Adaptive comprehensive control method of electromechanical equipment in smart tunnels based on deep learning

Abstract

The present invention relates to the technical field of electromechanical equipment control, and specifically discloses a smart tunnel electromechanical equipment adaptive comprehensive control method based on deep learning, including acquiring initial operating status data and position image information of electromechanical equipment through intelligent IoT sensors; importing the position image information of the electromechanical equipment and its initial operating status data into a BIM model for training and constructing an operation and maintenance BIM model; obtaining operation and maintenance samples based on deep learning technology and importing them into the operation and maintenance BIM model to obtain electromechanical equipment inspection tasks and output operation and maintenance signal parameters; performing inspection and analysis on the operation and maintenance signal parameters corresponding to different electromechanical equipment to determine whether they meet the inspection route requirements, and if not, adjusting the current inspection route, otherwise performing fault analysis on the operation and maintenance signal parameters; determining the failure of the electromechanical equipment, issuing a fault alarm signal and conducting an inspection of the electromechanical equipment, thereby realizing intelligent adaptive adjustment of the tunnel electromechanical equipment, improving the efficiency of tunnel safety operation and maintenance, and reducing the risk of safety accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of electromechanical equipment control, and in particular to an adaptive comprehensive control method for electromechanical equipment in a smart tunnel based on deep learning. Background Art

[0002] The current problems with the adaptive comprehensive management and control of tunnel electromechanical equipment in my country are mainly the relatively backward systematization, intelligence and information-based management and control technologies. The concept of focusing on reconstruction and neglecting maintenance has led to the inability of existing electromechanical equipment configuration to meet the needs of tunnel safety management and control, resulting in a low level of intelligent tunnel management and maintenance, low information data processing methods, and high reliance on maintenance personnel for operation. There is an urgent need to improve the efficiency of operation and maintenance fault handling response and realize paperless and traceable daily maintenance.

[0003] Applying modern information technologies such as Building Information Modeling (BIM) and the Internet of Things to the comprehensive management and control of electromechanical equipment in highway tunnels to create a visual, information-based, and intelligent green smart tunnel will effectively improve the quality and efficiency of tunnel management and maintenance.

[0004] The adaptive comprehensive management and control method of electromechanical equipment in smart tunnels refers to the use of advanced artificial intelligence technologies such as deep learning to conduct real-time monitoring, intelligent analysis and automatic control of electromechanical equipment in the tunnel to achieve high efficiency, safety and energy saving of equipment operation; at present, this method is difficult to achieve the purpose of optimizing tunnel operation management by automatically adjusting the working mode of electromechanical equipment according to the real-time operating status of electromechanical equipment in the tunnel and the energy consumption status of the tunnel. Summary of the invention

[0005] The purpose of the present invention is to provide an adaptive comprehensive control method for intelligent tunnel electromechanical equipment based on deep learning to solve the following technical problems:

[0006] How to intelligently realize adaptive adjustment of tunnel electromechanical equipment to improve tunnel safety operation and maintenance efficiency and reduce the risk of safety accidents.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An adaptive comprehensive control method for electromechanical equipment in smart tunnels based on deep learning, including:

[0009] Step 1: Acquire the initial operation status data and position image information of the electromechanical equipment through intelligent IoT sensors;

[0010] Step 2: Import the location image information of the electromechanical equipment and its initial operating status data into the current model for training and constructing an operation and maintenance BIM model;

[0011] Step 3: Based on deep learning technology, the target electromechanical equipment location image information and the real-time operation status data of the electromechanical equipment at its corresponding location are matched to obtain operation and maintenance samples, and the operation and maintenance samples are imported into the operation and maintenance BIM model for machine learning to obtain the electromechanical equipment inspection tasks and output the operation and maintenance signal parameters;

[0012] Step 4: Perform inspection and analysis on the operation and maintenance signal parameters corresponding to different electromechanical equipment, and determine whether the inspection route requirements are met based on the inspection and analysis results:

[0013] If not, adjust the current inspection route;

[0014] If yes, proceed to the next step;

[0015] Step 5: Perform fault analysis on the operation and maintenance signal parameters corresponding to the electromechanical equipment that meets the inspection route, and determine whether a mechanical and electrical equipment fault occurs based on the fault analysis results:

[0016] If so, a fault warning signal is issued;

[0017] If not, continue with the inspection of electromechanical equipment.

[0018] Preferably, the target electromechanical equipment position image information in step 3 includes a distribution image of the target electromechanical equipment position and a tunnel energy consumption display image; based on a historical electromechanical equipment tunnel energy consumption database, the historical tunnel energy consumption parameters are determined by matching the distribution image of the target electromechanical equipment position and the tunnel energy consumption display image;

[0019] The operation and maintenance signal parameters are obtained as follows:

[0020] S1. Collect historical tunnel energy consumption parameters at several time points at the location of the target electromechanical equipment and historical operating status data of the target electromechanical equipment;

[0021] S2. Select various tunnel energy consumption parameters and operation status data of the operation items associated with the corresponding time points to generate an operation and maintenance sample;

[0022] S3. The operation and maintenance samples of various tunnel energy consumption parameters obtained in real time are imported into the operation and maintenance BIM model for training to obtain the inspection tasks of various tunnel energy consumption parameters.

[0023] Preferably, the inspection task is obtained in the following manner:

[0024] Collect the distribution image of the target electromechanical equipment location, the tunnel energy consumption display image and the historical operation status data and input them into the operation and maintenance BIM model to obtain the operation and maintenance risk nodes and their operation and maintenance node tunnel energy consumption parameters;

[0025] Arrange tasks based on the energy consumption of the tunnel at the operation and maintenance node and whether there are risks in the operation and maintenance of electromechanical equipment at the node:

[0026] If the energy consumption of the operation and maintenance node tunnel is abnormal and there is an operation and maintenance risk of electromechanical equipment at the node, an operation and maintenance instruction is immediately generated and the position of the abnormal electromechanical equipment is located according to the energy consumption display image of the operation and maintenance node tunnel;

[0027] If the energy consumption of the tunnel at the operation and maintenance node is abnormal but there is no risk of operation and maintenance of electromechanical equipment at the node, an operation and maintenance instruction will be generated immediately and the abnormal electromechanical equipment will be located according to the energy consumption display image of the tunnel at the operation and maintenance node. The current operating status data will be used as an operation and maintenance sample and input into the operation and maintenance BIM model for training.

[0028] If the energy consumption of the operation and maintenance node tunnel is normal but there is an operation and maintenance risk of electromechanical equipment at the node, an operation and maintenance instruction is immediately generated and real-time operation and maintenance signal parameters are output.

[0029] Preferably, the inspection and analysis method in step 4 is:

[0030] By formula Get all electromechanical equipment at the node Inspection coefficient of item operation and maintenance risk type ;in, For the current node Electromechanical equipment Correlation coefficient of item operation and maintenance risk type; For the current node Operation and maintenance signal parameters of electromechanical equipment; For the current node Standard operation and maintenance signal parameters of electromechanical equipment; It is the preset operation and maintenance signal parameter deviation value of the same type of electromechanical equipment; For the The number of occurrences of each electromechanical equipment operation and maintenance risk type.

[0031] Preferably, the inspection analysis result is:

[0032] The inspection coefficient of the operation and maintenance risk type With the limited standard threshold range To compare:

[0033] like ∈ , then The inspection frequency of the route of the operation and maintenance risk type meets the requirements, and fault analysis is carried out;

[0034] like < , then The inspection frequency of the routes with operation and maintenance risk types is low, so the number of inspection routes and the number of inspections should be increased;

[0035] like > , then The inspection frequency of routes with operation and maintenance risk types is high, so the number of inspection routes and the number of inspections are reduced.

[0036] Preferably, the fault analysis method in step 5 is:

[0037] By formula Calculate the first Mechanical and electrical equipment operation and maintenance failure coefficient ;in, , are all preset inspection fault impact weight coefficients, and , All are greater than 0; ,in For the preset time period, is the current time, is the historical change time derived from the current time; For the The number of inspection cycles of each electromechanical equipment.

[0038] Preferably, the fault analysis result is:

[0039] Operation and maintenance failure factor With preset threshold To compare:

[0040] like Less than the preset threshold , then the electromechanical equipment is judged to be normal and the electromechanical equipment inspection continues;

[0041] like Greater than the preset threshold , it is judged that the electromechanical equipment is abnormal, that a electromechanical equipment failure occurs, and a fault alarm signal is issued.

[0042] Preferably, the process of establishing the operation and maintenance BIM model in step 2 includes:

[0043] Obtain the location image information of electromechanical equipment and its historical operating status data:

[0044] According to the tunnel energy consumption display of the electromechanical equipment position image information, normal historical operation status data and abnormal historical operation status data are obtained, and a positive sample set and a negative sample set are established respectively;

[0045] The positive sample set and the negative sample set as well as the tunnel energy consumption display images of their respective electromechanical equipment locations are input into the initial BIM model to construct the operation and maintenance BIM model, and a feedback learning mechanism is established for the operation and maintenance BIM model to output visualized chart information.

[0046] Beneficial effects of the present invention:

[0047] (1) The present invention uses intelligent IoT sensors combined with IoT technology to obtain the initial operating status data and location image information of electromechanical equipment, and combines the initial BIM model and deep learning technology to match the target electromechanical equipment location image information with the real-time operating status data of the electromechanical equipment at its corresponding position to obtain operation and maintenance samples; thus, the tunnel electromechanical equipment can be monitored and the operating data can be visualized.

[0048] (2) The present invention imports operation and maintenance samples into the operation and maintenance BIM model to perform machine learning to obtain the electromechanical equipment inspection tasks and output operation and maintenance signal parameters; performs operation and maintenance analysis on the operation and maintenance signal parameters corresponding to different electromechanical equipment to obtain the energy consumption information of different electromechanical equipment operation and maintenance risk nodes, and provides the patrol routes that need to be adjusted through the results of patrol analysis and calculation to increase or decrease the number of patrol routes and the number of patrol times; and realizes real-time information safety patrol and patrol maintenance process of electromechanical equipment.

[0049] (3) The present invention also uses fault analysis calculation to judge the fault analysis results of the operation and maintenance signals of electromechanical equipment that does not require patrol route adjustment, ensure the implementation of the electromechanical safety patrol process and provide early warning and maintenance processing for equipment failures. By monitoring the tunnel electromechanical equipment and intelligently analyzing the operation data, comprehensive monitoring of the operation and maintenance status of the electromechanical equipment and a safe patrol process are achieved, providing a simplified patrol fault judgment process for the electromechanical equipment.

[0050] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0052] Figure 1 This is a step diagram of the method for adaptive comprehensive control of electromechanical equipment in intelligent tunnels based on deep learning of the present invention;

[0053] Figure 2 This is a step diagram of a method for obtaining operation and maintenance signal parameters of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] The adaptive comprehensive management and control method of electromechanical equipment in smart tunnels refers to the use of advanced artificial intelligence technologies such as deep learning to conduct real-time monitoring, intelligent analysis and automatic control of electromechanical equipment in the tunnel to achieve high efficiency, safety and energy saving of equipment operation; at present, this method is difficult to achieve the purpose of optimizing tunnel operation management by automatically adjusting the working mode of electromechanical equipment according to the real-time operating status of electromechanical equipment in the tunnel and the energy consumption status of the tunnel.

[0056] See also Figure 1 As shown, in order to solve the above technical problems, the present invention designs an adaptive comprehensive control method for intelligent tunnel electromechanical equipment based on deep learning, and the specific method includes:

[0057] Step 1: Acquire the initial operation status data and position image information of the electromechanical equipment through intelligent IoT sensors;

[0058] Step 2: Import the location image information of the electromechanical equipment and its initial operating status data into the current model for training and constructing an operation and maintenance BIM model;

[0059] Step 3: Based on deep learning technology, the target electromechanical equipment location image information and the real-time operation status data of the electromechanical equipment at its corresponding location are matched to obtain operation and maintenance samples, and the operation and maintenance samples are imported into the operation and maintenance BIM model for machine learning to obtain the electromechanical equipment inspection tasks and output the operation and maintenance signal parameters;

[0060] Step 4: Perform inspection and analysis on the operation and maintenance signal parameters corresponding to different electromechanical equipment, and determine whether the inspection route requirements are met based on the inspection and analysis results:

[0061] If not, adjust the current inspection route;

[0062] If yes, proceed to the next step;

[0063] Step 5: Perform fault analysis on the operation and maintenance signal parameters corresponding to the electromechanical equipment that meets the inspection route, and determine whether a mechanical and electrical equipment fault occurs based on the fault analysis results:

[0064] If so, a fault warning signal is issued;

[0065] If not, continue with the inspection of electromechanical equipment.

[0066] In the above technical scheme, the adaptive comprehensive management and control method of intelligent tunnel electromechanical equipment based on deep learning in this embodiment uses modern information technologies such as deep learning technology, BIM building information model, and Internet of Things technology to monitor tunnel electromechanical equipment and visualize, informatize, and intelligently analyze operating data, thereby realizing comprehensive monitoring of the operation and maintenance status of electromechanical equipment and a safety inspection process.

[0067] First, in step 1, the initial operating status data of the electromechanical equipment and the position image information of the electromechanical equipment are collected through intelligent IoT sensors; Intelligent IoT sensors are a key component of IoT technology. They can not only sense the environment and collect data, but also perform real-time information analysis and processing, and seamlessly integrate with remote cloud platforms and artificial intelligence algorithms. They usually include wireless temperature sensors, wireless pressure sensors, wireless vibration sensors, and wireless current sensors; through the combination of these sensor integrations and IoT technology, the operating status data of the tunnel's electromechanical equipment can be obtained. The usual operating status data includes temperature, pressure, vibration frequency, and current intensity; and the specific operating status data is obtained by obtaining the position distribution image of the electromechanical equipment throughout the tunnel.

[0068] Secondly, in step 2, the position image information of the electromechanical equipment and its initial operating status data are imported into the current model for training to construct an operation and maintenance BIM model; the collected position image information and initial operating status data of the electromechanical equipment are imported into the initial BIM building information model model, and an operation and maintenance BIM model specifically for electromechanical equipment is constructed through training.

[0069] Specifically, as an implementation of the present invention, the process of establishing the operation and maintenance BIM model in step 2 includes:

[0070] Obtain the location image information of electromechanical equipment and its historical operating status data:

[0071] According to the tunnel energy consumption display of the electromechanical equipment position image information, normal historical operation status data and abnormal historical operation status data are obtained, and a positive sample set and a negative sample set are established respectively;

[0072] The positive sample set and the negative sample set as well as the tunnel energy consumption display images of their respective electromechanical equipment locations are input into the initial BIM model to construct the operation and maintenance BIM model, and a feedback learning mechanism is established for the operation and maintenance BIM model to output visualized chart information.

[0073] In the above technical scheme, the establishment process of the operation and maintenance BIM model in this embodiment includes a three-dimensional image display of the location of the electromechanical equipment, and the energy consumption of each electromechanical equipment is also displayed in level through the energy consumption image, and then the energy consumption level is used to determine whether the currently acquired historical operation status data is normal, and the normal historical operation status data and the abnormal historical operation status data are obtained. According to the normal or abnormal operation status, a positive sample set and a negative sample set are constructed to realize the division of the equipment operation status; of course, in the specific energy consumption level display process, a more refined range division or energy consumption data display division can also be performed to ensure that the equipment operation status is matched with the tunnel energy consumption, and the next step of model construction is carried out: specifically, the positive sample set and the negative sample set and the tunnel energy consumption display images of the electromechanical equipment positions are input into the initial BIM model to construct the operation and maintenance BIM model, and a feedback learning mechanism is established for the operation and maintenance BIM model to output visual chart information.

[0074] Third, in step three, the target electromechanical equipment position image information and the real-time operating status data of the electromechanical equipment at its corresponding position are matched based on deep learning technology to obtain operation and maintenance samples, and the operation and maintenance samples are imported into the operation and maintenance BIM model for machine learning to obtain the electromechanical equipment inspection tasks and output operation and maintenance signal parameters.

[0075] Specifically, as an implementation mode of the present invention, the target electromechanical equipment position image information in step 3 includes a distribution image of the target electromechanical equipment position and a tunnel energy consumption display image; based on a historical electromechanical equipment tunnel energy consumption database, the distribution image of the target electromechanical equipment position and the tunnel energy consumption display image are matched to determine the historical tunnel energy consumption parameters;

[0076] See also Figure 2 As shown in the figure, the method for obtaining the operation and maintenance signal parameters is as follows:

[0077] S1. Collect historical tunnel energy consumption parameters at several time points at the location of the target electromechanical equipment and historical operating status data of the target electromechanical equipment;

[0078] S2. Select various tunnel energy consumption parameters and operation status data of the operation items associated with the corresponding time points to generate an operation and maintenance sample;

[0079] S3. The operation and maintenance samples of various tunnel energy consumption parameters obtained in real time are imported into the operation and maintenance BIM model for training to obtain the inspection tasks of various tunnel energy consumption parameters.

[0080] In the above technical scheme, in this embodiment, by utilizing deep learning technology, the position image information of the target electromechanical equipment is matched with the real-time operation status data, and then these operation and maintenance samples are input into the operation and maintenance BIM model for machine learning to identify and predict the inspection tasks of the electromechanical equipment, and output the corresponding operation and maintenance signal parameters. The acquired target electromechanical equipment position image information includes the distribution image of the target electromechanical equipment position and the tunnel energy consumption display image. The distribution image of the target electromechanical equipment position is a three-dimensional image, and based on the historical electromechanical equipment tunnel energy consumption database, the distribution three-dimensional image of the target electromechanical equipment position and the tunnel energy consumption display image can be combined to perform device matching to determine the historical tunnel energy consumption parameters corresponding to each device.

[0081] The specific method for obtaining the operation and maintenance signal parameters is as follows: first, the historical tunnel energy consumption parameters at several time points at the location of the target electromechanical equipment and the historical operating status data of the target electromechanical equipment are collected; by combining the historical tunnel energy consumption parameters with the operating status data of the corresponding target electromechanical equipment, the operating load capacity of the electromechanical equipment can be determined, and the operation and maintenance capability status of the current equipment can be judged; then, the operating status data of the operation items of each tunnel energy consumption parameter and its corresponding time point are selected to generate an operation and maintenance sample; finally, the operation and maintenance samples of each tunnel energy consumption parameter obtained in real time are imported into the operation and maintenance BIM model for training to obtain the inspection tasks of each tunnel energy consumption parameter; by judging the equipment operation and maintenance situation, the inspection tasks corresponding to the energy consumption parameters of different electromechanical equipment are output according to the operation and maintenance samples, including inspection arrangements and adjustment of inspection routes for different operation and maintenance situations.

[0082] As an implementation mode of the present invention, the inspection task is obtained in the following manner:

[0083] Collect the distribution image of the target electromechanical equipment location, the tunnel energy consumption display image and the historical operation status data and input them into the operation and maintenance BIM model to obtain the operation and maintenance risk nodes and their operation and maintenance node tunnel energy consumption parameters;

[0084] Arrange tasks based on the energy consumption of the tunnel at the operation and maintenance node and whether there are risks in the operation and maintenance of electromechanical equipment at the node:

[0085] If the energy consumption of the operation and maintenance node tunnel is abnormal and there is an operation and maintenance risk of electromechanical equipment at the node, an operation and maintenance instruction is immediately generated and the position of the abnormal electromechanical equipment is located according to the energy consumption display image of the operation and maintenance node tunnel;

[0086] If the energy consumption of the tunnel at the operation and maintenance node is abnormal but there is no risk of operation and maintenance of electromechanical equipment at the node, an operation and maintenance instruction will be generated immediately and the abnormal electromechanical equipment will be located according to the energy consumption display image of the tunnel at the operation and maintenance node. The current operating status data will be used as an operation and maintenance sample and input into the operation and maintenance BIM model for training.

[0087] If the energy consumption of the operation and maintenance node tunnel is normal but there is an operation and maintenance risk of electromechanical equipment at the node, an operation and maintenance instruction is immediately generated and real-time operation and maintenance signal parameters are output.

[0088] In the above technical solution, the inspection task is obtained in this embodiment by collecting the distribution image of the target electromechanical equipment location and the tunnel energy consumption display image and historical operation status data and inputting them into the operation and maintenance BIM model to obtain the operation and maintenance risk node and its operation and maintenance node tunnel energy consumption parameters;

[0089] Tasks are arranged according to the energy consumption status of the operation and maintenance node tunnel and whether there are operation and maintenance risks of electromechanical equipment at the node. The judgment process is as follows: if the energy consumption of the operation and maintenance node tunnel is abnormal and there are operation and maintenance risks of electromechanical equipment at the node, an operation and maintenance instruction is generated immediately and the position of the abnormal electromechanical equipment is located according to the energy consumption display image of the operation and maintenance node tunnel; if the energy consumption of the operation and maintenance node tunnel is abnormal but there is no operation and maintenance risk of electromechanical equipment at the node, an operation and maintenance instruction is generated immediately and the position of the abnormal electromechanical equipment is located according to the energy consumption display image of the operation and maintenance node tunnel, and the current operating status data is used as an operation and maintenance sample and input into the operation and maintenance BIM model for training; if the energy consumption of the operation and maintenance node tunnel is normal but there are operation and maintenance risks of electromechanical equipment at the node, an operation and maintenance instruction is generated immediately and real-time operation and maintenance signal parameters are output.

[0090] Step 4: Perform inspection and analysis on the operation and maintenance signal parameters corresponding to different electromechanical equipment, and determine whether the current inspection route requirements are met based on the inspection and analysis results. If not, adjust the current inspection route; if so, proceed to the next step.

[0091] As an implementation mode of the present invention, the inspection and analysis method in step 4 is:

[0092] By formula Get all electromechanical equipment at the node Inspection coefficient of item operation and maintenance risk type ;in, For the current node Electromechanical equipment Correlation coefficient of item operation and maintenance risk type; For the current node Operation and maintenance signal parameters of electromechanical equipment; For the current node Standard operation and maintenance signal parameters of electromechanical equipment; It is the preset operation and maintenance signal parameter deviation value of the same type of electromechanical equipment; For the The number of occurrences of each electromechanical equipment operation and maintenance risk type.

[0093] In the above technical solution, the inspection analysis method in this embodiment is specifically to determine whether the route inspection frequency of the current operation and maintenance risk type is reasonable by obtaining the inspection coefficient, and specifically to calculate by obtaining the operation and maintenance signal of the electromechanical equipment at the current node and the operation and maintenance risk type of the electromechanical equipment, and then calculate by the formula Get all electromechanical equipment at the node Inspection coefficient of item operation and maintenance risk type The inspection frequency of the inspection route can be judged in time through the inspection coefficient.

[0094] It should be explained that the correlation coefficient Standard operation and maintenance signal parameters are obtained by machine fitting based on the historical risk level of electromechanical equipment operation and maintenance signals. This is historical data obtained in advance based on the simulation of operation and maintenance inspection risk signals, which will not be detailed here; It is the result obtained by optimizing control based on the machine model according to historical data. It is pre-designed and will not be described in detail here.

[0095] As an implementation mode of the present invention, the inspection analysis result is:

[0096] The inspection coefficient of the operation and maintenance risk type With the limited standard threshold range To compare:

[0097] like ∈ , then The inspection frequency of the route of the operation and maintenance risk type meets the requirements, and fault analysis is carried out;

[0098] like < , then The inspection frequency of the routes with operation and maintenance risk types is low, so the number of inspection routes and the number of inspections should be increased;

[0099] like > , then The inspection frequency of routes with operation and maintenance risk types is high, so the number of inspection routes and the number of inspections are reduced.

[0100] In the above technical solution, the specific analysis method of the inspection analysis result in this embodiment is to convert the inspection coefficient of the operation and maintenance risk type into With the limited standard threshold range Compare the sizes and determine if ∈ , then If the inspection frequency of the route of the operation and maintenance risk type meets the requirements, a fault analysis is performed; < , then The inspection frequency of the route with the risk type of operation and maintenance is low, so increase the number of inspection routes and the number of inspections; if > , then The inspection frequency of routes with operation and maintenance risk types is high, so the number of inspection routes and the number of inspections are reduced.

[0101] Fifth, step five performs fault analysis on the operation and maintenance signal parameters corresponding to the electromechanical equipment that meets the inspection route, and determines whether a electromechanical equipment fault occurs based on the fault analysis results. If so, a fault alarm signal is issued; if not, the electromechanical equipment inspection continues.

[0102] As an implementation mode of the present invention, the fault analysis method in step 5 is as follows:

[0103] By formula Calculate the first Mechanical and electrical equipment operation and maintenance failure coefficient ;in, , are all preset inspection fault impact weight coefficients, and , All are greater than 0; ,in For the preset time period, is the current time, is the historical change time derived from the current time; For the The number of inspection cycles of each electromechanical equipment.

[0104] In the above technical solution, the fault analysis method in this embodiment is to use the formula Calculate the first Mechanical and electrical equipment operation and maintenance failure coefficient ; By obtaining the mechanical and electrical equipment operation and maintenance fault coefficient, it is determined whether the current state of the mechanical and electrical equipment is normal, and then the mechanical and electrical equipment fault diagnosis is performed; Among them, , is the weight coefficient, which is selected and set after fitting the empirical data and will not be described in detail here.

[0105] As an implementation mode of the present invention, the fault analysis result is:

[0106] Operation and maintenance failure factor With preset threshold To compare:

[0107] like Less than the preset threshold , then the electromechanical equipment is judged to be normal and the electromechanical equipment inspection continues;

[0108] like Greater than the preset threshold , it is judged that the electromechanical equipment is abnormal, that a electromechanical equipment failure occurs, and a fault alarm signal is issued.

[0109] In the above technical solution, the fault analysis method in this embodiment is to use the operation and maintenance fault coefficient With preset threshold Compare the sizes and determine the failure operation and maintenance coefficient If it is less than the preset threshold , then the electromechanical equipment is judged to be normal and the electromechanical equipment inspection continues; if Greater than the preset threshold , it is judged that the electromechanical equipment is abnormal, that a electromechanical equipment failure occurs, and a fault alarm signal is issued.

[0110] The technical process of the adaptive comprehensive management and control method of intelligent tunnel electromechanical equipment based on deep learning in the present invention is as follows: the present invention obtains the initial operating status data and position image information of electromechanical equipment through intelligent IoT sensors combined with IoT technology, and combines the initial BIM model and the deep learning technology to match the target electromechanical equipment position image information with the real-time operating status data of the electromechanical equipment at its corresponding position to obtain operation and maintenance samples; the monitoring of tunnel electromechanical equipment and the visualization of operating data are realized.

[0111] The present invention imports operation and maintenance samples into the operation and maintenance BIM model to perform machine learning to obtain the inspection tasks of electromechanical equipment and output operation and maintenance signal parameters; performs operation and maintenance analysis on the operation and maintenance signal parameters corresponding to different electromechanical equipment to obtain the energy consumption information of different electromechanical equipment operation and maintenance risk nodes, and provides the results of the inspection analysis and calculation for the inspection routes that need to be adjusted to increase or reduce the number of inspection routes and the number of inspections; and realizes real-time information security inspection and inspection maintenance process of electromechanical equipment.

[0112] The present invention also judges the fault analysis results of the operation and maintenance signals of the electromechanical equipment that does not need to adjust the patrol route through fault analysis calculation, ensures the implementation of the electromechanical safety patrol process and provides early warning and maintenance processing for equipment failures. By monitoring the tunnel electromechanical equipment and intelligently analyzing the operation data, comprehensive monitoring of the operation and maintenance status of the electromechanical equipment and a safe patrol process are achieved, providing a simplified patrol fault judgment process for the electromechanical equipment.

[0113] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0114] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. An adaptive comprehensive control method for electromechanical equipment in smart tunnels based on deep learning, characterized in that: The method comprises: Step 1: Acquire the initial operation status data and position image information of the electromechanical equipment through intelligent IoT sensors; Step 2: Import the location image information of the electromechanical equipment and its initial operating status data into the current model for training and constructing an operation and maintenance BIM model; Step 3: Based on deep learning technology, the target electromechanical equipment location image information and the real-time operation status data of the electromechanical equipment at its corresponding location are matched to obtain operation and maintenance samples, and the operation and maintenance samples are imported into the operation and maintenance BIM model for machine learning to obtain the electromechanical equipment inspection tasks and output the operation and maintenance signal parameters; Step 4: Perform inspection and analysis on the operation and maintenance signal parameters corresponding to different electromechanical equipment, and determine whether the inspection route requirements are met based on the inspection and analysis results: If not, adjust the current inspection route; If yes, proceed to the next step; The inspection and analysis method in step 4 is: By formula , Get all electromechanical equipment at the node Inspection coefficient of item operation and maintenance risk type ;in, For the current node Electromechanical equipment Correlation coefficient of item operation and maintenance risk type; For the current node Operation and maintenance signal parameters of electromechanical equipment; For the current node Standard operation and maintenance signal parameters of electromechanical equipment; It is the preset operation and maintenance signal parameter deviation value of the same type of electromechanical equipment; For the Number of occurrences of each type of mechanical and electrical equipment operation and maintenance risk; The inspection and analysis results are: The inspection coefficient of the operation and maintenance risk type With the limited standard threshold range To compare: like ∈ , then The inspection frequency of the route of the operation and maintenance risk type meets the requirements, and fault analysis is carried out; like < , then The inspection frequency of the routes with operation and maintenance risk types is low, so the number of inspection routes and the number of inspections should be increased; like > , then The inspection frequency of the routes with the O&M risk type is high, so the number of inspection routes and the number of inspections should be reduced; Step 5: Perform fault analysis on the operation and maintenance signal parameters corresponding to the electromechanical equipment that meets the inspection route, and determine whether a mechanical and electrical equipment fault occurs based on the fault analysis results: If so, a fault warning signal is issued; If not, continue with the inspection of electromechanical equipment.

2. The method for adaptive comprehensive management and control of intelligent tunnel electromechanical equipment based on deep learning according to claim 1 is characterized in that: The target electromechanical equipment position image information in step 3 includes the distribution image of the target electromechanical equipment position and the tunnel energy consumption display image; based on the historical electromechanical equipment tunnel energy consumption database, the distribution image of the target electromechanical equipment position and the tunnel energy consumption display image are matched to determine the historical tunnel energy consumption parameters; the acquisition method of the operation and maintenance signal parameters is as follows: S1. Collect historical tunnel energy consumption parameters at several time points at the location of the target electromechanical equipment and historical operating status data of the target electromechanical equipment; S2. Select various tunnel energy consumption parameters and operation status data of the operation items associated with the corresponding time points to generate an operation and maintenance sample; S3. The operation and maintenance samples of various tunnel energy consumption parameters obtained in real time are imported into the operation and maintenance BIM model for training to obtain the inspection tasks of various tunnel energy consumption parameters.

3. The method for adaptive comprehensive management and control of intelligent tunnel electromechanical equipment based on deep learning according to claim 2 is characterized in that: The inspection task is obtained as follows: Collect the distribution image of the target electromechanical equipment location, the tunnel energy consumption display image and the historical operation status data and input them into the operation and maintenance BIM model to obtain the operation and maintenance risk nodes and their operation and maintenance node tunnel energy consumption parameters; Arrange tasks based on the energy consumption of the tunnel at the operation and maintenance node and whether there are risks in the operation and maintenance of electromechanical equipment at the node: If the energy consumption of the operation and maintenance node tunnel is abnormal and there is an operation and maintenance risk of electromechanical equipment at the node, an operation and maintenance instruction is immediately generated and the position of the abnormal electromechanical equipment is located according to the energy consumption display image of the operation and maintenance node tunnel; If the energy consumption of the tunnel at the operation and maintenance node is abnormal but there is no risk of operation and maintenance of electromechanical equipment at the node, an operation and maintenance instruction will be generated immediately and the abnormal electromechanical equipment will be located according to the energy consumption display image of the tunnel at the operation and maintenance node. The current operating status data will be used as an operation and maintenance sample and input into the operation and maintenance BIM model for training. If the energy consumption of the operation and maintenance node tunnel is normal but there is an operation and maintenance risk of electromechanical equipment at the node, an operation and maintenance instruction is immediately generated and real-time operation and maintenance signal parameters are output.

4. The method for adaptive comprehensive management and control of intelligent tunnel electromechanical equipment based on deep learning according to claim 1 is characterized in that: The fault analysis method in step 5 is: By formula , calculate and obtain the Mechanical and electrical equipment operation and maintenance failure coefficient ;in, , are all preset inspection fault impact weight coefficients, and , All are greater than 0; ,in For the preset time period, is the current time, is the historical change time derived from the current time; For the The number of inspection cycles of each electromechanical equipment.

5. The method for adaptive comprehensive control of intelligent tunnel electromechanical equipment based on deep learning according to claim 4 is characterized in that: The fault analysis results are: Operation and maintenance failure factor With preset threshold To compare: like Less than the preset threshold , then the electromechanical equipment is judged to be normal and the electromechanical equipment inspection continues; like Greater than the preset threshold , it is judged that the electromechanical equipment is abnormal, that a electromechanical equipment failure occurs, and a fault alarm signal is issued.

6. The method for adaptive comprehensive management and control of intelligent tunnel electromechanical equipment based on deep learning according to claim 1 is characterized in that: The process of establishing the operation and maintenance BIM model in step 2 includes: Obtain the location image information of electromechanical equipment and its historical operating status data: According to the tunnel energy consumption display of the electromechanical equipment position image information, normal historical operation status data and abnormal historical operation status data are obtained, and a positive sample set and a negative sample set are established respectively; The positive sample set and the negative sample set as well as the tunnel energy consumption display images of their respective electromechanical equipment locations are input into the initial BIM model to construct the operation and maintenance BIM model, and a feedback learning mechanism is established for the operation and maintenance BIM model to output visualized chart information.

Images