Fire-fighting facility engineering maintenance method and system based on digital twinning

Abstract

The invention relates to the technical field of fire-fighting engineering operation and maintenance, in particular to a fire-fighting equipment engineering maintenance method and system based on digital twinning. Performing data processing on the collected state data to obtain real-time state data of each fire-fighting device; synchronizing real-time state data of each fire-fighting device to the initial state digital twin model through a data interface to realize model state updating, and obtaining a real-time state digital twin model of the fire-fighting device project; comparing the initial state digital twinborn model with a real-time state digital twinborn model, and judging the performance state of each piece of fire-fighting equipment in the fire-fighting engineering area at a preset time node; and generating equipment maintenance early warning information according to the performance state of each fire-fighting equipment in the fire-fighting engineering area at the preset time node. According to the invention, efficient maintenance of fire-fighting equipment engineering is realized through a digital twinning technology, and the risk of fire-fighting equipment failure can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of fire protection engineering operation and maintenance, and in particular to a fire protection facility engineering maintenance method and system based on digital twins. Background Art

[0002] In recent years, with the acceleration of urbanization and the continuous expansion of building scale, fire safety issues have become increasingly prominent. Traditional fire protection facility engineering maintenance methods mainly rely on manual inspections and regular inspections, which have problems such as low efficiency, poor real-time performance, and difficulty in comprehensive coverage, and cannot meet the increasingly complex fire safety needs of modern buildings. Especially in large buildings and complex industrial environments, fire protection equipment is of various types, large in number, and widely distributed. Manual maintenance methods are not only time-consuming and labor-intensive, but also prone to missed inspections and false inspections, making it difficult to ensure the reliability and effectiveness of fire protection facilities. Once a fire occurs, these problems may cause fire protection facilities to fail to operate normally, resulting in serious casualties and property losses. In order to solve the above problems, there is an urgent need for a more intelligent, efficient, and reliable fire protection facility engineering maintenance method.

[0003] With the rapid development of information technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence, digital twin technology has emerged. By building a digital model of physical entities in virtual space, digital twin technology can achieve real-time mapping and interaction between the physical world and the information world, providing new ideas for the intelligent upgrade of various industries. Applying digital twin technology to the maintenance of fire protection facilities can realize real-time monitoring, fault warning, maintenance management and other functions of fire protection facilities, and improve the reliability and safety of fire protection facilities. Summary of the invention

[0004] The present invention overcomes the shortcomings of the prior art and provides a fire protection facility engineering maintenance method and system based on digital twins.

[0005] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: The first aspect of the present invention discloses a fire protection facility engineering maintenance method based on digital twin, comprising the following steps: S102: constructing an initial state digital twin model of the fire protection facility project based on the building structure drawings of the fire protection project area and the three-dimensional model diagram, layout planning location, attribute information and initial state data of the fire protection equipment; S104: Based on the Internet of Things technology, the status data of the fire-fighting equipment in the fire-fighting engineering area is collected at a preset time node, and the collected status data is processed to obtain the real-time status data of each fire-fighting equipment; S106: Synchronize the real-time status data of each fire-fighting equipment to the initial state digital twin model through the data interface, implement model status update, and obtain the real-time status digital twin model of the fire-fighting facility project; S108: Compare the initial state digital twin model with the real-time state digital twin model to determine the performance status of each firefighting equipment in the firefighting engineering area at a preset time node; wherein the performance status includes normal and abnormal; S110: Generate equipment maintenance warning information according to the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, and send the equipment maintenance warning information to a preset terminal for display.

[0006] Furthermore, the initial state digital twin model of the fire protection facility project is constructed based on the architectural structure drawings of the fire protection engineering area, the three-dimensional model diagram of the fire protection equipment, the layout planning location, attribute information and initial state data, specifically: Obtaining a building structure drawing of a fire protection engineering area, and constructing a building structure model of the fire protection engineering area according to the building structure drawing, wherein the building structure model includes walls, floor slabs, doors and windows; Obtaining a three-dimensional model diagram, layout planning location, attribute information, and initial state data of fire-fighting equipment in the fire-fighting engineering area; wherein the attribute information includes equipment type, specification, and performance; and the initial state data includes temperature, pressure, current, voltage, and response speed; According to the layout planning information of fire-fighting equipment, the three-dimensional models of various fire-fighting equipment are embedded into the corresponding positions of the building structure model to form a complete three-dimensional model of the fire-fighting facility project; Initializing the data interface of the three-dimensional model of the fire protection facility project, and binding the attribute information of each fire protection equipment with the fire protection equipment in the three-dimensional model of the fire protection facility project through the data interface to realize the integration of the attribute information; and associating the initial state data of each fire-fighting equipment with the fire-fighting equipment in the three-dimensional model of the fire-fighting facility engineering through the data interface to achieve integration of the initial state data; After the integration of attribute information and initial state data is achieved, the three-dimensional model of the fire protection facility project is mapped with the actual fire protection facility project to construct an initial state digital twin model of the fire protection facility project.

[0007] Furthermore, the collected status data is processed to obtain the real-time status data of each fire-fighting equipment, specifically: Constructing a three-dimensional space, and dividing a number of equal tetrahedral units in the three-dimensional space based on a triangulation method; acquiring the collected state data, and discretizing the collected state data, and importing each discretized state data into a blank tetrahedral unit respectively; Extracting features from the state data in each tetrahedral unit, obtaining feature vectors of the state data in each tetrahedral unit, and calculating feature similarities between the tetrahedral units based on the feature vectors of each state data; If the feature similarity between two tetrahedral units is greater than a preset threshold, the two tetrahedral units are fused; and so on, the tetrahedral units that meet the fusion conditions in the three-dimensional space are fused iteratively; After the iteration is completed, the fused tetrahedral units are defined as supertetrahedrons; the characteristic vectors of the state data within each supertetrahedron are obtained; The characteristic similarity between the state data in each hypertetrahedron is calculated according to the characteristic vector of the state data in each hypertetrahedron, and the characteristic similarity between the state data in each hypertetrahedron is weighted averaged to obtain the characteristic consistency measure of each hypertetrahedron; Compare the feature consistency measure of each hypertetrahedron with a preset measure value; define the hypertetrahedron whose feature consistency measure is greater than the preset measure value as an inward-looking hypertetrahedron; define the hypertetrahedron whose feature consistency measure is not greater than the preset measure value as an outward-looking hypertetrahedron; Performing an inward optimization process on the hypertetrahedron defined as an outward-extending hypertetrahedron, so as to optimize the hypertetrahedron defined as an outward-extending hypertetrahedron into an inward-extending hypertetrahedron; When all the hypertetrahedrons are cohesive hypertetrahedrons, each cohesive hypertetrahedron is cut out in the three-dimensional space, and the state data within the cut cohesive hypertetrahedron is obtained to obtain the real-time state data of each fire-fighting equipment.

[0008] Furthermore, the hypertetrahedron defined as an outward-extending hypertetrahedron is subjected to an inward-contraction optimization process to optimize the hypertetrahedron defined as an outward-extending hypertetrahedron into an inward-cohesive hypertetrahedron, specifically: S202: Acquire an external extensional hypertetrahedron, perform standardization processing on the state data within the external extensional hypertetrahedron to ensure that each feature has the same scale; calculate the covariance between the state data within the external extensional hypertetrahedron, and construct a covariance matrix of the state data within the external extensional hypertetrahedron according to the covariance between the state data within the external extensional hypertetrahedron; S204: performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors, selecting eigenvectors corresponding to the first k largest eigenvalues, and the selected k eigenvectors constitute the principal components of the new feature space; S206: projecting the state data in the external extensional hypertetrahedron into the new feature space to obtain dimension-reduced data; comparing each dimension-reduced data with the direction of the principal component in the new feature space to obtain the degree of deviation between each dimension-reduced data and the direction of the principal component in the new feature space; S208: marking the reduced-dimensional data whose deviation degree is greater than a preset deviation threshold as impurity data, and deleting the impurity data; S210: performing an inverse transformation on the remaining data in the new feature space, mapping it back to the original feature space, and completing the step of performing an inward optimization processing on the outward extension hypertetrahedron; S212: Obtain the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization; if the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization is still not greater than the preset measure value, repeat steps S204 to S210; until the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization is greater than the preset measure value, define the outward extension hypertetrahedron processed by the inward contraction optimization as a cohesive hypertetrahedron.

[0009] Furthermore, the initial state digital twin model is compared with the real-time state digital twin model to determine the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, specifically: Extracting an initial feature vector of each fire-fighting equipment from the initial state digital twin model, and extracting a real-time feature vector of the fire-fighting equipment from the real-time state digital twin model; Based on the cosine similarity algorithm, the initial feature vector of each fire-fighting equipment in the initial state digital twin model and the real-time feature vector of each fire-fighting equipment in the real-time state digital twin model are calculated to obtain the cosine similarity between the real-time feature vector of each fire-fighting equipment and the initial feature vector; If the cosine similarity between the real-time feature vector of a certain fire-fighting equipment and the initial feature vector is greater than a preset similarity threshold, the performance status of the fire-fighting equipment at the preset time node is marked as normal; If the cosine similarity between the real-time feature vector and the initial feature vector of a certain fire-fighting equipment is not greater than a preset similarity threshold, the performance status of the fire-fighting equipment at the preset time node is marked as abnormal.

[0010] Furthermore, equipment maintenance warning information is generated according to the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, and the equipment maintenance warning information is sent to a preset terminal for display, specifically: Obtain the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node; If there is fire-fighting equipment with an abnormal performance status in the fire-fighting engineering area at a preset time node, the location information of the fire-fighting equipment with an abnormal performance status is obtained in the real-time status digital twin model; and obtaining real-time status data of fire-fighting equipment with abnormal performance status in the real-time status digital twin model; Equipment maintenance warning information is generated based on the location information and real-time status data of the fire-fighting equipment with abnormal performance status, and the equipment maintenance warning information is sent to a preset terminal for display.

[0011] The second aspect of the present invention discloses a fire protection facility engineering maintenance system based on digital twins, the fire protection facility engineering maintenance system includes a memory and a processor, the memory stores a fire protection facility engineering maintenance method program, when the fire protection facility engineering maintenance method program is executed by the processor, any one of the fire protection facility engineering maintenance method steps is implemented.

[0012] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects: the collected status data is processed to obtain the real-time status data of each fire-fighting equipment; the real-time status data of each fire-fighting equipment is synchronized to the initial state digital twin model through the data interface to realize the model status update and obtain the real-time status digital twin model of the fire-fighting facility project; the initial state digital twin model is compared with the real-time state digital twin model to judge the performance status of each fire-fighting equipment in the fire-fighting project area at a preset time node; wherein the performance status includes normal and abnormal; according to the performance status of each fire-fighting equipment in the fire-fighting project area at a preset time node, equipment maintenance warning information is generated, and the equipment maintenance warning information is sent to a preset terminal for display. This method realizes efficient maintenance of fire-fighting facility projects through digital twin technology, and can effectively reduce the risk of fire-fighting equipment failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0014] Figure 1 This is the overall method flow chart of the fire protection facility engineering maintenance method; Figure 2 This is a partial method flow chart of the fire protection facility engineering maintenance method; Figure 3 This is the system framework diagram of the fire protection facility engineering maintenance system. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0017] like Figure 1 As shown, the first aspect of the present invention discloses a fire protection facility engineering maintenance method based on digital twin, comprising the following steps: S102: constructing an initial state digital twin model of the fire protection facility project based on the building structure drawings of the fire protection project area and the three-dimensional model diagram, layout planning location, attribute information and initial state data of the fire protection equipment; S104: Based on the Internet of Things technology, the status data of the fire-fighting equipment in the fire-fighting engineering area is collected at a preset time node, and the collected status data is processed to obtain the real-time status data of each fire-fighting equipment; wherein the real-time status data includes temperature, pressure, current, voltage and response speed; For example, the voltage data value of the fire-fighting equipment at a preset time node is collected through the voltage sensor inside the fire-fighting equipment, and then the collected voltage data value is sent to the cloud platform through the Internet of Things; S106: Synchronize the real-time status data of each fire-fighting equipment to the initial state digital twin model through the data interface, implement model status update, and obtain the real-time status digital twin model of the fire-fighting facility project; S108: Compare the initial state digital twin model with the real-time state digital twin model to determine the performance status of each firefighting equipment in the firefighting engineering area at a preset time node; wherein the performance status includes normal and abnormal; S110: Generate equipment maintenance warning information according to the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, and send the equipment maintenance warning information to a preset terminal for display.

[0018] This method achieves efficient maintenance of fire protection facility projects through digital twin technology. By processing the collected status data of fire protection equipment, high-quality real-time status data of fire protection equipment is obtained, so that the digital twin model updated by the real-time status data of each fire protection equipment can more truly and accurately reflect the real-time status and characteristics of the fire protection equipment, so that the performance status of the fire protection equipment can be monitored and accurately evaluated in real time, and by timely generating and displaying equipment maintenance warning information, maintenance personnel can quickly respond to potential problems, reduce the risk of failures, and improve maintenance efficiency.

[0019] Furthermore, the initial state digital twin model of the fire protection facility project is constructed based on the architectural structure drawings of the fire protection engineering area, the three-dimensional model diagram of the fire protection equipment, the layout planning location, attribute information and initial state data, specifically: Obtaining a building structure drawing of a fire protection engineering area, and constructing a building structure model of the fire protection engineering area according to the building structure drawing, wherein the building structure model includes walls, floor slabs, doors and windows; Obtaining a three-dimensional model diagram, layout planning location, attribute information, and initial state data of fire-fighting equipment in the fire-fighting engineering area; wherein the attribute information includes equipment type, specification, and performance; and the initial state data includes temperature, pressure, current, voltage, and response speed; According to the layout planning information of fire-fighting equipment, the three-dimensional models of various fire-fighting equipment are embedded into the corresponding positions of the building structure model to form a complete three-dimensional model of the fire-fighting facility project; Initializing the data interface of the three-dimensional model of the fire protection facility project, and binding the attribute information of each fire protection equipment with the fire protection equipment in the three-dimensional model of the fire protection facility project through the data interface to realize the integration of the attribute information; and associating the initial state data of each fire-fighting equipment with the fire-fighting equipment in the three-dimensional model of the fire-fighting facility engineering through the data interface to achieve integration of the initial state data; After the integration of attribute information and initial state data is achieved, the three-dimensional model of the fire protection facility project is mapped with the actual fire protection facility project to construct an initial state digital twin model of the fire protection facility project.

[0020] This step is based on digital twin technology and integrates various information of the fire engineering area to build an accurate initial state digital twin model. First, the building structure model including walls, floors, doors and windows is constructed using the building structure drawings, which provides a basic spatial framework for the entire fire protection facility project. Next, the three-dimensional model diagram, layout planning location, attribute information and initial state data of the fire protection equipment are obtained, where the attribute information covers the key features of the equipment, and the initial state data reflects the specific state of the equipment at the beginning, such as key parameters such as temperature and pressure. Then, the three-dimensional model of the fire protection equipment is embedded in the building structure model according to the layout plan to form a complete three-dimensional model, which enables the fire protection equipment and the building structure to be accurately integrated in the virtual space. By initializing the data interface, binding the attribute information with the fire protection equipment and associating the initial state data with the equipment, the effective integration of information is achieved, ensuring that all features and states of the equipment in the model can be accurately presented. Finally, the constructed three-dimensional model of the fire protection facility project is mapped with the actual fire protection facility project, so as to construct a highly realistic and information-rich initial state digital twin model. Through this step, a comprehensive digital reproduction of the fire protection engineering area is achieved, making the model highly authentic and referenceable.

[0021] Furthermore, the collected status data is processed to obtain the real-time status data of each fire-fighting equipment, specifically: Constructing a three-dimensional space, and dividing a number of equal tetrahedral units in the three-dimensional space based on a triangulation method; acquiring the collected state data, and discretizing the collected state data, and importing each discretized state data into a blank tetrahedral unit respectively; Extracting features from the state data in each tetrahedral unit, obtaining feature vectors of the state data in each tetrahedral unit, and calculating feature similarities between the tetrahedral units based on the feature vectors of each state data; If the feature similarity between two tetrahedral units is greater than a preset threshold, the two tetrahedral units are fused; and so on, the tetrahedral units that meet the fusion conditions in the three-dimensional space are fused iteratively; After the iteration is completed, the fused tetrahedral units are defined as supertetrahedrons; the characteristic vectors of the state data within each supertetrahedron are obtained; The characteristic similarity between the state data in each hypertetrahedron is calculated according to the characteristic vector of the state data in each hypertetrahedron, and the characteristic similarity between the state data in each hypertetrahedron is weighted averaged to obtain the characteristic consistency measure of each hypertetrahedron; Compare the feature consistency measure of each hypertetrahedron with a preset measure value; define the hypertetrahedron whose feature consistency measure is greater than the preset measure value as an inward-looking hypertetrahedron; define the hypertetrahedron whose feature consistency measure is not greater than the preset measure value as an outward-looking hypertetrahedron; Performing an inward optimization process on the hypertetrahedron defined as an outward-extending hypertetrahedron, so as to optimize the hypertetrahedron defined as an outward-extending hypertetrahedron into an inward-extending hypertetrahedron; When all the hypertetrahedrons are cohesive hypertetrahedrons, each cohesive hypertetrahedron is cut out in the three-dimensional space, and the state data within the cut cohesive hypertetrahedron is obtained to obtain the real-time state data of each fire-fighting equipment.

[0022] This step accurately obtains the real-time status data of fire-fighting equipment by constructing a three-dimensional space and performing segmentation and data processing. First, the triangulation method is used to construct equal tetrahedral units, which provides a basic framework for data segmentation and analysis. The collected status data is discretized and imported into tetrahedral units to achieve the preliminary distribution of the data. Then, feature vectors are obtained through feature extraction, and the feature similarity is calculated to determine the similarity between tetrahedral units, and then fusion processing is performed, and continuous iterative optimization is performed to form a hypertetrahedron. By calculating the feature consistency measure of the hypertetrahedron and comparing it with the preset measure value, the cohesive and extensible hypertetrahedrons are distinguished, and the hypertetrahedrons defined as extensible are optimized inward to ensure that the final ones are all cohesive hypertetrahedrons. Finally, the status data is obtained from the cohesive hypertetrahedron to obtain accurate real-time status data.

[0023] This step can more accurately denoise and classify the collected status data of fire-fighting equipment, thereby obtaining high-quality real-time status data of fire-fighting equipment. The digital twin model subsequently updated with the real-time status data of each fire-fighting equipment can more realistically and accurately reflect the real-time status and characteristics of the fire-fighting equipment, including subtle differences and similarities between equipment, thereby improving the accuracy and reliability of the model, and can effectively integrate and analyze complex status data, enhance the model's data processing and presentation capabilities, thereby accurately analyzing anomalies and changing trends in status data, and providing more targeted and timely data support for the maintenance and management of fire-fighting facilities, thereby better ensuring the safety and effectiveness of fire-fighting facility projects.

[0024] Furthermore, the hypertetrahedron defined as an outward-extending hypertetrahedron is subjected to an inward-contracting optimization process to optimize the hypertetrahedron defined as an outward-extending hypertetrahedron into an inward-cohesive hypertetrahedron, such as Figure 2 As shown, specifically: S202: Acquire an external extensional hypertetrahedron, perform standardization processing on the state data within the external extensional hypertetrahedron to ensure that each feature has the same scale; calculate the covariance between the state data within the external extensional hypertetrahedron, and construct a covariance matrix of the state data within the external extensional hypertetrahedron according to the covariance between the state data within the external extensional hypertetrahedron; S204: performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors, selecting eigenvectors corresponding to the first k largest eigenvalues, and the selected k eigenvectors constitute the principal components of the new feature space; S206: projecting the state data in the external extensional hypertetrahedron into the new feature space to obtain dimension-reduced data; comparing each dimension-reduced data with the direction of the principal component in the new feature space to obtain the degree of deviation between each dimension-reduced data and the direction of the principal component in the new feature space; S208: marking the reduced-dimensional data whose deviation degree is greater than a preset deviation threshold as impurity data, and deleting the impurity data; S210: performing an inverse transformation on the remaining data in the new feature space, mapping it back to the original feature space, and completing the step of performing an inward optimization processing on the outward extension hypertetrahedron; S212: Obtain the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization; if the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization is still not greater than the preset measure value, repeat steps S204 to S210; until the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization is greater than the preset measure value, define the outward extension hypertetrahedron processed by the inward contraction optimization as a cohesive hypertetrahedron.

[0025] Specifically, first, the state data within the extensional hypertetrahedron is standardized to ensure that the scale of each feature (such as temperature, pressure, etc.) is consistent, so as to facilitate subsequent eigenvalue decomposition and comparison. Then, the covariance between these state data is calculated, and the covariance matrix is ​​constructed. The covariance matrix can reflect the correlation between different features. The covariance matrix is ​​subjected to eigenvalue decomposition to obtain eigenvalues ​​and eigenvectors. The eigenvectors corresponding to the first k largest eigenvalues ​​are selected. These vectors constitute the principal components of the new feature space, which can represent the main change directions in the original data. The state data within the extensional hypertetrahedron is projected into the new feature space for dimensionality reduction. By comparing the data after dimensionality reduction with the direction of the principal components in the new feature space, the degree of deviation of the data can be determined. The dimensionality reduction data with a deviation greater than the preset threshold is marked as impurity data and deleted. This step is intended to remove outliers or noise, thereby improving the purity of the data and the quality of analysis. The remaining data is inversely transformed and mapped back to the original feature space to complete the shrinkage optimization process. Finally, the feature consistency metric of the outward extension hypertetrahedron after optimization is evaluated. If the preset metric value is still not met, the iteration is repeated until the preset standard is met. Through the above-mentioned inward optimization processing steps, the accuracy and consistency of the fire equipment status data can be effectively improved, and the noise and outliers in the data can be reduced, so that the real-time status digital twin model can more accurately reflect the actual operating status of the fire equipment, and can effectively improve the reliability and accuracy of the real-time status digital twin model obtained by subsequent updates.

[0026] Furthermore, the initial state digital twin model is compared with the real-time state digital twin model to determine the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, specifically: Extracting an initial feature vector of each fire-fighting equipment from the initial state digital twin model, and extracting a real-time feature vector of the fire-fighting equipment from the real-time state digital twin model; Based on the cosine similarity algorithm, the initial feature vector of each fire-fighting equipment in the initial state digital twin model and the real-time feature vector of each fire-fighting equipment in the real-time state digital twin model are calculated to obtain the cosine similarity between the real-time feature vector of each fire-fighting equipment and the initial feature vector; If the cosine similarity between the real-time feature vector of a certain fire-fighting equipment and the initial feature vector is greater than a preset similarity threshold, the performance status of the fire-fighting equipment at the preset time node is marked as normal; If the cosine similarity between the real-time feature vector and the initial feature vector of a certain fire-fighting equipment is not greater than a preset similarity threshold, the performance status of the fire-fighting equipment at the preset time node is marked as abnormal.

[0027] Specifically, first, the initial feature vectors of each fire-fighting equipment are extracted from the initial state digital twin model. These feature vectors represent the key features of the equipment in the initial state. At the same time, the real-time feature vectors of the fire-fighting equipment are extracted from the real-time state digital twin model. These vectors reflect the state characteristics of the equipment at the current moment. Then, the cosine similarity algorithm is used to calculate the similarity between the initial feature vector and the real-time feature vector. Cosine similarity is an indicator that measures the degree of similarity between two vectors in direction. Its value range is between -1 and 1. The closer the value is to 1, the more similar the two vectors are, and the closer the value is to -1, the less similar the two vectors are. If the cosine similarity between the real-time feature vector and the initial feature vector of a certain fire-fighting equipment is greater than the preset similarity threshold, it means that the real-time state of the equipment is very close to the initial state, so the performance state of the equipment is marked as normal. On the contrary, if the cosine similarity between the real-time feature vector and the initial feature vector is not greater than the preset similarity threshold, it indicates that there is a significant difference between the real-time state of the equipment and the initial state, and a fault or performance degradation may have occurred, so the performance state of the equipment is marked as abnormal. This step quickly analyzes whether the performance status of each fire-fighting equipment is normal by quantifying the initial state digital twin model and the real-time state digital twin model.

[0028] Furthermore, equipment maintenance warning information is generated according to the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, and the equipment maintenance warning information is sent to a preset terminal for display, specifically: Obtain the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node; If there is fire-fighting equipment with an abnormal performance status in the fire-fighting engineering area at a preset time node, the location information of the fire-fighting equipment with an abnormal performance status is obtained in the real-time status digital twin model; and obtaining real-time status data of fire-fighting equipment with abnormal performance status in the real-time status digital twin model; Equipment maintenance warning information is generated based on the location information and real-time status data of the fire-fighting equipment with abnormal performance status, and the equipment maintenance warning information is sent to a preset terminal for display.

[0029] Specifically, if it is found that the performance status of fire-fighting equipment is abnormal at the preset time node, the system will further obtain the detailed location information of these abnormal equipment in the real-time status digital twin model to indicate the specific equipment locations that need to be inspected and repaired for maintenance personnel, thereby improving maintenance efficiency. At the same time, the system will also obtain the real-time status data of these abnormal equipment in the real-time status digital twin model to provide maintenance personnel with detailed information on the current status of the equipment, so that maintenance personnel can remotely conduct a preliminary analysis of the performance status of fire-fighting equipment. And the generated equipment maintenance warning information will be sent to the preset terminals for display, including the large screen of the monitoring center, the mobile devices of maintenance personnel, or any other devices that are easy to view and respond to.

[0030] In this embodiment, the fire protection facility engineering maintenance method further includes the following steps: Obtaining state characteristic data corresponding to various abnormal state types of fire-fighting equipment through a big data network, defining observation states according to various abnormal state types, defining conditional nodes according to the state characteristic data corresponding to various abnormal state types, connecting the observation states and conditional nodes in a directed ring, and obtaining a topological graph structure of a conditional random field; According to the topological graph structure, the transition frequency between each observation state is counted, the state transition probability between each observation state is calculated according to the transition frequency, and the state transition matrix is ​​constructed according to the state transition probability between each observation state; At the same time, the topological graph structure is subjected to correlation analysis based on the grey correlation analysis method to obtain the correlation between each conditional node and the observed state, and the probability of the fire-fighting equipment observing a certain state feature under the preset conditions is calculated according to the correlation between each conditional node and the observed state, and the emission probability matrix is ​​constructed according to the probability of the fire-fighting equipment observing a certain state feature under the preset conditions; Introduce the Viterbi algorithm, initialize the dynamic programming table, set the initial state probability distribution, and calculate the optimal path probability of each observed state at the initial moment based on the state transfer matrix; For each time step, the optimal path probability of each observed state at the current moment is calculated according to the state transfer matrix and the emission probability matrix, and the predecessor state of the optimal path is recorded; Then, through iterative calculation, the dynamic programming table is gradually updated until all time steps are traversed; the dynamic programming table is backtracked to obtain the global optimal abnormal state sequence; A prediction model is constructed based on a graph neural network, and the globally optimal abnormal state sequence is embedded into the prediction model to obtain an abnormal state type prediction model for fire-fighting equipment; Acquire real-time status data of fire-fighting equipment with abnormal performance status, import the real-time status data of fire-fighting equipment with abnormal performance status into the abnormal status type prediction model for prediction, and acquire the abnormal status type of the fire-fighting equipment with abnormal performance status; Generate prediction information based on the abnormal state type of the fire-fighting equipment whose performance state is abnormal, and send the prediction information to a preset terminal for display.

[0031] It should be noted that the state transition probability and emission probability are calculated by statistical transfer frequency and grey correlation analysis, and the state transfer matrix and emission probability matrix are constructed. The Viterbi algorithm is introduced to initialize the dynamic programming table, and the optimal path probability is calculated based on the state transfer matrix and emission probability matrix. Through iterative calculation and backtracking, the global optimal abnormal state sequence is obtained, and a prediction model is constructed based on the graph neural network. Finally, the real-time state data is imported into the prediction model for prediction, and the prediction information is generated and displayed on the preset terminal. This method realizes the self-diagnosis of the abnormal state of fire-fighting equipment, reduces the work difficulty of maintenance staff, improves the work efficiency of maintenance staff, and provides intelligent decision-making support for the maintenance of fire-fighting facilities, thereby improving the success rate of maintenance.

[0032] In this embodiment, the fire protection facility engineering maintenance method further includes the following steps: Obtaining the failure hidden danger probability value of the fire-fighting equipment under various working characteristic conditions through the big data network; wherein the working characteristic conditions include the total service time and the working environment factor; Introduce graph neural network, and use various working characteristic conditions as the first graph node, and use the failure hidden danger probability value under various working characteristic conditions as the second graph node; Obtaining a connection weight between the first graph node and the second graph node based on a back propagation algorithm, and mapping the first graph node and the second graph node to rows and columns of an adjacency matrix, respectively; Filling the adjacency matrix according to the connection weights, assigning a non-zero weight value to the corresponding position of the adjacency matrix if there is a connection between the nodes, otherwise assigning a value of zero; and finally generating an adjacency matrix reflecting the correlation between the working characteristic conditions and the failure hidden danger probability value; Constructing a knowledge graph, and importing the adjacency matrix into the knowledge graph for storage to obtain a feature knowledge graph; and regularly updating the feature knowledge graph; At a preset time point, the real-time working characteristic conditions of the fire-fighting equipment are obtained based on the Internet of Things, and the real-time working characteristic conditions are imported into the characteristic knowledge graph for matching, so as to obtain the failure hidden danger probability value of the fire-fighting equipment at the preset time node; If the failure hidden danger probability value of the fire-fighting equipment at the preset time node is greater than the preset probability value, a state failure warning information is generated, and the state failure warning information is sent to a preset terminal for display.

[0033] It should be noted that, since the feature knowledge graph contains the adjacency matrix of the association relationship between the working feature conditions and the failure hidden danger probability value, and the adjacency matrix is ​​formed by mapping the first graph node (working feature condition) and the second graph node (failure hidden danger probability value) to the rows and columns of the matrix respectively, and obtaining the connection weights between them based on the back propagation algorithm, and filling them according to the connection weights, the corresponding rows or columns of the real-time working feature conditions can be found in the graph. Then, using the connection weight information stored in the graph, combined with the calculation method of the graph neural network, through the mapping relationship from the stored working feature conditions to the failure hidden danger probability value, the real-time working feature conditions are propagated and calculated, and the connection weights and association relationships stored in the graph are used as prior knowledge. After the information aggregation and update operation of the graph neural network, the information of the real-time working feature conditions is processed according to the existing association relationship and weight, and finally the failure hidden danger probability value of the fire-fighting equipment at the preset time node is obtained.

[0034] This method establishes the association between working characteristic conditions and failure hidden danger probability values ​​through big data networks and graph neural networks, stores these relationships in knowledge graphs and updates them regularly to ensure the accuracy and timeliness of information; uses the Internet of Things to obtain real-time data, and conducts real-time status assessment of fire-fighting equipment based on the information stored in the characteristic knowledge graph. When it is found that the probability of equipment failure hidden danger exceeds the threshold, an early warning information will be generated and sent to the preset terminal. This process realizes the monitoring and early warning functions of fire-fighting equipment, and can notify relevant personnel in time so that they can take corresponding measures to avoid possible dangers, thereby realizing the monitoring and early warning of fire-fighting equipment failure hidden dangers.

[0035] The second aspect of the present invention discloses a fire protection facility engineering maintenance system 6 based on digital twins, such as Figure 3 As shown, the fire protection facility engineering maintenance system includes a memory 41 and a processor 52. The memory 41 stores a fire protection facility engineering maintenance method program. When the fire protection facility engineering maintenance method program is executed by the processor 52, any one of the fire protection facility engineering maintenance method steps is implemented.

[0036] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0037] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0038] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0039] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0040] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0041] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A fire protection facility engineering maintenance method based on digital twins, characterized in that: The following steps are involved: S102: constructing an initial state digital twin model of the fire protection facility project based on the building structure drawings of the fire protection project area and the three-dimensional model diagram, layout planning location, attribute information and initial state data of the fire protection equipment; S104: Based on the Internet of Things technology, the status data of the fire-fighting equipment in the fire-fighting engineering area is collected at a preset time node, and the collected status data is processed to obtain the real-time status data of each fire-fighting equipment; S106: Synchronize the real-time status data of each fire-fighting equipment to the initial state digital twin model through the data interface, implement model status update, and obtain the real-time status digital twin model of the fire-fighting facility project; S108: Compare the initial state digital twin model with the real-time state digital twin model to determine the performance status of each firefighting equipment in the firefighting engineering area at a preset time node; wherein the performance status includes normal and abnormal; S110: Generate equipment maintenance warning information according to the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, and send the equipment maintenance warning information to a preset terminal for display.

2. According to a fire protection facility engineering maintenance method based on digital twins according to claim 1, it is characterized in that: The initial state digital twin model of the fire protection facility project is constructed based on the architectural structure drawings of the fire protection engineering area, the three-dimensional model diagram of the fire protection equipment, the layout planning location, attribute information and initial state data, specifically: Obtaining a building structure drawing of a fire protection engineering area, and constructing a building structure model of the fire protection engineering area according to the building structure drawing, wherein the building structure model includes walls, floor slabs, doors and windows; Obtaining a three-dimensional model diagram, layout planning location, attribute information, and initial state data of fire-fighting equipment in the fire-fighting engineering area; wherein the attribute information includes equipment type, specification, and performance; and the initial state data includes temperature, pressure, current, voltage, and response speed; According to the layout planning information of fire-fighting equipment, the three-dimensional models of various fire-fighting equipment are embedded into the corresponding positions of the building structure model to form a complete three-dimensional model of the fire-fighting facility project; Initializing the data interface of the three-dimensional model of the fire protection facility project, and binding the attribute information of each fire protection equipment with the fire protection equipment in the three-dimensional model of the fire protection facility project through the data interface to realize the integration of the attribute information; and associating the initial state data of each fire-fighting equipment with the fire-fighting equipment in the three-dimensional model of the fire-fighting facility engineering through the data interface to achieve integration of the initial state data; After the integration of attribute information and initial state data is achieved, the three-dimensional model of the fire protection facility project is mapped with the actual fire protection facility project to construct an initial state digital twin model of the fire protection facility project.

3. According to a fire protection facility engineering maintenance method based on digital twins according to claim 1, it is characterized in that: The collected status data is processed to obtain the real-time status data of each fire-fighting equipment, specifically: Constructing a three-dimensional space, and dividing a number of equal tetrahedral units in the three-dimensional space based on a triangulation method; acquiring the collected state data, and discretizing the collected state data, and importing each discretized state data into a blank tetrahedral unit respectively; Extracting features from the state data in each tetrahedral unit, obtaining feature vectors of the state data in each tetrahedral unit, and calculating feature similarities between the tetrahedral units based on the feature vectors of each state data; If the feature similarity between two tetrahedral units is greater than a preset threshold, the two tetrahedral units are fused; By analogy, the tetrahedral units that meet the fusion conditions in the three-dimensional space are subjected to fusion iterative processing; After the iteration is completed, the fused tetrahedral units are defined as supertetrahedrons; Obtaining characteristic vectors of state data within each hypertetrahedron; The characteristic similarity between the state data in each hypertetrahedron is calculated according to the characteristic vector of the state data in each hypertetrahedron, and the characteristic similarity between the state data in each hypertetrahedron is weighted averaged to obtain the characteristic consistency measure of each hypertetrahedron; Comparing the characteristic consistency metric of each hypertetrahedron with a preset metric value; A hypertetrahedron whose feature consistency measure is greater than a preset measure value is defined as a cohesive hypertetrahedron; A hypertetrahedron whose feature consistency measure is not greater than a preset measure value is defined as an external hypertetrahedron; Performing an inward optimization process on the hypertetrahedron defined as an outward-extending hypertetrahedron, so as to optimize the hypertetrahedron defined as an outward-extending hypertetrahedron into an inward-extending hypertetrahedron; When all the hypertetrahedrons are cohesive hypertetrahedrons, each cohesive hypertetrahedron is cut out in the three-dimensional space, and the state data within the cut cohesive hypertetrahedron is obtained to obtain the real-time state data of each fire-fighting equipment.

4. According to a fire protection facility engineering maintenance method based on digital twins according to claim 3, it is characterized in that: The hypertetrahedron defined as an outward-extending hypertetrahedron is subjected to inward-contraction optimization processing to optimize the hypertetrahedron defined as an outward-extending hypertetrahedron into an inward-cohesive hypertetrahedron, specifically: S202: Acquire an external extensional hypertetrahedron, perform standardization processing on the state data within the external extensional hypertetrahedron to ensure that each feature has the same scale; calculate the covariance between the state data within the external extensional hypertetrahedron, and construct a covariance matrix of the state data within the external extensional hypertetrahedron according to the covariance between the state data within the external extensional hypertetrahedron; S204: performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors, selecting eigenvectors corresponding to the first k largest eigenvalues, and the selected k eigenvectors constitute the principal components of the new feature space; S206: projecting the state data in the external extensional hypertetrahedron into the new feature space to obtain dimension-reduced data; comparing each dimension-reduced data with the direction of the principal component in the new feature space to obtain the degree of deviation between each dimension-reduced data and the direction of the principal component in the new feature space; S208: marking the reduced-dimensional data whose deviation degree is greater than a preset deviation threshold as impurity data, and deleting the impurity data; S210: performing an inverse transformation on the remaining data in the new feature space, mapping it back to the original feature space, and completing the step of performing an inward optimization processing on the outward extension hypertetrahedron; S212: Obtain the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization; if the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization is still not greater than the preset measure value, repeat steps S204 to S210; until the feature consistency measure of the outward extension hypertetrahedron processed by the inward contraction optimization is greater than the preset measure value, define the outward extension hypertetrahedron processed by the inward contraction optimization as a cohesive hypertetrahedron.

5. According to a fire protection facility engineering maintenance method based on digital twins according to claim 1, it is characterized in that: The initial state digital twin model is compared with the real-time state digital twin model to determine the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, specifically: Extracting an initial feature vector of each fire-fighting equipment from the initial state digital twin model, and extracting a real-time feature vector of the fire-fighting equipment from the real-time state digital twin model; Based on the cosine similarity algorithm, the initial feature vector of each fire-fighting equipment in the initial state digital twin model and the real-time feature vector of each fire-fighting equipment in the real-time state digital twin model are calculated to obtain the cosine similarity between the real-time feature vector of each fire-fighting equipment and the initial feature vector; If the cosine similarity between the real-time feature vector of a certain fire-fighting equipment and the initial feature vector is greater than a preset similarity threshold, the performance status of the fire-fighting equipment at the preset time node is marked as normal; If the cosine similarity between the real-time feature vector and the initial feature vector of a certain fire-fighting equipment is not greater than a preset similarity threshold, the performance status of the fire-fighting equipment at the preset time node is marked as abnormal.

6. A fire protection facility engineering maintenance method based on digital twin according to claim 5, characterized in that: Generate equipment maintenance warning information according to the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node, and send the equipment maintenance warning information to a preset terminal for display, specifically: Obtain the performance status of each fire-fighting equipment in the fire-fighting engineering area at a preset time node; If there is fire-fighting equipment with an abnormal performance status in the fire-fighting engineering area at a preset time node, the location information of the fire-fighting equipment with an abnormal performance status is obtained in the real-time status digital twin model; and obtaining real-time status data of fire-fighting equipment with abnormal performance status in the real-time status digital twin model; Equipment maintenance warning information is generated based on the location information and real-time status data of the fire-fighting equipment with abnormal performance status, and the equipment maintenance warning information is sent to a preset terminal for display.

7. A fire protection facility engineering maintenance system based on digital twins, characterized in that: The fire protection facility engineering maintenance system includes a memory and a processor, wherein a fire protection facility engineering maintenance method program is stored in the memory, and when the fire protection facility engineering maintenance method program is executed by the processor, the fire protection facility engineering maintenance method steps as described in any one of claims 1 to 6 are implemented.

Images