Simulation training method and device for interactive fault processing and electronic equipment

Abstract

The embodiment of the invention discloses a simulation training method and device for interactive fault processing and electronic equipment. The method comprises the steps of constructing a fault model in a three-dimensional scene through randomly generated fault information, transmitting the fault model to a target trainee based on interactive equipment, and then obtaining a target fault processing instruction issued by the target trainee, and determining a target fault processing behavior corresponding to the target fault processing instruction according to a preset virtual character behavior library, finally controlling a virtual character to execute the target fault processing behavior in the fault model based on the three-dimensional-distributed interaction system, and generating an operation report according to an equipment simulation fault processing result. According to the simulation training method, the purpose of fault processing training in the virtual three-dimensional environment is achieved, the simulation training method does not need actual training site and time limitation, the training efficiency is improved, meanwhile, potential safety hazards of misoperation are avoided, and the use satisfaction degree of a user is improved through targeted fault training for all trainees.

Description

TECHNICAL FIELD

[0001] One or more embodiments of the present specification relate to the technical field of industrial simulation training, and in particular to a simulation training method for interactive fault handling. BACKGROUND

[0002] With the widespread application of intelligent control technology in thermal power plants, the fault maintenance ability of the staff inside the plant is also increasingly required, so when expanding new thermal power plants or introducing new staff, the staff need to be trained in fault handling first. The existing traditional fault training method generally adopts on-site plant training or written word training, either because the written word training lacks a real three-dimensional environment, resulting in poor training effect and inability to improve the actual fault handling ability of the staff, or because the on-site plant training needs to actually arrange training processes to wait for the operation of production equipment, resulting in not only a waste of a lot of training time and a lot of production materials, but also a safety hazard of misoperation in a real environment. SUMMARY

[0003] The embodiment of the present specification provides a simulation training method, device and electronic equipment for interactive fault handling, and the technical scheme is as follows: In a first aspect, the embodiment of the present specification provides a simulation training method for interactive fault handling, and the method comprises: constructing a fault model in a three-dimensional scene based on randomly generated fault information, and transmitting the fault model to target training personnel based on an interactive device; obtaining a target fault handling instruction issued by the target training personnel, and determining a target fault handling behavior corresponding to the target fault handling instruction according to a preset virtual character behavior library; controlling a virtual character to perform the target fault handling behavior in the fault model based on a three-dimensional-distributed interactive system, and generating an operation report according to a device simulation fault handling result.

[0004] In a second aspect, a simulation training device for interactive fault handling is provided, and the device comprises: a construction module configured to construct a fault model in a three-dimensional scene based on randomly generated fault information, and transmit the fault model to target training personnel based on an interactive device a determination module configured to obtain a target fault handling instruction issued by the target training personnel, and determine a target fault handling behavior corresponding to the target fault handling instruction according to a preset virtual character behavior library; an execution module configured to control a virtual character to perform the target fault handling behavior in the fault model based on a three-dimensional-distributed interactive system, and generate an operation report according to a device simulation fault handling result.

[0005] In a third aspect, an electronic device is provided, including a device processor and a memory; The device processor is connected with the memory. The memory is configured to store executable program codes. The device processor runs a program corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0006] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer readable storage medium stores instructions, which, when executed on a computer or a device processor, causes the computer or the device processor to execute the method provided in the first aspect or any possible implementation manner of the first aspect.

[0007] The technical solutions provided by some embodiments of the present specification have at least the following beneficial effects: In one or more embodiments of the present specification, a fault model is constructed in a three-dimensional scene based on randomly generated fault information, the fault model is transmitted to target trainees based on an interactive device, target fault handling instructions issued by the target trainees are acquired, target fault handling behaviors corresponding to the target fault handling instructions are determined according to a preset virtual character behavior library, and finally the virtual characters perform the target fault handling behaviors in the fault model based on a three-dimensional-distributed interactive system, and an operation report is generated according to a device simulation fault handling result. The target fault handling instructions issued by the target trainees are transmitted through the three-dimensional-distributed interactive system, the virtual characters perform the target fault handling behaviors corresponding to the target fault handling instructions in the three-dimensional fault scene, the purpose of fault handling training in a virtual three-dimensional environment is achieved, the simulation training method does not require actual training sites and time limits, the training efficiency is improved, and the safety hazards of misoperation are avoided, the use satisfaction of users is improved through targeted fault training for each trainee, and the use satisfaction of users is improved through targeted fault training for each trainee. BRIEF DESCRIPTION OF DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0009] Figure 1 A flowchart of an interactive fault handling simulation training method provided by an embodiment of the present specification; Figure 2A structural schematic diagram of an interactive fault processing simulation training device provided by an embodiment of the present specification is shown. Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present specification is shown. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application.

[0011] The terms "first", "second", "third", etc. in the description and claims of the present specification and the above drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0012] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes can be made to the functions and arrangements of described elements without departing from the scope of the present specification. Various examples can appropriately omit, replace or add various processes or components. For example, the described methods can be executed in a different order from the described order, and various steps can be added, omitted or combined. In addition, features described with respect to some examples can be combined into other examples.

[0013] Please refer to Figure 1 , Figure 1 A whole flowchart of an interactive fault processing simulation training method provided by an embodiment of the present specification is shown.

[0014] As Figure 1 shown, the interactive fault processing simulation training method can at least include the following steps: Step 101, constructing a fault model in a three-dimensional scene based on randomly generated fault information, and transmitting the fault model to target training personnel based on an interactive device.

[0015] In the embodiment of the present specification, the simulation training system applied by the simulation training method of interactive fault handling can be provided with an interactive device. After the target trainee wears the interactive device, a corresponding randomly generated fault model is generated in the three-dimensional scene. The target trainee issues a fault handling instruction through voice, controls a virtual character to handle the fault in the fault model, and finally evaluates the simulation fault handling result according to the obtained operation report, so as to deduce whether the fault handling instruction is correct to achieve the simulation training purpose of interactive fault handling. Therefore, in order for the target trainee to be able to simulate fault handling in the three-dimensional scene, the three-dimensional model scene of the training thermal power plant area needs to be obtained first. Then, in order to further enhance the authenticity of simulation training, improve the quality of training effect, avoid repeated single rule fault handling scenes, realize the automation, diversification and high-fidelity reproduction of fault scenes, all theoretically faultable device states in the three-dimensional scene of the thermal power plant area need to be determined first, and then fault information is randomly generated. Finally, the corresponding fault model is constructed in the three-dimensional scene according to the fault information.

[0016] Specifically, when the fault information is randomly generated, all theoretically faultable device type numbers can be determined first, and a Monte Carlo random sampling algorithm is used to randomly generate fault numbers. Then, the fault devices of each number are combined to obtain the fault information. When the corresponding fault model is constructed in the three-dimensional scene according to the fault information, the fault information can be visualized and mapped through the fault characteristics under the initialized scene. The corresponding basic layer of the static three-dimensional model and the visualized fault layer are layered and stacked to obtain the corresponding fault model. The fault information can also be input into the generated network of the constructed fault model, and the corresponding three-dimensional fault model can be obtained.

[0017] In one implementation manner, before the fault model is constructed in the three-dimensional scene based on the randomly generated fault information, the method further includes: determining the weight coefficients corresponding to each fault type according to the historical training records of the target trainee; determining the target fault information corresponding to the target trainee based on the weight coefficients; constructing the fault model in the three-dimensional scene based on the randomly generated fault information: constructing the fault model in the three-dimensional scene based on the target fault information.

[0018] In the embodiments of the present specification, since the target training personnel has a situation that the success rate of handling a certain fault type is continuously too high or too low, in order to accurately target the training of each target training personnel, reduce the invalid training time, and reduce the training cost, before the simulation training of the target training personnel, the historical training record corresponding to the target training personnel can be acquired first, and the weight distribution of each fault type is performed in the historical training record according to the historical fault handling success rate, to obtain each weight coefficient. Then, each weight coefficient is compared with a preset weight threshold value, as an example, the weight threshold value is 0.7, the fault type with a weight coefficient greater than 0.85 is determined as a selected type, and a random selection is performed in the finally obtained selected type pool to obtain target fault information. After that, when the fault model is constructed according to the randomly generated fault information, the fault model can be constructed only according to the target fault information.

[0019] In an implementable manner, the fault model is constructed in a three-dimensional scene based on the randomly generated fault information, comprising: acquiring an original thermal power plant area three-dimensional model and a historical fault model corresponding to each historical fault information; constructing a fault model generation network corresponding to the original thermal power plant area three-dimensional model and each historical fault model based on a conditional generative adversarial algorithm; determining a target fault model corresponding to the target fault information according to the fault model generation network.

[0020] In the embodiments of the present specification, when the fault model is constructed in a three-dimensional scene according to the fault information, the point cloud data of the thermal power plant area is first acquired by laser scanning, reconstructed into the original thermal power plant area three-dimensional model by MeshLab, and a large number of historical fault cases are extracted in the historical database, each historical fault case including historical fault information and a corresponding historical fault model. Then, using the CGAN network in the conditional generative adversarial algorithm, a fault model generation network is constructed based on the original thermal power plant area three-dimensional model, and using the historical fault cases, the historical fault information is used as the network input, and the historical fault model is used as the network output to train it, to obtain the trained fault model generation network. Finally, the target fault information is input into the fault model generation network, and the corresponding target fault model is obtained.

[0021] Step 102, acquiring the target fault handling instruction issued by the target training personnel, and determining the target fault handling behavior corresponding to the target fault handling instruction according to a preset virtual character behavior library.

[0022] In the embodiments of the present disclosure, after the fault model is constructed in the three-dimensional scene according to the randomly generated fault information, the target trainee receives and observes the fault model through the interactive device, and issues the target fault handling instruction by judgment. Since the virtual character in the three-dimensional simulation system cannot directly identify the target fault handling instruction issued by the target trainee, the target fault handling instruction needs to be converted into a target fault handling behavior that can be directly executed. Specifically, the target fault handling instruction issued by the target trainee can be a voice instruction issued through an industrial-grade microphone array, or a text instruction input through a touch screen or an industrial keyboard. Therefore, the target fault handling instruction can be first preprocessed by natural language processing technology, and then input into a virtual character behavior library that is pre-constructed by statistical analysis of a large number of historical fault handling behaviors. Each standard handling instruction corresponds to a fault handling behavior, so that the target fault handling behavior corresponding to the target fault handling instruction can be obtained by querying the virtual character behavior library.

[0023] As an example, the target fault handling instruction is “please close the safety valve on the main steam pipeline immediately”, and after standardization preprocessing, it becomes “action = close, object = safety valve, location = main steam pipeline, emergency level = high”. The target fault handling behavior determined by querying the preset virtual character behavior library is “walk to the valve position, rotate the handwheel by 90°, and confirm the pressure gauge reading”.

[0024] In an implementation manner, the determining the target fault handling behavior corresponding to the target fault handling instruction according to the preset virtual character behavior library comprises: analyzing the target fault handling instruction based on natural language processing technology to obtain target instruction information; determining each handling action corresponding to the target instruction information according to the preset virtual character behavior library; sorting the trajectories of each handling action based on the execution priority to obtain the target fault handling behavior.

[0025] In the embodiments of the present specification, in order to convert the target fault handling instruction issued by the target trainer into machine executable structured information, solve the instruction ambiguity problem in the traditional training system, and eliminate environmental noise by using an adaptive LMS filtering algorithm, redundant words (such as "please" and "trouble") are removed, and the terminology (such as "water pump" is converted to "centrifugal pump") is standardized to standardize the text. Then, the target fault handling instruction is analyzed by the BERT+BiLSTM model in the natural language processing technology to obtain the target instruction information, for example, "action: close, check; object: cooling water pump, pressure gauge; location: B area". Further, in order to ensure that the subsequent virtual character operation conforms to the industrial safety specification, the hierarchical structure storage standardized operation unit is used to build the virtual character behavior library, for example, when the instruction information is "close the device", the corresponding processing action is ["move to the device position", "press the stop button", "confirm the status indicator light"]. Further, in order to avoid operation sequence errors, the execution priority of each processing action is determined, and the trajectory of each processing action is sorted according to the execution priority to obtain the target fault handling behavior.

[0026] As an example, the priority weights of "confirm the status indicator light", "press the stop button", and "move to the device position" are 0.6, 0.8, and 0.9 respectively, so the target fault handling behavior is to move to the device position first, then press the stop button, and finally confirm the status indicator light.

[0027] Step 103, controlling the virtual character to execute the target fault handling behavior in the fault model based on the three-dimensional-distributed interactive system, and generating an operation report according to the device simulation fault handling result.

[0028] In the embodiments of the present specification, after determining the fault model in the three-dimensional scene and the target fault handling behavior, the three-dimensional fault model and the virtual character can be initialized based on the three-dimensional-distributed interactive system, the real-time data stream of pressure, temperature and the like is mapped to the visualization layer of the three-dimensional fault model, the behavior of the virtual character is bound, the virtual character is driven through the skeletal animation system, the collision detection boundary is set, the physical collision body is added to the virtual character and the equipment, and the operation space theory compliance is ensured. Then, the target fault handling behavior is disassembled into atomic action instructions (such as “move to coordinates (x, y, z)” and “apply torque 5Nm”) by using a distributed task scheduling framework, and the equipment state change is calculated, the virtual character action and the equipment state are updated through three-dimensional rendering, and the execution of the target fault handling behavior is completed. Finally, the operation behavior data is obtained by recording the virtual character action trajectory (path, speed), operation time (such as valve closing time 3.2s), and error operation (such as triggering alarm without wearing safety gloves), the equipment response data is obtained by collecting key parameters (such as pressure change rate, temperature fluctuation range, and fault elimination time) output by the physical engine, and finally the operation report is generated according to the equipment simulation fault handling result corresponding to the operation behavior data and the equipment response data, so as to evaluate the operation score of the target trainee in this equipment simulation fault handling, so as to improve the fault handling ability for subsequent low-score problems, and achieve the purpose of simulation training.

[0029] In an implementable manner, the control of the virtual character to execute the target fault handling behavior in the fault model based on the three-dimensional-distributed interactive system comprises: constructing a distributed task scheduling framework based on a time-sensitive network protocol and a distributed clock synchronization algorithm; controlling the virtual character to execute the target fault handling behavior in the fault model according to the distributed task scheduling framework.

[0030] In the embodiment of the present application, based on the three-dimensional-distributed interactive system control virtual person in the fault model to perform the target fault handling behavior, it is necessary to first integrate the TSN protocol stack (IEEE 802.1Qbv) on the basis of Profinet industrial Ethernet, configure the traffic scheduling table, and in order to allocate priority queue for the action instruction of the virtual person, it is necessary to reserve bandwidth ≥ 100 Mbps, then set the time-aware shaper to divide the control cycle into 125 μs time slots, ensure the transmission of the action instruction in the fixed time slot, and deploy the TSN switch (Cisco IE-3400) to enable the preemption MAC (IEEE 802.1Qbu) to realize the active avoidance of low-priority data flow to high-priority instruction to deploy the time-sensitive network protocol. Then, the IEEE 1588 precision time protocol is used to build the master-slave clock architecture, the master clock source is elected to deploy the GPS time service module, the time accuracy is ≤ ± 50 ns, the slave node uses the transparent clock to compensate the link delay, and the synchronization accuracy reaches ± 1 μs, so as to realize the distributed clock synchronization. Further, through the deployed time-sensitive network protocol and the distributed clock synchronization algorithm, the action of the virtual person is decomposed into atomic tasks, encapsulated into task packets with timestamps, and a task priority matrix is established, so as to build a distributed task scheduling framework. Finally, according to the built distributed task scheduling framework, the virtual person is controlled to execute the task packet with timestamp in the three-dimensional simulation engine of the fault model, and the execution of the target fault handling behavior is realized.

[0031] In an implementable manner, the controlling the virtual person to execute the target fault handling behavior in the fault model according to the distributed task scheduling framework comprises: determining a distributed system control instruction corresponding to the target fault handling behavior according to the distributed task scheduling framework; updating the fault device state in the fault model based on the distributed system control instruction.

[0032] In the embodiment of the present application, when the target fault handling behavior is executed according to the distributed task scheduling framework, the target fault handling behavior can be received first, and then it is disassembled into atomic operation units through the behavior analysis tree, and then each atomic operation is allocated an execution node and a time window through the timing and resource allocation in the distributed task scheduling framework. Further, the distributed system control instruction is obtained by encapsulating the atomic operation, and is sent to the target edge node. Then, the edge node in the edge node execution layer receives the distributed system control instruction, controls the virtual device through the device driver interface, and updates the fault device state in the fault model combined with the physical engine simulation data.

[0033] In an implementable manner, the generating the operation report according to the device simulation fault handling result comprises: Determine the device state processing data corresponding to the device simulation fault processing result based on the blockchain consensus algorithm; Generate an operation report according to the comparison result of the device state processing data and the device state standard data.

[0034] In the embodiments of the present application, after obtaining the device simulation fault processing result, the device simulation fault processing result (such as valve opening, pressure value, temperature curve, operation timestamp, etc.) can be converted into a structured data packet through a blockchain consensus algorithm, and the device ID, operation instruction sequence and physical quantity measurement value are associated using the JSON-LD format to obtain the device state processing data. Then, the device state processing data and the device state standard data are compared respectively, and an operation report is generated according to the comparison result. As an example, the reactor pressure standard data is 0.4 MPa or less, and the device state processing data is 0.6 MPa, then the corresponding operation report includes but is not limited to that the reactor pressure fault processing is not up to standard.

[0035] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order other than that described in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0036] Next, please refer to Figure 2 , Figure 2 A structural schematic diagram of an interactive fault handling simulation training device provided by the embodiments of the present application is shown. It should be noted that, Figure 2 The interactive fault handling simulation training device shown is used to execute the method of the embodiments of the present application Figure 1 The method of the embodiments shown is only shown with parts related to the embodiments of the present application for the convenience of description, and the specific technical details not disclosed are referred to the embodiments shown in the present application Figure 1 .

[0037] As Figure 2 shown, the interactive fault handling simulation training device can at least include: The construction module 201 is configured to construct a fault model in a three-dimensional scene based on randomly generated fault information, and transmit the fault model to target trainees based on interactive devices The determination module 202 is configured to obtain target fault handling instructions issued by the target trainees, and determine target fault handling behaviors corresponding to the target fault handling instructions according to a preset virtual character behavior library; The execution module 203 is configured to control the virtual character to perform the target fault handling behavior in the fault model based on the three-dimensional-distributed interaction system, and generate an operation report according to a simulation fault handling result of the device.

[0038] In an implementation, the construction module 201 is specifically configured to: determine a weight coefficient corresponding to each fault type according to a historical training record of the target trainee; determine target fault information corresponding to the target trainee based on the weight coefficient; construct the fault model in the three-dimensional scene based on the randomly generated fault information: construct the fault model in the three-dimensional scene based on the target fault information.

[0039] In an implementation, the construction module 201 is specifically further configured to: obtain an original thermal power plant area three-dimensional model and a historical fault model corresponding to each historical fault information; construct a fault model generation network corresponding to the original thermal power plant area three-dimensional model and each historical fault model based on a conditional generative adversarial network; determine a target fault model corresponding to the target fault information according to the fault model generation network.

[0040] In an implementation, the determination module 202 is specifically configured to: analyze the target fault handling instruction based on a natural language processing technology to obtain target instruction information; determine each handling action corresponding to the target instruction information according to a preset virtual character behavior library; sort trajectories of each handling action based on an execution priority to obtain a target fault handling behavior.

[0041] In an implementation, the execution module 203 is specifically configured to: construct a distributed task scheduling framework based on a time-sensitive network protocol and a distributed clock synchronization algorithm; control the virtual character to perform the target fault handling behavior in the fault model based on the distributed task scheduling framework.

[0042] In an implementation, the execution module 203 is specifically further configured to: determine a distributed system control instruction corresponding to the target fault handling behavior according to the distributed task scheduling framework; update a fault device state in the fault model based on the distributed system control instruction.

[0043] In an implementation, the execution module 203 is specifically further configured to: Determine the device state processing data corresponding to the device simulation fault processing result based on the blockchain consensus algorithm; Generate an operation report according to the comparison result of the device state processing data and the device state standard data.

[0044] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be realized by means of software and / or hardware. The "unit" and "module" in the specification refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, and the hardware may, for example, be a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0045] The various processing units and / or modules of the embodiments of the present application can be realized by means of analog circuits that implement the functions described in the embodiments of the present application, or can be realized by means of software that executes the functions described in the embodiments of the present application.

[0046] Next, please refer to Figure 3 , Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present specification is shown.

[0047] As Figure 3 shown, the electronic device 300 can include at least one device processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0048] The communication bus 302 can be used to realize the connection and communication of the above-mentioned components.

[0049] The user interface 303 can include a key, and the optional user interface can also include a standard wired interface, a wireless interface.

[0050] The network interface 304 can include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0051] The device processor 301 can include one or more processing cores. The device processor 301 connects various parts within the entire electronic device 300 by various interfaces and lines, executes various functions of the electronic device 300 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Alternatively, the device processor 301 can be implemented in at least one of a hardware form of a DSP, an FPGA, and a PLA. The device processor 301 can integrate one or a combination of a CPU, a GPU, and a modem. Among them, the CPU mainly processes an operating system, a user interface, and an application program; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the device processor 301, but can be implemented by a separate chip.

[0052] The memory 305 can include a RAM and can also include a ROM. Alternatively, the memory 305 includes a non-transitory computer readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 305 can also be at least one storage device located away from the aforementioned device processor 301. As shown, the memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and program instructions. Figure 3 As shown, the memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and program instructions.

[0053] Specifically, the device processor 301 can be used to call the simulation training application program of interactive fault processing stored in the memory 305, and specifically perform the following operations: Construct a fault model in a three-dimensional scene based on randomly generated fault information, and transmit the fault model to the target trainee based on an interactive device Obtain the target fault handling instruction issued by the target trainee, and determine the target fault handling behavior corresponding to the target fault handling instruction according to a preset virtual character behavior library; Control the virtual character to perform the target fault handling behavior in the fault model based on a three-dimensional-distributed interactive system, and generate an operation report according to a device simulation fault handling result.

[0054] As an option of the embodiment of the present specification, the fault information generated randomly further comprises, before constructing the fault model in the three-dimensional scene: According to the historical training records of the target training personnel, determine the weight coefficients corresponding to each fault type; Based on each of the weight coefficients, determine the target fault information corresponding to the target training personnel; The fault model is constructed in the three-dimensional scene based on the randomly generated fault information: The fault model is constructed in the three-dimensional scene based on the target fault information.

[0055] As an option of the embodiment of the present specification, the fault model is constructed in the three-dimensional scene based on the randomly generated fault information, comprising: Obtain the original thermal power plant area three-dimensional model and the historical fault model corresponding to each historical fault information; Based on the conditional generative adversarial algorithm, construct a fault model generation network corresponding to the original thermal power plant area three-dimensional model and each historical fault model; According to the fault model generation network, determine the target fault model corresponding to the target fault information.

[0056] As an option of the embodiment of the present specification, the target fault handling behavior corresponding to the target fault handling instruction is determined according to the preset virtual character behavior library, comprising: Based on natural language processing technology, analyze the target fault handling instruction to obtain target instruction information; According to the preset virtual character behavior library, determine each processing action corresponding to the target instruction information; Based on the execution priority, sort the trajectories of each of the processing actions to obtain the target fault handling behavior.

[0057] As an option of the embodiment of the present specification, the target fault handling behavior of the virtual character in the fault model is controlled based on the three-dimensional-distributed interactive system, comprising: Based on the time-sensitive network protocol and the distributed clock synchronization algorithm, construct a distributed task scheduling framework; According to the distributed task scheduling framework, control the virtual character to execute the target fault handling behavior in the fault model.

[0058] As an option of the embodiment of the present specification, the target fault handling behavior of the virtual character in the fault model is controlled according to the distributed task scheduling framework, comprising: According to the distributed task scheduling framework, determine the distributed system control instruction corresponding to the target fault handling behavior; Based on the distributed system control instruction, update the fault equipment state in the fault model.

[0059] As an option of the embodiments of the present specification, the operation report generated according to the device simulation fault processing result comprises: determining the device state processing data corresponding to the device simulation fault processing result based on the blockchain consensus algorithm; generating the operation report according to the comparison result of the device state processing data and the device state standard data.

[0060] The embodiments of the present specification also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the steps of the above method. The computer readable storage medium can include but is not limited to any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, micro-drives, and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0061] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0062] In the above embodiments, the description of each embodiment is focused on, and the part not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0063] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented by other ways. For example, the device embodiments described above are only schematic, and for example, the division of the units is only a logical function division, and there can be another division way in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some service interfaces, devices or units, and can be electrical or other forms.

[0064] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed on multiple network units. Part or all of the units may be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0065] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0066] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0067] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer readable storage medium, which can include a flash disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, etc.

[0068] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve the desired result. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. An interactive fault handling simulation training method, characterized in that, The method includes: A fault model is constructed in a 3D scene based on randomly generated fault information, and the fault model is transmitted to the target trainees via an interactive device. Obtain the target fault handling instructions issued by the target trainee, and determine the target fault handling behavior corresponding to the target fault handling instructions based on the preset virtual character behavior library; The system controls a virtual character to perform the target fault handling behavior in the fault model based on a 3D-distributed interactive system, and generates an operation report based on the equipment simulation fault handling results.

2. The method according to claim 1, characterized in that, Before constructing the fault model in the 3D scene based on randomly generated fault information, the following steps are also included: The weighting coefficients for each fault type are determined based on the historical training records of the target trainees. The target fault information corresponding to the target trainees is determined based on each of the weighting coefficients. The fault model is constructed in the three-dimensional scene based on randomly generated fault information: A fault model is constructed in a 3D scene based on the target fault information.

3. The method according to claim 1, characterized in that, The construction of a fault model in a 3D scene based on randomly generated fault information includes: Obtain the original 3D model of the thermal power plant area and the historical fault models corresponding to each historical fault information; Based on the conditional generative adversarial algorithm, a fault model generation network is constructed to generate the original 3D model of the thermal power plant area and the corresponding fault model for each historical fault model. The target fault model corresponding to the target fault information is determined based on the fault model generation network.

4. The method according to claim 1, characterized in that, The step of determining the target fault handling behavior corresponding to the target fault handling instruction based on a preset virtual character behavior library includes: The target fault handling instructions are parsed using natural language processing technology to obtain target instruction information; The processing actions corresponding to the target instruction information are determined based on a preset virtual character behavior database; Based on the execution priority, the trajectory of each processing action is sorted to obtain the target fault handling behavior.

5. The method according to claim 1, characterized in that, The method of controlling a virtual character based on a 3D-distributed interactive system to perform the target fault handling behavior in the fault model includes: A distributed task scheduling framework is constructed based on time-sensitive networking protocol and distributed clock synchronization algorithm; The distributed task scheduling framework controls the virtual character to perform the target fault handling behavior in the fault model.

6. The method according to claim 5, characterized in that, The step of controlling the virtual character to perform the target fault handling behavior in the fault model according to the distributed task scheduling framework includes: The distributed system control instructions corresponding to the target fault handling behavior are determined based on the distributed task scheduling framework. The state of the faulty device in the fault model is updated based on the distributed system control instructions.

7. The method according to claim 1, characterized in that, The generation of an operation report based on the equipment simulation fault handling results includes: The equipment status processing data corresponding to the equipment simulation fault processing results is determined based on the blockchain consensus algorithm. An operation report is generated based on the comparison results between the equipment status processing data and the equipment status standard data.

8. An interactive fault handling simulation training device, characterized in that, The device includes: A construction module is used to build a fault model in a 3D scene based on randomly generated fault information, and to transmit the fault model to the target trainees via an interactive device; The determination module is used to obtain the target fault handling instructions issued by the target trainee, and determine the target fault handling behavior corresponding to the target fault handling instructions based on the preset virtual character behavior library; The execution module is used to control the virtual character to perform the target fault handling behavior in the fault model based on the three-dimensional distributed interactive system, and to generate an operation report based on the equipment simulation fault handling results.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as described in any one of claims 1-7.

Images