Water conservancy project information management method and system based on BIM

Abstract

The invention discloses a BIM-based water conservancy project information management method and system, belongs to the technical field of water conservancy project information management, and aims to obtain a BIM model with GIS information by combining a BIM technology and a GIS technology, so that more comprehensive water conservancy project information can be obtained. And then identifying the preprocessed water conservancy project information in combination with a pre-deployed deep learning algorithm to obtain a water conservancy project operation safety monitoring result, and performing safety early warning on the water conservancy project according to the water conservancy project operation safety monitoring result, so that the management efficiency of the water conservancy project information can be effectively improved; and the operation safety degree of the water conservancy project is further improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of water conservancy project information management, and in particular relates to a water conservancy project information management method and system based on BIM. Background Art

[0002] With the rapid development of water conservancy project construction in my country, the scale of projects continues to expand and the complexity of projects is increasing. Traditional water conservancy project information management methods have problems such as information islands, poor coordination, and waste of resources. Building Information Modeling (BIM), as an emerging information technology, has been widely used in the construction industry. Applying BIM technology to the field of water conservancy projects will help improve the level of project management. In the existing technology, BIM technology is often only used for simple information viewing and storage, and BIM information cannot be efficiently managed and applied. Although the degree of informatization has been improved, BIM information cannot be effectively used for the safety management of water conservancy projects. Summary of the invention

[0003] The present invention provides a water conservancy project information management method and system based on BIM, so as to solve the problems in the prior art.

[0004] On the one hand, the present invention provides a water conservancy project information management method based on BIM, comprising: Collecting the three-dimensional data of the water conservancy project, and constructing a BIM model of the water conservancy project according to the three-dimensional data of the water conservancy project, and integrating the BIM model into the GIS system to obtain a BIM model with GIS information; Based on the BIM model with GIS information, water conservancy project information corresponding to the water conservancy project is collected, and the water conservancy project information is preprocessed to obtain the preprocessed water conservancy project information; Use the pre-deployed deep learning algorithm to identify the pre-processed water conservancy project information and obtain the water conservancy project operation safety monitoring results; When the water conservancy project operation safety monitoring result meets the preset conditions, water conservancy project safety warning information is generated and the water conservancy project safety warning information is transmitted to the equipment designated by the staff.

[0005] Furthermore, based on the BIM model with GIS information, water conservancy project information corresponding to the water conservancy project is collected, and the water conservancy project information is preprocessed to obtain the preprocessed water conservancy project information, including: Based on the BIM model with GIS information, the rainfall, current water level, continuous water level change rate and meteorological data of the water conservancy project location are collected to obtain water conservancy project information; The rainfall, current water level, continuous water level change rate and meteorological data at the location of the water conservancy project are normalized to obtain the pre-processed water conservancy project information.

[0006] Furthermore, a pre-deployed deep learning algorithm is used to identify the pre-processed water conservancy project information to obtain the water conservancy project operation safety monitoring results, including: The pre-processed water conservancy project information is constructed into a matrix or vector to obtain the input data of the deep learning algorithm; Inputting the input data into a pre-deployed deep learning algorithm to obtain output data of the deep learning algorithm, and using the output data of the deep learning algorithm as water level prediction information; Determine whether the water level prediction information is greater than or equal to a preset water level warning threshold. If so, determine that the water conservancy project operation safety monitoring result is unsafe operation; otherwise, determine that the water conservancy project operation safety monitoring result is safe operation.

[0007] Furthermore, the pre-deployment method of the deep learning algorithm includes: Construct a CNN-LSTM algorithm to obtain a deep learning algorithm, and initialize the population based on the hyperparameters of the deep learning algorithm; After applying the hyperparameters contained in the individuals in the population to the deep learning algorithm, the fitness corresponding to each individual is obtained using training samples, and the optimal individual is determined based on the fitness corresponding to each individual; For the best individual, a random flight strategy integrating population information is used to perform a global search for the best individual, and the best individual after the global search is obtained; For any individual, a local search is performed on the individual using an adaptive local search strategy with random pairing information interaction to obtain the individual after a local search. For any individual after a local search, a chaotic local search strategy influenced by the population search state is used to conduct a secondary search on the individual to obtain the individual after the secondary search. For the individuals after the secondary search, an adaptive explosion adjustment strategy integrating the optimal position information is used to quickly search for the target individuals, and the target individuals after the rapid search are obtained; The best individual after global search and the target individual after fast search are merged into the population again; The random flight strategy, the adaptive local search strategy, the chaotic local search strategy and the adaptive explosion adjustment strategy are repeatedly executed until the maximum number of training times is reached, the optimal individual is re-determined, and the deep learning algorithm is deployed according to the optimal individual.

[0008] Furthermore, for the optimal individual, a random flight strategy integrating population information is used to perform a global search for the optimal individual, and the optimal individual after the global search is obtained, including: The Levy flight is used to generate a random step length control factor, and the random step length control factor is used to control the preset flight step length to obtain the flight step length after control; For the optimal individual, the population information is fused with the information between the optimal individuals to obtain the population fusion information; According to the population fusion information and the flight step length after control, a global search is performed on the optimal individual to obtain the optimal individual after the global search; Determine whether the fitness corresponding to the optimal individual after the global search has increased. If so, accept the global search. Otherwise, reject the global search and use the original optimal individual directly as the optimal individual after the global search.

[0009] Furthermore, for any individual, a local search is performed on the individual using an adaptive local search strategy of random pairing information interaction to obtain the individual after the local search, including: For any individual, randomly match the individual with another individual to obtain the information interaction individual corresponding to each individual; According to the individuals and the information interaction individuals corresponding to the individuals, a first information interaction factor, a second information interaction factor and a third information interaction factor are obtained; According to the first information interaction factor, the second information interaction factor and the third information interaction factor, a local search is performed on the individual to obtain the individual after the local search.

[0010] Furthermore, for any individual after a local search, a chaotic local search strategy influenced by the population search state is used to conduct a secondary search on the individual, and the individuals after the secondary search are obtained, including: Based on the current number of training times, determine the population search state factor; Obtaining a population convergence degree factor, and obtaining a chaotic local search step length according to the population search state factor and the population convergence degree factor; According to the chaotic local search step, a secondary search is performed on the individual to obtain the individual after the secondary search.

[0011] Furthermore, for the individuals after the secondary search, an adaptive explosion adjustment strategy integrating the optimal position information is used to quickly search the target individuals, and the target individuals after the quick search are obtained, including: For the individuals after the secondary search, obtain the fitness of each individual and arrange the individuals in descending order of fitness; Based on the individuals after arrangement, take the last N individuals as the target individuals; For any target individual, a certain amount of explosion information is generated near the optimal individual, and the search speed corresponding to the target individual is obtained according to the explosion information; According to the search speed corresponding to the target individual, a rapid search is performed on the target individual to obtain the target individual after the rapid search.

[0012] Furthermore, when the water conservancy project operation safety monitoring result meets the preset conditions, water conservancy project safety warning information is generated, and the water conservancy project safety warning information is transmitted to the equipment designated by the staff, including: When the water conservancy project operation safety monitoring result is that the operation is unsafe, water conservancy project safety warning information is generated; wherein the water conservancy project safety warning information includes text information and / or sound and light alarm information; The water conservancy project safety warning information is transmitted to the equipment designated by the staff.

[0013] On the other hand, the present invention provides a BIM-based water conservancy project information management system, including: a BIM model building module, a water conservancy project information processing module, a water conservancy project information identification module and a safety warning module; The BIM model building module is used to collect the three-dimensional data of the water conservancy project, and build a BIM model of the water conservancy project according to the three-dimensional data of the water conservancy project, and at the same time integrate the BIM model into the GIS system to obtain a BIM model with GIS information; The water conservancy project information processing module is used to collect water conservancy project information corresponding to the water conservancy project based on the BIM model with GIS information, and pre-process the water conservancy project information to obtain the pre-processed water conservancy project information; The water conservancy project information identification module is used to identify the pre-processed water conservancy project information using a pre-deployed deep learning algorithm to obtain the water conservancy project operation safety monitoring results; The safety warning module is used to generate water conservancy project safety warning information when the water conservancy project operation safety monitoring results meet preset conditions, and transmit the water conservancy project safety warning information to the equipment designated by the staff.

[0014] The present invention provides a BIM-based water conservancy project information management method and system, which combines BIM technology and GIS technology to obtain a BIM model with GIS information, and can obtain more comprehensive water conservancy project information. Then, the pre-processed water conservancy project information is identified in combination with a pre-deployed deep learning algorithm to obtain the water conservancy project operation safety monitoring result, and a safety early warning is issued for the water conservancy project based on the water conservancy project operation safety monitoring result, which can not only effectively improve the management efficiency of water conservancy project information, but also further improve the operation safety of water conservancy projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0016] Figure 1 A flow chart of a water conservancy project information management method based on BIM provided in an embodiment of the present invention.

[0017] Figure 2 A structural schematic diagram of a water conservancy project information management system based on BIM provided in an embodiment of the present invention.

[0018] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0019] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0020] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] like Figure 1 As shown, an embodiment of the present invention provides a water conservancy project information management method based on BIM, including: S11, collecting three-dimensional data of the water conservancy project, and constructing a BIM model of the water conservancy project according to the three-dimensional data of the water conservancy project, and integrating the BIM model into the GIS system to obtain a BIM model with GIS information; BIM (Building Information Modeling) is a digital management tool that improves the efficiency of planning, design, construction and operation by creating and managing digital representations of the physical and functional characteristics of building projects. GIS (Geographic Information System) is a system for collecting, managing, analyzing and displaying geospatial data.

[0022] The combination of BIM (Building Information Modeling) and GIS (Geographic Information System) is a powerful technology fusion that combines detailed information of construction projects with geospatial data to provide a more comprehensive perspective for planning, design, construction and management. It can not only achieve more comprehensive water conservancy project information management, but also improve the safety management capabilities of water conservancy projects.

[0023] S12, based on the BIM model with GIS information, collecting water conservancy project information corresponding to the water conservancy project, and preprocessing the water conservancy project information to obtain the preprocessed water conservancy project information; The BIM model with GIS information can effectively analyze the geographical location and spatial status of water conservancy projects (such as water conservancy dams). Water conservancy project information can be some operating parameters of water conservancy dams. When these operating parameters exceed the predetermined indicators, an alarm can be generated. In order to further improve the management efficiency of water conservancy projects, water conservancy project information can be used for information prediction, so as to achieve early warning effects. Compared with existing technologies, which only issue early warnings after a certain parameter exceeds a threshold, it has higher security.

[0024] S13, using a pre-deployed deep learning algorithm to identify the pre-processed water conservancy project information to obtain the water conservancy project operation safety monitoring results; The pre-deployed deep learning algorithms can be some algorithms with data prediction capabilities. The gradient descent intelligent optimization algorithm can be used to pre-deploy the deep learning algorithms, so that the deep learning algorithms have the ability to identify water conservancy project information.

[0025] The results of water conservancy project operation safety monitoring can include unsafe operation or safe operation, so that staff can discover and handle abnormalities in a timely manner to ensure the normal operation of the water conservancy project.

[0026] S14. When the water conservancy project operation safety monitoring result meets the preset conditions, water conservancy project safety warning information is generated and the water conservancy project safety warning information is transmitted to the equipment designated by the staff.

[0027] The water conservancy project safety warning information can be text warning information and / or sound and light warning information. The text warning information can be transmitted to the staff's mobile device, and the sound and light warning information can be transmitted to the sound and light alarm equipment at the water conservancy project site, thereby realizing the warning function.

[0028] In the embodiment of the present invention, based on the BIM model with GIS information, water conservancy project information corresponding to the water conservancy project is collected, and the water conservancy project information is preprocessed to obtain the preprocessed water conservancy project information, including: Based on the BIM model with GIS information, the rainfall, current water level, continuous water level change rate and meteorological data of the water conservancy project location are collected to obtain water conservancy project information; The rainfall, current water level, continuous water level change rate and meteorological data at the location of the water conservancy project are normalized to obtain the pre-processed water conservancy project information.

[0029] The rainfall can be set to the rainfall within the next hour, the continuous water level change rate can be the water level change rate between the first M time nodes with a half-hour cycle and the current time node as the starting point, and the meteorological data can be the weather information for L consecutive days (such as heavy rain, heavy rain, light rain, etc., subject to the regulations of the Meteorological Bureau). In order to facilitate understanding of the above scheme, an example can be given: the water conservancy project information after preprocessing can be [a1, b1, c1, c2, c3, d1, d2, d3]. Assuming that the time of collecting the water conservancy project information is 12:00, then a1 is the expected rainfall between 12:00 and 13:00 in the weather forecast, b1 represents the water level in the water conservancy project at 12:00, c1 represents the water level change rate from 11:30 to 12:00, c2 represents the water level change rate from 11:00 to 11:30, c3 represents the water level change rate from 10:30 to 11:00, d1 represents the weather information of the day, d2 represents the weather information of the previous day, and d1 represents the weather information of the previous two days. However, it is worth noting that the types and quantities of the above water conservancy project information are examples, and other data can also be used as water conservancy project information.

[0030] In the embodiment of the present invention, a pre-deployed deep learning algorithm is used to identify the pre-processed water conservancy project information to obtain the water conservancy project operation safety monitoring results, including: The pre-processed water conservancy project information is constructed into a matrix or vector to obtain the input data of the deep learning algorithm; For example, when the data sampling frequency is high, it can be constructed as a matrix; when the data sampling frequency is low, it can be constructed as a vector.

[0031] Inputting the input data into a pre-deployed deep learning algorithm to obtain output data of the deep learning algorithm, and using the output data of the deep learning algorithm as water level prediction information; Determine whether the water level prediction information is greater than or equal to a preset water level warning threshold. If so, determine that the water conservancy project operation safety monitoring result is unsafe operation; otherwise, determine that the water conservancy project operation safety monitoring result is safe operation.

[0032] In an embodiment of the present invention, the pre-deployment method of the deep learning algorithm includes: Construct a CNN-LSTM (convolutional neural network-long short-term memory network) algorithm to obtain a deep learning algorithm, and initialize the population based on the hyperparameters of the deep learning algorithm; For the hyperparameters of the CNN-LSTM algorithm, they can be randomly initialized between the upper and lower limits of the hyperparameters, and the obtained hyperparameters can be encoded into vectors, so that an individual can be obtained, and after obtaining multiple different individuals, these individuals can be formed into a population.

[0033] After applying the hyperparameters contained in the individuals in the population to the deep learning algorithm, the fitness corresponding to each individual is obtained using training samples, and the optimal individual is determined based on the fitness corresponding to each individual; The training samples can be historical water conservancy project information and water level information corresponding to the historical water conservancy project information in the future period, such as the water level information in the next one or two hours based on the sampling time of the historical water conservancy project information. The training samples can be factual data that has occurred and been recorded, and water level prediction can be achieved by learning from these data.

[0034] Furthermore, the loss function value corresponding to each individual can be obtained through the cross entropy loss function, and the fitness corresponding to each individual can be obtained after the loss function value is negative. At this time, the individual with the largest fitness is the optimal individual.

[0035] For the best individual, a random flight strategy integrating population information is used to perform a global search for the best individual, and the best individual after the global search is obtained; For any individual, a local search is performed on the individual using an adaptive local search strategy with random pairing information interaction to obtain the individual after a local search. For any individual after a local search, a chaotic local search strategy influenced by the population search state is used to conduct a secondary search on the individual to obtain the individual after the secondary search. For the individuals after the secondary search, an adaptive explosion adjustment strategy integrating the optimal position information is used to quickly search for the target individuals, and the target individuals after the rapid search are obtained; The best individual after global search and the target individual after fast search are merged into the population again; The random flight strategy, the adaptive local search strategy, the chaotic local search strategy and the adaptive explosion adjustment strategy are repeatedly executed until the maximum number of training times is reached, the optimal individual is re-determined, and the deep learning algorithm is deployed according to the optimal individual.

[0036] In the prior art, due to the use of the gradient descent intelligent optimization algorithm, the algorithm often falls into the local optimum, which ultimately leads to poor water conservancy project safety early warning capabilities. Therefore, the embodiment of the present invention provides a more efficient training algorithm to avoid the algorithm from falling into the local optimum while providing stronger and faster search capabilities.

[0037] In the embodiment of the present invention, for the optimal individual, a random flight strategy integrating population information is used to perform a global search for the optimal individual, and the optimal individual after the global search is obtained, including: Levy flight is used to generate random step length control factors, and the random step length control factors are used to control the preset flight step length. The flight step length after control is: ;in, represents the random step size control factor, Indicates the preset flight step length; For the optimal individual, the population information is fused with the information between the optimal individuals, and the population fusion information is obtained as follows: ;in, Indicates t During the training process j The individual d dimensional hyperparameters, j =1,2,…,K, K represents the total number of individuals, The optimal individual d dimensional hyperparameters, d =1,2,…,D, D represents the total dimension of hyperparameters in the individual, || represents the absolute value symbol; According to the population fusion information and the flight step length after control, a global search is performed for the optimal individual, and the optimal individual after the global search is obtained as: ;in, represents the optimal individual after global search. d dimensional hyperparameter.

[0038] Determine whether the fitness corresponding to the optimal individual after the global search has increased. If so, accept the global search. Otherwise, reject the global search and use the original optimal individual directly as the optimal individual after the global search.

[0039] The embodiment of the present invention adopts a random flight strategy that integrates population information to perform a global search for the optimal individual, which can integrate population information and improve the ability of the optimal individual to jump out of the local optimal solution, and performs fitness judgment after the search, which can effectively ensure the convergence speed of the algorithm.

[0040] In the embodiment of the present invention, for any individual, a local search is performed on the individual using an adaptive local search strategy of random pairing information interaction to obtain the individual after the local search, including: For any individual, randomly match the individual with another individual to obtain the information interaction individual corresponding to each individual; According to the individuals and the information interaction individuals corresponding to the individuals, the first information interaction factor, the second information interaction factor and the third information interaction factor are obtained as follows: , as well as ;in, represents the first information interaction factor, Indicates t During the training process i The individual d dimensional hyperparameters, i =1,2,…,K, K represents the total number of individuals, Indicates t During the training process i The first information interaction individual corresponding to the individual d dimensional hyperparameters, represents the second information interaction factor, Indicates t During the training process i The individual d +1-dimensional hyperparameters, Indicates t During the training process i The first information interaction individual corresponding to the individual d +1-dimensional hyperparameters, represents the third information interaction factor; It is worth noting that when When d=D, then Set to , Same reason.

[0041] According to the first information interaction factor, the second information interaction factor and the third information interaction factor, a local search is performed on the individual, and the individual obtained after the local search is: ;in, Indicates i The individual after a local search ddimensional hyperparameter.

[0042] The embodiment of the present invention adopts an adaptive local search strategy of random pairing information interaction to perform a local search on individuals, so that individuals can quickly search according to the differences between individuals interacting with information, which can not only improve the diversity of the algorithm, but also improve the convergence speed of the algorithm, and improve the possibility of finding the global optimal position.

[0043] Optionally, since the parameters of adjacent dimensions are fused at the same time, only the hyperparameters with the same upper and lower limits can be optimized, thereby ensuring that each individual can achieve the search.

[0044] In the embodiment of the present invention, for any individual after a local search, a chaotic local search strategy influenced by the population search state is used to perform a secondary search on the individual to obtain the individual after the secondary search, including: Based on the current number of training times, the population search state factor is determined as: ;in, represents the population search state factor during the t-th training process, represents the population search state factor during the t+1th training process, represents a random number between [3.75,4], and the initial value of the population search state factor is set to 0.5; The population convergence factor is obtained as: ;in, It represents the sum of the fitness of all individuals in the population after a local search during the t-1th training process. It represents the sum of the fitness of all individuals in the population after a local search during the t-th training process. Represents the population convergence factor.

[0045] According to the population search state factor and the population convergence degree factor, the chaotic local search step length is obtained;

[0046] in, represents the first threshold, represents the second threshold, and Greater than , represents the chaotic local search step length during the t-th training process, represents the chaotic local search step length during the t+1th training process, Represents the ratio of the interval length of the variable to the maximum number of training times; According to the chaotic local search step, a secondary search is performed on the individual, and the individual after the secondary search is obtained as follows: ;in, Indicates t During the training process m The individual after a local search d dimensional hyperparameters, Indicates m The individual after the second search d dimensional hyperparameters, m =1,2,…,K, K represents the total number of individuals, Represents a random number between [-1,1].

[0047] The embodiment of the present invention adopts a chaotic local search strategy influenced by the population search state to perform a secondary search on individuals. The local search speed can be adaptively adjusted according to the current population convergence state. When the algorithm has not converged, a larger search step can be given. At this time, the algorithm can be effectively prevented from falling into the local optimum. As the algorithm iterates, the population converges, forcing the step size to gradually decrease, converting to a fine search, thereby improving the search accuracy.

[0048] In the embodiment of the present invention, for the individuals after the secondary search, an adaptive explosion adjustment strategy integrating the optimal position information is used to quickly search the target individuals, and the target individuals after the quick search are obtained, including: For the individuals after the secondary search, obtain the fitness of each individual and arrange the individuals in descending order of fitness; Based on the individuals after arrangement, take the last N individuals as target individuals; where N can be equal to K; That is, N individuals with the smallest fitness are taken as target individuals. These target individuals are in a poor position in the solution space, which will seriously affect the speed of the algorithm. Therefore, the embodiment of the present invention performs a fast search for these individuals to improve the convergence speed of the algorithm.

[0049] For any target individual, a certain amount of explosion information is generated near the optimal individual; The explosion information is generated as follows: ;in, Indicates t The target individual's d dimensional hyperparameters, The optimal individual d dimensional hyperparameters, Represents a random number between [-1,1], Indicates the explosion information. d Dimensional hyperparameters; According to the explosion information, the explosion information with the largest fitness is determined, and the search speed corresponding to the target individual is obtained according to the explosion information with the largest fitness: ,in, Indicates t During the training process, the target individual d The speed of the dimensional hyperparameters, Indicates t +1 target individual during training d The speed of the dimensional hyperparameters, represents the preset inertia weight, represents the learning factor, Represents a random number between (0,1), The first explosion information with the largest fitness d dimensional hyperparameter.

[0050] According to the search speed corresponding to the target individual, a quick search is performed on the target individual, and the target individual after the quick search is obtained as: ;in, represents the first d dimensional hyperparameter.

[0051] The embodiment of the present invention adopts an adaptive explosion adjustment strategy that integrates optimal position information to quickly search for target individuals, which can enable the target individuals to quickly approach a better area, while avoiding the homogenization of the population, maintaining population diversity, and avoiding falling into a local optimum.

[0052] Optionally, after each search, each individual may be subjected to out-of-bounds processing to ensure the effectiveness of the algorithm.

[0053] In an embodiment of the present invention, when the water conservancy project operation safety monitoring result meets the preset conditions, water conservancy project safety warning information is generated, and the water conservancy project safety warning information is transmitted to a device designated by a staff member, including: When the water conservancy project operation safety monitoring result is that the operation is unsafe, water conservancy project safety warning information is generated; wherein the water conservancy project safety warning information includes text information and / or sound and light alarm information; The water conservancy project safety warning information is transmitted to the equipment designated by the staff.

[0054] like Figure 2 As shown, an embodiment of the present invention provides a water conservancy project information management system based on BIM, including: a BIM model building module 21, a water conservancy project information processing module 22, a water conservancy project information identification module 23 and a safety warning module 24; The BIM model building module 21 is used to collect the three-dimensional data of the water conservancy project, and build a BIM model of the water conservancy project according to the three-dimensional data of the water conservancy project, and integrate the BIM model into the GIS system to obtain a BIM model with GIS information; The water conservancy project information processing module 22 is used to collect water conservancy project information corresponding to the water conservancy project based on the BIM model with GIS information, and pre-process the water conservancy project information to obtain the pre-processed water conservancy project information; The water conservancy project information identification module 23 is used to identify the pre-processed water conservancy project information using a pre-deployed deep learning algorithm to obtain the water conservancy project operation safety monitoring results; The safety warning module 24 is used to generate water conservancy project safety warning information when the water conservancy project operation safety monitoring result meets the preset conditions, and transmit the water conservancy project safety warning information to the equipment designated by the staff.

[0055] A BIM-based water conservancy project information management system provided in an embodiment of the present invention can execute the above-mentioned method and technical solution. Its principles and beneficial effects are similar and will not be repeated here.

[0056] The present invention provides a BIM-based water conservancy project information management method and system, which combines BIM technology and GIS technology to obtain a BIM model with GIS information, and can obtain more comprehensive water conservancy project information. Then, the pre-processed water conservancy project information is identified in combination with a pre-deployed deep learning algorithm to obtain the water conservancy project operation safety monitoring result, and a safety early warning is issued for the water conservancy project based on the water conservancy project operation safety monitoring result, which can not only effectively improve the management efficiency of water conservancy project information, but also further improve the operation safety of water conservancy projects.

[0057] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A BIM-based water conservancy project information management method, characterized in that: include: Collecting the three-dimensional data of the water conservancy project, and constructing a BIM model of the water conservancy project according to the three-dimensional data of the water conservancy project, and integrating the BIM model into the GIS system to obtain a BIM model with GIS information; Based on the BIM model with GIS information, water conservancy project information corresponding to the water conservancy project is collected, and the water conservancy project information is preprocessed to obtain the preprocessed water conservancy project information; Use the pre-deployed deep learning algorithm to identify the pre-processed water conservancy project information and obtain the water conservancy project operation safety monitoring results; When the water conservancy project operation safety monitoring result meets the preset conditions, water conservancy project safety warning information is generated and transmitted to the equipment designated by the staff.

2. The BIM-based water conservancy project information management method according to claim 1 is characterized in that: Based on the BIM model with GIS information, water conservancy project information corresponding to the water conservancy project is collected, and the water conservancy project information is preprocessed to obtain the preprocessed water conservancy project information, including: Based on the BIM model with GIS information, the rainfall, current water level, continuous water level change rate and meteorological data of the water conservancy project location are collected to obtain water conservancy project information; The rainfall, current water level, continuous water level change rate and meteorological data at the location of the water conservancy project are normalized to obtain the pre-processed water conservancy project information.

3. The BIM-based water conservancy project information management method according to claim 2 is characterized in that: The pre-deployed deep learning algorithm is used to identify the pre-processed water conservancy project information and obtain the water conservancy project operation safety monitoring results, including: The pre-processed water conservancy project information is constructed into a matrix or vector to obtain the input data of the deep learning algorithm; Inputting the input data into a pre-deployed deep learning algorithm to obtain output data of the deep learning algorithm, and using the output data of the deep learning algorithm as water level prediction information; Determine whether the water level prediction information is greater than or equal to a preset water level warning threshold. If so, determine that the water conservancy project operation safety monitoring result is unsafe operation; otherwise, determine that the water conservancy project operation safety monitoring result is safe operation.

4. The BIM-based water conservancy project information management method according to claim 3 is characterized in that: The pre-deployment method of the deep learning algorithm comprises: Construct a CNN-LSTM algorithm to obtain a deep learning algorithm, and initialize the population based on the hyperparameters of the deep learning algorithm; After applying the hyperparameters contained in the individuals in the population to the deep learning algorithm, the fitness corresponding to each individual is obtained using training samples, and the optimal individual is determined based on the fitness corresponding to each individual; For the best individual, a random flight strategy integrating population information is used to perform a global search for the best individual, and the best individual after the global search is obtained; For any individual, a local search is performed on the individual using an adaptive local search strategy with random pairing information interaction to obtain the individual after a local search. For any individual after a local search, a chaotic local search strategy influenced by the population search state is used to conduct a secondary search on the individual to obtain the individual after the secondary search. For the individuals after the secondary search, an adaptive explosion adjustment strategy integrating the optimal position information is used to quickly search for the target individuals, and the target individuals after the rapid search are obtained; The best individual after global search and the target individual after fast search are merged into the population again; The random flight strategy, the adaptive local search strategy, the chaotic local search strategy and the adaptive explosion adjustment strategy are repeatedly executed until the maximum number of training times is reached, the optimal individual is re-determined, and the deep learning algorithm is deployed according to the optimal individual.

5. The BIM-based water conservancy project information management method according to claim 4 is characterized in that: For the best individual, a random flight strategy integrating population information is used to perform a global search for the best individual, and the best individual after the global search is obtained, including: The Levy flight is used to generate a random step length control factor, and the random step length control factor is used to control the preset flight step length to obtain the flight step length after control; For the optimal individual, the population information is fused with the information between the optimal individuals to obtain the population fusion information; According to the population fusion information and the flight step length after control, a global search is performed on the optimal individual to obtain the optimal individual after the global search; Determine whether the fitness corresponding to the optimal individual after the global search has increased. If so, accept the global search. Otherwise, reject the global search and use the original optimal individual directly as the optimal individual after the global search.

6. The BIM-based water conservancy project information management method according to claim 5 is characterized in that: For any individual, a local search is performed on the individual using an adaptive local search strategy with random pairing information interaction to obtain the individual after a local search, including: For any individual, randomly match the individual with another individual to obtain the information interaction individual corresponding to each individual; According to the individuals and the information interaction individuals corresponding to the individuals, a first information interaction factor, a second information interaction factor and a third information interaction factor are obtained; According to the first information interaction factor, the second information interaction factor and the third information interaction factor, a local search is performed on the individual to obtain the individual after the local search.

7. The BIM-based water conservancy project information management method according to claim 6 is characterized in that: For any individual after a local search, a chaotic local search strategy influenced by the population search state is used to conduct a secondary search on the individual, and the individuals after the secondary search are obtained, including: Based on the current number of training times, determine the population search state factor; Obtaining a population convergence degree factor, and obtaining a chaotic local search step length according to the population search state factor and the population convergence degree factor; According to the chaotic local search step, a secondary search is performed on the individual to obtain the individual after the secondary search.

8. The BIM-based water conservancy project information management method according to claim 7 is characterized in that: For the individuals after the secondary search, an adaptive explosion adjustment strategy integrating the optimal position information is used to quickly search the target individuals, and the target individuals after the rapid search are obtained, including: For the individuals after the secondary search, obtain the fitness of each individual and arrange the individuals in descending order of fitness; Based on the individuals after arrangement, take the last N individuals as the target individuals; For any target individual, a certain amount of explosion information is generated near the optimal individual, and the search speed corresponding to the target individual is obtained according to the explosion information; According to the search speed corresponding to the target individual, a rapid search is performed on the target individual to obtain the target individual after the rapid search.

9. The BIM-based water conservancy project information management method according to claim 8, characterized in that: When the water conservancy project operation safety monitoring result meets the preset conditions, water conservancy project safety warning information is generated and transmitted to the equipment designated by the staff, including: When the water conservancy project operation safety monitoring result is that the operation is unsafe, water conservancy project safety warning information is generated; wherein the water conservancy project safety warning information includes text information and / or sound and light alarm information; The water conservancy project safety warning information is transmitted to the equipment designated by the staff.

10. A BIM-based water conservancy project information management system, characterized in that: include: BIM model construction module, water conservancy project information processing module, water conservancy project information identification module and safety warning module; The BIM model building module is used to collect the three-dimensional data of the water conservancy project, and build a BIM model of the water conservancy project according to the three-dimensional data of the water conservancy project, and at the same time integrate the BIM model into the GIS system to obtain a BIM model with GIS information; The water conservancy project information processing module is used to collect water conservancy project information corresponding to the water conservancy project based on the BIM model with GIS information, and pre-process the water conservancy project information to obtain the pre-processed water conservancy project information; The water conservancy project information identification module is used to identify the pre-processed water conservancy project information using a pre-deployed deep learning algorithm to obtain the water conservancy project operation safety monitoring results; The safety warning module is used to generate water conservancy project safety warning information when the water conservancy project operation safety monitoring results meet preset conditions, and transmit the water conservancy project safety warning information to the equipment designated by the staff.

Images