Explosion risk integrated intelligent decision-making method driven by multi-source and multi-mode data fusion

Abstract

The invention relates to an explosion risk integrated intelligent decision-making method driven by multi-source and multi-modal data fusion, and belongs to the technical field of dust monitoring. The method comprises the following steps: S1, unifying multi-source and multi-modal data to the same spatial-temporal scale by adopting a multi-source and multi-modal data spatial-temporal fusion method; s2, constructing a dust explosion risk classification early warning model based on deep learning based on historical explosion risk data and dust concentration and spark detection data monitored in real time; and S3, according to different explosion risk levels, constructing a multi-source and multi-mode data fusion driving and cloud-edge-end hierarchical collaboration-based dust explosion risk intelligent decision model. The efficiency of aluminum magnesium dust explosion risk early warning and disposal decision making can be improved, and timely early warning and decision making are achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of dust monitoring, and relates to an integrated intelligent decision-making method for explosion risk driven by multi-source and multi-modal data fusion. Background Art

[0002] In the field of industrial production and life, aluminum-magnesium dust explosion is a very important form of explosion disaster. Since dust explosion has great destructive power, it is difficult to control once an explosion occurs, which can easily cause great harm to people's production and life. At present, among industrial accidents, dust explosion accidents occur frequently and account for a large proportion. Aluminum-magnesium dust explosion needs to go through a more complicated process, and in this process there will be many physical factors that affect aluminum-magnesium dust, thus forming a certain explosion mechanism and causing dust explosion accidents.

[0003] At present, the early warning and disposal decision-making of aluminum-magnesium dust explosion risks are not timely. Therefore, in order to better avoid and eliminate the occurrence of dust explosion accidents, an intelligent decision-making method that can predict explosion risks in advance is urgently needed. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide an integrated intelligent decision-making method for explosion risk driven by multi-source and multi-modal data fusion to solve the problem of untimely warning and disposal decision-making of aluminum-magnesium dust explosion risks.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] An integrated intelligent decision-making method for explosion risk driven by multi-source and multi-modal data fusion, specifically comprising the following steps:

[0007] S1: Use the multi-source multi-modal data spatiotemporal fusion method to unify multi-source multi-modal data to the same spatiotemporal scale;

[0008] S2: Based on large-scale historical explosion risk data and real-time monitoring data such as dust concentration and spark detection, a dust explosion risk classification and early warning model based on deep learning is constructed;

[0009] S3: According to different explosion risk levels, a dust explosion risk intelligent decision-making model driven by multi-source and multi-modal data fusion and based on the hierarchical collaboration of "cloud (decision-making platform) - edge (edge ​​control) - end (intelligent perception)" is constructed.

[0010] Furthermore, in step S1, the multi-source multi-modal data spatiotemporal fusion method specifically converts multi-source multi-modal data such as dust concentration monitoring, particle size collection, temperature and humidity sensing, spark detection and video monitoring into the same spatiotemporal representation; then, quality assessment and data cleaning methods are performed on the multi-source multi-modal heterogeneous spatiotemporal data in the same space-time to achieve all-round fusion of data at the data layer, feature layer and decision layer.

[0011] Furthermore, in step S2, constructing a dust explosion risk classification warning model based on deep learning specifically includes: designing risk classification and disposal plans for different types of explosion risks, and building an intelligent decision-making knowledge base; designing an intelligent decision-making algorithm based on a hierarchical decision-making model for multi-objective optimization, so as to realize the selection and execution of optimal explosion suppression measures and emergency plans under different warning levels.

[0012] Furthermore, step S3 specifically includes: designing a hierarchical collaborative intelligent decision-making technology based on "cloud-edge-end" to address the timeliness issue of explosion risk disposal decisions; using technologies such as distributed and parallel computing to improve the speed of the decision-making algorithm, and using technologies such as multi-task learning to improve the robustness and scalability of the intelligent decision-making algorithm.

[0013] The beneficial effects of the present invention are as follows: the present invention adopts multi-source and multi-modal data spatiotemporal fusion technology to unify the data to the same spatiotemporal scale; based on large-scale historical explosion risk data and real-time monitoring of dust concentration, spark detection and other data, a dust explosion risk warning model based on deep learning is constructed to solve the real-time advance warning of explosion risks; on this basis, for different explosion risk levels, a dust explosion risk intelligent decision-making model driven by multi-source and multi-modal data fusion and based on the hierarchical collaboration of "cloud (decision-making platform) - edge (edge ​​control) - end (intelligent perception)" is constructed to solve the problem of real-time disposal decision-making.

[0014] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0016] Figure 1 This is a schematic diagram of the integrated intelligent decision-making method for explosion risk driven by multi-source and multi-modal data fusion of the present invention; DETAILED DESCRIPTION

[0017] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and the features in the embodiments can be combined with each other without conflict.

[0018] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0019] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0020] See also Figure 1 The present invention provides an integrated intelligent decision-making method for explosion risk driven by multi-source and multi-modal data fusion, which specifically includes:

[0021] (1) Spatiotemporal fusion of multi-source and multi-modal data.

[0022] In order to solve the spatiotemporal consistency problem of multi-source and multi-modal data such as dust concentration monitoring, particle size collection, temperature and humidity perception, spark detection, and video surveillance, a spatiotemporal representation and conversion method of multi-source heterogeneous data is designed to convert the multi-source and multi-modal data into the same spatiotemporal representation. Then, a quality assessment and data cleaning method are performed on the multi-source and multi-modal heterogeneous spatiotemporal data in the same space and time to achieve all-round integration of data at the data layer, feature layer, and decision layer.

[0023] (2) Explosion risk classification and grading decision-making scheme. Design risk grading and disposal schemes for different types of explosion risks and build an intelligent decision-making knowledge base; study the graded decision-making model based on multi-objective optimization, design an intelligent decision-making algorithm, and realize the selection and execution of the optimal explosion suppression measures and emergency plans under different warning levels.

[0024] (3) Intelligent decision-making model based on cloud-edge-end hierarchical collaboration.

[0025] In order to solve the timeliness problem of explosion risk disposal decision-making, the research and design are based on the "cloud-edge-end" hierarchical collaborative intelligent decision-making technology. Distributed and parallel computing technologies are used to improve the speed of decision-making algorithms, and multi-task learning and other technologies are used to improve the robustness and scalability of intelligent decision-making algorithms.

[0026] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. An integrated intelligent decision-making method for explosion risk driven by multi-source and multi-modal data fusion, characterized in that: The method specifically comprises the following steps: S1: Use the multi-source multi-modal data spatiotemporal fusion method to unify multi-source multi-modal data to the same spatiotemporal scale; S2: Based on historical explosion risk data and real-time monitoring of dust concentration and spark detection data, a dust explosion risk classification and early warning model based on deep learning is constructed; S3: According to different explosion risk levels, a dust explosion risk intelligent decision-making model driven by multi-source and multi-modal data fusion and based on "cloud-edge-end" hierarchical collaboration is constructed.

2. The explosion risk integrated intelligent decision-making method according to claim 1, characterized in that: In step S1, the multi-source multi-modal data spatiotemporal fusion method specifically converts the multi-source multi-modal data of dust concentration monitoring, particle size collection, temperature and humidity perception, spark detection and video monitoring into the same spatiotemporal representation; then performs quality assessment and data cleaning methods on the multi-source multi-modal heterogeneous spatiotemporal data in the same spatiotemporal, to achieve all-round fusion of data at the data layer, feature layer and decision layer.

3. The explosion risk integrated intelligent decision-making method according to claim 1 is characterized in that: In step S2, building a dust explosion risk classification warning model based on deep learning specifically includes: designing risk classification and disposal plans for different types of explosion risks and building an intelligent decision-making knowledge base; designing an intelligent decision-making algorithm based on a hierarchical decision-making model for multi-objective optimization to achieve the selection and execution of optimal explosion suppression measures and emergency plans under different warning levels.

4. The explosion risk integrated intelligent decision-making method according to claim 1, characterized in that: Step S3 specifically includes: designing a hierarchical collaborative intelligent decision-making technology based on "cloud-edge-end" to address the timeliness issue of explosion risk disposal decisions; using distributed and parallel computing technologies to improve the speed of decision-making algorithms, and using multi-task learning and other technologies to improve the robustness and scalability of intelligent decision-making algorithms.

Images