Hydropower station operation and maintenance methods, devices, equipment, and media based on mixed reality

Abstract

This invention discloses a method, apparatus, equipment, and medium for the operation and maintenance of hydropower stations based on mixed reality, including: acquiring historical operation datasets of the target hydropower station within a historical period; obtaining a neural network model for predicting unit equipment failures; determining the failure probability of each unit of equipment in the target hydropower station at a target time node based on the neural network model; determining a first mixed reality inspection path based on the failure probability and the criticality of each unit of equipment; determining a second automated inspection path; sending the first mixed reality inspection path to a virtual reality device and the second automated inspection path to an automated inspection device, which are then used together to inspect the target hydropower station. This invention belongs to the field of hydropower station equipment inspection. This invention combines virtual reality technology with unmanned inspection equipment technology, resulting in higher efficiency in unit equipment inspection.

Description

Technical Field

[0001] This invention relates to the field of hydropower station equipment inspection, and in particular to hydropower station operation and maintenance methods, devices, equipment and media based on mixed reality. Background Technology

[0002] A hydroelectric power station is a facility that uses the energy of flowing water to generate electricity. Hydroelectric power stations are typically built near rivers or reservoirs, utilizing the kinetic energy (such as the flow of river water) or potential energy (such as the water level difference in a reservoir). Their main components include turbines, generators, transformers, and switchyards.

[0003] Hydropower stations contain numerous pieces of equipment, and potential equipment hazards can threaten the safe and stable operation of the hydropower plant. Therefore, regular inspections are necessary to conduct safety checks on the equipment within the hydropower plant. Currently, the main inspection method relies on manual labor, which may have problems such as untimely inspections, high safety risks, large manpower requirements, and the inability to scientifically analyze and predict equipment performance data. This hinders the timely detection and elimination of potential safety hazards in the hydropower station, thus affecting its safe and stable operation. Therefore, there is an urgent need to propose a better inspection method. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for the operation and maintenance of hydropower stations based on mixed reality, which solves the technical problem of low efficiency in existing technologies that rely on manual inspections, and achieves the technical effect of improving inspection efficiency.

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

[0006] Obtain the historical operation dataset of the target hydropower station within a historical period. The historical operation dataset includes water flow data, unit operation status data, and meteorological and geological environmental data. The unit operation status data includes unit equipment operation parameters and unit equipment performance parameters.

[0007] Based on the historical operation dataset of the target hydropower station, the neural network model to be trained is trained to obtain the unit equipment fault prediction neural network model. The unit equipment fault prediction neural network model is used to predict the fault probability of each unit equipment of the target hydropower station.

[0008] Obtain the real-time operation dataset of the target hydropower station, and determine the failure probability of each unit of the target hydropower station at the target time node based on the unit equipment failure prediction neural network model;

[0009] Based on the failure probability of each unit's equipment and the criticality of each unit's equipment, determine the first path for mixed reality inspection;

[0010] The second path for automated inspection is determined based on the failure probability of each unit's equipment, the criticality of each unit's equipment, and the distance parameters of each unit's equipment.

[0011] The first path of mixed reality inspection is sent to the virtual reality device, and the second path of automated inspection is sent to the automated inspection device, and they are used together to inspect the target hydropower station.

[0012] Furthermore, based on the failure probability of each unit's equipment and the criticality of each unit's equipment, the first path for mixed reality inspection is determined, including:

[0013] The urgency score for the inspection of each unit's equipment is determined based on the failure probability of each unit's equipment and the criticality of each unit's equipment.

[0014] The inspection urgency scores are sorted in descending order, and the equipment of each unit is connected in series according to the sorting order to obtain the first path of mixed reality inspection.

[0015] Furthermore, based on the failure probability of each unit's equipment and the criticality of each unit's equipment, the urgency score for the unit's equipment inspection is determined, including:

[0016]

[0017] Among them, H i Score the urgency of the inspection of the i-th unit equipment, α i Let be the failure probability of the i-th unit equipment, e be the base of the exponential function, and core be the value of the failure probability. i The core level of the i-th unit equipment.

[0018] Furthermore, based on the failure probability of each unit's equipment, the criticality of each unit's equipment, and the distance parameters between each unit's equipment, a second path for automated inspection is determined, including:

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

[0020] Based on the maximum distance and the distance between the automated inspection equipment and the unit equipment, determine the distance parameters of the unit equipment;

[0021] The inspection convenience score of the unit equipment is determined based on the failure probability of the unit equipment, the core status of the unit equipment, and the distance parameters of the unit equipment.

[0022] The inspection convenience scores are sorted in descending order, and the equipment of each unit is connected in series according to the sorting order to obtain the second path of automated inspection.

[0023] Furthermore, based on the failure probability of the unit equipment, the criticality of the unit equipment, and the distance parameters of the unit equipment, a convenient inspection score for the unit equipment is determined, including:

[0024]

[0025] Among them, B i Score the ease of inspection for the i-th unit equipment, α i Let be the failure probability of the i-th unit equipment, e be the base of the exponential function, and core be the value of the failure probability. i For the core level of the i-th unit equipment, l max The maximum distance between the automated inspection equipment and several unit equipment, l i Let be the distance between the i-th unit equipment and the automated inspection equipment.

[0026] Furthermore, based on the historical operation dataset of the target hydropower station, the neural network model to be trained is trained to obtain a neural network model for predicting unit equipment faults, including:

[0027] The historical operation dataset of the target hydropower station is input into the neural network model to be trained to obtain the predicted failure probability of each unit equipment.

[0028] Determine the actual failure probability of the generating units and equipment from the historical operation dataset of the target hydropower station;

[0029] Based on the predicted failure probability and the corresponding actual failure probability of the unit equipment, the neural network model to be trained is trained. When the preset training requirements are met, the neural network model to be trained is used as the unit equipment failure prediction neural network model.

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

[0031]

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

[0033] Secondly, the present invention provides a hydropower station operation and maintenance device based on mixed reality, the device comprising:

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

[0035] The training module is used to train the neural network model to be trained based on the historical operation dataset of the target hydropower station, so as to obtain the unit equipment fault prediction neural network model. 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] The prediction module is used to acquire the real-time operation dataset of the target hydropower station and determine the failure probability of each unit of the target hydropower station at the target time node based on the unit equipment failure prediction neural network model.

[0037] The first path module is used to determine the first path for mixed reality inspection based on the failure probability of each unit's equipment and the criticality of each unit's equipment.

[0038] The second path module is used to determine the second path for automated inspection based on the failure probability of each unit's equipment, the criticality of each unit's equipment, and the distance parameters of each unit's equipment.

[0039] The inspection module is used to send the first mixed reality inspection path to the virtual reality device and the second automated inspection path to the automated inspection device, and together they are used to inspect the target hydropower station.

[0040] Thirdly, the present invention provides an electronic device, comprising:

[0041] processor;

[0042] Memory used to store processor-executable instructions;

[0043] The processor is configured to execute a mixed reality-based hydropower station operation and maintenance method as provided in the first aspect.

[0044] Fourthly, the present invention provides a non-transitory computer-readable storage medium that, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform the mixed reality-based hydropower station operation and maintenance method provided in the first aspect.

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

[0046] This invention, by determining a first path for mixed reality inspection and a second path for automated inspection, can combine virtual reality technology and unmanned inspection technology to complete the inspection of a target hydropower station.

[0047] When determining the first inspection path, the advantages of virtual reality technology were taken into account, while the influence of actual distance was ignored. The paths were sorted according to the importance of each unit, which can improve the efficiency of equipment inspection.

[0048] When determining the second path for automated inspection, not only the importance of the unit equipment was considered, but also the impact of distance, making the second path for automated inspection more reasonable and improving inspection efficiency.

[0049] The loss function provided by this invention combines cross-entropy loss and regularization, ensuring that the loss function not only focuses on the model's fit to the training data (through cross-entropy loss) but also considers the model's complexity (through regularization). Regularization helps reduce the model's variance, preventing the model from becoming overly reliant on the specific features of the training set, thereby improving performance on new data. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart illustrating the hydropower station operation and maintenance method based on mixed reality provided by this invention;

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

[0053] Figure 3 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0054] This invention provides a mixed reality-based hydropower station operation and maintenance method, which solves the technical problem of low inspection efficiency of hydropower station unit equipment in the prior art.

[0055] The technical solution of this invention is to solve the above-mentioned technical problems, and the overall idea is as follows:

[0056] A mixed reality-based hydropower station operation and maintenance method includes: acquiring historical operation datasets of the target hydropower station within a historical period, wherein the historical operation datasets include water flow data, unit operating status data, and meteorological and geological environmental data, and the unit operating status data includes unit equipment operating parameters and unit equipment performance parameters; training a neural network model to be trained based on the historical operation datasets of the target hydropower station to obtain a unit equipment fault prediction neural network model, which is used to predict the fault probability of each unit equipment of the target hydropower station; acquiring real-time operation datasets 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 mixed reality inspection path based on the fault probability and criticality of each unit equipment; determining a second automated inspection path based on the fault probability, criticality, and distance parameters of each unit equipment; sending the first mixed reality inspection path to a virtual reality device and the second automated inspection path to an automated inspection device, which are then used together to inspect the target hydropower station.

[0057] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0058] First, it should be clarified that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0059] This invention provides, for example Figure 1 The hybrid reality-based hydropower station operation and maintenance method shown includes steps S11-S16:

[0060] Step S11: Obtain the historical operation dataset of the target hydropower station within the historical period. The historical operation dataset includes water flow data, unit operation status data, and meteorological and geological environment data. 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 dataset within the historical period refers to the operation data of the target hydropower station in the past.

[0062] Water flow data refers to the amount of water flowing through a hydropower station and the water level in the reservoir where the station is located. Water flow data determines the turbine's rotational speed and the generator's output power, making it a crucial parameter for the generating units within the target hydropower station.

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

[0064] The operating parameters of the generator set equipment can include the operating indicators of each generator set, such as speed, temperature and pressure. These 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 generating unit can include data on the generator set's operating efficiency, reliability, and service life. For example, this includes power generation efficiency (the proportion of water flow energy converted into electrical energy) and failure frequency. This data allows for the identification of potential problems and the implementation of preventative measures to reduce downtime and maintenance costs.

[0066] In addition to the data directly related to power plant operation mentioned above, the impact of the external environment can also be considered. Meteorological and geological environmental data can 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 operational efficiency of hydropower stations. For example, extreme weather may cause sudden changes in water flow, while geological instability may threaten the safety of infrastructure.

[0067] Step S12: Based on the historical operation dataset of the target hydropower station, train the neural network model to be trained to obtain the unit equipment fault prediction neural network model. The unit equipment fault prediction neural network model is used to predict the fault probability of each unit equipment of the target hydropower station.

[0068] The historical dataset can be divided into a training set, a test set, and a validation set. The proportion of each set can be determined according to the actual situation, and there is no restriction here.

[0069] Based on the historical operation dataset of the target hydropower station, a neural network model to be trained is obtained to obtain a neural network model for predicting unit equipment failures. This includes: inputting the historical operation dataset of the target hydropower station into the neural network model to be trained to obtain the predicted failure probability of each unit equipment; determining the actual failure probability of the unit equipment in the historical operation dataset of the target hydropower station; training the neural network model to be trained based on the predicted failure probability and the corresponding actual failure probability of the unit equipment; and when the preset training requirements are met, using the neural network model to be trained as the neural network model for predicting unit equipment failures.

[0070] Specifically, historical operational datasets can be input into a pre-built neural network model to be trained. Based on the data in the historical operational dataset, the failure probability of each unit in the target hydropower station can be predicted. For more information on failure probability prediction, please refer to the patent document (CN202310316684.5). Pre-set training requirements may include the number of training iterations and the pass rate of the results, etc., which are not limited here.

[0071] In addition, this 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 equipment, and y i Let p be the actual failure probability of the i-th unit equipment. i Let be the predicted failure probability of the i-th unit equipment, ln be the logarithmic function with base 10, θ be the regularization coefficient, and U be the trainable parameters of the neural network model to be trained.

[0074] The loss function provided by this invention combines cross-entropy loss and regularization, ensuring that the loss function not only focuses on the model's fit to the training data (through cross-entropy loss) but also considers the model's complexity (through regularization). Regularization helps reduce the model's variance, preventing the model from becoming overly reliant on the specific features of the training set, thereby improving 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 of the target hydropower station at the target time node based on the unit equipment failure prediction neural network model.

[0076] Based on the above training, a neural network model for predicting unit equipment failure is obtained. The real-time operation dataset of the target hydropower station is taken and input into the neural network model for predicting unit equipment failure, so as to predict the failure probability of each unit equipment of the target hydropower station at a certain time node in the future. After obtaining the failure probabilities of several units equipment of the target hydropower station at a certain time node in the future, steps S14 and S15 are executed.

[0077] Step S14: Determine the first path for mixed reality inspection based on the failure probability of each unit's equipment and the criticality of each unit's equipment.

[0078] Based on the failure probability of each unit's equipment and the criticality of each unit's equipment, the inspection urgency score of the unit's equipment is determined; several inspection urgency scores are sorted in descending order, and each unit's equipment is sequentially connected in the sorting order to obtain the first path of mixed reality inspection.

[0079] Failure probability refers to the likelihood that each unit of equipment will fail at a future point in time, and can be determined using the method provided in this invention. Criticality refers to the importance of the unit of equipment within the overall system. A failure of equipment with high criticality may lead to greater losses or more severe impacts.

[0080] After obtaining the inspection urgency scores for all unit equipment, the equipment is ranked from highest to lowest according to these scores. The aim is to prioritize the equipment that requires the most attention in order to reduce potential risks and losses.

[0081] It can be understood that the first path of mixed reality inspection is an inspection path provided for relevant personnel using virtual reality equipment. Using virtual reality equipment can ignore the influence of real distance. Therefore, in this invention, the importance of the unit equipment is reflected by the inspection urgency score, and the inspection path is constructed based on the importance of the unit equipment, giving full play to the advantages of virtual reality technology.

[0082] Based on the failure probability of each unit's equipment and the criticality of each unit's equipment, the urgency score for the unit's equipment inspection is determined, including:

[0083]

[0084] Among them, H i Score the urgency of the inspection of the i-th unit equipment, α i Let be the failure probability of the i-th unit equipment, e be the base of the exponential function, and core be the value of the failure probability. i The core level of the i-th unit equipment.

[0085] It should be noted that the level of core importance can be determined based on relevant historical experience, and no restrictions are imposed here.

[0086] By using an exponential function, the impact of coreness on inspection urgency scores is non-linearly amplified. This means that even if two devices have the same probability of failure, a device with higher coreness will have a significantly higher inspection urgency score than the other. This approach is suitable for critical equipment where a failure would have serious consequences (e.g., the main generator in a hydroelectric power station). Devices with high coreness typically play a vital role in the system and therefore require higher priority for attention and maintenance.

[0087] By ranking equipment based on the calculated inspection urgency score, priority can be given to addressing the most critical equipment, ensuring the most effective use of limited human and material resources. This allows for the timely identification and resolution of problems with key equipment, helping to reduce unexpected downtime and improve the reliability and stability of the entire hydropower station system.

[0088] Step S15: Determine the second path for automated inspection based on the failure probability of each unit's equipment, the criticality of each unit's equipment, and the distance parameters of each unit's equipment.

[0089] Determine the maximum distance between the automated inspection equipment and several unit equipment; based on the maximum distance and the distance between the automated inspection equipment and the unit equipment, determine the distance parameters of the unit equipment; based on the failure probability of the unit equipment, the core status of the unit equipment, and the distance parameters of the unit equipment, determine the inspection convenience score of the unit equipment; sort the several inspection convenience scores in descending order, and connect each unit equipment in sequence according to the sorting order to obtain the second path of automated inspection.

[0090] Automated inspection equipment can be inspection robots or inspection drones, etc. Automated inspection equipment is generally stationed in a fixed area. The distance between the automated inspection equipment and each piece of equipment in the unit can be obtained sequentially, and several distances can be compared to determine the maximum distance.

[0091] Understandably, the second path of automated inspection is the inspection route of the automated inspection equipment. When performing tasks, the automated inspection equipment needs to move to the locations of various equipment units. By determining the distance parameters of each piece of equipment and combining them with the probability of failure and its criticality, an optimal inspection path can be planned, thereby reducing the robot's movement time and energy consumption. Priority can be given to inspecting equipment that is closer and has a higher probability of failure, and critical tasks can be completed in the shortest possible time.

[0092] The ease of inspection of the unit's equipment is determined by the following criteria:

[0093]

[0094] Among them, B i Score the ease of inspection for the i-th unit equipment, α i Let be the failure probability of the i-th unit equipment, e be the base of the exponential function, and core be the value of the failure probability. i For the core level of the i-th unit equipment, l max The maximum distance between the automated inspection equipment and several unit equipment, l i Let be the distance between the i-th unit equipment and the automated inspection equipment.

[0095] Step S16: The first mixed reality inspection path is sent to the virtual reality device, and the second automated inspection path is sent to the automated inspection device, and they are used together to inspect the target hydropower station.

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

[0097] In summary, this invention provides a mixed reality-based hydropower station operation and maintenance method. The method includes: acquiring a historical operation dataset of the target hydropower station within a historical period, wherein the historical operation dataset includes water flow data, unit operation status data, and meteorological and geological environmental 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 dataset of the target hydropower station to obtain a unit equipment fault prediction neural network model, which is used to predict the fault probability of each unit equipment of the target hydropower station; acquiring a real-time operation dataset 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 mixed reality inspection path based on the fault probability of each unit equipment and the core status of each unit equipment; determining a second automated inspection path based on the fault probability of each unit equipment, the core status of each unit equipment, and the distance parameters of each unit equipment; sending the first mixed reality inspection path to a virtual reality device and the second automated inspection path to an automated inspection device, which are then used together to inspect the target hydropower station. This invention, by determining a first mixed reality inspection path and a second automated inspection path, combines virtual reality and unmanned inspection technologies to jointly inspect a target hydropower station. In determining the first inspection path, the advantages of virtual reality technology are considered, while the impact of actual distance is ignored. The path is prioritized based on the importance of each generating unit, enabling comprehensive equipment inspection. In determining the second automated inspection path, not only the importance of the generating units but also the impact of distance are considered, making the second automated inspection path more rational. The loss function provided by this invention combines cross-entropy loss and regularization, ensuring that the loss function not only focuses on the model's fit to the training data (through cross-entropy loss) but also considers the model's complexity (through regularization). Regularization helps reduce model variance, preventing the model from overly relying on specific features of the training set, thereby improving performance on new data.

[0098] Based on the same inventive concept, the present invention also provides, for example... Figure 2 The mixed reality-based hydropower station operation and maintenance device shown includes:

[0099] The acquisition module 21 is used to acquire the historical operation dataset of the target hydropower station within a historical period. The historical operation dataset includes water flow data, unit operation status data and meteorological and geological environment data. The unit operation status data includes unit equipment operation parameters and unit equipment performance parameters.

[0100] Training module 22 is used to train the neural network model to be trained based on the historical operation dataset of the target hydropower station, so as to obtain the unit equipment fault prediction neural network model. The unit equipment fault prediction neural network model is used to predict the fault probability of each unit equipment of the target hydropower station.

[0101] The prediction module 23 is used to acquire the real-time operation dataset of the target hydropower station and determine the failure probability of each unit of the target hydropower station at the target time node based on the unit equipment failure prediction neural network model.

[0102] The first path module 24 is used to determine the first path of mixed reality inspection based on the failure probability of each unit's equipment and the core nature of each unit's equipment.

[0103] The second path module 25 is used to determine the second path for automated inspection based on the failure probability of each unit's equipment, the criticality of each unit's equipment, and the distance parameters of each unit's equipment.

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

[0105] Based on the same inventive concept, the present invention also provides, for example... Figure 3 An electronic device shown includes:

[0106] Processor 31;

[0107] Memory 32 is used to store executable instructions of processor 31;

[0108] The processor 31 is configured to execute a mixed reality-based hydropower station operation and maintenance method as described above.

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

[0110] Since the electronic device described in this embodiment is an electronic device used to implement the information processing method in the embodiments of the present invention, those skilled in the art can understand the specific implementation methods and various variations of the electronic device in this embodiment based on the information processing method described in the embodiments of the present invention. Therefore, how the electronic device implements the method in the embodiments of the present invention will not be described in detail here. Any 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 will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0112] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0113] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0114] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1A step that specifies a function in one or more boxes.

[0115] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0116] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A hydropower station operation and maintenance method based on mixed reality, characterized in that, The method includes: Obtain the historical operation dataset of the target hydropower station within a historical period. The historical operation dataset includes water flow data, unit operation status data, and meteorological and geological environmental data. The unit operation status data includes unit equipment operation parameters and unit equipment performance parameters. Based on the historical operation dataset of the target hydropower station, the neural network model to be trained is trained to obtain the unit equipment fault prediction neural network model, which is used to predict the fault probability of each unit equipment of the target hydropower station. Obtain the real-time operation dataset of the target hydropower station, and determine the failure probability of each unit of the target hydropower station at the target time node based on the unit equipment failure prediction neural network model; Based on the failure probability and criticality of each unit's equipment, a first path for mixed reality inspection is determined, including: determining the inspection urgency score of each unit's equipment based on its failure probability and criticality; sorting several inspection urgency scores in descending order and sequentially connecting each unit's equipment according to the sorting order to obtain the first path for mixed reality inspection. Based on the failure probability of each unit's equipment, the criticality of each unit's equipment, and the distance parameters of each unit's equipment, a second automated inspection path is determined, including: determining the maximum distance between the automated inspection equipment and several unit's equipment; determining the distance parameters of the unit's equipment based on the maximum distance and the distance between the automated inspection equipment and the unit's equipment; determining the inspection convenience score of the unit's equipment based on the failure probability of the unit's equipment, the criticality of the unit's equipment, and the distance parameters of the unit's equipment; sorting the several inspection convenience scores in descending order, and sequentially connecting each unit's equipment according to the sorting order to obtain the second automated inspection path; The first mixed reality inspection path is sent to the virtual reality device, and the second automated inspection path is sent to the 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 as described in claim 1, characterized in that, Based on the failure probability of each unit's equipment and the criticality of each unit's equipment, the urgency score for the unit's equipment inspection is determined, including: Among them, H i Score the urgency of the inspection of the i-th unit equipment, α i Let be the failure probability of the i-th unit equipment, e be the base of the exponential function, and core be the value of the failure probability. i The core level of the i-th unit equipment.

3. The hydropower station operation and maintenance method based on mixed reality as described in claim 1, characterized in that, Based on the failure probability of the unit's equipment, the criticality of the equipment, and the distance parameters of the equipment, an inspection convenience score for the unit's equipment is determined, including: Among them, B i Score the ease of inspection for the i-th unit equipment, α i Let be the failure probability of the i-th unit equipment, e be the base of the exponential function, and core be the value of the failure probability. i For the core level of the i-th unit equipment, l max The maximum distance between the automated inspection equipment and several unit equipment, l i Let be the distance between the i-th unit equipment and the automated inspection equipment.

4. The hydropower station operation and maintenance method based on mixed reality as described in claim 1, characterized in that, Based on the historical operation dataset of the target hydropower station, a neural network model to be trained is obtained, which includes: The historical operation dataset of the target hydropower station is input into the neural network model to be trained to obtain the predicted failure probability of each unit equipment. In the historical operation dataset of the target hydropower station, determine the actual failure probability of the generating equipment; The neural network model to be trained is trained based on the predicted failure probability and the corresponding actual failure probability of the unit equipment. When the preset training requirements are met, the neural network model to be trained is used as the fault prediction neural network model of the unit equipment.

5. The hydropower station operation and maintenance method based on mixed reality as described in claim 4, characterized in that, The loss function of the neural network model to be trained includes: Where M is the loss function, N is the number of unit equipment, and y i Let p be the actual failure probability of the i-th unit equipment. i Let be the predicted failure probability of the i-th unit equipment, ln be the logarithmic function with base 10, θ be the regularization coefficient, and U be the trainable parameters of the neural network model to be trained.

6. A hydropower station operation and maintenance device based on mixed reality, characterized in that, The apparatus used in the mixed reality-based hydropower station operation and maintenance method according to any one of claims 1-5 includes: The acquisition module is used to acquire the historical operation dataset of the target hydropower station within a historical period. The historical operation dataset includes water flow data, unit operation status data, and meteorological and geological environment data. The unit operation status data includes unit equipment operation parameters and unit equipment performance parameters. The training module is used to train the neural network model to be trained based on the historical operation dataset of the target hydropower station, so as to obtain the unit equipment fault prediction neural network model, which is used to predict the fault probability of each unit equipment of the target hydropower station. The prediction module is used to acquire the real-time operation dataset of the target hydropower station and determine the failure probability of each unit of the target hydropower station at the target time node based on the unit equipment failure prediction neural network model. The first path module is used to determine the first path for mixed reality inspection based on the failure probability of each unit's equipment and the criticality of each unit's equipment. The second path module is used to determine the second path for automated inspection based on the failure probability of each unit's equipment, the criticality of each unit's equipment, and the distance parameters of each unit's equipment. The inspection module is used to send the first mixed reality inspection path to the virtual reality device and the second automated inspection path to the automated inspection device, and together they are used to inspect the target hydropower station.

7. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the mixed reality-based hydropower station operation and maintenance method as described in any one of claims 1 to 5.

8. 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 able to execute the mixed reality-based hydropower station operation and maintenance method as described in any one of claims 1 to 5.

Images