CN115526515B - Safety monitoring system of gate for water conservancy and hydropower - Google Patents
Safety monitoring system of gate for water conservancy and hydropower Download PDFInfo
- Publication number
- CN115526515B CN115526515B CN202211236708.8A CN202211236708A CN115526515B CN 115526515 B CN115526515 B CN 115526515B CN 202211236708 A CN202211236708 A CN 202211236708A CN 115526515 B CN115526515 B CN 115526515B
- Authority
- CN
- China
- Prior art keywords
- gate
- data
- value
- determining
- information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063114—Status monitoring or status determination for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Abstract
The invention discloses a safety monitoring system of a gate for water conservancy and hydropower, which comprises: the data acquisition module is arranged on the gate and used for acquiring the operation data of the gate; the first determining module is used for inputting the operation data into a pre-constructed regression model and determining the state information of the gate; the matching module is used for matching the state information with preset state information in a preset database and determining whether the running state of the gate is abnormal or not according to a matching result; and the alarm module is used for carrying out abnormity detection when the matching module determines that the running state of the gate is abnormal, determining an abnormal device and sending an alarm prompt. And predicting the state information of the gate based on the operation data and the regression model of the gate, so that the state information of the gate can be conveniently determined in advance, and whether the operation state of the gate is abnormal or not can be further judged. The loss is convenient to reduce, the maintenance timeliness is improved, meanwhile, abnormal devices in the gate system can be quickly positioned, the fault is convenient to quickly identify, and corresponding measures are taken.
Description
Technical Field
The invention relates to the technical field of safety monitoring, in particular to a safety monitoring system of a gate for water conservancy and hydropower.
Background
In the field of water conservancy and hydropower, a gate system must be guaranteed to be in a high-performance state to regulate river water. In order to ensure that the system can be put into use at any time, the overhaul of the equipment is inevitable. In the prior art, corresponding measures are taken only when the medium gate fails, and large loss is still caused, so that the maintenance timeliness is influenced. Meanwhile, abnormal devices in the gate system cannot be quickly positioned, so that the faults are not easy to quickly identify and corresponding measures are taken. For example, chinese patent application CN109597344A discloses a real-time online monitoring system for a water and electricity engineering arc steel gate, which can realize safety assessment and operation mode of 'no-person on duty' for the gate, but still has the problems of inaccurate monitoring result and poor real-time performance.
Therefore, the invention provides a safety monitoring system of the gate for water conservancy and hydropower.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, the invention aims to provide a safety monitoring system of a gate for water conservancy and hydropower, which predicts the state information of the gate based on the operation data and the regression model of the gate, is convenient to determine the state information of the gate in advance and further judges whether the operation state of the gate is abnormal. The loss is convenient to reduce, the maintenance timeliness is improved, meanwhile, abnormal devices in the gate system can be quickly positioned, the fault is convenient to quickly identify, and corresponding measures are taken.
In order to achieve the above object, an embodiment of the present invention provides a safety monitoring system for a gate for water conservancy and hydropower, including:
the data acquisition module is arranged on the gate and used for acquiring the operation data of the gate;
the data processing module is used for carrying out data preprocessing on the operating data, and the data preprocessing comprises the steps of data cleaning, data integration, data transformation and data reduction;
the first determining module is used for inputting the operation data subjected to data preprocessing into a pre-constructed regression model and determining the state information of the gate;
the matching module is used for matching the state information with preset state information in a preset database and determining whether the running state of the gate is abnormal or not according to a matching result;
and the alarm module is used for carrying out abnormity detection when the matching module determines that the running state of the gate is abnormal, determining an abnormal device and sending an alarm prompt.
According to some embodiments of the invention, the data acquisition module further comprises:
setting a collaborative process corresponding to the setting of the operation data for the gate, and constructing a collaborative process data pool; wherein, the first and the second end of the pipe are connected with each other,
each collaborative process corresponds to one data exception;
setting a virtual container between the collaborative process data pool and the running data; wherein, the first and the second end of the pipe are connected with each other,
the virtual container includes: the assistant inspection loading module and the assistant inspection module;
adding a collaborative process in a collaborative process data pool through a collaborative loading module;
the running data of any time period is copied through the cooperation module, and the running data is copied in the cooperation module to carry out one-by-one cooperation through the cooperation processes in the cooperation process data pool, so as to judge whether data abnormity exists.
According to some embodiments of the invention, a method for constructing a regression model comprises:
acquiring historical operation data and corresponding historical state information of a gate;
analyzing the historical operating data, determining operating parameters, establishing a matching relation between the operating parameters and historical state information, and generating a matching database;
establishing state information protocol dictionaries for historical state information in the matching database in different dimensions;
and establishing a regression model of the running parameters matched with the state information by the state information protocol dictionary based on a regression algorithm.
According to some embodiments of the invention, the data acquisition module comprises:
the acceleration sensor is used for detecting acceleration information of the support arms on the two sides of the gate;
the speed sensor is used for detecting the speed information of the support arms on the two sides of the gate;
the strain sensor is used for acquiring structural stress information of the gate;
the displacement sensor is used for detecting the opening information of the gate;
the inclination angle sensor is used for checking inclination angle information when the gate is lifted or landed;
the operational data includes speed information, acceleration information, structural stress information, opening information, and inclination information.
According to some embodiments of the invention, further comprising:
a first detection module to:
when the abnormal device is determined to be the hydraulic hoist, collecting a vibration signal of the hydraulic hoist;
decomposing the vibration signal based on a CEEMDAN algorithm, determining a plurality of IMF components, and further determining a plurality of vibration components;
calculating a Hausdorff distance between each vibration component and the vibration signal, and judging whether the Hausdorff distance is greater than a preset distance threshold value;
screening out a vibration component with the Hausdorff distance smaller than a preset threshold value as a target vibration component;
inputting the target vibration component into a first recognition model which is trained in advance, and outputting the fault type of the hydraulic hoist corresponding to the target vibration component;
and the first transmission module is used for transmitting the fault type to a server.
According to some embodiments of the invention, further comprising:
a second detection module to:
shooting a structural image of the abnormal device;
carrying out filtering processing on the structural image to obtain a filtering image;
processing the filtered image based on a canny edge detection algorithm, determining gradient information of each pixel point in the filtered image, determining edge pixel points according to the gradient information, and determining edge characteristics of the filtered image according to the edge pixel points;
inputting the edge characteristics into a second recognition model trained in advance, and outputting surface fault information of an abnormal device;
and the second transmission module is used for transmitting the surface fault information to a server.
According to some embodiments of the present invention, determining gradient information of each pixel point in the filtered image, and determining edge pixel points according to the gradient information, includes:
unifying the filtered images in a preset coordinate system, and determining a coordinate value corresponding to each pixel point in the filtered images in the preset coordinate system;
determining at least two gradient solving directions of the filtering image based on a preset coordinate system, calculating a gradient value of each pixel point in the corresponding gradient solving direction based on the pixel value and the coordinate value of each pixel point in the filtering image, and calculating a comprehensive gradient value of each pixel point based on the gradient value of each pixel point in each gradient solving direction;
determining gradient distribution data of the filtered image based on the comprehensive gradient value of each pixel point, determining pixel distribution data of the filtered image, performing corresponding point addition processing on the pixel distribution data and the gradient distribution data to obtain a contrast enhancement value of each pixel point, and obtaining a contrast enhancement image of the filtered image based on the contrast enhancement value of each pixel point;
performing edge detection on the contrast enhanced image based on a canny edge detection algorithm to determine an initial edge in the contrast enhanced image, and screening out two similar edge pixel points which are closest to the corresponding initial edge pixel points from the remaining initial edge pixel points except the corresponding initial edge pixel points in the initial edge;
calculating the average distance value of each initial edge pixel point and the corresponding similar edge pixel point, summarizing the average distance values of all the initial edge pixel points, and obtaining an average distance value set;
and deleting initial edge pixel points corresponding to the outliers in the distance average value set in the initial edge to obtain a final edge, and taking all pixel points in the final edge as edge pixel points.
According to some embodiments of the present invention, determining the edge feature of the filtered image according to the edge pixel point includes:
determining adjacent edge pixel points of each edge pixel point, and determining the direction from the edge pixel point to the corresponding adjacent edge pixel point based on the coordinate value of each edge pixel point in a preset coordinate system;
calculating pixel difference values between the edge pixel points and the corresponding adjacent edge pixel points, taking the corresponding pointing direction as a vector direction, and taking the corresponding pixel difference values as a vector mode, and determining the pointing vector from the edge pixel points to the corresponding adjacent edge pixel points;
taking the average value of the pointing vectors of the edge pixel points and all the corresponding adjacent edge pixel points as a local characterization vector of the corresponding edge pixel point;
determining a physical center coordinate value of a final edge based on the coordinate value of each edge pixel point under a preset coordinate system, and calculating a coordinate difference value between the coordinate value of each edge pixel point under the preset coordinate system and the physical center coordinate value;
sequencing all edge pixel points based on the sequence of the coordinate difference values from small to large to obtain an edge pixel point sequence, and sequencing local characterization vectors of all the edge pixel points based on the edge pixel point sequence to obtain a local characterization vector sequence;
and marking outliers of the local characterization vector sequence to obtain a marked sequence, and taking the marked sequence as the edge feature of the filtering image.
According to some embodiments of the invention, further comprising:
a third detection module to:
measuring and calculating N times to determine the impedance value of a cable included in the hydraulic hoist;
and calculating the reliability of the cable according to the impedance value and a preset algorithm:
wherein p is the reliability of the cable; s 0 Impedance value of cable, S, being a predetermined standard i The impedance value of the cable measured for the ith time;
comparing the reliability with a preset reliability, and when the reliability is determined to be smaller than the preset reliability, indicating that the cable is abnormal; otherwise, the cable is normal;
the first transmission module is further used for generating prompt information and transmitting the prompt information to the server when the cable is abnormal.
According to some embodiments of the invention, the matching module comprises:
the second determining module is used for extracting the characteristics of the state information and determining key information;
the third determining module is used for extracting the characteristics of the preset state information and determining standard key information;
and the keyword matching module is used for matching the key information with standard key information corresponding to preset state information respectively.
According to some embodiments of the invention, the keyword matching module is further configured to calculate a matching degree of the key information and standard key information corresponding to preset state information, and determine whether the operation state of the gate is abnormal according to the matching degree;
calculating the matching degree of the key information and the standard key information corresponding to the preset state information, wherein the calculating step comprises the following steps:
obtaining Q1 keywords included by the key information, and performing numerical processing to generate a vector C1;
performing numerical processing on Q1 standard keywords corresponding to standard key information of M pieces of preset state information in a preset database to generate a matrix J1, wherein the matrix J1 comprises M rows and Q1 columns;
calculating the matching degree of the key information and the standard key information corresponding to the preset state information:
wherein d is i Matching degree of the key information and the ith piece of standard key information; j1 i,j Is the value of the ith row and J column of the matrix J1; c1 j1 Is the value of the j1 th of vector C1; j1 i,j1 Is the value of the ith row and J1 column of the matrix J1, wherein i =1, 2, 3 \8230, M, J1=1, 2, 3 \8230, 8230, Q1;
when the matching degree obtained by calculation is smaller than the value range of the preset matching value, judging that the running state of the gate is abnormal;
and when the calculated matching degree falls into the value range of the preset matching value, judging that the running state of the gate is not abnormal.
The invention provides a safety monitoring system of a gate for water conservancy and hydropower, which predicts the state information of the gate based on the operation data and a regression model of the gate, is convenient to determine the state information of the gate in advance and further judges whether the operation state of the gate is abnormal. The loss is convenient to reduce, the maintenance timeliness is improved, meanwhile, abnormal devices in the gate system can be quickly positioned, the fault is convenient to quickly identify, and corresponding measures are taken.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
In the drawings:
FIG. 1 is a block diagram of a safety monitoring system for a water conservancy and hydropower gate according to an embodiment of the invention;
FIG. 2 is a flow diagram of a method of constructing a regression model according to one embodiment of the invention;
FIG. 3 is a block diagram of a matching module in accordance with one embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
As shown in fig. 1, an embodiment of the present invention provides a safety monitoring system for a gate for water conservancy and hydropower, including:
the data acquisition module is arranged on the gate and used for acquiring operation data of the gate;
the data processing module is used for carrying out data preprocessing on the operating data, and the data preprocessing comprises the steps of data cleaning, data integration, data transformation and data reduction;
the first determining module is used for inputting the operation data subjected to data preprocessing into a pre-constructed regression model and determining the state information of the gate;
the matching module is used for matching the state information with preset state information in a preset database and determining whether the running state of the gate is abnormal or not according to a matching result;
and the alarm module is used for carrying out abnormity detection when the matching module determines that the running state of the gate is abnormal, determining an abnormal device and sending an alarm prompt.
The working principle of the technical scheme is as follows: acquiring operation data of the gate based on a data acquisition module, inputting the operation data into a pre-constructed regression model, and determining state information of the gate; and matching the state information with preset state information in a preset database according to a matching module, determining whether the running state of the gate is abnormal or not according to a matching result, and performing abnormality detection when the running state of the gate is abnormal, wherein the abnormality detection mainly aims at detection of each device in a gate system, determines an abnormal device and sends an alarm prompt. The preset state information in the preset database represents the respective states of the gate.
And before the first determining module inputs the operating data into a pre-constructed regression model, performing data preprocessing on the operating data to ensure the accuracy of the data input into the regression model, and further improving the accuracy of output. Data cleansing can change "black" to "white," dirty "data to" clean, "dirty data representing formally and contextually dirty, formally dirty, such as: missing values, with special symbols, dirty on content, such as: an outlier. Data integration is the merging of multiple data sources into one data store, and of course, if the analyzed data is originally in one data store, the integration of the data is not needed. The data transformation is to be converted into a suitable form to meet the needs of software or analytical theory. Data reduction refers to finding useful characteristics of data depending on a found target on the basis of understanding of a mining task and the content of the data, so as to reduce the data size, and further reduce the data volume to the maximum extent on the premise of keeping the original appearance of the data as much as possible. The data normalization can reduce the influence of invalid and wrong data on modeling, shorten the time and reduce the space for storing the data.
The beneficial effects of the above technical scheme are as follows: and predicting the state information of the gate based on the operation data and the regression model of the gate, so that the state information of the gate can be conveniently determined in advance, and whether the operation state of the gate is abnormal or not can be further judged. The device is convenient to reduce loss and improve maintenance timeliness, and can quickly position abnormal devices in a gate system, quickly identify faults and take corresponding measures.
According to some embodiments of the invention, the data acquisition module further comprises:
setting a collaborative process corresponding to the setting of the operation data for the gate, and constructing a collaborative process data pool; wherein the content of the first and second substances,
each collaborative process corresponds to one data exception;
setting a virtual container between the collaborative process data pool and the running data; wherein the content of the first and second substances,
the virtual container includes: the system comprises a collaborative loading module and a collaborative module;
adding a collaborative process in a collaborative process data pool through a collaborative loading module;
the running data of any time period is copied through the cooperation module, and the running data is copied in the cooperation module to carry out one-by-one cooperation through the cooperation processes in the cooperation process data pool, so as to judge whether data abnormity exists.
The invention belongs to a safety detection system, and when the invention is implemented in detail, safety detection is carried out through a remote platform, but the existing safety monitoring technology can monitor a certain time period, a certain moment and different types of operation data. Such as water speed data, water quantity data, and even if the water quality monitoring function exists in the gate, the water quality can be continuously monitored. However, in the prior art, the monitoring of the operation data in various different modes cannot be realized, so the invention provides: the invention relates to a 'cooperative process', which can be a water speed cooperative process, a water quality cooperative process, or a water quantity or water speed cooperative process at a certain moment to judge whether water speed abnormality exists, can also set different types of cooperative processes aiming at different types of gates to realize comprehensive operation data detection, and is also provided with a virtual container which can be added with the cooperative process on the same side, and can carry out one-by-one cooperative process in the virtual container without mutual interference among different processes.
In an alternative embodiment:
obtaining the copy data through a collaborating module, and determining the data characteristics of the copy data:
wherein F represents the data characteristics of the copy data in the time period of 0 to T; collecting the copy data in a time period of 0-T; f (t) represents the data value of the operation data at the time t; l is t，i The type coefficient represents the ith type of operation data at the time t; t is max Represents the maximum time value corresponding to the time T from 0 to T;
and calculating the correlation between each collaborative process and the data characteristics according to the data characteristics:
wherein, X (F (t), h) represents the correlation value of the jth collaborative process and data characteristics in the collaborative process data pool; g (F (t), h) j ) Is composed ofA mahalanobis distance function; h is a total of j Representing a characteristic value of the jth collaborative process in the collaborative process data pool;
representing the average characteristic value of the collaborative process in the collaborative process data pool; />
An average data value representing the operational data; j and i belong to positive integers;
and determining all correlation values of the data characteristics of each collaborative inspection process and the copied data, comparing the correlation values, determining the corresponding collaborative inspection process when the correlation value is maximum, collaborating the copied data, and judging whether data abnormity exists or not.
In the invention, in order to judge that each type of running data is matched with the type or the process, and the correlation is higher, the invention adopts the steps that firstly, the data needing to be collaborated are subjected to characteristic calculation to determine the specific data characteristics, and then, the data collaborating is carried out according to the data characteristics and the correlation of the collaborating process, under the condition, the data needing to be detected can be detected through the most matched collaborating process, and the accuracy of the detection result is ensured; the copy data includes information indicating the presence of a gate and actual operation data.
As shown in fig. 2, according to some embodiments of the present invention, the method for constructing the regression model includes steps S11-S14:
s11, acquiring historical operation data and corresponding historical state information of a gate;
s12, analyzing the historical operating data, determining operating parameters, establishing a matching relation between the operating parameters and historical state information, and generating a matching database;
s13, establishing state information protocol dictionaries for the historical state information in the matching database in different dimensions;
and S14, establishing a regression model of the running parameters matched with the state information by the state information protocol dictionary based on a regression algorithm.
The beneficial effects of the above technical scheme are that: and accurately constructing a regression model based on the historical operation data of the gate and the corresponding historical state information.
According to some embodiments of the invention, the data acquisition module comprises:
the acceleration sensor is used for detecting acceleration information of the support arms on the two sides of the gate;
the speed sensor is used for detecting the speed information of the support arms on the two sides of the gate;
the strain sensor is used for acquiring structural stress information of the gate;
the displacement sensor is used for detecting the opening information of the gate;
the inclination angle sensor is used for checking inclination angle information when the gate is lifted or descended;
the gate operation data comprises speed information, acceleration information, structural stress information, opening information and inclination angle information.
The beneficial effects of the above technical scheme are that: the speed information, the acceleration information, the structural stress information, the opening degree information and the inclination angle information of the gate are collected, the comprehensiveness of collected operation data is guaranteed, and therefore the accuracy of the predicted state based on a regression model is facilitated.
According to some embodiments of the invention, further comprising:
a first detection module to:
when the abnormal device is determined to be the hydraulic hoist, collecting a vibration signal of the hydraulic hoist;
decomposing the vibration signal based on a CEEMDAN algorithm, determining a plurality of IMF components, and further determining a plurality of vibration components;
calculating a Hausdorff distance between each vibration component and the vibration signal, and judging whether the Hausdorff distance is greater than a preset distance threshold value;
screening out a vibration component with the Hausdorff distance smaller than a preset threshold value as a target vibration component;
inputting the target vibration component into a preset trained first recognition model, and outputting the fault type of the hydraulic hoist corresponding to the target vibration component;
and the first transmission module is used for transmitting the fault type to a server.
The working principle of the technical scheme is as follows: screening out a vibration component with the Hausdorff distance smaller than a preset threshold value as a target vibration component; the influence of noise and extraneous signals is eliminated for effective signal components.
Inputting the target vibration component into a preset trained first recognition model, and outputting the fault type of the hydraulic hoist corresponding to the target vibration component; the fault type of the hydraulic hoist can be determined accurately.
The beneficial effects of the above technical scheme are as follows: after the abnormal device is determined, the fault type of the abnormal device is determined, so that the comprehensive detection of the fault is realized, the corresponding maintenance measures can be determined in time based on the fault type, and the maintenance timeliness is improved. Realize the quick transmission of fault type based on first transmission module, the monitoring personnel of being convenient for in time obtain corresponding data, labour saving and time saving improves monitoring efficiency.
According to some embodiments of the invention, further comprising:
a second detection module to:
shooting a structural image of the abnormal device;
carrying out filtering processing on the structural image to obtain a filtering image;
processing the filtered image based on a canny edge detection algorithm, determining gradient information of each pixel point in the filtered image, determining edge pixel points according to the gradient information, and determining edge characteristics of the filtered image according to the edge pixel points;
inputting the edge characteristics into a second recognition model trained in advance, and outputting surface fault information of an abnormal device;
and the second transmission module is used for transmitting the surface fault information to a server.
The working principle of the technical scheme is as follows: the structure image is a surface image of the anomalous device.
Carrying out filtering processing on the structural image to obtain a filtering image; the signal-to-noise ratio of the image is improved, and the influence of image noise is reduced.
The gradient information includes gradient direction and gradient strength.
The beneficial effects of the above technical scheme are that: acquiring a structural image of the abnormal device, determining edge characteristics, identifying based on a second identification model, and outputting surface fault information of the abnormal device; and based on a second transmission module, for transmitting the surface failure information to a server.
According to some embodiments of the present invention, determining gradient information of each pixel point in the filtered image, and determining edge pixel points according to the gradient information, includes:
unifying the filtered images in a preset coordinate system, and determining a coordinate value corresponding to each pixel point in the filtered images in the preset coordinate system;
determining at least two gradient solving directions of the filtering image based on a preset coordinate system, calculating a gradient value of each pixel point in the corresponding gradient solving direction based on the pixel value and the coordinate value of each pixel point in the filtering image, and calculating a comprehensive gradient value of each pixel point based on the gradient value of each pixel point in each gradient solving direction;
determining gradient distribution data of the filtering image based on the comprehensive gradient value of each pixel point, determining pixel distribution data of the filtering image, performing corresponding point addition processing on the pixel distribution data and the gradient distribution data to obtain a contrast enhancement value of each pixel point, and obtaining a contrast enhancement image of the filtering image based on the contrast enhancement value of each pixel point;
performing edge detection on the contrast enhanced image based on a canny edge detection algorithm to determine an initial edge in the contrast enhanced image, and screening out two similar edge pixel points which are closest to the corresponding initial edge pixel points from the remaining initial edge pixel points except the corresponding initial edge pixel points in the initial edge;
calculating the average distance value of each initial edge pixel point and the corresponding similar edge pixel point, summarizing the average distance values of all the initial edge pixel points, and obtaining an average distance value set;
and deleting initial edge pixel points corresponding to the outliers in the distance average value set in the initial edge to obtain a final edge, and taking all pixel points in the final edge as edge pixel points.
In this embodiment, the preset coordinate system is a coordinate system prepared in advance for unifying the coordinate values of each pixel in the filtered image according to a preset format.
In this embodiment, the gradient calculation direction is a gradient calculation direction when the gradient value of each pixel in the filtered image is subsequently determined, and may be, for example, a positive direction of an abscissa axis of a preset coordinate system, or a positive direction of an ordinate axis of the preset coordinate system.
In this embodiment, based on the pixel value and the coordinate value of each pixel point in the filtered image, the gradient value of each pixel point in the corresponding gradient solving direction is calculated, that is:
and summarizing the coordinate value of each pixel point based on the filtering image, determining an adjacent pixel point of the corresponding pixel point in the corresponding gradient solving direction, and taking the pixel difference value between the corresponding pixel point and the adjacent pixel point as the gradient value of the corresponding pixel point in the corresponding gradient solving direction.
In this embodiment, based on the gradient value of each pixel point in each gradient solving direction, the comprehensive gradient value of each pixel point is calculated, that is:
and taking the average value of the gradient values of the corresponding pixel points in each gradient calculation direction as the comprehensive gradient value of the corresponding pixel points.
In this embodiment, the gradient distribution data is data including the integrated gradient value of each pixel in the filtered image.
In this embodiment, the pixel distribution data is distribution data including a pixel value of each pixel in the filtered image.
In this embodiment, the pixel distribution data and the gradient distribution data are subjected to corresponding point addition processing to obtain a contrast enhancement value of each pixel point, which is:
and based on the pixel distribution data and the gradient distribution data, summing the pixel values of the corresponding pixels and the comprehensive gradient value to obtain a contrast enhancement value of the corresponding pixel with your.
In this embodiment, the contrast-enhanced image is an image obtained by marking the contrast enhancement value of each pixel point on the filtered image.
In this embodiment, the initial edge is an edge in the filtered image obtained after performing edge detection on the contrast enhanced image based on the canny edge detection algorithm.
In this embodiment, the similar edge pixel points are two edge pixel points that are closest to the corresponding initial edge pixel point in the initial edge except the corresponding initial edge pixel point.
In this embodiment, the distance average is an average of distances between each initial edge pixel and all corresponding similar edge pixels.
In this embodiment, the distance average set is a set obtained by summarizing the distance averages of all the initial edge pixel points.
In this embodiment, the final edge is an edge obtained by deleting initial edge pixel points corresponding to outliers in the distance average value set in the initial edge.
The beneficial effects of the above technology are: corresponding point addition processing is carried out on gradient distribution data determined based on the comprehensive gradient values of the pixel points in the multiple gradient obtaining directions and pixel distribution data of the filtering image, the line pixel difference value of each pixel point and adjacent pixel points in the filtering image is larger and the contrast is stronger under the condition that the pixel distribution characteristics in the filtering image are kept, the effect of detecting the edge by using a canny edge detection algorithm subsequently is better, smooth denoising of the initial edge is realized by judging the distance between initial edge pixel points in the initial edge determined based on the canny edge detection algorithm, and then the edge in the filtering image and the corresponding edge pixel points are more accurate and complete.
According to some embodiments of the present invention, determining the edge feature of the filtered image according to the edge pixel point includes:
determining adjacent edge pixel points of each edge pixel point, and determining the pointing direction from each edge pixel point to the corresponding adjacent edge pixel point based on the coordinate value of each edge pixel point in a preset coordinate system;
calculating pixel difference values between the edge pixel points and the corresponding adjacent edge pixel points, taking the corresponding pointing direction as a vector direction, and taking the corresponding pixel difference value as a vector mode, and determining pointing vectors from the edge pixel points to the corresponding adjacent edge pixel points;
taking the average value of the pointing vectors of the edge pixel points and all the corresponding adjacent edge pixel points as a local characterization vector of the corresponding edge pixel point;
determining a physical center coordinate value of a final edge based on the coordinate value of each edge pixel point under a preset coordinate system, and calculating a coordinate difference value between the coordinate value of each edge pixel point under the preset coordinate system and the physical center coordinate value;
sequencing all edge pixel points based on the sequence of the coordinate difference values from small to large to obtain an edge pixel point sequence, and sequencing local characterization vectors of all the edge pixel points based on the edge pixel point sequence to obtain a local characterization vector sequence;
and marking outliers of the local characterization vector sequence to obtain a marked sequence, and taking the marked sequence as the edge feature of the filtering image.
In this embodiment, the adjacent edge pixel is the edge pixel adjacent to the corresponding edge pixel.
In this embodiment, based on the coordinate value of each edge pixel in the preset coordinate system, the pointing direction from the edge pixel to the corresponding adjacent edge pixel is determined, that is:
calculating an abscissa value corresponding to an adjacent edge pixel point and an abscissa value difference value and an ordinate value difference value corresponding to the edge pixel point based on the coordinate value of each edge pixel point in a preset coordinate system;
and taking the arctangent value of the ratio of the longitudinal coordinate difference value and the horizontal coordinate difference value as the angle of the corresponding pointing direction.
In this embodiment, the pointing vector is determined from the edge pixel to the corresponding adjacent edge pixel after the corresponding pointing direction is taken as the vector direction and the corresponding pixel difference value is taken as the modulus of the vector.
In this embodiment, the pixel difference is a difference between the pixel value of the edge pixel and the pixel value of the corresponding adjacent edge pixel.
In this embodiment, the local characterization vector is an average value of the pointing vectors of the edge pixel and all the corresponding adjacent edge pixels.
In this embodiment, the physical center coordinate value of the final edge is an average value of coordinate values of all edge pixel points in the preset coordinate system.
In this embodiment, the edge pixel point sequence is a sequence obtained by sorting all edge pixel points in a sequence from small to large based on the coordinate difference.
In this embodiment, the local feature vector sequence is a sequence obtained by sorting the local feature vectors of all the edge pixel points based on the edge pixel point sequence.
In this embodiment, the marker sequence is a sequence obtained after marking outliers of the local token vector sequence.
The beneficial effects of the above technology are: determining a directional vector of a pixel change characteristic between a characterization edge pixel point and a corresponding edge pixel point based on a pixel difference value and a coordinate difference value of the edge pixel point and an adjacent edge pixel point, and determining a local characterization characteristic of a pixel distribution characteristic of the corresponding edge pixel point in an adjacent local area based on all directional vectors of the edge pixel points; and sequencing the local characterization sequences of all the edge pixel points by combining the distances from the physical central points to obtain a sequence capable of characterizing the local characteristics of the edge pixel points in the filtered image, namely obtaining the edge characteristics capable of characterizing the local characteristics of the edge pixel points in the filtered image.
According to some embodiments of the invention, further comprising:
a third detection module to:
measuring and calculating N times to determine the impedance value of a cable included in the hydraulic hoist;
and calculating the reliability of the cable according to the impedance value and a preset algorithm:
wherein p is the reliability of the cable; s 0 Impedance value of cable, S, being a predetermined standard i The impedance value of the cable measured for the ith time;
comparing the reliability with a preset reliability, and when the reliability is determined to be smaller than the preset reliability, indicating that the cable is abnormal; otherwise, the cable is normal;
the first transmission module is also used for generating prompt information and transmitting the prompt information to the server when the cable is abnormal.
The working principle and the beneficial effects of the technical scheme are as follows: a third detection module to: measuring and calculating N times to determine the impedance value of a cable included in the hydraulic hoist; and calculating the reliability of the cable according to the impedance value and a preset algorithm: comparing the reliability with a preset reliability, and when the reliability is determined to be less than the preset reliability, indicating that the cable is abnormal; otherwise, the cable is normal; the first transmission module is further used for generating prompt information and transmitting the prompt information to the server when the cable is abnormal. Whether the cable included in the hydraulic hoist has a fault or not is accurately identified. Based on the formula, the reliability of the cable is accurately calculated, the accuracy of judging the reliability and the preset reliability is improved, and whether the cable is abnormal or not is accurately judged.
As shown in fig. 3, according to some embodiments of the invention, the matching module comprises:
the second determining module is used for extracting the characteristics of the state information and determining key information;
the third determining module is used for extracting the characteristics of the preset state information and determining standard key information;
and the keyword matching module is used for matching the key information with standard key information corresponding to preset state information respectively.
The working principle and the beneficial effects of the technical scheme are as follows: performing feature extraction on the state information based on a second determination module to determine key information; performing feature extraction based on the preset state information of a third determination module, and determining standard key information; the key information comprises at least one keyword; the standard key information comprises at least one standard key word; the key information is matched with the standard key information corresponding to the preset state information respectively based on the keyword matching module, so that the matching amount is reduced, and the matching efficiency is improved.
According to some embodiments of the invention, the keyword matching module is further configured to calculate a matching degree of the key information and standard key information corresponding to preset state information, and determine whether the operation state of the gate is abnormal according to the matching degree;
calculating the matching degree of the key information and the standard key information corresponding to the preset state information, wherein the matching degree comprises the following steps:
obtaining Q1 keywords included by the key information, and performing numerical processing to generate a vector C1;
performing numerical processing on M standard keywords Q1 corresponding to standard key information of preset state information in a preset database to generate a matrix J1, wherein the matrix J1 comprises M rows and Q1 columns;
calculating the matching degree of the key information and the standard key information corresponding to the preset state information:
wherein, d i Matching degree of the key information and the ith piece of standard key information; j1 i,j Is the value of the ith row and J column of the matrix J1; c1 j1 Is the value of the j1 th of vector C1; j1 i,j1 Is the value of the ith row and J1 column of the matrix J1, wherein i =1, 2, 3 \8230, M, J1=1, 2, 3 \8230, 8230, Q1;
when the matching degree obtained by calculation is smaller than the value range of the preset matching value, judging that the running state of the gate is abnormal;
and when the calculated matching degree falls into the value range of the preset matching value, judging that the running state of the gate is not abnormal.
The working principle and the beneficial effects of the technical scheme are as follows: based on the matching degree, the quantitative processing is realized, and whether the running state of the gate is abnormal or not is judged conveniently and accurately. Specifically, the corresponding standard key information with the highest matching degree is used as target information, the target information is identified, and whether the running state of the gate is abnormal or not is determined. When the matching degree is calculated, obtaining Q1 keywords included by the key information, and carrying out numerical processing to generate a vector C1; performing numerical processing on Q1 standard keywords corresponding to standard key information of M pieces of preset state information in a preset database to generate a matrix J1, wherein the matrix J1 comprises M rows and Q1 columns; the matching degree of the key information and the standard key information corresponding to the preset state information is accurately calculated based on the formula, the principle of the formula of the matching degree is mainly determined based on the value of 'distance' between the key information and the standard key information data corresponding to the preset state information, it can be understood that when the value of 'distance' between the key information and the standard key information data corresponding to the preset state information is smaller, the matching degree is higher, and when the value of 'distance' between the key information and the standard key information data is larger, the matching degree is lower, the calculation mode is convenient for accurately determining the standard key information with the highest matching degree, and further accurately judging whether the running state is abnormal.
According to some embodiments of the invention, the first transmission module comprises one or more of a WiFi communication module, a ZigBee communication module, and a 4G communication module.
The beneficial effects of the above technical scheme are as follows: the WiFi communication module, the ZigBee communication module or other 4G communication modules can improve the data transmission way and the safety.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. The utility model provides a safety monitoring system of gate for water conservancy water and electricity which characterized in that includes:
the data acquisition module is arranged on the gate and used for acquiring the operation data of the gate;
the data processing module is used for carrying out data preprocessing on the operating data, and the data preprocessing comprises the steps of data cleaning, data integration, data transformation and data reduction;
the first determining module is used for inputting the operation data subjected to data preprocessing into a pre-constructed regression model and determining the state information of the gate;
the matching module is used for matching the state information with preset state information in a preset database and determining whether the running state of the gate is abnormal or not according to a matching result;
the alarm module is used for carrying out abnormity detection when the matching module determines that the running state of the gate is abnormal, determining an abnormal device and sending an alarm prompt;
further comprising:
a second detection module to:
shooting a structural image of the abnormal device;
carrying out filtering processing on the structural image to obtain a filtering image;
determining gradient information of each pixel point in the filtering image, determining edge pixel points according to the gradient information, and determining edge characteristics of the filtering image according to the edge pixel points;
inputting the edge characteristics into a second recognition model trained in advance, and outputting surface fault information of an abnormal device;
the second transmission module is used for transmitting the surface fault information to a server;
determining gradient information of each pixel point in the filtering image, and determining edge pixel points according to the gradient information, wherein the determining comprises the following steps:
unifying the filtered images in a preset coordinate system, and determining a coordinate value corresponding to each pixel point in the filtered images in the preset coordinate system;
determining at least two gradient solving directions of the filtering image based on a preset coordinate system, calculating a gradient value of each pixel point in the corresponding gradient solving direction based on the pixel value and the coordinate value of each pixel point in the filtering image, and calculating a comprehensive gradient value of each pixel point based on the gradient value of each pixel point in each gradient solving direction;
determining gradient distribution data of the filtered image based on the comprehensive gradient value of each pixel point, determining pixel distribution data of the filtered image, performing corresponding point addition processing on the pixel distribution data and the gradient distribution data to obtain a contrast enhancement value of each pixel point, and obtaining a contrast enhancement image of the filtered image based on the contrast enhancement value of each pixel point;
performing edge detection on the contrast enhanced image based on a canny edge detection algorithm to determine an initial edge in the contrast enhanced image, and screening out two similar edge pixel points which are closest to the corresponding initial edge pixel points from the remaining initial edge pixel points except the corresponding initial edge pixel points in the initial edge;
calculating the average distance value of each initial edge pixel point and the corresponding similar edge pixel point, summarizing the average distance values of all the initial edge pixel points, and obtaining an average distance value set;
deleting initial edge pixel points corresponding to outliers in the distance average value set in the initial edge to obtain a final edge, and taking all pixel points in the final edge as edge pixel points;
determining the edge characteristics of the filtering image according to the edge pixel points, comprising the following steps:
determining adjacent edge pixel points of each edge pixel point, and determining the pointing direction from each edge pixel point to the corresponding adjacent edge pixel point based on the coordinate value of each edge pixel point in a preset coordinate system;
calculating pixel difference values between the edge pixel points and the corresponding adjacent edge pixel points, taking the corresponding pointing direction as a vector direction, and taking the corresponding pixel difference value as a vector mode, and determining pointing vectors from the edge pixel points to the corresponding adjacent edge pixel points;
taking the average value of the pointing vectors of the edge pixel points and all the corresponding adjacent edge pixel points as a local characterization vector of the corresponding edge pixel point;
determining a physical center coordinate value of a final edge based on the coordinate value of each edge pixel point under a preset coordinate system, and calculating a coordinate difference value between the coordinate value of each edge pixel point under the preset coordinate system and the physical center coordinate value;
sequencing all edge pixel points based on the sequence of the coordinate difference values from small to large to obtain an edge pixel point sequence, and sequencing local characterization vectors of all the edge pixel points based on the edge pixel point sequence to obtain a local characterization vector sequence;
and marking outliers of the local characterization vector sequence to obtain a marked sequence, and taking the marked sequence as the edge feature of the filtering image.
2. The safety monitoring system of a gate for water conservancy and hydropower of claim 1, wherein the data acquisition module further comprises:
setting a collaborative process corresponding to the setting of the operation data for the gate, and constructing a collaborative process data pool; wherein, the first and the second end of the pipe are connected with each other,
each collaborating process corresponds to one data exception;
setting a virtual container between the collaborative process data pool and the running data; wherein, the first and the second end of the pipe are connected with each other,
the virtual container includes: the system comprises a collaborative loading module and a collaborative module;
adding a collaborative process in a collaborative process data pool through a collaborative loading module;
the running data of any time period is copied through the cooperation module, and the running data is copied in the cooperation module to carry out one-by-one cooperation through the cooperation processes in the cooperation process data pool, so as to judge whether data abnormity exists.
3. The safety monitoring system of a gate for water conservancy and hydropower according to claim 1, wherein the method for constructing the regression model comprises:
acquiring historical operation data and corresponding historical state information of a gate;
analyzing the historical operating data, determining operating parameters, establishing a matching relation between the operating parameters and historical state information, and generating a matching database;
establishing state information protocol dictionaries for historical state information in the matching database in different dimensions;
and establishing a regression model of the running parameters matched with the state information by the state information protocol dictionary based on a regression algorithm.
4. The safety monitoring system of a gate for water conservancy and hydropower of claim 1, wherein the data acquisition module comprises:
the acceleration sensor is used for detecting acceleration information of support arms on two sides of the gate;
the speed sensor is used for detecting the speed information of the support arms on the two sides of the gate;
the strain sensor is used for acquiring structural stress information of the gate;
the displacement sensor is used for detecting the opening information of the gate;
the inclination angle sensor is used for checking inclination angle information when the gate is lifted or descended;
the operation data comprises speed information, acceleration information, structural stress information, opening information and inclination angle information;
a first detection module to:
when the abnormal device is determined to be a hydraulic hoist, collecting a vibration signal of the hydraulic hoist;
decomposing the vibration signal based on a CEEMDAN algorithm, determining a plurality of IMF components, and further determining a plurality of vibration components;
calculating a Hausdorff distance between each vibration component and the vibration signal, and judging whether the Hausdorff distance is greater than a preset distance threshold value;
screening out a vibration component with the Hausdorff distance smaller than a preset threshold value as a target vibration component;
inputting the target vibration component into a first recognition model which is trained in advance, and outputting the fault type of the hydraulic hoist corresponding to the target vibration component;
and the first transmission module is used for transmitting the fault type to a server.
5. A safety monitoring system for a water conservancy and hydropower gate as claimed in claim 4, further comprising:
a third detection module to:
measuring and calculating N times to determine the impedance value of a cable included in the hydraulic hoist;
and calculating the reliability of the cable according to the impedance value and a preset algorithm:
wherein p is the reliability of the cable; s 0 Impedance value of cable, S, being a predetermined standard i The impedance value of the cable measured for the ith time;
comparing the reliability with a preset reliability, and when the reliability is determined to be less than the preset reliability, indicating that the cable is abnormal; otherwise, the cable is normal;
the first transmission module is also used for generating prompt information and transmitting the prompt information to the server when the cable is abnormal.
6. The safety monitoring system of a water conservancy and hydropower gate of claim 1, wherein the matching module comprises:
the second determining module is used for extracting the characteristics of the state information and determining key information;
the third determining module is used for extracting the characteristics of the preset state information and determining standard key information;
and the keyword matching module is used for matching the key information with standard key information corresponding to preset state information respectively.
7. The safety monitoring system of the gate for the water conservancy and hydropower according to claim 6, wherein the keyword matching module is further configured to calculate a matching degree of the key information and standard key information corresponding to preset state information, and determine whether the operation state of the gate is abnormal according to the matching degree;
calculating the matching degree of the key information and the standard key information corresponding to the preset state information, wherein the matching degree comprises the following steps:
obtaining Q1 keywords included by the key information, and performing numerical processing to generate a vector C1;
performing numerical processing on M standard keywords Q1 corresponding to standard key information of preset state information in a preset database to generate a matrix J1, wherein the matrix J1 comprises M rows and Q1 columns;
calculating the matching degree of the key information and the standard key information corresponding to the preset state information:
wherein, d i Matching degree of the key information and the ith standard key information; j1 i,j Is the value of the ith row and J column of the matrix J1; c1 j1 Is the value of the j1 th of vector C1; j1 i,j1 Is the value of the ith row and J1 column of the matrix J1, wherein i =1, 2, 3 \8230, 823030, M, J1=1, 2, 3 \8230, 8230, Q1;
when the calculated matching degree is smaller than the value range of the preset matching value, judging that the running state of the gate is abnormal;
and when the calculated matching degree falls into the value range of the preset matching value, judging that the running state of the gate is not abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211236708.8A CN115526515B (en) | 2022-10-10 | 2022-10-10 | Safety monitoring system of gate for water conservancy and hydropower |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211236708.8A CN115526515B (en) | 2022-10-10 | 2022-10-10 | Safety monitoring system of gate for water conservancy and hydropower |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115526515A CN115526515A (en) | 2022-12-27 |
| CN115526515B true CN115526515B (en) | 2023-04-04 |
Family
ID=84701229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211236708.8A Active CN115526515B (en) | 2022-10-10 | 2022-10-10 | Safety monitoring system of gate for water conservancy and hydropower |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115526515B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051897B (en) * | 2023-01-28 | 2023-06-27 | 合肥中科类脑智能技术有限公司 | Door opening and closing state detection method and device, edge processing equipment and storage medium |
| CN116522150B (en) * | 2023-07-03 | 2023-09-08 | 交通运输部水运科学研究所 | Prediction method and system for arch collapse degree of herringbone door body structure of ship lock |
| CN117418515A (en) * | 2023-08-17 | 2024-01-19 | 夏禹智水(杭州)数字科技有限公司 | Radial gate safety monitoring method, system and device and electronic equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170178297A1 (en) * | 2014-02-19 | 2017-06-22 | Yissum Research Development Company Of The Hebrew University Of Jerusalem Ltd. | Method and system for dehazing natural images using color-lines |
| CN108989438A (en) * | 2018-07-26 | 2018-12-11 | 青柠智云（杭州）科技有限责任公司 | Implementation method, the device and system of data distribution network |
| CN111811642B (en) * | 2020-07-22 | 2022-05-03 | 三一重机有限公司 | Fault detection method and fault detection device for excavator engine |
| CN114670898A (en) * | 2022-04-19 | 2022-06-28 | 北京运达华开科技有限公司 | Multifunctional track detection system |
-
2022
- 2022-10-10 CN CN202211236708.8A patent/CN115526515B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115526515A (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115526515B (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN112581463A (en) | Image defect detection method and device, electronic equipment, storage medium and product | |
| CN111737909B (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| CN111505424A (en) | Large experimental device power equipment fault diagnosis method based on deep convolutional neural network | |
| Wang et al. | A real-time bridge crack detection method based on an improved inception-resnet-v2 structure | |
| CN111652295B (en) | Railway wagon coupler yoke key joist falling fault identification method | |
| CN112419299A (en) | Bolt loss detection method, device, equipment and storage medium | |
| CN111563896B (en) | Image processing method for detecting abnormality of overhead line system | |
| CN108154498A (en) | A kind of rift defect detecting system and its implementation | |
| CN112419298A (en) | Bolt node plate corrosion detection method, device, equipment and storage medium | |
| CN114689600A (en) | Method and system for detecting surface crack of bridge concrete structure | |
| Liao et al. | A channel-spatial-temporal attention-based network for vibration-based damage detection | |
| CN115861210A (en) | Transformer substation equipment abnormity detection method and system based on twin network | |
| CN113128555B (en) | Method for detecting abnormality of train brake pad part | |
| Hamdi et al. | Fully automated approach for patterned fabric defect detection | |
| CN117523177A (en) | Gas pipeline monitoring system and method based on artificial intelligent hybrid big model | |
| CN104504265A (en) | Method for safety evaluation of monitoring information of in-service bridge | |
| CN116842379A (en) | Mechanical bearing residual service life prediction method based on DRSN-CS and BiGRU+MLP models | |
| CN114662619B (en) | Bridge monitoring system based on multi-source data fusion | |
| CN115995056A (en) | Automatic bridge disease identification method based on deep learning | |
| CN115270875A (en) | Diaphragm pump running state monitoring method based on deep learning | |
| Han et al. | Damage detection of quayside crane structure based on improved faster R-CNN | |
| CN114004138A (en) | Building monitoring method and system based on big data artificial intelligence and storage medium | |
| Zhang et al. | A Flexible Monitoring Framework via Dynamic-Multilayer Graph Convolution Network | |
| Shin et al. | Visualization for explanation of deep learning-based defect detection model using class activation map |
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 |