CN116730226B - Safety intelligent supervision system and method for cantilever crane - Google Patents
Safety intelligent supervision system and method for cantilever crane Download PDFInfo
- Publication number
- CN116730226B CN116730226B CN202311029742.2A CN202311029742A CN116730226B CN 116730226 B CN116730226 B CN 116730226B CN 202311029742 A CN202311029742 A CN 202311029742A CN 116730226 B CN116730226 B CN 116730226B
- Authority
- CN
- China
- Prior art keywords
- time sequence
- feature vector
- cantilever crane
- speed
- load
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 230000006870 function Effects 0.000 claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 239000013598 vector Substances 0.000 claims description 170
- 230000003993 interaction Effects 0.000 claims description 104
- 230000004927 fusion Effects 0.000 claims description 52
- 238000005457 optimization Methods 0.000 claims description 26
- 238000005070 sampling Methods 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000012098 association analyses Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 6
- 230000000737 periodic effect Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 14
- 230000008859 change Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002452 interceptive effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000004913 activation Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Control And Safety Of Cranes (AREA)
Abstract
A safety intelligent monitoring system of cantilever crane and its method are disclosed. Firstly, collecting operation parameters of a cantilever crane, wherein the operation parameters are speed and load, then, monitoring and evaluating the operation state of the cantilever crane based on the operation parameters, sending out an alarm and an instruction to control the cantilever crane to stop or adjust when an abnormal or dangerous situation is found, and then displaying the operation state and safety rating information of the cantilever crane on a screen and providing corresponding operation and management functions. Thus, the problems of low efficiency, low precision and poor timeliness caused by manual cycle or periodic inspection can be avoided, so that the supervision effect is improved, the accident risk is reduced, and the working efficiency is improved.
Description
Technical Field
The present disclosure relates to the field of intelligent supervision, and more particularly, to a secure intelligent supervision system of a cantilever crane and a method thereof.
Background
Cantilever cranes are a common industrial equipment used for lifting and handling goods at construction sites, ports, logistics centers and the like. However, there is a certain safety risk due to the influence of factors such as heavy load and complex working environment during the operation of the cantilever crane. In order to ensure the safe operation of the cantilever crane, the safety supervision of the cantilever crane is important.
However, the conventional supervision method of the cantilever crane mainly depends on experience of an operator and manual periodic or periodic inspection, and is easily affected by subjective factors, and errors or negligence are generated. Meanwhile, a manual period or a regular inspection mode needs to consume a large amount of time and manpower resources, and the running state information of the cantilever crane cannot be obtained in real time. This means that if an abnormal situation occurs between inspection, the supervisory system cannot timely detect and take measures, increasing the risk of an accident. Furthermore, since the jib crane is often operated in complex working environments, such as high altitudes, small spaces or in severe weather conditions. The traditional supervision method has certain limitations when dealing with complex environments and variable working conditions, and cannot provide accurate safety assessment and control.
Thus, an optimized safety intelligent supervision scheme for a cantilever crane is desired.
Disclosure of Invention
In view of this, the present disclosure proposes a safety intelligent supervision system of a cantilever crane and a method thereof, which can automatically monitor and evaluate the operation state of the cantilever crane in real time based on the variation of the operation parameters of the cantilever crane, and issue an alarm and an instruction to control the suspension crane to stop or adjust when an abnormal or dangerous situation is found.
According to an aspect of the present disclosure, there is provided a safety intelligent supervision system of a cantilever crane, comprising: the operation parameter data acquisition module is used for acquiring operation parameters of the cantilever crane, wherein the operation parameters are speed and load; the operation state monitoring module is used for monitoring and evaluating the operation state of the cantilever crane based on the operation parameters, and sending out an alarm and an instruction to control the cantilever crane to stop or adjust when an abnormal or dangerous situation is found; and the display management module is used for displaying the running state and the safety rating information of the cantilever crane on a screen and providing corresponding operation and management functions.
In the above-mentioned cantilever crane's safe intelligent supervisory systems, the running state monitoring module includes: the data acquisition unit is used for acquiring speed values and load values of the monitored cantilever crane at a plurality of preset time points in a preset time period through the sensor network; the operation parameter data time sequence characteristic interaction unit is used for carrying out time sequence collaborative association analysis on the speed values and the load values of the plurality of preset time points so as to obtain operation speed-load time sequence interaction characteristics; and the running state detection unit is used for determining whether the running state of the monitored cantilever crane is normal or not based on the running speed-load time sequence interaction characteristic.
In the above-mentioned intelligent monitoring system for cantilever crane, the operation parameter data time sequence feature interaction unit includes: a data time sequence arrangement subunit, configured to arrange the speed values and the load values at the multiple predetermined time points into an operation speed time sequence input vector and an operation load time sequence input vector according to a time dimension respectively; the data time sequence feature extraction subunit is used for respectively passing the operation speed time sequence input vector and the operation load time sequence input vector through a time sequence feature extractor based on a one-dimensional convolution layer to obtain an operation speed time sequence feature vector and an operation load time sequence feature vector; and the operation parameter time sequence characteristic interaction subunit is used for carrying out characteristic interaction on the operation speed time sequence characteristic vector and the operation load time sequence characteristic vector to obtain the operation speed-load time sequence interaction characteristic.
In the above-mentioned intelligent monitoring system for cantilever crane, the operation parameter timing sequence feature interaction subunit is configured to: and performing feature interaction based on an attention mechanism on the operation speed time sequence feature vector and the operation load time sequence feature vector by using an inter-feature attention layer to obtain an operation speed-load time sequence interaction feature vector as the operation speed-load time sequence interaction feature.
In the above-mentioned intelligent monitoring system for safety of a cantilever crane, the running state detection unit includes: the interaction characteristic optimization subunit is used for carrying out characteristic distribution optimization on the running speed-load time sequence interaction characteristic vector so as to obtain an optimized running speed-load time sequence interaction characteristic vector; and the running state classification judging subunit is used for enabling the optimized running speed-load time sequence interaction characteristic vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the running state of the monitored cantilever crane is normal or not.
In the above-mentioned intelligent monitoring system for cantilever crane, the interaction feature optimization subunit includes: the dense point distributed sampling fusion secondary subunit is used for carrying out homogeneous Gilbert space metric dense point distributed sampling fusion on the operation speed time sequence feature vector and the operation load time sequence feature vector to obtain a fusion feature vector; and the feature fusion optimization secondary subunit is used for fusing the fusion feature vector and the running speed-load time sequence interaction feature vector to obtain the optimized running speed-load time sequence interaction feature vector.
In the above-mentioned cantilever crane's safe intelligent supervisory systems, the intensive point distribution sampling fuses second grade subunit for: carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the operation speed time sequence feature vector and the operation load time sequence feature vector by using the following fusion optimization formula to obtain the fusion feature vector; the fusion optimization formula is as follows: wherein ,/>Is the operating speed timing feature vector, +.>Is the said operational load time sequence feature vector, +.>A transpose vector representing the run load timing feature vector, < >>Represent Min distance and +.>Is super-parameter (herba Cinchi Oleracei)> and />The global feature mean of the running speed time sequence feature vector and the running load time sequence feature vector are respectively, and the feature vector +.>Andare all row vectors, +.>For multiplying by position point +.>For the addition of position->Is the fusion feature vector.
In the above-mentioned cantilever crane's safe intelligent supervisory systems, the running state classification judges the subunit, is used for: performing full-connection coding on the optimized operation speed-load time sequence interaction feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the present disclosure, there is provided a safety intelligent supervision method of a cantilever crane, comprising: collecting operation parameters of the cantilever crane, wherein the operation parameters are speed and load; monitoring and evaluating the operation state of the cantilever crane based on the operation parameters, and sending out an alarm and an instruction to control the cantilever crane to stop or adjust when an abnormal or dangerous situation is found; and displaying the running state and the safety rating information of the cantilever crane on a screen, and providing corresponding operation and management functions.
In the above-mentioned intelligent monitoring method for safety of a cantilever crane, monitoring and evaluating the operation state of the cantilever crane based on the operation parameters, and when an abnormal or dangerous situation is found, giving an alarm and an instruction to control the cantilever crane to stop or adjust, including: acquiring speed values and load values of a monitored cantilever crane at a plurality of preset time points in a preset time period through a sensor network; carrying out time sequence collaborative association analysis on the speed values and the load values of the plurality of preset time points to obtain operation speed-load time sequence interaction characteristics; and determining whether the running state of the monitored cantilever crane is normal or not based on the running speed-load time sequence interaction characteristic.
According to the embodiment of the disclosure, the operation parameters of the cantilever crane are firstly collected, wherein the operation parameters are speed and load, then the operation state of the cantilever crane is monitored and evaluated based on the operation parameters, when an abnormal or dangerous situation is found, an alarm and an instruction are sent out to control the cantilever crane to stop or adjust, and then the operation state and safety rating information of the cantilever crane are displayed on a screen, and corresponding operation and management functions are provided. Thus, the problems of low efficiency, low precision and poor timeliness caused by manual cycle or periodic inspection can be avoided, so that the supervision effect is improved, the accident risk is reduced, and the working efficiency is improved.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 illustrates a block diagram of a secure intelligent supervisory system of a cantilever crane according to an embodiment of the present disclosure.
Fig. 2 illustrates a block diagram of the operational status monitoring module in the safety intelligent supervision system of the cantilever crane according to an embodiment of the present disclosure.
Fig. 3 shows a block diagram of the operational parameter data timing characteristic interaction unit in the safety intelligent supervision system of the cantilever crane according to an embodiment of the present disclosure.
Fig. 4 shows a block diagram of the operation state detection unit in the safety intelligent supervision system of the cantilever crane according to an embodiment of the present disclosure.
Fig. 5 shows a block diagram of the interaction feature optimization subunit in the secure intelligent supervisory system of a cantilever crane according to an embodiment of the present disclosure.
Fig. 6 illustrates a flow chart of a method of secure intelligent supervision of a cantilever crane according to an embodiment of the disclosure.
Fig. 7 shows an architectural schematic diagram of sub-step S120 of a secure intelligent supervision method of a cantilever crane according to an embodiment of the disclosure.
Fig. 8 illustrates an application scenario diagram of a secure intelligent supervisory system of a cantilever crane according to an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the disclosure. All other embodiments, which can be made by one of ordinary skill in the art without undue burden based on the embodiments of the present disclosure, are also within the scope of the present disclosure.
As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
Fig. 1 shows a block diagram schematic of a secure intelligent supervisory system of a cantilever crane according to an embodiment of the present disclosure. As shown in fig. 1, a safety intelligent supervision system 100 of a cantilever crane according to an embodiment of the present disclosure includes: an operation parameter data acquisition module 110, configured to acquire an operation parameter of the cantilever crane, where the operation parameter is a speed and a load; the operation state monitoring module 120 is configured to monitor and evaluate an operation state of the cantilever crane based on the operation parameter, and send out an alarm and an instruction to control the cantilever crane to stop or adjust when an abnormal or dangerous situation is found; and a display management module 130 for displaying the operation state and safety rating information of the jib crane on a screen and providing corresponding operation and management functions.
Aiming at the technical problems, the technical concept of the disclosure is to collect operating parameter data, such as a speed value and a load value, of a cantilever crane at a plurality of time points through a sensor network, introduce a data processing and analyzing algorithm at the rear end to perform time sequence interaction characteristic analysis of the speed value and the load value, automatically monitor and evaluate the operating state of the cantilever crane in real time based on the operating parameter change condition of the cantilever crane, and send out an alarm and an instruction to control the cantilever crane to stop or adjust when abnormal or dangerous conditions are found. Through the mode, the problems of low efficiency, low precision and poor timeliness caused by manual cycle or regular inspection can be avoided, so that the supervision effect is improved, the accident risk is reduced, and the working efficiency is improved.
Accordingly, as shown in fig. 2, the operation state monitoring module 120 includes: a data acquisition unit 121 for acquiring speed values and load values of the monitored cantilever crane at a plurality of predetermined time points within a predetermined time period through a sensor network; an operation parameter data time sequence feature interaction unit 122, configured to perform time sequence collaborative correlation analysis on the speed values and the load values at the multiple predetermined time points to obtain operation speed-load time sequence interaction features; and an operating state detection unit 123 for determining whether the operating state of the monitored jib crane is normal based on the operating speed-load time sequence interaction characteristic.
Specifically, in the technical scheme of the present disclosure, first, speed values and load values of a monitored cantilever crane acquired by a sensor network at a plurality of predetermined time points within a predetermined time period are acquired. Then, taking into consideration that the speed value and the load value of the monitored cantilever crane have a time sequence dynamic change rule in the time dimension, and the speed value and the load value of the monitored cantilever crane also have mutual influence to determine the running state of the crane, that is, the speed value and the load value of the monitored cantilever crane also have a time sequence cooperative association relationship in the time dimension, so that the monitoring of the running state of the cantilever crane is influenced. Therefore, in the technical solution of the present disclosure, in order to enable the time sequence collaborative correlation feature interaction of the speed value and the load value of the monitored cantilever crane to perform the operation state monitoring, it is necessary to further arrange the speed value and the load value of the plurality of predetermined time points into an operation speed time sequence input vector and an operation load time sequence input vector according to a time dimension, so as to integrate the time sequence distribution information of the speed value and the load value of the monitored cantilever crane, respectively.
And then, carrying out feature mining on the operation speed time sequence input vector and the operation load time sequence input vector through a time sequence feature extractor based on a one-dimensional convolution layer, so as to extract time sequence associated feature information of the speed value and the load value of the monitored cantilever crane in the time dimension, namely time sequence change features of the load value and the speed value in the time dimension, thereby obtaining an operation speed time sequence feature vector and an operation load time sequence feature vector.
Further, an inter-feature attention layer is used to perform attention mechanism-based feature interactions on the operational speed time sequence feature vector and the operational load time sequence feature vector to obtain an operational speed-load time sequence interaction feature vector, so as to capture the association and interaction between the operational speed time sequence change feature and the operational load time sequence change feature. It should be appreciated that since the goal of the traditional attention mechanism is to learn an attention weight matrix, a greater weight is given to important features and a lesser weight is given to secondary features, thereby selecting more critical information to the current task goal. This approach is more focused on weighting the importance of individual features, while ignoring the dependency between features. The attention layer between the features can capture the correlation and the mutual influence between the time sequence change features of the running speed and the time sequence change features of the running load through the feature interaction based on an attention mechanism, learn the dependency relationship between different features, and interact and integrate the features according to the dependency relationship, so that the running speed-load time sequence interaction feature vector is obtained.
Accordingly, as shown in fig. 3, the operation parameter data timing characteristic interaction unit 122 includes: a data timing arrangement subunit 1221, configured to arrange the speed values and the load values at the plurality of predetermined time points into an operation speed timing input vector and an operation load timing input vector according to a time dimension, respectively; a data timing feature extraction subunit 1222, configured to pass the operation speed timing input vector and the operation load timing input vector through a one-dimensional convolution layer-based timing feature extractor to obtain an operation speed timing feature vector and an operation load timing feature vector, respectively; and an operation parameter time sequence feature interaction subunit 1223, configured to perform feature interaction on the operation speed time sequence feature vector and the operation load time sequence feature vector to obtain the operation speed-load time sequence interaction feature. It should be appreciated that the data timing arrangement sub-unit 1221 functions to arrange the speed values and load values at a plurality of predetermined time points in a time dimension into an operation speed timing input vector and an operation load timing input vector, which arrange the input speed and load data in a time sequence for subsequent feature extraction and interaction operations. The data timing feature extraction subunit 1222 is configured to process the operation speed timing input vector and the operation load timing input vector by using a timing feature extractor based on a one-dimensional convolution layer to obtain an operation speed timing feature vector and an operation load timing feature vector, where the one-dimensional convolution layer can capture local patterns and features in the timing data, so as to extract useful timing features. The function of the operation parameter timing feature interaction subunit 1223 is to perform a feature interaction on the operation speed timing feature vector and the operation load timing feature vector to obtain operation speed-load timing interaction features, and this subunit may use some specific methods or operations, such as connection, weighted addition, element-by-element multiplication, etc., to interact the timing features of the speed and load to obtain the association and interaction between them. The subunits play different roles in the whole time sequence characteristic interaction unit of the operation parameter data, are used for processing and extracting time sequence characteristics of input data and performing characteristic interaction so as to obtain time sequence interaction characteristics between the operation speed and the load, and can be used for further analysis, modeling or decision.
It should be noted that the one-dimensional convolution layer is a neural network layer commonly used in deep learning. It is used for processing data having a time sequence or sequence structure, such as time sequence data, text data, etc. The one-dimensional convolution layer can effectively extract local features in the input data and retain time sequence information of the input data. The input to the one-dimensional convolution layer is a one-dimensional vector, similar to a time step in time series data or a word sequence in text data. It convolves the input by defining a set of learnable convolution kernels (also called filters). The convolution kernel slides over the input and multiplies and sums the input element by element at each location, generating an output signature. The main function of the one-dimensional convolution layer is to extract local patterns and features in the input data. By varying the size and number of convolution kernels, one-dimensional convolution layers can capture features of different scales. The convolution layer can also reduce the parameter number of the model by sharing the weight parameter, thereby improving the efficiency and generalization capability of the model. In the data timing feature extraction subunit, a one-dimensional convolution layer based timing feature extractor is used for processing the running speed timing input vector and the running load timing input vector and extracting the timing features of the running speed timing input vector and the running load timing input vector. These timing features can help the model understand the dynamics and patterns of the input data to better model and predict the operating parameters.
More specifically, the operation parameter timing characteristic interaction subunit 1223 is configured to: and performing feature interaction based on an attention mechanism on the operation speed time sequence feature vector and the operation load time sequence feature vector by using an inter-feature attention layer to obtain an operation speed-load time sequence interaction feature vector as the operation speed-load time sequence interaction feature. It is worth mentioning that the inter-Feature attention layer (Feature-wise Attention Layer) is an application of an attention mechanism for interaction and weighting between different features in a neural network, which can help the network to adaptively focus and select the most relevant features at the Feature level to improve the expressive power and performance of the model. The inter-feature attention layer adjusts the importance of features by calculating attention weights based on interactions and correlations of input features. These weights may be used to weight sum the features to obtain an interactive representation between the features. In the operational parameter timing feature interaction subunit, an inter-feature attention layer is used to perform feature interactions on the operational speed timing feature vector and the operational load timing feature vector. By calculating the attention weight, it can automatically determine which timing characteristics are more important in a particular situation, thereby enhancing the timing interaction characteristics between the operating speed and the load. This helps the model better understand and capture the dependencies and dependencies between operating parameters. The inter-feature attention layer can improve the expressive power of the model, so that the model can be better adapted to different input data and tasks. By adaptively learning the relationships between features, it can provide a richer and targeted representation of features, thereby improving the performance and generalization ability of the model.
And then, the running speed-load time sequence interaction characteristic vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the running state of the monitored cantilever crane is normal or not. That is, the classification process is performed by using the time sequence interaction characteristic between the speed time sequence variation characteristic and the load time sequence variation characteristic of the monitored cantilever crane, so that the running state of the cantilever crane is automatically monitored and evaluated in real time based on the running parameter variation condition of the cantilever crane, and when an abnormal or dangerous condition is found, an alarm and an instruction are sent out to control the cantilever crane to stop or adjust.
Accordingly, as shown in fig. 4, the operation state detection unit 123 includes: the interaction characteristic optimization subunit 1231 is configured to perform characteristic distribution optimization on the running speed-load time sequence interaction characteristic vector to obtain an optimized running speed-load time sequence interaction characteristic vector; and an operation state classification judging subunit 1232, configured to pass the optimized operation speed-load time sequence interaction feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the operation state of the monitored cantilever crane is normal. It should be understood that the operation state detection unit is a module for detecting and classifying the operation state of the monitored jib crane, and includes an interaction characteristic optimization subunit and an operation state classification judgment subunit. The purpose of the interaction feature optimization subunit 1231 is to extract more discriminative and expressive feature representations by optimizing the interaction features, which helps to reduce redundant information in the features and enhance discrimination of operational states. The function of the run state classification decision subunit 1232 is to map the optimized feature vectors to different run state classes, e.g., normal and abnormal states, and the classifier may be a common machine learning algorithm, such as a Support Vector Machine (SVM), random Forest (Random Forest), or deep learning model, such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN). Through the combination of the interaction characteristic optimizing sub-unit and the running state classifying and judging sub-unit, the running state detecting unit can extract key information from the optimized characteristics and accurately classify and judge the running state of the cantilever crane. This facilitates real-time monitoring and identification of abnormal operating conditions of the jib crane, and intervention and maintenance by taking corresponding measures.
More specifically, as shown in fig. 5, the interaction feature optimization subunit 1231 includes: the dense point distribution sampling fusion secondary subunit 12311 is configured to perform homogeneous gilbert spatial metric dense point distribution sampling fusion on the operation speed timing sequence feature vector and the operation load timing sequence feature vector to obtain a fusion feature vector; and a feature fusion optimization secondary subunit 12312, configured to fuse the fusion feature vector and the operation speed-load time sequence interaction feature vector to obtain the optimized operation speed-load time sequence interaction feature vector. It should be appreciated that the interactive feature optimization subunit 1231 includes two secondary subunits, a dense point distribution sampling fusion secondary subunit 12311 and a feature fusion optimization secondary subunit 12312. The dense point distribution sampling fusion secondary subunit 12311 is configured to perform homogeneous gilbert spatial metric dense point distribution sampling fusion on an operation speed time sequence feature vector and an operation load time sequence feature vector to obtain a fusion feature vector, where homogeneous gilbert spatial metric dense point distribution sampling is a feature extraction method, and performs dense sampling on the time sequence feature vector and performs transformation and fusion on sampling points by using homogeneous gilbert transformation, so as to obtain a fusion feature vector with better expressive power and distinguishing property. The feature fusion optimization secondary subunit 12312 is configured to fuse the fusion feature vector with the operation speed-load time sequence interaction feature vector to obtain an optimized operation speed-load time sequence interaction feature vector, where the objective of this subunit is to optimally fuse the fusion feature and the time sequence interaction feature obtained by fusion of dense point distribution samples, so as to improve the expressive power and discriminant of the feature, and the fusion can be implemented by simple vector stitching, weighted summation, or other specific fusion strategies, and the specific method depends on the characteristics of the task and the data. Through the combination of the dense point distributed sampling fusion secondary subunit and the feature fusion optimization secondary subunit, the interactive feature optimization subunit can fuse and optimize the time sequence features of the running speed and the load, so that the feature representation with more differentiation and expression is obtained, and the accuracy and the robustness of running state detection are improved.
In particular, in the technical solution of the present disclosure, the inter-feature attention layer may extract an interaction feature expressing a dependency relationship between the operation speed time-series feature vector and the operation load time-series feature vector, so as to obtain the operation speed-load time-series interaction feature vector, and therefore, if the representation of the operation speed-load time-series interaction feature vector on a one-dimensional time-series local correlation feature of a speed value and a load value expressed by each of the operation speed time-series feature vector and the operation load time-series feature vector by the operation speed-load time-series interaction feature vector can be further enhanced, the expression effect of the operation speed-load time-series interaction feature vector may be enhanced.
And, the applicant of the present disclosure considers the dense mining pattern local correlation feature expression under the one-dimensional convolution kernel scale based on the sequential feature homogeneous coding of the one-dimensional convolution layer, in which the operation speed sequential feature vector and the operation load sequential feature vector are a speed value and a load value, respectively, and thus, the operation is performed on the dataLine speed timing feature vectors, e.g. denoted asAnd said operational load timing feature vector, e.g. denoted +.>And performing homogeneous Gilbert spatial metric dense point distribution sampling fusion.
Accordingly, in one specific example, the dense point distributed sampling fusion two-level subunit 12311 is configured to: carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the operation speed time sequence feature vector and the operation load time sequence feature vector by using the following fusion optimization formula to obtain the fusion feature vector; the fusion optimization formula is as follows: wherein ,/>Is the operating speed timing feature vector, +.>Is the said operational load time sequence feature vector, +.>A transpose vector representing the run load timing feature vector, < >>Represent Min distance and +.>Is super-parameter (herba Cinchi Oleracei)> and />Is the global feature average of the running speed time sequence feature vector and the running load time sequence feature vector respectively, andfeature vector-> and />Are all row vectors, +.>For multiplying by position point +.>For the addition of position->Is the fusion feature vector.
Here, by applying the time sequence feature vector to the running speedAnd said operational load timing feature vector +.>A homogeneous gilbert spatial metric of the feature distribution center of (2) to +.>And said operational load timing feature vector +. >The fusion feature distribution of the cross-distance constraint point-by-point feature association is used as a bias term to realize feature dense point sampling pattern distribution fusion in the association constraint limit of the feature distribution, so that the homogeneous sampling association fusion among vectors is enhanced. Then, the fusion feature vector is added again>By fusing the operation speed-load time sequence interaction characteristic vector, the operation speed-load time sequence interaction characteristic can be improvedThe feature expression of the sign vector improves the accuracy of the classification result obtained by the classifier. Therefore, the operation state of the cantilever crane can be automatically monitored and evaluated in real time based on the change condition of the operation parameters of the cantilever crane, and when an abnormal or dangerous condition is found, an alarm and an instruction are sent out to control the cantilever crane to stop or adjust, so that the supervision effect is improved, the accident risk is reduced, and the working efficiency is improved.
Further, the operation state classification judgment subunit 1232 is configured to: performing full-connection coding on the optimized operation speed-load time sequence interaction feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
That is, in the technical solution of the present disclosure, the labels of the classifier include a normal running state of the monitored cantilever crane (first label) and an abnormal running state of the monitored cantilever crane (second label), wherein the classifier determines to which classification label the optimized running speed-load time sequence interaction feature vector belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a concept set by human, and in fact, during the training process, the computer model does not have a concept of "whether the operation state of the monitored jib crane is normal", which is simply that there are two kinds of classification tags and the probability that the output characteristic is under the two kinds of classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result of whether the operation state of the monitored cantilever crane is normal is actually converted into the classified probability distribution conforming to the natural rule through classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether the operation state of the monitored cantilever crane is normal.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
It should be noted that full-connection coding refers to performing linear transformation and nonlinear activation on input data through a full-connection layer to obtain a coded feature vector. In the running state classification judging subunit, the optimized running speed-load time sequence interaction feature vector is subjected to full-connection coding to obtain a coding classification feature vector, and then the feature vector is input into a Softmax classification function of the classifier for classification. The function of the full-join encoding is to map the input feature vector to a higher dimensional feature space and introduce a nonlinear relationship through a nonlinear activation function, thereby extracting a richer, more abstract feature representation. The weight parameters in the full connection layer can be learned and optimized through a training process, so that the coded feature vector is better adapted to a specific classification task. The original optimized running speed-load time sequence interaction feature vector can be converted into a code classification feature vector with more discriminant and expressive force through full-connection coding. After the encoded classification feature vector passes through the Softmax classification function, each element of the vector is mapped into a probability value through the normalization operation of the Softmax function, and the probability that the sample belongs to different classification categories is represented. Finally, the running state classification result of the monitored cantilever crane can be determined according to the probability value. Full-connection coding is widely applied to feature extraction and classification tasks in deep learning, and can gradually extract high-level features from low-level features through multi-layer full-connection layer stacking and nonlinear activation function introduction, so that the expression capacity and classification performance of a model are improved.
In summary, the safety intelligent monitoring system 100 of the cantilever crane according to the embodiments of the present disclosure is illustrated, which can avoid the problems of low efficiency, low precision and poor timeliness caused by manual cycle or periodic inspection, thereby improving the monitoring effect, reducing the accident risk, and improving the working efficiency.
As described above, the safety intelligent supervision system 100 of a cantilever crane according to the embodiment of the present disclosure may be implemented in various terminal devices, for example, a server having a safety intelligent supervision algorithm of a cantilever crane, or the like. In one example, the secure intelligent supervisory system 100 of the cantilever crane may be integrated into the terminal equipment as one software module and/or hardware module. For example, the secure intelligent supervisory system 100 of the cantilever crane may be a software module in the operating system of the terminal device or may be an application developed for the terminal device; of course, the safety intelligent supervision system 100 of the cantilever crane can equally well be one of the numerous hardware modules of the terminal equipment.
Alternatively, in another example, the secure intelligent supervisory system 100 of the cantilever crane and the terminal device may be separate devices, and the secure intelligent supervisory system 100 of the cantilever crane may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Fig. 6 illustrates a flow chart of a method of secure intelligent supervision of a cantilever crane according to an embodiment of the disclosure. As shown in fig. 6, a safety intelligent supervision method of a cantilever crane according to an embodiment of the present disclosure includes: s110, collecting operation parameters of the cantilever crane, wherein the operation parameters are speed and load; s120, monitoring and evaluating the operation state of the cantilever crane based on the operation parameters, and sending out an alarm and an instruction to control the cantilever crane to stop or adjust when an abnormal or dangerous situation is found; and S130, displaying the running state and the safety rating information of the cantilever crane on a screen, and providing corresponding operation and management functions.
In one possible implementation, fig. 7 shows a schematic diagram of the system architecture of sub-step S120 of the safety intelligent supervision method of a cantilever crane according to an embodiment of the present disclosure. As shown in fig. 7, monitoring and evaluating the operating state of the cantilever crane based on the operating parameters, and upon finding an abnormal or dangerous condition, issuing an alarm and an instruction to control the cantilever crane to stop or adjust, including: acquiring speed values and load values of a monitored cantilever crane at a plurality of preset time points in a preset time period through a sensor network; carrying out time sequence collaborative association analysis on the speed values and the load values of the plurality of preset time points to obtain operation speed-load time sequence interaction characteristics; and determining whether the running state of the monitored cantilever crane is normal or not based on the running speed-load time sequence interaction characteristic.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described safety intelligent supervision method of the cantilever crane have been described in detail in the above description of the safety intelligent supervision system of the cantilever crane with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
Fig. 8 illustrates an application scenario diagram of a secure intelligent supervisory system of a cantilever crane according to an embodiment of the present disclosure. As shown in fig. 8, in this application scenario, first, an operation parameter of the cantilever crane (for example, D illustrated in fig. 8) is collected, where the operation parameter is a speed and a load, and then, the operation parameter is input to a server (for example, S illustrated in fig. 8) where a safety intelligent supervision algorithm of the cantilever crane is deployed, where the server can process the operation parameter using the safety intelligent supervision algorithm of the cantilever crane to obtain a classification result for indicating whether an operation state of the monitored cantilever crane is normal.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted 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-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (4)
1. A secure intelligent supervisory system for a cantilever crane, comprising:
the operation parameter data acquisition module is used for acquiring operation parameters of the cantilever crane, wherein the operation parameters are speed and load;
the operation state monitoring module is used for monitoring and evaluating the operation state of the cantilever crane based on the operation parameters, and sending out an alarm and an instruction to control the cantilever crane to stop or adjust when an abnormal or dangerous situation is found; and
the display management module is used for displaying the running state and the safety rating information of the cantilever crane on a screen and providing corresponding operation and management functions;
Wherein, the running state monitoring module includes:
the data acquisition unit is used for acquiring speed values and load values of the monitored cantilever crane at a plurality of preset time points in a preset time period through the sensor network;
the operation parameter data time sequence characteristic interaction unit is used for carrying out time sequence collaborative association analysis on the speed values and the load values of the plurality of preset time points so as to obtain operation speed-load time sequence interaction characteristics; and
the running state detection unit is used for determining whether the running state of the monitored cantilever crane is normal or not based on the running speed-load time sequence interaction characteristics;
wherein, the operation parameter data time sequence characteristic interaction unit comprises:
a data time sequence arrangement subunit, configured to arrange the speed values and the load values at the multiple predetermined time points into an operation speed time sequence input vector and an operation load time sequence input vector according to a time dimension respectively;
the data time sequence feature extraction subunit is used for respectively passing the operation speed time sequence input vector and the operation load time sequence input vector through a time sequence feature extractor based on a one-dimensional convolution layer to obtain an operation speed time sequence feature vector and an operation load time sequence feature vector; and
An operation parameter time sequence feature interaction subunit, configured to perform feature interaction on the operation speed time sequence feature vector and the operation load time sequence feature vector to obtain the operation speed-load time sequence interaction feature;
wherein the operation state detection unit includes:
the interaction characteristic optimization subunit is used for carrying out characteristic distribution optimization on the running speed-load time sequence interaction characteristic vector so as to obtain an optimized running speed-load time sequence interaction characteristic vector; and
the running state classification judging subunit is used for enabling the optimized running speed-load time sequence interaction characteristic vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the running state of the monitored cantilever crane is normal or not;
wherein the interaction characteristic optimization subunit comprises:
the dense point distributed sampling fusion secondary subunit is used for carrying out homogeneous Gilbert space metric dense point distributed sampling fusion on the operation speed time sequence feature vector and the operation load time sequence feature vector to obtain a fusion feature vector; and
the feature fusion optimization secondary subunit is used for fusing the fusion feature vector and the running speed-load time sequence interaction feature vector to obtain the optimized running speed-load time sequence interaction feature vector;
The dense point distributed sampling fusion two-level subunit is used for:
carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the operation speed time sequence feature vector and the operation load time sequence feature vector by using the following fusion optimization formula to obtain the fusion feature vector;
the fusion optimization formula is as follows:
，
wherein ,is the operating speed timing feature vector, +.>Is the said operational load time sequence feature vector, +.>A transpose vector representing the run load timing feature vector, < >>Represent Min distance and +.>Is the parameter of the ultrasonic wave to be used as the ultrasonic wave, and />The global feature mean of the running speed time sequence feature vector and the running load time sequence feature vector are respectively, and the feature vector +.> and />Are all row vectors, +.>For multiplying by position point +.>For the addition of position->Is the fusion feature vector.
2. The safety intelligent supervision system of a jib crane according to claim 1, wherein the operating parameter timing characteristic interaction subunit is configured to:
and performing feature interaction based on an attention mechanism on the operation speed time sequence feature vector and the operation load time sequence feature vector by using an inter-feature attention layer to obtain an operation speed-load time sequence interaction feature vector as the operation speed-load time sequence interaction feature.
3. The safety intelligent supervision system of a cantilever crane according to claim 2, wherein the operating state classification judgment subunit is configured to:
performing full-connection coding on the optimized operation speed-load time sequence interaction feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and
and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
4. A method of intelligent safety supervision for a cantilever crane, for use in the intelligent safety supervision system for a cantilever crane of claim 1, comprising:
collecting operation parameters of the cantilever crane, wherein the operation parameters are speed and load;
monitoring and evaluating the operation state of the cantilever crane based on the operation parameters, and sending out an alarm and an instruction to control the cantilever crane to stop or adjust when an abnormal or dangerous situation is found; and
displaying the running state and the safety rating information of the cantilever crane on a screen, and providing corresponding operation and management functions;
wherein monitoring and evaluating the operating state of the jib crane based on the operating parameters and when an abnormal or dangerous condition is found, issuing an alarm and an instruction to control the jib crane to stop or adjust comprises:
Acquiring speed values and load values of a monitored cantilever crane at a plurality of preset time points in a preset time period through a sensor network;
carrying out time sequence collaborative association analysis on the speed values and the load values of the plurality of preset time points to obtain operation speed-load time sequence interaction characteristics; and
and determining whether the running state of the monitored cantilever crane is normal or not based on the running speed-load time sequence interaction characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311029742.2A CN116730226B (en) | 2023-08-16 | 2023-08-16 | Safety intelligent supervision system and method for cantilever crane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311029742.2A CN116730226B (en) | 2023-08-16 | 2023-08-16 | Safety intelligent supervision system and method for cantilever crane |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116730226A CN116730226A (en) | 2023-09-12 |
| CN116730226B true CN116730226B (en) | 2023-10-27 |
Family
ID=87919082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311029742.2A Active CN116730226B (en) | 2023-08-16 | 2023-08-16 | Safety intelligent supervision system and method for cantilever crane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116730226B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1997045358A1 (en) * | 1996-05-24 | 1997-12-04 | Siemens Aktiengesellschaft | Method and arrangement for preventing load collisions in a suspended load movement apparatus |
| JP2002081425A (en) * | 2000-09-04 | 2002-03-22 | Sekisui Chem Co Ltd | Fastening member and fastening method |
| JP2012111617A (en) * | 2010-11-26 | 2012-06-14 | Kito Corp | Operation state measuring device of hoisting device and hoisting device |
| CN102730571A (en) * | 2012-06-01 | 2012-10-17 | 华中科技大学 | Online monitoring and fault diagnosing system for crane |
| CN203965033U (en) * | 2013-12-03 | 2014-11-26 | 内蒙古北方重工业集团有限公司 | A kind of boom-type roadheader spindle vibration monitoring running state device |
| CN104310229A (en) * | 2014-08-20 | 2015-01-28 | 四川建设机械（集团）股份有限公司 | Remote monitoring system of tower crane |
| CN110127526A (en) * | 2019-06-05 | 2019-08-16 | 重庆两江新区管理委员会 | A kind of wisdom early warning system for derrick crane |
| CN210133831U (en) * | 2019-04-29 | 2020-03-10 | 南京市特种设备安全监督检验研究院 | Safety monitoring system for mast crane |
| CN113233334A (en) * | 2021-05-18 | 2021-08-10 | 山西航天清华装备有限责任公司 | Straight arm type lorry-mounted crane control system and control method thereof |
| CN113460898A (en) * | 2020-03-30 | 2021-10-01 | 江苏徐工工程机械研究院有限公司 | Crane function safety moment limiter system |
| CN113911925A (en) * | 2021-09-14 | 2022-01-11 | 杭州大杰智能传动科技有限公司 | System and method for early warning and monitoring of working space of intelligent tower crane |
| CN114599600A (en) * | 2019-09-13 | 2022-06-07 | 卡斯淘Msc有限公司 | Method for determining crane or jib operating envelope on a jack-up platform unit, jack-up platform unit |
| CN115660161A (en) * | 2022-10-18 | 2023-01-31 | 三峡大学 | Medium-term and small-term load probability prediction method based on time sequence fusion Transformer model |
-
2023
- 2023-08-16 CN CN202311029742.2A patent/CN116730226B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1997045358A1 (en) * | 1996-05-24 | 1997-12-04 | Siemens Aktiengesellschaft | Method and arrangement for preventing load collisions in a suspended load movement apparatus |
| JP2002081425A (en) * | 2000-09-04 | 2002-03-22 | Sekisui Chem Co Ltd | Fastening member and fastening method |
| JP2012111617A (en) * | 2010-11-26 | 2012-06-14 | Kito Corp | Operation state measuring device of hoisting device and hoisting device |
| CN102730571A (en) * | 2012-06-01 | 2012-10-17 | 华中科技大学 | Online monitoring and fault diagnosing system for crane |
| CN203965033U (en) * | 2013-12-03 | 2014-11-26 | 内蒙古北方重工业集团有限公司 | A kind of boom-type roadheader spindle vibration monitoring running state device |
| CN104310229A (en) * | 2014-08-20 | 2015-01-28 | 四川建设机械（集团）股份有限公司 | Remote monitoring system of tower crane |
| CN210133831U (en) * | 2019-04-29 | 2020-03-10 | 南京市特种设备安全监督检验研究院 | Safety monitoring system for mast crane |
| CN110127526A (en) * | 2019-06-05 | 2019-08-16 | 重庆两江新区管理委员会 | A kind of wisdom early warning system for derrick crane |
| CN114599600A (en) * | 2019-09-13 | 2022-06-07 | 卡斯淘Msc有限公司 | Method for determining crane or jib operating envelope on a jack-up platform unit, jack-up platform unit |
| CN113460898A (en) * | 2020-03-30 | 2021-10-01 | 江苏徐工工程机械研究院有限公司 | Crane function safety moment limiter system |
| CN113233334A (en) * | 2021-05-18 | 2021-08-10 | 山西航天清华装备有限责任公司 | Straight arm type lorry-mounted crane control system and control method thereof |
| CN113911925A (en) * | 2021-09-14 | 2022-01-11 | 杭州大杰智能传动科技有限公司 | System and method for early warning and monitoring of working space of intelligent tower crane |
| CN115660161A (en) * | 2022-10-18 | 2023-01-31 | 三峡大学 | Medium-term and small-term load probability prediction method based on time sequence fusion Transformer model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116730226A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Salehi et al. | Emerging artificial intelligence methods in structural engineering | |
| CN116639010B (en) | Intelligent control system and method for charging pile | |
| CN116625438A (en) | Gas pipe network safety on-line monitoring system and method thereof | |
| CN111583592B (en) | Experimental environment safety early warning method based on multidimensional convolution neural network | |
| Sajedi et al. | Dual Bayesian inference for risk‐informed vibration‐based damage diagnosis | |
| CN110379036A (en) | Intelligent substation patrol recognition methods, system, device and storage medium | |
| CN110852881A (en) | Risk account identification method and device, electronic equipment and medium | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN116186594B (en) | Method for realizing intelligent detection of environment change trend based on decision network combined with big data | |
| CN115019209A (en) | Method and system for detecting state of electric power tower based on deep learning | |
| CN116861924A (en) | Project risk early warning method and system based on artificial intelligence | |
| CN114048817A (en) | Deep learning input set priority test method based on variation strategy | |
| CN116930042B (en) | Building waterproof material performance detection equipment and method | |
| CN116872961B (en) | Control system for intelligent driving vehicle | |
| CN116730226B (en) | Safety intelligent supervision system and method for cantilever crane | |
| CN117422990A (en) | Bridge structure classification and evaluation method based on machine learning | |
| CN113269433B (en) | Tax risk prediction method, apparatus, medium and computer program product | |
| CN114429032A (en) | Bridge health online intelligent monitoring system | |
| CN116821800B (en) | Structure state classification method and related equipment based on semi-supervised generation countermeasure network | |
| Shahoud et al. | Incorporating unsupervised deep learning into meta learning for energy time series forecasting | |
| CN116934304B (en) | Intelligent power distribution room equipment operation maintenance management system and method thereof | |
| Alshawabkeh et al. | Automated Pavement Crack Detection Using Deep Feature Selection and Whale Optimization Algorithm. | |
| CN116311950B (en) | Path selection method and V2X test system based on virtual-real fusion technology | |
| Chavhan et al. | Machine Learning Based Placement Prediction-A Comparative Study | |
| CN117784710B (en) | Remote state monitoring system and method for numerical control machine tool |
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 |