CN117634895B - Non-coal mine safety dynamic risk assessment system and assessment method thereof - Google Patents
Non-coal mine safety dynamic risk assessment system and assessment method thereof Download PDFInfo
- Publication number
- CN117634895B CN117634895B CN202410113061.2A CN202410113061A CN117634895B CN 117634895 B CN117634895 B CN 117634895B CN 202410113061 A CN202410113061 A CN 202410113061A CN 117634895 B CN117634895 B CN 117634895B
- Authority
- CN
- China
- Prior art keywords
- job
- representing
- layer
- nodes
- evaluated
- 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
- 238000012502 risk assessment Methods 0.000 title claims abstract description 47
- 239000003245 coal Substances 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000004927 fusion Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 14
- 238000012512 characterization method Methods 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 230000002411 adverse Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000005065 mining Methods 0.000 abstract description 9
- 238000007405 data analysis Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of mine safety management, and discloses a non-coal mine safety dynamic risk assessment system and an assessment method thereof, wherein the non-coal mine safety dynamic risk assessment system comprises a mine data acquisition module, a mining data acquisition module and a mining data analysis module, wherein the mine data acquisition module is used for acquiring data of an operation system for managing a mine; a first risk assessment module for acquiring job layer data within a period of time before an execution time point of a job operation to be assessed, and then inputting a dynamic risk assessment model, and outputting a value representing a risk of the job operation to be assessed; according to the risk assessment method, risk prediction is carried out on the unexecuted operation in the mine operation system, dynamic changes and mutual influences of the operation system are comprehensively considered, accuracy is improved compared with a method for assessing the risk by independently considering the attribute and the parameter of the operation project, the risk caused by human factor intervention of an operator is fully considered, and the risk caused by the human factor is accommodated in the risk assessment.
Description
Technical Field
The invention relates to the technical field of mine safety management, in particular to a non-coal mine safety dynamic risk assessment system and an assessment method thereof.
Background
The invention with the bulletin number of CN115375137B discloses a safety risk early warning prediction system of a non-coal mine tailing pond, which is used for judging the risk of a monitored item by collecting real-time operation data of each item to be monitored of the non-coal mine tailing pond and determining a risk assessment index based on attribute characteristics of each item to be monitored; however, in fact, for underground operations other than coal mines, the respective operation systems and the operation projects are not independent, there is an influence related to each other, the influence between the systems is ignored only by judging the risk through the parameter attribute of the operation project itself, and a deviation exists.
Disclosure of Invention
The invention provides a non-coal mine safety dynamic risk assessment system and an assessment method thereof, which solve the technical problems that in the related art, risks can only be judged based on the influence of completed operation on monitoring projects, and accidents are difficult to avoid for some risks with short development time.
The invention provides a non-coal mine safety dynamic risk assessment system, which comprises:
the mine data acquisition module is used for acquiring data of an operation system for managing a mine;
a mine personnel management module for managing data of mine operators;
a mine operation management module for managing data of operation operations of the mine;
a job layer generation module for generating a plurality of job layer data including job nodes and edges connecting the job nodes; the operation nodes comprise passive nodes and active nodes, wherein one passive node has a representation relationship with part of an operation system, and one active node has a representation relationship with a mine operator or an operation;
an edge exists between two passive nodes to indicate that the parts of the operating system represented by the two passive nodes have a connection relationship;
the condition that there is an edge between two active nodes is: one of the two active nodes represents a mine operator to execute the operation represented by the other active node;
the condition that there is an edge between the active node and the passive node is: the operation of the job represented by the active node acts on the part of the operating system represented by the passive node;
a first risk assessment module for collecting job layer data within a period of time before an execution time point of a job operation to be assessed, and then inputting a dynamic risk assessment model, the dynamic risk assessment model comprising: a layer information encoding layer for fusing the associated job layer data of the job operation to be evaluated, excluding the job layer data of the execution time point of the job operation to be evaluated;
the layer information fusion layer is used for fusing all associated operation layer data of the operation to be evaluated;
the cross-layer information fusion layer is used for fusing all the operation layer data of the execution time point of the operation to be evaluated;
a first output layer for outputting a value representing a risk of a job operation to be evaluated.
Further, the operation system comprises a roadway operation system, a water supply operation system, a drainage operation system and a communication operation system.
Further, the length of the period in the work layer data in the period before the execution time point of the work operation to be evaluated is acquired is 1 minute to 100 minutes.
Further, the conditions under which the job layer data is associated with the job operation to be evaluated are: the operating system represented by the passive node in the job layer data is the same as the operating system for which the job operation to be evaluated is directed.
Further, the calculation formula of the layer information encoding layer is as follows:
；
；
a kth layer coding feature representing an ith job node,/->And->Characterization features of the ith and jth job nodes, respectively representing kth job layer data, +.>、/>And->Representing first, second and third weight parameters respectively,a set of job nodes representing edges in the kth job layer data with the ith job node, +.>Representing Sigmoid function->Fusion weights of the ith and jth job nodes representing kth job layer data, +.>Representing vector concatenation->Representing a total number of job nodes in the kth job layer data;
the calculation formula of the layer information fusion layer is as follows:
；
；
，/>；
fusion characteristics of the ith job node of the job layer data representing the execution time point of the job operation to be evaluated, +.>A set of job nodes having edges with an ith job node in job layer data representing execution time points of job operations to be evaluated, H representing a set of job layer data fused by a layer information encoding layer,/a>、/>And->Representing the fourth, fifth and sixth weight parameter, respectively,/->Total number of job nodes of job layer data representing execution time point of job operation to be evaluated, +.>Fusion weights of an ith and a jth job node of job layer data representing execution time points of job operations to be evaluated, +.>And->A kth layer coding feature representing an ith and jth job node of layer information coding layer output,/->And->Non-linear transformation characteristics of the ith and jth job nodes of the job layer data representing execution time points of the job operation to be evaluated;
the calculation formula of the cross-layer information fusion layer is as follows:
；
；
coding feature of the ith job node representing the ith job layer data, +.>And->Characterization features of the ith and jth job nodes, respectively representing the jth job layer data,/>And->Respectively representing a seventh weight parameter and an eighth weight parameter,>a set of job nodes representing sides with the ith job node in the t-th job layer data, +.>Fusion weights of ith and jth job nodes representing the tth job layer data, +.>An exponential function that is based on a natural constant;
the calculation formula of the first output layer is as follows:
；
；
fusion characteristics of job nodes representing the job operation to be evaluated in the job layer data representing the execution time point of the job operation to be evaluated, +.>Represents a ninth weight parameter,>representing the first bias parameter, ">Representing cross-layer set vectors, ">Splicing or summing of coding features of all job nodes of the t-th job layer data representing the execution time point of the job operation to be evaluated, V represents a set of all job layer data representing the execution time point of the job operation to be evaluated,/-, and>representing the stitching function.
Further, the first output layer outputs a risk value, the higher the risk value is indicative of the greater risk of the job operation to be evaluated.
Further, the first output layer outputs an evaluation vector, the evaluation vector comprising two components, respectively representing the risk and risk-free possibility of the operation to be evaluated, if the component representing the risk of the operation to be evaluated is greater than or equal to the other component, the operation to be evaluated is risk, otherwise the operation to be evaluated is risk-free.
Further, the first output layer outputs a risk type vector including a plurality of components respectively representing risk types of the job operation to be evaluated, the risk types including: no risk, insufficient operator capacity, operator fatigue and adverse effect on other operating systems.
The invention provides a non-coal mine safety dynamic risk assessment method, which is based on the non-coal mine safety dynamic risk assessment system, and comprises the following steps:
step 201, generating a plurality of operation layer data, wherein the operation layer data comprises operation nodes and edges connected with the operation nodes; the operation nodes comprise passive nodes and active nodes, wherein one passive node has a representation relationship with part of an operation system, and one active node has a representation relationship with a mine operator or an operation;
step 202, collecting job layer data in a period of time before an execution time point of a job operation to be evaluated;
step 203, inputting the collected operation layer data into a dynamic risk assessment model, and outputting a value representing the risk of operation to be assessed;
step 204, judging whether to terminate execution of the operation to be evaluated according to whether the operation to be evaluated has risk;
and if the operation to be evaluated is at risk, terminating execution of the operation to be evaluated, otherwise, not terminating execution of the operation to be evaluated.
The present invention provides a storage medium storing non-transitory computer readable instructions that, when executed by a computer, enable the steps of a non-coal mine safety dynamic risk assessment method as described above.
The invention has the beneficial effects that: according to the risk assessment method, risk prediction is carried out on the unexecuted operation in the mine operation system, dynamic changes and mutual influences of the operation system are comprehensively considered, accuracy is improved compared with a method for assessing the risk by independently considering the attribute and the parameter of the operation project, the risk caused by human factor intervention of an operator is fully considered, and the risk caused by the human factor is accommodated in the risk assessment.
Drawings
FIG. 1 is a schematic diagram of a non-coal mine safety dynamic risk assessment system;
FIG. 2 is a schematic diagram of a non-coal mine safety dynamic risk assessment system according to a second embodiment of the present invention;
FIG. 3 is a flow chart of a non-coal mine safety dynamic risk assessment method of the present invention.
In the figure: the system comprises a mine data acquisition module 101, a mine personnel management module 102, a mine operation management module 103, a working layer generation module 104, a first risk assessment module 105, a dynamic image acquisition system 106, an image sequence generation module 107 and a second risk identification module 108.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
In one embodiment of the present invention, a system for evaluating the dynamic risk of non-coal mine safety is provided, as shown in fig. 1, comprising:
the mine data acquisition module is used for acquiring data of an operation system for managing a mine;
a mine personnel management module for managing data of mine operators;
the data of the mine operator includes the ID, age, post name, name of equipment once operated, and the number of operation errors of the mine operator.
A mine operation management module for managing data of operation operations of the mine;
the data of the job operation includes steps, target equipment or nodes, parameter variables, designated mine operators, and the like.
A job layer generation module for generating a plurality of job layer data including job nodes and edges connecting the job nodes; the operation nodes comprise passive nodes and active nodes, wherein one passive node has a representation relationship with part of an operation system, and one active node has a representation relationship with a mine operator or an operation;
an edge exists between two passive nodes to indicate that the parts of the operating system represented by the two passive nodes have a connection relationship;
the condition that there is an edge between two active nodes is: one of the two active nodes represents a mine operator performing a work operation represented by the other active node.
The condition that there is an edge between the active node and the passive node is: the job operations represented by the active nodes act on the part of the operating system represented by the passive nodes.
The aforementioned work operation refers to an operation performed by a manual operation acting on the work system.
In one embodiment of the invention, the operating system comprises a roadway operating system, a water supply operating system, a water discharge operating system and a communication operating system.
Not all the operating systems are detailed in this embodiment, and there may be more operating systems according to different situations of mines.
Examples of the representation relationship of passive nodes of the job layer data to portions of the job system are:
the passive node represents a roadway node of the roadway operation system, and specifically, the roadway node can be a winch house, a mining working face, a mining area substation, a mining area middle car park, a mining area upper car park, a mining area ore bin, a mining area mountain climbing track and a transportation main roadway; the connection relation of the roadway nodes can be tidied through a mine roadway layout schematic diagram, and the connection on the diagram represents the connection of the roadway nodes.
A passive node represents a valve of the water supply operation system;
a passive node represents a pump of the drainage system;
a passive node represents a base station of a communication operating system.
The operation layer data generated by the method is dynamic data, and dynamic change can be generated along with the execution of operation; according to this rule, an active node representing a job operation is deleted after the job operation is completed.
In order to predict future dynamic security risks, a prediction needs to be made regarding the risk of future operation, and in one embodiment of the present invention, one future operation is selected as a target of risk prediction.
Collecting operation layer data in a period of time before an execution time point of operation to be evaluated;
the default value of the length of the foregoing time period is 10 minutes, and specifically, a length of 1 minute to 100 minutes may be selected;
there may also be other non-executed job operations within the time period between the execution time point of the job operation to be evaluated and the current time point, so that new job layer data is still updated and generated within this time period.
A first risk assessment module for collecting job layer data within a period of time before an execution time point of a job operation to be assessed, and then inputting a dynamic risk assessment model, the dynamic risk assessment model comprising:
a layer information encoding layer for fusing the associated job layer data of the job operation to be evaluated, excluding the job layer data of the execution time point of the job operation to be evaluated;
the conditions under which the job layer data is associated with the job operation to be evaluated are: the operating system represented by the passive node in the job layer data is the same as the operating system for which the job operation to be evaluated is directed.
The calculation formula of the layer information coding layer is as follows:
a kth layer coding feature representing an ith job node,/->And->Characterization features of the ith and jth job nodes, respectively representing kth job layer data, +.>、/>And->Representing first, second and third weight parameters respectively,a set of job nodes representing edges in the kth job layer data with the ith job node, +.>Representing Sigmoid function->Fusion weights of the ith and jth job nodes representing kth job layer data, +.>Representing vector concatenation->Representing a total number of job nodes in the kth job layer data;
the layer information fusion layer is used for fusing all associated operation layer data of the operation to be evaluated;
the calculation formula of the layer information fusion layer is as follows:
fusion characteristics of the ith job node of the job layer data representing the execution time point of the job operation to be evaluated, +.>A set of job nodes having edges with an ith job node in job layer data representing execution time points of job operations to be evaluated, H representing a set of job layer data fused by a layer information encoding layer,/a>、/>And->Representing the fourth, fifth and sixth weight parameter, respectively,/->Total number of job nodes of job layer data representing execution time point of job operation to be evaluated, +.>Fusion weights of an ith and a jth job node of job layer data representing execution time points of job operations to be evaluated, +.>And->A kth layer coding feature representing an ith and jth job node of layer information coding layer output,/->And->Non-linear transformation characteristics of the ith and jth job nodes of the job layer data representing execution time points of the job operation to be evaluated;
there may be a case where a certain job layer data does not have the ith job node, thenIs zero vector;
the cross-layer information fusion layer is used for fusing all the operation layer data of the execution time point of the operation to be evaluated;
the calculation formula of the cross-layer information fusion layer is as follows:
coding feature of the ith job node representing the ith job layer data, +.>And->Characterization features of the ith and jth job nodes, respectively representing the jth job layer data,/>And->Respectively representing a seventh weight parameter and an eighth weight parameter,>a set of job nodes representing sides with the ith job node in the t-th job layer data, +.>Fusion weights of ith and jth job nodes representing the tth job layer data, +.>An exponential function that is based on a natural constant;
a first output layer for outputting a value representing a risk of a job operation to be evaluated;
the calculation formula of the first output layer is as follows:
fusion characteristics of job nodes representing the job operation to be evaluated in the job layer data representing the execution time point of the job operation to be evaluated, +.>Represents a ninth weight parameter,>representing the first bias parameter, ">Representing cross-layer set vectors, ">Splicing or summing of coding features of all job nodes of the t-th job layer data representing the execution time point of the job operation to be evaluated, V represents a set of all job layer data representing the execution time point of the job operation to be evaluated,/-, and>representing a stitching function->Representing splice->；
In one embodiment of the invention, the first output layer outputs a risk value, the higher the risk value representing the greater the risk of the job operation to be evaluated.
In one embodiment of the invention, the first output layer outputs an evaluation vector comprising two components, representing the risk and risk-free possibility of the job operation to be evaluated, respectively, if the component representing the risk of the job operation to be evaluated is greater than or equal to the other component, then the job operation to be evaluated is risk, otherwise, no risk is represented.
In one embodiment of the present invention, the first output layer outputs a risk type vector including a plurality of components respectively representing risk types of the job operation to be evaluated, the risk types including: the risk is avoided, the capability of operators is insufficient, the operators are tired, the adverse effects on other operating systems are generated, and the basis for diagnosing and modifying the operation to be evaluated can be provided for the manager through the identification of the risk type.
The aforementioned characteristic features of the job node are generated from data of the portion of the job system represented by the job node or data of the mine operator or data of the job operation.
The data of the part of the operating system or the data of the mine operator or the data of the operation are generally represented by the mode of text data, and the characterization features can be generated by a text vectorization method, including models such as a single Hot Model (One Hot Model), a word bag Model (Bag of Words Model), a word frequency-inverse document frequency (TF-IDF), an N-Gram Model (N-Gram) and the like and methods.
Of course, the characterization features can also be generated by a non-semantic coding mode such as single-hot coding.
The dynamic risk assessment model can be trained based on a back-propagation method by constructing samples from historical data.
According to the invention, the dynamic risk assessment model can learn the change of the dynamic information of the operation system related to the operation to be assessed, and fuse the information segments of all operation systems when the operation to be assessed is executed, learn the influence rule of the operation on the dynamic operation system, and predict the risk of the operation.
The risky job operations to be evaluated in the history data correspond to the results of the risk occurrence, so that the sample data are less, and the lack of training samples of the type can lead to the lack of model learning the risky job operations to be evaluated, which affects the accuracy of the evaluation.
In one embodiment of the invention, a method of constructing a training sample is provided, comprising:
constructing an analogue simulation system of the operating system, then performing field operation by a mine operator, and uploading the action on the operating system, which can be generated by the field operation, to the analogue simulation system;
the simulation operation is performed by the simulation system, and the generated result is used as a reference for the output of the dynamic risk assessment model.
Uploading to the simulation system may be a parameter variable generated after the device or node on which the job operates. Such as pump flow, communication bandwidth.
In the range of mine operation, the operation of the tailing pond belongs to a relatively independent operation system separated from a main mining area, the tailing pond of the conventional nonmetallic mine adopts an upstream tailing dam building method, the dynamic change of the beach top is large, the infiltration line is high, the risk of safety accidents is high, and the requirement on safety management is high.
In one embodiment of the invention, a non-coal mine safety dynamic risk assessment system is provided, as shown in fig. 2, and further includes:
a dynamic image acquisition system 106 for acquiring a remote sensing image of the tailing pond, wherein the remote sensing image comprises an initial dam and a dry spreading of the tailing pond;
an image sequence generation module 107, which extracts the remote sensing images of the tailing pond before the current time point to generate an image sequence, wherein the image sequence comprises the remote sensing images of the tailing pond when the tailing pond is built to be not in operation, and further comprises the remote sensing images of the initial stage, the middle stage and the final stage of each layer of the dam, and the remote sensing images are sequenced from early to late according to shooting time;
the initial stage of the dam refers to when the sub-dam of the dam is generated, the middle stage refers to when the beach height of the layer of the dam is increased by half of the maximum beach height of the layer of the dam, and the final stage of the dam refers to when the beach height of the layer of the dam is highest.
The second risk identification module 108 is configured to input the image sequence into a tailings pond risk identification model, where the tailings pond risk identification model includes a spatial pattern discovery layer and a second output layer, and a calculation formula of the spatial pattern discovery layer is as follows:
wherein the method comprises the steps ofAnd->1 st and t remote sensing images representing an image sequence, respectively,/->、/>Representing the t-th, t-1 th image features, respectively,>、/>、/>representing the first, second, third intermediate diagram feature, respectively,/respectively>Representing convolution,/->Representation ofDot product, ->、/>、/>Represents the eleventh, twelfth, thirteenth weight parameter, < ->、/>、/>Representing eleventh, twelfth, thirteenth bias parameters;
the calculation formula of the second output layer is as follows:
indicate->Individual image features->Is the total number of sequence units of the image sequence, +.>Representing a fourteenth weight parameter,>representing a fourteenth bias parameter;
t comprises two components, representing the risk and risk-free possibilities of the tailings pond, respectively, and if the component representing the risk of the tailings pond is greater than or equal to the other component, the tailings pond is at risk, otherwise, the tailings pond is not at risk.
The risk indicated above is that the immersion line height exceeded.
The result of whether the tailing pond with the training sample reference is at risk or not is finished through off-line monitoring, and the comprehensive and accurate monitoring result provides accurate reference.
In the prior art, normal on-line monitoring of a seepage line of a tailing pond is generally carried out by adopting an osmometer or a ground penetrating radar with fixed point positions, and discrete data of local point positions sometimes miss abnormal leakage of partial areas and miss risk points. The foregoing embodiments provide a method for discovering potential risks based on the pile-up dynamics characteristics of a tailings pond expressed by a global image sequence of the tailings pond, which can be used as an aid for general online monitoring.
In one embodiment of the invention, a method for evaluating the safety dynamic risk of a non-coal mine is provided, as shown in fig. 3, and comprises the following steps:
step 201, generating a plurality of operation layer data, wherein the operation layer data comprises operation nodes and edges connected with the operation nodes; the operation nodes comprise passive nodes and active nodes, wherein one passive node has a representation relationship with part of an operation system, and one active node has a representation relationship with a mine operator or an operation;
step 202, collecting job layer data in a period of time before an execution time point of a job operation to be evaluated;
step 203, inputting the collected operation layer data into a dynamic risk assessment model, and outputting a value representing the risk of operation to be assessed;
step 204, judging whether to terminate execution of the operation to be evaluated according to whether the operation to be evaluated has risk;
and if the operation to be evaluated is at risk, terminating execution of the operation to be evaluated, otherwise, not terminating execution of the operation to be evaluated.
At least one embodiment of the present invention provides a storage medium storing non-transitory computer readable instructions that, when executed by a computer, are capable of performing the steps of a non-coal mine safety dynamic risk assessment method as described above.
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (9)
1. A non-coal mine safety dynamic risk assessment system, comprising:
the mine data acquisition module is used for acquiring data of an operation system for managing a mine;
a mine personnel management module for managing data of mine operators;
a mine operation management module for managing data of operation operations of the mine;
a job layer generation module for generating a plurality of job layer data including job nodes and edges connecting the job nodes; the operation nodes comprise passive nodes and active nodes, wherein one passive node has a representation relationship with part of an operation system, and one active node has a representation relationship with a mine operator or an operation;
an edge exists between two passive nodes to indicate that the parts of the operating system represented by the two passive nodes have a connection relationship;
the condition that there is an edge between two active nodes is: one of the two active nodes represents a mine operator to execute the operation represented by the other active node;
the condition that there is an edge between the active node and the passive node is: the operation of the job represented by the active node acts on the part of the operating system represented by the passive node;
a first risk assessment module for collecting job layer data within a period of time before an execution time point of a job operation to be assessed, and then inputting a dynamic risk assessment model, the dynamic risk assessment model comprising: a layer information encoding layer for fusing the associated job layer data of the job operation to be evaluated, excluding the job layer data of the execution time point of the job operation to be evaluated;
the layer information fusion layer is used for fusing all associated operation layer data of the operation to be evaluated;
the cross-layer information fusion layer is used for fusing all the operation layer data of the execution time point of the operation to be evaluated;
a first output layer for outputting a value representing a risk of a job operation to be evaluated;
the calculation formula of the layer information coding layer is as follows:
；
；
a kth layer coding feature representing an ith job node,/->And->Characterization features of the ith and jth job nodes, respectively representing kth job layer data, +.>、/>And->Respectively are provided withRepresenting the first, second and third weight parameters +.>A set of job nodes representing edges in the kth job layer data with the ith job node, +.>The Sigmoid function is represented as a function,fusion weights of the ith and jth job nodes representing kth job layer data, +.>Representing vector concatenation->Representing a total number of job nodes in the kth job layer data;
the calculation formula of the layer information fusion layer is as follows:
；
；
，/>；
fusion characteristics of the ith job node of the job layer data representing the execution time point of the job operation to be evaluated, +.>A set of job nodes having edges with an ith job node in job layer data representing execution time points of job operations to be evaluated, H representing a set of job layer data fused by a layer information encoding layer,/a>、/>And->Representing the fourth, fifth and sixth weight parameter, respectively,/->Total number of job nodes of job layer data representing execution time point of job operation to be evaluated, +.>Fusion weights of an ith and a jth job node of job layer data representing execution time points of job operations to be evaluated, +.>And->A kth layer coding feature representing an ith and jth job node of layer information coding layer output,/->And->Non-linear transformation characteristics of the ith and jth job nodes of the job layer data representing execution time points of the job operation to be evaluated;
the calculation formula of the cross-layer information fusion layer is as follows:
；
；
coding feature of the ith job node representing the ith job layer data, +.>And->Characterization features of the ith and jth job nodes, respectively representing the jth job layer data,/>And->Respectively representing a seventh weight parameter and an eighth weight parameter,>a set of job nodes representing sides with the ith job node in the t-th job layer data, +.>Fusion weights of ith and jth job nodes representing the tth job layer data, +.>An exponential function that is based on a natural constant;
the calculation formula of the first output layer is as follows:
；
；
fusion characteristics of job nodes representing the job operation to be evaluated in the job layer data representing the execution time point of the job operation to be evaluated, +.>Represents a ninth weight parameter,>representing the first bias parameter, ">Representing cross-layer set vectors, ">Splicing or summing of coding features of all job nodes of the t-th job layer data representing the execution time point of the job operation to be evaluated, V represents a set of all job layer data representing the execution time point of the job operation to be evaluated,/-, and>representing the stitching function.
2. The non-coal mine safety dynamic risk assessment system according to claim 1, wherein the operation system comprises a roadway operation system, a water supply operation system, a water drainage operation system and a communication operation system.
3. The non-coal mine safety dynamic risk assessment system according to claim 1, wherein the length of the period of time in the working layer data in a period of time before the execution time point of the working operation to be assessed is collected is 1 minute to 100 minutes.
4. The non-coal mine safety dynamic risk assessment system according to claim 1, wherein the conditions for associating the operation layer data with the operation to be assessed are: the operating system represented by the passive node in the job layer data is the same as the operating system for which the job operation to be evaluated is directed.
5. The non-coal mine safety dynamic risk assessment system according to claim 1, wherein the first output layer outputs a risk value, the higher the risk value is indicative of the greater risk of the work operation to be assessed.
6. A non-coal mine safety dynamic risk assessment system according to claim 1, wherein the first output layer outputs an assessment vector comprising two components representing the likelihood of risk and non-risk of the operation to be assessed, respectively, if the component representing the risk of the operation to be assessed is greater than or equal to the other component, then it represents the risk of the operation to be assessed, otherwise it represents the non-risk.
7. The system of claim 1, wherein the first output layer outputs a risk type vector comprising a plurality of components each representing a risk type of a job operation to be evaluated, the risk type comprising: no risk, insufficient operator capacity, operator fatigue and adverse effect on other operating systems.
8. A non-coal mine safety dynamic risk assessment method, characterized in that the non-coal mine safety dynamic risk assessment system according to any one of claims 1-7 performs the following steps:
step 201, generating a plurality of operation layer data, wherein the operation layer data comprises operation nodes and edges connected with the operation nodes; the operation nodes comprise passive nodes and active nodes, wherein one passive node has a representation relationship with part of an operation system, and one active node has a representation relationship with a mine operator or an operation;
step 202, collecting job layer data in a period of time before an execution time point of a job operation to be evaluated;
step 203, inputting the collected operation layer data into a dynamic risk assessment model, and outputting a value representing the risk of operation to be assessed;
step 204, judging whether to terminate execution of the operation to be evaluated according to whether the operation to be evaluated has risk;
and if the operation to be evaluated is at risk, terminating execution of the operation to be evaluated, otherwise, not terminating execution of the operation to be evaluated.
9. A storage medium storing non-transitory computer readable instructions which, when executed by a computer, are capable of performing the steps of a non-coal mine safety dynamic risk assessment method according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410113061.2A CN117634895B (en) | 2024-01-26 | 2024-01-26 | Non-coal mine safety dynamic risk assessment system and assessment method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410113061.2A CN117634895B (en) | 2024-01-26 | 2024-01-26 | Non-coal mine safety dynamic risk assessment system and assessment method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117634895A CN117634895A (en) | 2024-03-01 |
| CN117634895B true CN117634895B (en) | 2024-04-12 |
Family
ID=90034216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410113061.2A Active CN117634895B (en) | 2024-01-26 | 2024-01-26 | Non-coal mine safety dynamic risk assessment system and assessment method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117634895B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102246499B1 (en) * | 2019-12-13 | 2021-05-04 | 주식회사 이에스피 | System and method for mine safety integrated management |
| CN113988530A (en) * | 2021-09-29 | 2022-01-28 | 应急管理部通信信息中心 | Non-coal mine safety risk assessment grading method and system |
| CN114819677A (en) * | 2022-05-09 | 2022-07-29 | 中国石油大学(华东) | Multi-factor fusion well control risk dynamic quantitative evaluation method and system |
| CN115222242A (en) * | 2022-07-16 | 2022-10-21 | 成都圣瑞锋机械设备有限公司 | High-altitude operation safety online monitoring, analyzing and early warning system based on wireless sensor |
| CN115841170A (en) * | 2022-10-11 | 2023-03-24 | 重庆大学 | Real-time identification and dynamic regulation and control method for coordination state of coal and gas co-mining operation |
| CN116167588A (en) * | 2023-03-02 | 2023-05-26 | 中盈学宇技术有限公司 | Intelligent potential safety hazard analysis platform for coal mine production |
| CN117010683A (en) * | 2023-06-20 | 2023-11-07 | 华中科技大学 | Operation safety risk prediction method based on hybrid neural network and multiple agents |
-
2024
- 2024-01-26 CN CN202410113061.2A patent/CN117634895B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102246499B1 (en) * | 2019-12-13 | 2021-05-04 | 주식회사 이에스피 | System and method for mine safety integrated management |
| CN113988530A (en) * | 2021-09-29 | 2022-01-28 | 应急管理部通信信息中心 | Non-coal mine safety risk assessment grading method and system |
| CN114819677A (en) * | 2022-05-09 | 2022-07-29 | 中国石油大学(华东) | Multi-factor fusion well control risk dynamic quantitative evaluation method and system |
| CN115222242A (en) * | 2022-07-16 | 2022-10-21 | 成都圣瑞锋机械设备有限公司 | High-altitude operation safety online monitoring, analyzing and early warning system based on wireless sensor |
| CN115841170A (en) * | 2022-10-11 | 2023-03-24 | 重庆大学 | Real-time identification and dynamic regulation and control method for coordination state of coal and gas co-mining operation |
| CN116167588A (en) * | 2023-03-02 | 2023-05-26 | 中盈学宇技术有限公司 | Intelligent potential safety hazard analysis platform for coal mine production |
| CN117010683A (en) * | 2023-06-20 | 2023-11-07 | 华中科技大学 | Operation safety risk prediction method based on hybrid neural network and multiple agents |
Non-Patent Citations (3)
| Title |
|---|
| 复杂系统工程作业贝叶斯网络风险方法研究;熊娜;张孝东;李飞;马超;;现代防御技术;20181017(第05期);全文 * |
| 煤矿安全风险防控及预警系统设计;徐晓建;;工矿自动化;20200331(第03期);全文 * |
| 粗糙集和神经网络相融合的钻井安全评价模型;李建;李珂;王兵;;西南石油大学学报(自然科学版);20171031(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117634895A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jaafari et al. | Spatial prediction of slope failures in support of forestry operations safety | |
| Bakhtavar et al. | Green blasting policy: simultaneous forecast of vertical and horizontal distribution of dust emissions using artificial causality-weighted neural network | |
| CN108763763A (en) | A kind of bridge structure strain-responsive abnormity early warning method | |
| Zhang et al. | Risk-based estimate for operational safety in complex projects under uncertainty | |
| CN115063020B (en) | Multi-dimensional safety scheduling device and method for cascade hydropower station based on risk monitoring fusion | |
| CN102222313A (en) | Urban evolution simulation structure cell model processing method based on kernel principal component analysis (KPCA) | |
| CN105678417A (en) | Prediction method and device for tunnel face water inflow of construction tunnel | |
| Wu et al. | A dynamic decision approach for risk analysis in complex projects | |
| Li et al. | Integrated parameter optimization approach: Just-in-time (JIT) operational control strategy for TBM tunnelling | |
| Wu et al. | A novel comprehensive quantitative method for various geological disaster evaluations in underground engineering: multidimensional finite interval cloud model (MFICM) | |
| CN116777608A (en) | Agricultural financial risk supervision system, method and storage medium based on big data | |
| Singh et al. | Artificial Neural Network on Graphical Processing Unit and its emphasis on ground water level prediction | |
| Lu et al. | Using cased based reasoning for automated safety risk management in construction industry | |
| Marjani et al. | The large-scale wildfire spread prediction using a multi-kernel convolutional neural network | |
| CN117634895B (en) | Non-coal mine safety dynamic risk assessment system and assessment method thereof | |
| Bazan-Krzywoszanska et al. | The use of urban indicators in forecasting a real estate value with the use of deep neural network | |
| Ghasemi et al. | Improving the method of roof fall susceptibility assessment based on fuzzy approach | |
| Khadr et al. | Integration of data-driven modeling and stochastic modeling for multi-purpose reservoir simulation | |
| Al-Azzam et al. | Flood prediction and risk assessment using advanced geo-visualization and data mining techniques: a case study in the Red-Lake valley | |
| Yi et al. | A survey on prognostic and health management for special vehicles | |
| Salazar et al. | A methodology for dam safety evaluation and anomaly detection based on boosted regression trees | |
| Wu et al. | Assessing the suitability of imperialist competitive algorithm for the predicting aims: an engineering case | |
| Parsamehr et al. | A BIM-based two-stage fuzzy inference system for safety risk prediction in building construction projects | |
| Temız et al. | SPATIAL MULTI CRITERIA DECISION MAKING IN FOREST FIRE FIGHTING PLANNING. | |
| Wu et al. | A framework for identifying mine water inrush cases based on dynamic monitoring data |
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 |