Hydropower station operation and maintenance method, device and equipment based on mixed reality and medium

Abstract

The invention discloses a hydropower station operation and maintenance method and device based on mixed reality, equipment and a medium. The method comprises the steps of obtaining a historical operation data set of a target hydropower station in a historical period; obtaining a unit equipment fault prediction neural network model; determining the fault probability of each set device of the target hydropower station under the target time node based on the set device fault prediction neural network model; according to the fault probability of each unit device and the core degree of each unit device, determining a mixed reality inspection first path; determining an automatic inspection second path; and sending the mixed reality inspection first path to a virtual reality device, and sending the automatic inspection second path to an automatic inspection device, and jointly using the mixed reality inspection first path and the automatic inspection second path to inspect the target hydropower station. The invention belongs to the field of hydropower station equipment inspection. According to the invention, the virtual reality technology and the unmanned inspection equipment technology are combined, so that the unit equipment inspection efficiency is higher.

Description

Technical Field

[0001] The present invention relates to the field of equipment inspection in hydropower stations, and particularly to a method, device, equipment, and medium for hydropower station operation and maintenance based on mixed reality. Background Art

[0002] A hydropower station is a facility that uses the energy of water flow to generate electric energy. Hydropower stations are usually built near rivers or reservoirs, using the kinetic energy of water flow (such as the flow of river water) or potential energy (such as the water level difference in a reservoir). Its main components include water turbines, generators, transformers, and switchyards, etc.

[0003] There are many devices in a hydropower station, and potential problems with the devices pose a threat to the safe and stable operation of the hydropower plant. Therefore, it is necessary to conduct safety inspections on the devices inside the hydropower plant through regular inspections. Currently, the main inspection method still relies on manual inspections, which may have problems such as untimely inspections, high safety risks, large manpower requirements, and the inability to scientifically analyze and predict device performance data, and cannot promptly detect and eliminate the safety hazards existing in the hydropower station, thus affecting the safe and stable operation of the hydropower station. Therefore, there is an urgent need to propose a better inspection method. Summary of the Invention

[0004] The present invention provides a method, device, equipment, and medium for hydropower station operation and maintenance based on mixed reality, solving the technical problem of too low efficiency of relying on manual inspections in the prior art, and achieving the technical effect of improving the inspection efficiency.

[0005] In a first aspect, the present invention provides a method for hydropower station operation and maintenance based on mixed reality, the method comprising:

[0006] Obtain a historical operation data set of a target hydropower station in a historical period, wherein the historical operation data set includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit device operation parameters and unit device performance parameters;

[0007] Based on the historical operation data set of the target hydropower station, train a neural network model to be trained to obtain a unit device fault prediction neural network model, and the unit device fault prediction neural network model is used to predict the fault probability of each unit device of the target hydropower station;

[0008] Obtain the real-time operation data set of the target hydropower station, and determine the fault probability of each unit device of the target hydropower station at a target time node based on the unit device fault prediction neural network model;

[0009] Determine a first mixed reality inspection path according to the fault probability of each unit device and the core degree of each unit device;

[0010] Determine the second path of automated inspection according to the failure probability of each unit device, the core degree of each unit device, and the distance parameter of each unit device;

[0011] Send the first path of mixed reality inspection to the virtual reality device, and send the second path of automated inspection to the automated inspection device, and they are jointly used for inspecting the target hydropower station.

[0012] Furthermore, determine the first path of mixed reality inspection according to the failure probability of each unit device and the core degree of each unit device, including:

[0013] Determine the inspection urgency score of the unit device according to the failure probability of each unit device and the core degree of each unit device;

[0014] Sort several inspection urgency scores in descending order, and connect each unit device in sequence according to the sorting order to obtain the first path of mixed reality inspection.

[0015] Furthermore, determine the inspection urgency score of the unit device according to the failure probability of each unit device and the core degree of each unit device, including:

[0016]

[0017] Among them, H i is the inspection urgency score of the i-th unit device, α i is the failure probability of the i-th unit device, e is the base of the exponential function, and core i is the core degree of the i-th unit device.

[0018] Furthermore, determine the second path of automated inspection according to the failure probability of each unit device, the core degree of each unit device, and the distance parameter of each unit device, including:

[0019] Determine the maximum distance between the automated inspection device and several unit devices;

[0020] According to the maximum distance and the distance between the automated inspection device and the unit device, determine the distance parameter of the unit device;

[0021] According to the failure probability of the unit device, the core degree of the unit device, and the distance parameter of the unit device, determine the inspection convenience score of the unit device;

[0022] Sort several inspection convenience scores in descending order, and connect each unit device in sequence according to the sorting order to obtain the second path of automated inspection.

[0023] Further, according to the failure probability of the unit equipment, the core degree of the unit equipment, and the distance parameter of the unit equipment, determine the inspection convenience score of the unit equipment, including:

[0024]

[0025] Among them, B i is the inspection convenience score of the i-th unit equipment, α i is the failure probability of the i-th unit equipment, e is the base of the exponential function, core i is the core degree of the i-th unit equipment, l max is the maximum distance between the automated inspection equipment and several unit equipments, l i is the distance between the i-th unit equipment and the automated inspection equipment.

[0026] Further, based on the historical operation data set of the target hydropower station, train the neural network model to be trained to obtain a neural network model for predicting unit equipment failures, including:

[0027] Input the historical operation data set of the target hydropower station into the neural network model to be trained for training, and obtain the predicted failure probability corresponding to each unit equipment;

[0028] In the historical operation data set of the target hydropower station, determine the true failure probability corresponding to the unit equipment;

[0029] According to the predicted failure probability of the unit equipment and the corresponding true failure probability, train the neural network model to be trained. When the preset training requirements are met, use the neural network model to be trained as the neural network model for predicting unit equipment failures.

[0030] Further, the loss function of the neural network model to be trained includes:

[0031]

[0032] Among them, M is the loss function, N is the number of unit equipments, y i is the true failure probability of the i-th unit equipment, p i is the predicted failure probability of the i-th unit equipment, ln is the logarithmic function with base 10, θ is the regularization coefficient, and U is the trainable parameter of the neural network model to be trained.

[0033] In the second aspect, the present invention provides a hydropower station operation and maintenance device based on mixed reality. The device includes:

[0034] An acquisition module, configured to acquire a historical operation dataset of a target hydropower station within a historical period, where the historical operation dataset includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit equipment operation parameters and unit equipment performance parameters;

[0035] A training module, configured to train a neural network model to be trained based on the historical operation dataset of the target hydropower station to obtain a unit equipment fault prediction neural network model, where the unit equipment fault prediction neural network model is used to predict the fault probability of each unit equipment of the target hydropower station;

[0036] A prediction module, configured to acquire a real-time operation dataset of the target hydropower station and determine the fault probability of each unit equipment of the target hydropower station at a target time node based on the unit equipment fault prediction neural network model;

[0037] A first path module, configured to determine a first mixed reality inspection path according to the fault probability of each unit equipment and the core degree of each unit equipment;

[0038] A second path module, configured to determine a second automated inspection path according to the fault probability of each unit equipment, the core degree of each unit equipment, and the distance parameter of each unit equipment;

[0039] An inspection module, configured to send the first mixed reality inspection path to a virtual reality device and send the second automated inspection path to an automated inspection device, and they are jointly used to inspect the target hydropower station.

[0040] In a third aspect, the present invention provides an electronic device, including:

[0041] A processor;

[0042] A memory for storing executable instructions of the processor;

[0043] Wherein, the processor is configured to execute to implement the hydropower station operation and maintenance method based on mixed reality provided in the first aspect.

[0044] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the electronic device, enabling the electronic device to execute and implement the hydropower station operation and maintenance method based on mixed reality provided in the first aspect.

[0045] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0046] By determining the first mixed reality inspection path and the second automated inspection path, the present invention can combine virtual reality technology and unmanned inspection technology to jointly complete the inspection of the target hydropower station.

[0047] When determining the first inspection path, the advantages of virtual reality technology are considered, the influence of the actual distance is ignored, and the paths are sorted according to the importance of each unit, which can improve the efficiency of equipment inspection.

[0048] When determining the second automated inspection path, not only the importance of the unit equipment is considered, but also the distance influence is taken into account, making the second automated inspection path more reasonable and improving the inspection efficiency.

[0049] The loss function provided by the present invention combines cross-entropy loss and regularization, making the loss function not only focus on the fitting degree of the model to the training data (through cross-entropy loss), but also take into account the complexity of the model (through regularization). Regularization helps to reduce the variance of the model, making the model not overly dependent on the specific features of the training set, thereby improving the performance on new data. Brief Description of the Drawings

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0051] Figure 1 It is a schematic flow chart of the hydropower station operation and maintenance method based on mixed reality provided by the present invention;

[0052] Figure 2 It is a schematic structural diagram of the hydropower station operation and maintenance device based on mixed reality provided by the present invention;

[0053] Figure 3 It is a schematic structural diagram of an electronic device provided by the present invention. Detailed Embodiments

[0054] By providing a hydropower station operation and maintenance method based on mixed reality, the embodiments of the present invention solve the technical problem of low inspection efficiency of hydropower station unit equipment in the prior art.

[0055] The technical solution of the present invention to solve the above technical problem is generally as follows:

[0056] A method for operation and maintenance of a hydropower station based on mixed reality, the method includes: obtaining a historical operation data set of a target hydropower station within a historical period, where the historical operation data set includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit equipment operation parameters and unit equipment performance parameters; training a neural network model to be trained based on the historical operation data set of the target hydropower station to obtain a unit equipment fault prediction neural network model, and the unit equipment fault prediction neural network model is used to predict the fault probability of each unit equipment of the target hydropower station; obtaining a real-time operation data set of the target hydropower station, and determining the fault probability of each unit equipment of the target hydropower station at a target time node based on the unit equipment fault prediction neural network model; determining a first path for mixed reality inspection according to the fault probability of each unit equipment and the core degree of each unit equipment; determining a second path for automated inspection according to the fault probability of each unit equipment, the core degree of each unit equipment, and the distance parameter of each unit equipment; sending the first path for mixed reality inspection to a virtual reality device, and sending the second path for automated inspection to an automated inspection device, and jointly using them to inspect the target hydropower station.

[0057] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0058] First, it should be noted that the term "and / or" appearing in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the front and back associated objects.

[0059] The present invention provides a Figure 1 hydropower station operation and maintenance method based on mixed reality as shown in

[0060] Step S11: Obtain a historical operation data set of a target hydropower station within a historical period, where the historical operation data set includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit equipment operation parameters and unit equipment performance parameters.

[0061] The target hydropower station refers to the hydropower station to be inspected. The historical operation data set within the historical period refers to the operation data of the target hydropower station in the past time.

[0062] The water flow data refers to the data of the water volume flowing through the hydropower station and the water level data of the reservoir where the hydropower station is located. The water flow data is one of the important parameters for determining the rotation speed of the water turbine and the output power of the generator, and is important for the unit equipment in the target hydropower station.

[0063] The operating status data of the unit includes the operating parameters of the unit equipment and the performance parameters of the unit equipment.

[0064] The operating parameters of the unit equipment may include the operation indicators of each generator set, such as rotational speed, temperature, and pressure, etc. The above parameters can be used to monitor the real-time working status of the equipment and are the basis for judging whether the equipment is operating normally.

[0065] The performance parameters of the unit equipment may include data such as the working efficiency, reliability, and service life of the generator set. Such as power generation efficiency (the ratio of the energy of unit water flow converted into electric energy) and failure frequency, etc. Through the above data, potential problems can be identified and preventive measures can be taken to reduce downtime and maintenance costs.

[0066] In addition to the above data directly related to the operation of the power station, the influence of the external environment can also be added. The meteorological and geological environment data may include meteorological data such as rainfall, temperature, and wind speed, as well as geological data such as seismic activity and foundation stability. Changes in external conditions may affect the safety and operation efficiency of the hydropower station. For example, extreme weather may cause sudden changes in water flow, while geological instability may threaten the safety of the infrastructure.

[0067] Step S12, based on the historical operation data set of the target hydropower station, train the neural network model to be trained to obtain a neural network model for predicting equipment failures of the unit. The neural network model for predicting equipment failures of the unit is used to predict the failure probability of each unit equipment of the target hydropower station.

[0068] The historical operation data set can be divided into a training set, a test set, and a validation set. Among them, the proportion of each set can be determined according to the actual situation and is not limited here.

[0069] Based on the historical operation data set of the target hydropower station, train the neural network model to be trained to obtain a neural network model for predicting equipment failures of the unit, including: inputting the historical operation data set of the target hydropower station into the neural network model to be trained for training to obtain the predicted failure probability corresponding to each unit equipment; determining the true failure probability corresponding to the unit equipment in the historical operation data set of the target hydropower station; training the neural network model to be trained according to the predicted failure probability and the corresponding true failure probability of the unit equipment. When the preset training requirements are met, the neural network model to be trained is used as the neural network model for predicting equipment failures of the unit.

[0070] Specifically, the historical operation dataset can be input into the preset neural network model to be trained. Based on the data in the historical operation dataset, the failure probability of each unit device in the target hydropower station can be predicted. The prediction of the failure probability can also refer to the patent document (CN202310316684.5). The preset training requirements can include the number of training times and the passing rate of the results, etc., which are not limited here.

[0071] In addition, the present invention also provides a loss function for the neural network model to be trained, including:

[0072]

[0073] where M is the loss function, N is the number of unit devices, y i is the true failure probability of the i-th unit device, and p i is the predicted failure probability of the i-th unit device. ln is the logarithmic function with base 10, θ is the regularization coefficient, and U is the trainable parameter of the neural network model to be trained.

[0074] The loss function provided by the present invention combines cross-entropy loss and regularization, so that the loss function not only focuses on the fitting degree of the model to the training data (through cross-entropy loss), but also takes into account the complexity of the model (through regularization). Regularization helps to reduce the variance of the model, so that the model does not overly rely on the specific features of the training set, thereby improving the performance on new data.

[0075] Step S13: Obtain the real-time operation dataset of the target hydropower station, and determine the failure probability of each unit device of the target hydropower station at the target time node based on the unit device failure prediction neural network model.

[0076] Based on the above training, the unit device failure prediction neural network model is obtained. Take the real-time operation dataset of the target hydropower station and input the real-time operation dataset into the unit device failure prediction neural network model to predict the failure probability of each unit device of the target hydropower station at a future time node. After obtaining the failure probabilities of several unit devices of the target hydropower station at a future time node in sequence, execute Step S14 and Step S15.

[0077] Step S14: Determine the first path of mixed reality inspection according to the failure probability of each unit device and the core degree of each unit device.

[0078] According to the failure probability of each unit device and the core degree of each unit device, determine the inspection urgency score of the unit device; sort the several inspection urgency scores in descending order, and connect each unit device in series according to the sorting order to obtain the first path of mixed reality inspection.

[0079] The failure probability refers to the likelihood of each unit device failing at a certain future time point, which can be determined by the method provided in the present invention. The core degree refers to the importance of the unit device in the overall system. Once a device with a high core degree fails, it may cause greater losses or more serious impacts.

[0080] After obtaining the inspection urgency scores of all unit devices, the devices are sorted in descending order according to these scores. The purpose is to prioritize the handling of those devices that most need attention in order to reduce potential risks and losses.

[0081] It can be understood that the first path of mixed reality inspection is the inspection path provided for relevant staff using virtual reality devices. Using virtual reality devices can ignore the influence of real - world distances. Therefore, in the present invention, the importance of unit devices is reflected through the inspection urgency scores, and the inspection path is constructed based on the importance of unit devices, giving full play to the advantages of virtual reality technology.

[0082] According to the failure probability of each unit device and the core degree of each unit device, determine the inspection urgency score of the unit device, including:

[0083]

[0084] where H i is the inspection urgency score of the i - th unit device, α i is the failure probability of the i - th unit device, e is the base of the exponential function, and core i is the core degree of the i - th unit device.

[0085] It should be noted that the core degree can be determined according to relevant historical experience and is not restricted here.

[0086] By using the exponential function, the influence of the core degree on the inspection urgency score is non - linearly amplified. That is, even if the failure probabilities of two devices are the same, if one device has a higher core degree, its inspection urgency score will be significantly higher than that of the other device. This is suitable for key devices (such as the main generator in a hydropower station) that will cause serious consequences once they fail. Devices with a high core degree usually play a crucial role in the system, so they require more priority attention and maintenance.

[0087] By sorting the devices according to the calculated inspection urgency scores, those devices that most need attention can be prioritized, ensuring the most effective use of limited human and material resources. It can timely detect and solve problems of key devices, which helps to reduce unexpected downtime and improve the reliability and stability of the entire hydropower station system.

[0088] Step S15: Determine the second automated inspection path according to the failure probability, core degree, and distance parameter of each unit device.

[0089] Determine the maximum distance between the automated inspection device and several unit devices; according to the maximum distance and the distance between the automated inspection device and the unit device, determine the distance parameter of the unit device; according to the failure probability, core degree, and distance parameter of the unit device, determine the inspection convenience score of the unit device; perform a descending order sorting on several inspection convenience scores, and connect each unit device in sequence according to the sorting order to obtain the second automated inspection path.

[0090] The automated inspection device can be an inspection robot or an inspection drone, etc. The automated inspection device is generally fixed and parked in a fixed area. The distance between the automated inspection device and each unit device can be obtained in sequence, and several distances can be compared to obtain the maximum distance.

[0091] It can be understood that the second automated inspection path is the inspection route of the automated inspection device. The automated inspection device needs to move to the positions of each unit device when performing tasks. By determining the distance parameter of each device and combining the failure probability and core degree, an optimal inspection path can be planned, thereby reducing the movement time and energy consumption of the robot. Devices with relatively short distances and high failure probabilities can be inspected preferentially, and key tasks can be completed in the shortest time.

[0092] Determining the inspection convenience score of the unit device includes:

[0093]

[0094] Among them, B i is the inspection convenience score of the i-th unit device, α i is the failure probability of the i-th unit device, e is the base of the exponential function, core i is the core degree of the i-th unit device, l max is the maximum distance between the automated inspection device and several unit devices, l i is the distance between the i-th unit device and the automated inspection device.

[0095] Step S16: Send the first mixed reality inspection path to the virtual reality device, and send the second automated inspection path to the automated inspection device, and use them together to inspect the target hydropower station.

[0096] After sending the first path of mixed reality inspection to the virtual reality device and the second path of automated inspection to the automated inspection device, the inspection of the target hydropower station can begin.

[0097] In summary, the present invention provides a method for operation and maintenance of a hydropower station based on mixed reality. The method includes: obtaining a historical operation data set of the target hydropower station in a historical period, where the historical operation data set includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit equipment operation parameters and unit equipment performance parameters; training a neural network model to be trained based on the historical operation data set of the target hydropower station to obtain a unit equipment fault prediction neural network model, where the unit equipment fault prediction neural network model is used to predict the fault probability of each unit equipment of the target hydropower station; obtaining the real-time operation data set of the target hydropower station and determining the fault probability of each unit equipment of the target hydropower station at the target time node based on the unit equipment fault prediction neural network model; determining the first path of mixed reality inspection according to the fault probability of each unit equipment and the core degree of each unit equipment; determining the second path of automated inspection according to the fault probability of each unit equipment, the core degree of each unit equipment, and the distance parameter of each unit equipment; sending the first path of mixed reality inspection to the virtual reality device and sending the second path of automated inspection to the automated inspection device, and jointly using them to inspect the target hydropower station. By determining the first path of mixed reality inspection and the second path of automated inspection, the present invention can combine virtual reality technology and unmanned inspection technology to jointly complete the inspection of the target hydropower station. When determining the first path of inspection, the advantages of virtual reality technology are considered, the influence of the actual distance is ignored, and the paths are sorted according to the importance of each unit, so that the equipment inspection can be completed. When determining the second path of automated inspection, not only the importance of the unit equipment is considered, but also the distance influence is considered, making the second path of automated inspection more reasonable. The loss function provided by the present invention combines cross-entropy loss and regularization, so that the loss function not only focuses on the fitting degree of the model to the training data (through cross-entropy loss), but also takes into account the complexity of the model (through regularization). Regularization helps to reduce the variance of the model, so that the model does not overly rely on the specific features of the training set, thereby improving the performance on new data.

[0098] Based on the same inventive concept, the present invention also provides a Figure 2 hydropower station operation and maintenance device based on mixed reality as shown in

[0099] An acquisition module 21, configured to acquire a historical operation data set of the target hydropower station in a historical period, where the historical operation data set includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit equipment operation parameters and unit equipment performance parameters;

[0100] A training module 22, configured to train a neural network model to be trained based on the historical operation dataset of the target hydropower station, so as to obtain a neural network model for predicting the faults of unit equipment, where the neural network model for predicting the faults of unit equipment is used to predict the fault probabilities of the unit equipment of the target hydropower station;

[0101] A prediction module 23, configured to obtain the real-time operation dataset of the target hydropower station, and determine the fault probabilities of the unit equipment of the target hydropower station at the target time node based on the neural network model for predicting the faults of unit equipment;

[0102] A first path module 24, configured to determine the first mixed reality inspection path according to the fault probabilities of the unit equipment and the core degrees of the unit equipment;

[0103] A second path module 25, configured to determine the second automated inspection path according to the fault probabilities of the unit equipment, the core degrees of the unit equipment, and the distance parameters of the unit equipment;

[0104] An inspection module 26, configured to send the first mixed reality inspection path to the virtual reality device, and send the second automated inspection path to the automated inspection device, and they are jointly used to inspect the target hydropower station.

[0105] Based on the same inventive concept, the present invention also provides an electronic device as shown in Figure 3 which includes:

[0106] A processor 31;

[0107] A memory 32 for storing executable instructions of the processor 31;

[0108] Wherein, the processor 31 is configured to execute to implement the hydropower station operation and maintenance method based on mixed reality provided as described above.

[0109] Based on the same inventive concept, the present invention also provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by the processor 31 of the electronic device, the electronic device can execute to implement the hydropower station operation and maintenance method based on mixed reality provided as described above.

[0110] Since the electronic device introduced in this embodiment is the one used to implement the information processing method in the embodiments of the present invention, based on the information processing method introduced in the embodiments of the present invention, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the detailed introduction of how this electronic device implements the method in the embodiments of the present invention will not be provided here. As long as the electronic device used by those skilled in the art to implement the information processing method in the embodiments of the present invention falls within the scope of protection of the present invention.

[0111] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0112] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0113] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide means for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1Steps of the functions specified in one or more boxes.

[0115] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0116] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A hydropower station operation and maintenance method based on mixed reality, characterized in that: The method comprises: Acquire a historical operation data set of the target hydropower station in a historical period, wherein the historical operation data set includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit equipment operation parameters and unit equipment performance parameters; Based on the historical operation data set of the target hydropower station, the neural network model to be trained is trained to obtain a unit equipment failure prediction neural network model, wherein the unit equipment failure prediction neural network model is used to predict the failure probability of each unit equipment of the target hydropower station; Acquire a real-time operating data set of the target hydropower station, and determine the failure probability of each unit equipment of the target hydropower station at a target time node based on the unit equipment failure prediction neural network model; Determine the first mixed reality inspection path based on the failure probability of each unit and the core degree of each unit; Determine the second automated inspection path according to the failure probability of each unit equipment, the core degree of each unit equipment and the distance parameter of each unit equipment; The mixed reality inspection first path is sent to a virtual reality device, and the automated inspection second path is sent to an automated inspection device, and they are used together to inspect the target hydropower station.

2. The hydropower station operation and maintenance method based on mixed reality according to claim 1, characterized in that: According to the failure probability of each unit and the core degree of each unit, the first mixed reality inspection path is determined, including: Determine the inspection urgency score of each unit equipment according to the failure probability of each unit equipment and the core degree of each unit equipment; A plurality of inspection urgency scores are sorted in descending order, and the equipment of each unit is connected in series in sequence according to the sorting order to obtain the first mixed reality inspection path.

3. The hydropower station operation and maintenance method based on mixed reality according to claim 2, characterized in that: According to the failure probability of each unit and the core degree of each unit, the inspection urgency score of the unit is determined, including: Among them, H i is the inspection urgency score of the i-th unit equipment, α i is the failure probability of the i-th unit equipment, e is the base of the exponential function, core i is the core degree of the equipment of the ith unit.

4. The hydropower station operation and maintenance method based on mixed reality according to claim 1, characterized in that: According to the failure probability of each unit equipment, the core degree of each unit equipment and the distance parameters of each unit equipment, the second automated inspection path is determined, including: Determine the maximum distance between the automated inspection equipment and a plurality of unit equipment; Determine the distance parameter of the unit equipment according to the maximum distance and the distance between the automated inspection equipment and the unit equipment; Determine the inspection convenience score of the unit equipment according to the failure probability of the unit equipment, the core degree of the unit equipment and the distance parameter of the unit equipment; The inspection convenience scores are sorted in descending order, and the equipment of each unit is connected in series in sequence according to the sorting order to obtain the second automated inspection path.

5. The hydropower station operation and maintenance method based on mixed reality according to claim 4, characterized in that: According to the failure probability of the unit equipment, the core degree of the unit equipment and the distance parameter of the unit equipment, the inspection convenience score of the unit equipment is determined, including: Among them, B i is the inspection convenience score of the i-th unit equipment, α i is the failure probability of the i-th unit equipment, e is the base of the exponential function, core i is the core degree of the i-th unit equipment, l max is the maximum distance between the automated inspection equipment and several units of equipment, l i is the distance between the i-th unit equipment and the automated inspection equipment.

6. The hydropower station operation and maintenance method based on mixed reality according to claim 1, characterized in that: Based on the historical operation data set of the target hydropower station, the neural network model to be trained is trained to obtain a unit equipment fault prediction neural network model, including: Inputting the historical operation data set of the target hydropower station into the neural network model to be trained to obtain the predicted failure probability corresponding to each unit equipment; Determining the actual failure probability corresponding to the unit equipment in the historical operation data set of the target hydropower station; The neural network model to be trained is trained according to the predicted failure probability of the unit equipment and the corresponding actual failure probability. When the preset training requirements are met, the neural network model to be trained is used as the neural network model for predicting failures of the unit equipment.

7. The hydropower station operation and maintenance method based on mixed reality according to claim 6, characterized in that: The loss function of the neural network model to be trained includes: Among them, M is the loss function, N is the number of equipment in the unit, and y i is the actual failure probability of the i-th unit equipment, p i is the predicted failure probability of the i-th unit equipment, ln is the logarithmic function with a base of 10, θ is the regularization coefficient, and U is the trainable parameter of the neural network model to be trained.

8. The operation and maintenance device of a hydropower station based on mixed reality is characterized by: The device comprises: An acquisition module is used to acquire a historical operation data set of a target hydropower station in a historical period, wherein the historical operation data set includes water flow data, unit operation status data, and meteorological and geological environment data, and the unit operation status data includes unit equipment operation parameters and unit equipment performance parameters; A training module, used for training the neural network model to be trained based on the historical operation data set of the target hydropower station to obtain a unit equipment failure prediction neural network model, wherein the unit equipment failure prediction neural network model is used to predict the failure probability of each unit equipment of the target hydropower station; A prediction module, used to obtain a real-time operation data set of the target hydropower station, and determine the failure probability of each unit equipment of the target hydropower station at a target time node based on the unit equipment failure prediction neural network model; A first path module is used to determine a first mixed reality inspection path according to the failure probability of each unit equipment and the core degree of each unit equipment; The second path module is used to determine the second automated inspection path according to the failure probability of each unit equipment, the core degree of each unit equipment and the distance parameter of each unit equipment; The inspection module is used to send the mixed reality inspection first path to the virtual reality device, and send the automated inspection second path to the automated inspection device, and both are used to inspect the target hydropower station.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; Wherein, the processor is configured to execute to implement the hydropower station operation and maintenance method based on mixed reality as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is enabled to implement the hydropower station operation and maintenance method based on mixed reality as described in any one of claims 1 to 7.

Images