interface 605; output device 606 outputs output information to the exterior of computing device 600 for use by a user.
That is, the calculation device shown in fig. 6 can also be implemented as a training device for a model of elevator guide rail state detection, or as a detection device for elevator guide rail state, which training device, or detection device, can comprise: a memory storing computer-executable instructions, and a processor. The processor, when executing the computer-executable instructions, may implement a method for training a model for elevator guide rail state detection, or a method for detecting elevator guide rail state, provided by embodiments of the present invention.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium has computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement a method for training a model for elevator guide rail state detection, or a method for detecting elevator guide rail state, provided by embodiments of the present invention.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuits, semiconductor Memory devices, Read-Only memories (ROMs), flash memories, Erasable Read-Only memories (EROMs), floppy disks, Compact disk Read-Only memories (CD-ROMs), optical disks, hard disks, optical fiber media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (12)
1. A training method for a model for elevator guide rail condition detection, characterized in that the training method comprises:
obtaining elevator data at a plurality of moments, wherein the elevator data comprises data of at least two dimensions in guide rail vibration information, elevator running speed and elevator position information;
and training a preset neural network based on the elevator data at the plurality of moments.
2. The training method of claim 1, wherein the training a preset neural network based on the elevator data at the plurality of time instants comprises:
fusing data of at least two dimensions in the elevator data at multiple moments to obtain fused data;
and training a preset neural network based on the fusion data.
3. The training method according to claim 2, wherein the fusing the data of at least two dimensions in the elevator data at the plurality of time points to obtain fused data comprises:
acquiring N elevator data of each dimension in elevator data of at least two dimensions;
fusing the N elevator data of each dimension into the fused data of at least two dimensions.
4. The training method of claim 3, wherein the obtaining of the at least two dimensions of elevator data, N elevator data for each dimension, comprises:
and acquiring N elevator data of each of at least two dimensions from the elevator data at the plurality of moments in a sliding window mode.
5. Training method according to claim 4, wherein said fusing N elevator data of each dimension into said fused data of at least two dimensions comprises:
carrying out normalization processing on the N elevator data of each dimension to obtain N normalized elevator data of each dimension;
fusing the normalized N elevator data of each dimension into the fused data of at least two dimensions.
6. A method of detecting a condition of an elevator guide rail, the method comprising:
acquiring real-time elevator data at a plurality of moments, wherein the real-time elevator data comprises data of at least two dimensions in real-time guide rail vibration information, real-time elevator running speed and real-time elevator position information;
calculating the real-time elevator data using a model to obtain state data of the elevator guide rails, wherein the model is obtained based on the training method of any one of claims 1 to 5.
7. A detection system for elevator guide rail condition, the detection system comprising:
the guide rail vibration information acquisition equipment is used for acquiring real-time guide rail vibration information of the elevator at multiple moments;
the elevator running speed acquisition equipment is used for acquiring the real-time elevator running speeds at multiple moments;
the elevator position information acquisition equipment is used for acquiring real-time elevator position information at multiple moments;
a processor for calculating real-time elevator data comprising data of at least two dimensions of real-time guide rail vibration information, real-time elevator running speed and real-time elevator position information using a model to obtain state data of the elevator guide rails, wherein the model is obtained based on the training method of any one of claims 1 to 5.
8. The detection system of claim 7,
and the processor is further used for generating alarm information according to the state data when the state data meets a preset condition, and sending the alarm information to the client so that the client can generate prompt information according to the alarm information.
9. Training device for a model for elevator guide rail condition detection, characterized in that the training device comprises:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring elevator data at a plurality of moments, and the elevator data comprises data of at least two dimensions in guide rail vibration information, elevator running speed and elevator position information;
and the processing module is used for training a preset neural network based on the elevator data at the moments.
10. A detection device for detecting a condition of a guide rail of an elevator, the detection device comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring real-time elevator data at a plurality of moments, and the real-time elevator data comprises data of at least two dimensions in real-time guide rail vibration information, real-time elevator running speed and real-time elevator position information;
a processing module for calculating the real-time elevator data using a model to obtain status data of elevator guide rails, wherein the model is obtained based on the training method of any one of claims 1 to 5.
11. An electronic device, characterized in that the electronic device comprises: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements the training method of any one of claims 1-5 or implements the method of detecting the state of an elevator guide rail of claim 6.
12. A computer storage medium, characterized in that the computer storage medium has stored thereon computer program instructions which, when executed by a processor, implement the training method according to any one of claims 1-5 or the method of detecting the state of an elevator guide rail according to claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011325442.5A CN112607555B (en) | 2020-11-23 | 2020-11-23 | Training method and detection method of model for elevator guide rail state detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011325442.5A CN112607555B (en) | 2020-11-23 | 2020-11-23 | Training method and detection method of model for elevator guide rail state detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112607555A true CN112607555A (en) | 2021-04-06 |
| CN112607555B CN112607555B (en) | 2022-12-27 |
Family
ID=75225571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011325442.5A Active CN112607555B (en) | 2020-11-23 | 2020-11-23 | Training method and detection method of model for elevator guide rail state detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112607555B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115744526A (en) * | 2023-01-06 | 2023-03-07 | 常熟理工学院 | Elevator brake action state detection method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378045A (en) * | 2019-07-24 | 2019-10-25 | 湘潭大学 | A kind of pre- maintaining method of guide precision based on deep learning |
| CN110405537A (en) * | 2019-07-17 | 2019-11-05 | 湘潭大学 | A kind of method for building up of the guide precision prediction model based on deep learning |
| CN111563603A (en) * | 2020-04-21 | 2020-08-21 | 西人马（厦门）科技有限公司 | Elevator health state evaluation method and device and storage medium |
-
2020
- 2020-11-23 CN CN202011325442.5A patent/CN112607555B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110405537A (en) * | 2019-07-17 | 2019-11-05 | 湘潭大学 | A kind of method for building up of the guide precision prediction model based on deep learning |
| CN110378045A (en) * | 2019-07-24 | 2019-10-25 | 湘潭大学 | A kind of pre- maintaining method of guide precision based on deep learning |
| CN111563603A (en) * | 2020-04-21 | 2020-08-21 | 西人马（厦门）科技有限公司 | Elevator health state evaluation method and device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115744526A (en) * | 2023-01-06 | 2023-03-07 | 常熟理工学院 | Elevator brake action state detection method and system |
| CN115744526B (en) * | 2023-01-06 | 2023-04-25 | 常熟理工学院 | Elevator brake action state detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112607555B (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| CN109397703B (en) | Fault detection method and device | |
| CN114585983B (en) | Method, device and system for detecting abnormal operation state of equipment | |
| CN104732276B (en) | One kind metering production facility on-line fault diagnosis method | |
| EP2863282B1 (en) | System and method for detecting anomaly associated with driving a vehicle | |
| JP4431163B2 (en) | Abnormality detection system for moving body and abnormality detection method for moving body | |
| KR101519217B1 (en) | Apparatus for judging driver inattention and method thereof | |
| CN109919066B (en) | Method and device for detecting density abnormality of passengers in rail transit carriage | |
| CN112607555B (en) | Training method and detection method of model for elevator guide rail state detection | |
| CN112070180B (en) | Power grid equipment state judging method and device based on information physical bilateral data | |
| CN111348535B (en) | Health state monitoring system and method for escalator used in rail transit station | |
| CN101807314B (en) | Method for processing embedded vehicle working condition hybrid heterogeneous data information in real time | |
| CN115744521A (en) | Elevator Internet of things maintenance remote supervision and management method and system | |
| CN117454221A (en) | Abnormality identification method for multi-sensor fusion of high-speed rail traction braking system | |
| CN115959549A (en) | Escalator fault diagnosis method based on digital twinning | |
| CN112519835B (en) | Train speed determination method and device, electronic equipment and readable storage medium | |
| CN111780809B (en) | Rail vehicle part temperature and vibration monitoring and early warning method and system thereof | |
| CN112781877A (en) | Fault diagnosis method, device and system for bearings of walking parts | |
| CN115114124A (en) | Host risk assessment method and device | |
| JP4044837B2 (en) | Abnormality detection system for moving body, and abnormality detection method for moving body | |
| CN116186877A (en) | Method and device for detecting characteristics of a vehicle | |
| CN115310367A (en) | Mine air quality monitoring system based on LSTM neural network | |
| CN111573488A (en) | Escalator abnormity detection method, escalator abnormity detection device, escalator abnormity detection equipment and readable storage medium | |
| CN117302313B (en) | Rail transit emergency working condition cooperative scheduling method and system | |
| CN114954587B (en) | Rail engineering vehicle running part fault analysis 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 |