Routing inspection method and system for comprehensive pipe gallery of nuclear power plant, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a nuclear power plant comprehensive pipe gallery inspection method and system, electronic equipment and a storage medium, and belongs to the technical field of inspection robots. The method comprises the steps that a track is arranged in the comprehensive pipe gallery, and an inspection robot is installed on the track; obtaining an inspection starting instruction, and executing an inspection operation based on the inspection starting instruction; acquiring corresponding environment sound data in a process of executing the inspection operation in real time; transmitting the environment sound data to a local server, so that the local server inputs the environment sound data to a sound analysis model for anomaly recognition analysis to obtain an anomaly recognition result, and determining an abnormal inspection area based on the anomaly recognition result and the inspection position data of the inspection robot; receiving an abnormality identification result and an abnormal inspection area transmitted by the local server; and performing fine positioning in the inspection abnormal area based on an abnormal identification result, and determining a target abnormal source. The embodiment of the invention can safely and reliably inspect the utility tunnel of the nuclear power plant.

Description

Technical Field

[0001] The present application relates to the technical field of inspection robots, and in particular to an inspection method, system, electronic equipment and storage medium for an integrated pipeline corridor of a nuclear power plant. Background Art

[0002] The nuclear power plant integrated pipe gallery is widely distributed and is an important comprehensive sub-item in the nuclear power plant, connecting a large number of equipment and systems. The pipe gallery is full of water, gas pipelines and cables, which poses a risk of leakage and fire. However, the pipe gallery is an underground project, which is difficult to detect and intervene in time and requires regular inspections.

[0003] In the related technologies, inspections of nuclear power plant integrated pipe corridors are mostly carried out manually, which is time-consuming and labor-intensive, prone to omissions of inspection items, and the environment of the integrated pipe corridor is complex, prone to safety issues such as personnel falling and bumping. Therefore, how to safely and reliably inspect the integrated pipe corridors of nuclear power plants has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a nuclear power plant integrated pipeline corridor inspection method, system, electronic equipment and storage medium, aiming to safely and reliably inspect the nuclear power plant integrated pipeline corridor.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a nuclear power plant integrated pipe gallery inspection method, which is applied to an inspection robot. A track is provided in the integrated pipe gallery, and the inspection robot is installed on the track. The method includes:

[0006] Obtaining a patrol inspection start instruction, and performing a patrol inspection operation based on the patrol inspection start instruction;

[0007] Real-time collection of environmental sound data corresponding to the process of performing the inspection operation;

[0008] The environmental sound data is transmitted to a local server, so that the local server inputs the environmental sound data into a pre-trained sound analysis model for abnormality recognition analysis to obtain an abnormality recognition result, and determines the abnormal inspection area based on the abnormality recognition result and the inspection position data of the inspection robot; wherein the inspection position data is obtained by the local server in real time;

[0009] Receiving the abnormality identification result and the abnormal inspection area transmitted from the local server;

[0010] Based on the abnormality identification result, precise positioning is performed in the inspection abnormal area to determine the target abnormality source.

[0011] In some embodiments, the inspection robot includes a sound sensor array, and the real-time collection of corresponding environmental sound data during the execution of the inspection operation includes:

[0012] Acquiring the environmental sound data by collecting sound through a single sound sensor in the sound sensor array;

[0013] The performing precise positioning in the inspection abnormal area based on the abnormality identification result to determine the target abnormality source includes:

[0014] Start each sound sensor of the sound sensor array to collect sound in the abnormal inspection area to obtain sound array data;

[0015] Transmitting the sound array data to the local server in real time, so that the local server performs phase difference distance analysis based on the sound array data and the inspection position data to determine the location where the abnormality occurs;

[0016] The abnormality occurrence location transmitted from the local server is received, and the target abnormality source is determined according to the abnormality occurrence location.

[0017] In some embodiments, the inspection robot further includes an image sensor, a temperature sensor, and an infrared sensor, and the method further includes:

[0018] Acquire images through the image sensor to obtain environmental image data;

[0019] Collecting temperature through the temperature sensor to obtain ambient temperature data;

[0020] Collect infrared data through the infrared sensor to obtain infrared image data;

[0021] The environmental image data, the environmental temperature data and the infrared image data are transmitted to the local server, so that the local server inputs the environmental image data into a pre-trained image analysis model for abnormality recognition analysis to obtain an image recognition result; and based on the image recognition result, the environmental temperature data and the infrared image data, the abnormality recognition result is verified, and the danger level of the target abnormality source is assessed to obtain a comprehensive assessment result.

[0022] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a nuclear power plant integrated pipe gallery inspection method, which is applied to a local server, and the method includes:

[0023] Receive environmental sound data transmitted by the inspection robot;

[0024] Inputting the environmental sound data into a pre-trained sound analysis model for abnormality recognition analysis to obtain an abnormality recognition result;

[0025] Acquire the inspection position data of the inspection robot in real time, and determine the inspection abnormal area based on the abnormality recognition result and the inspection position data of the inspection robot;

[0026] The abnormality identification result and the abnormal inspection area are transmitted to the corresponding inspection robot, so that the inspection robot can accurately locate the abnormal inspection area based on the abnormality identification result and determine the target abnormality source.

[0027] In some embodiments, the step of inputting the environmental sound data into a pre-trained sound analysis model for abnormality recognition analysis and obtaining an abnormality recognition result further includes pre-training the sound analysis model, specifically including:

[0028] Obtain a model training set; wherein the model training set includes a plurality of sound training samples, each sound training sample is configured with a corresponding sound sample label;

[0029] Inputting the sound training sample into the original sound analysis model for sample recognition training to obtain a sample recognition result;

[0030] Comparing the sample recognition result corresponding to the sound training sample with the sound sample label to obtain comparison deviation data;

[0031] The model parameters of the sound analysis model are updated based on the comparison deviation data, and the sound training sample is input into the sound analysis model for sample recognition training until the sound analysis model meets the preset training termination condition, thereby obtaining the pre-trained sound analysis model.

[0032] In some embodiments, the abnormality identification result and the abnormal inspection area are transmitted to the corresponding inspection robot, so that the inspection robot can accurately locate the abnormal inspection area based on the abnormality identification result and determine the target abnormality source, and further includes:

[0033] Selecting an adapted target response plan from a plurality of candidate response plans based on the abnormality identification result; wherein the candidate response plan represents a pre-prepared processing plan corresponding to the abnormality identification result;

[0034] Control the inspection robot to go to the emergency processing tool station closest to the target abnormality source, and automatically equip the corresponding emergency processing equipment based on the target response plan;

[0035] The inspection robot is controlled to go to the inspection abnormal area, and the emergency processing equipment is used to perform emergency processing on the target abnormal source.

[0036] In some embodiments, the local server further includes resource distribution data, wherein the resource distribution data records the distribution of various resources in the integrated pipe gallery, and the abnormal identification result and the abnormal inspection area are transmitted to the corresponding inspection robot, so that the inspection robot performs precise positioning in the abnormal inspection area based on the abnormal identification result, and after determining the target abnormal source, it also includes:

[0037] Based on the target abnormal source and the resource distribution data corresponding to the inspection abnormal area, a hazard level assessment is performed on the target abnormal source to obtain a comprehensive assessment result;

[0038] An alarm message is issued based on the target abnormal source and the comprehensive evaluation result to notify relevant personnel to handle the target abnormal source.

[0039] To achieve the above-mentioned purpose, the third aspect of the embodiment of the present application proposes a nuclear power plant integrated pipe gallery inspection system, the system comprising an inspection robot and a local server, specifically comprising:

[0040] The inspection robot obtains an inspection start instruction and performs an inspection operation based on the inspection start instruction; the inspection robot collects corresponding environmental sound data in real time during the execution of the inspection operation; the inspection robot transmits the environmental sound data to the local server, and the local server inputs the environmental sound data into a pre-trained sound analysis model for abnormality recognition and analysis to obtain an abnormality recognition result, and the local server determines the inspection abnormality area based on the inspection position data of the inspection robot; wherein the inspection position data is obtained by the local server in real time; the inspection robot receives the abnormality recognition result and the inspection abnormality area transmitted by the local server; the inspection robot performs precise positioning in the inspection abnormality area based on the abnormality recognition result to determine the target abnormality source.

[0041] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the nuclear power plant integrated pipeline corridor inspection method described in the first aspect when executing the computer program.

[0042] To achieve the above-mentioned purpose, the fifth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the nuclear power plant integrated pipeline corridor inspection method described in the first aspect above.

[0043] The present application proposes a nuclear power plant integrated pipe corridor inspection method, system, electronic device and storage medium, which sets a track in the nuclear power plant integrated pipe corridor, and installs the inspection robot on the track so that the inspection robot can travel on the track, thereby avoiding the inspection robot from being affected by the complex environment of the nuclear power plant integrated pipe corridor, and can perform inspection operations more reliably. The inspection robot performs inspection operations on the nuclear power plant integrated pipe corridor, which reduces the number of times relevant personnel enter the nuclear power plant integrated pipe corridor, thereby reducing the possibility of injury to relevant personnel and improving the safety of inspecting the nuclear power plant integrated pipe corridor. The inspection robot obtains the inspection start instruction, performs the inspection operation on the integrated pipe corridor, collects the corresponding environmental sound data of the inspection robot in the process of performing the inspection operation in real time, and transmits the environmental sound data to the local server, so that the local server inputs the environmental sound data into the pre-trained sound analysis model for abnormal recognition analysis, obtains the abnormal recognition result, and determines the inspection abnormal area based on the abnormal recognition result and the inspection position data of the inspection robot. The inspection robot receives the abnormal identification results and inspection abnormal areas transmitted from the local server, and accurately locates the inspection abnormal area based on the abnormal identification results to determine the target abnormal source. By collecting environmental sound data, the sound generated by abnormal problems can be collected in the complex environment of the nuclear power plant integrated pipe corridor, and input into the sound analysis model pre-trained on the local server to obtain abnormal identification results, thereby predicting abnormal problems in the nuclear power plant integrated pipe corridor, and by accurately locating the inspection abnormal area, the target abnormal source can be reliably determined, and the nuclear power plant integrated pipe corridor can be safely and reliably inspected. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of the nuclear power plant integrated pipe gallery inspection method provided in the embodiment of the present application;

[0045] Figure 2 yes Figure 1 Flowchart of step S102 and step S109 in FIG.

[0046] Figure 3 yes Figure 1 The flowchart before step S105 in FIG.

[0047] Figure 4 yes Figure 1 The flowchart after step S109 in FIG.

[0048] Figure 5 yes Figure 1 Another flowchart after step S109 in;

[0049] Figure 6 yes Figure 1 Another flowchart after step S109 in;

[0050] Figure 7 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0053] The embodiments of the present application provide a method, system, electronic equipment and storage medium for inspecting the integrated pipeline corridor of a nuclear power plant, aiming to inspect the integrated pipeline corridor of a nuclear power plant safely and reliably.

[0054] The nuclear power plant integrated pipeline corridor inspection method, system, electronic equipment and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the nuclear power plant integrated pipeline corridor inspection method in the embodiments of the present application is described.

[0055] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0056] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0057] The nuclear power plant integrated pipe corridor inspection method provided in the embodiment of the present application relates to the field of inspection robot technology. The nuclear power plant integrated pipe corridor inspection method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the nuclear power plant integrated pipe corridor inspection method, etc., but is not limited to the above forms.

[0058] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0059] Reference Figure 1 is an optional flow chart of the nuclear power plant integrated pipeline corridor inspection method provided in the embodiment of the present application, Figure 1 The method includes two execution entities, a patrol robot and a local server, and may include but is not limited to steps S101 to S109.

[0060] Step S101, the inspection robot obtains an inspection start instruction and performs an inspection operation based on the inspection start instruction;

[0061] Step S102, the inspection robot collects corresponding environmental sound data in real time during the inspection operation;

[0062] Step S103, the inspection robot transmits the environmental sound data to the local server;

[0063] Step S104, the local server receives the environmental sound data transmitted by the inspection robot;

[0064] Step S105, the local server inputs the environmental sound data into the pre-trained sound analysis model for abnormality recognition analysis to obtain an abnormality recognition result;

[0065] Step S106, the local server obtains the inspection position data of the inspection robot in real time, and determines the inspection abnormal area based on the abnormality recognition result and the inspection position data of the inspection robot;

[0066] Step S107, the local server transmits the abnormality recognition result and the abnormal inspection area to the corresponding inspection robot;

[0067] Step S108, the inspection robot receives the abnormality recognition result and the inspection abnormal area transmitted from the local server;

[0068] Step S109: The inspection robot performs precise positioning in the inspection abnormal area based on the abnormality recognition result to determine the target abnormality source.

[0069] In the steps S101 to S109 shown in the embodiment of the present application, a track is set in the integrated pipe corridor of the nuclear power plant, and the inspection robot is installed on the track so that the inspection robot travels on the track, thereby avoiding the inspection robot from being affected by the complex environment of the integrated pipe corridor of the nuclear power plant, and can perform inspection operations more reliably. The inspection robot performs inspection operations on the integrated pipe corridor of the nuclear power plant, which reduces the number of times relevant personnel enter the integrated pipe corridor of the nuclear power plant, thereby reducing the possibility of injury to relevant personnel and improving the safety of inspecting the integrated pipe corridor of the nuclear power plant. The inspection robot obtains the inspection start instruction, performs inspection operations on the integrated pipe corridor, collects the corresponding environmental sound data of the inspection robot in the process of performing the inspection operation in real time, and transmits the environmental sound data to the local server. The local server inputs the environmental sound data into the pre-trained sound analysis model for abnormal recognition analysis, obtains the abnormal recognition result, and determines the inspection abnormal area based on the abnormal recognition result and the inspection position data of the inspection robot. The inspection robot receives the abnormal recognition result and the inspection abnormal area transmitted from the local server, and accurately locates in the inspection abnormal area based on the abnormal recognition result to determine the target abnormal source. By collecting environmental sound data, the sounds generated by abnormal problems can be collected in the complex environment of the nuclear power plant's integrated pipeline corridor, and input into the sound analysis model pre-trained on the local server to obtain abnormal recognition results, thereby predicting abnormal problems existing in the nuclear power plant's integrated pipeline corridor, and by accurately locating the abnormal area during inspection, the target abnormal source can be reliably determined, thereby achieving safe and reliable inspection of the nuclear power plant's integrated pipeline corridor.

[0070] In some embodiments, a track is provided in the nuclear power plant integrated pipe corridor, and the inspection robot is installed on the track so that the inspection robot can travel on the track, and the track can satisfy the inspection robot to achieve smooth movement and precise position control. The setting mode of the track can be changed based on the environment of the nuclear power plant integrated pipe corridor or the projects that need to be focused on in the nuclear power plant integrated pipe corridor.

[0071] In some embodiments, the track is arranged on the ceiling of the nuclear power plant integrated pipe gallery so that the inspection robot can run above the nuclear power plant integrated pipe gallery. On the one hand, the inspection robot can avoid being affected by objects placed on the ground of the nuclear power plant integrated pipe gallery, and can better collect environmental sound data. On the other hand, when an emergency occurs, the inspection robot runs above the nuclear power plant integrated pipe gallery and will not affect the rapid movement of personnel in the nuclear power plant integrated pipe gallery. In some embodiments, a telescopic mechanism can be arranged between the inspection robot and the track so that the inspection robot can move away from and close to the track, thereby adjusting the distance of the inspection robot relative to the ceiling.

[0072] In other embodiments, the track is set on the wall of the nuclear power plant integrated pipe gallery, so that the inspection robot runs on one side of the nuclear power plant integrated pipe gallery. In this way, the inspection robot can better inspect the pipes or items in the nuclear power plant integrated pipe gallery, and will not cause too much trouble to the actions of relevant personnel in the nuclear power plant integrated pipe gallery.

[0073] In some embodiments, the nuclear power plant integrated pipe corridor is divided into multiple inspection intervals, and at least one inspection robot is set in each inspection interval. Different inspection robots can be configured according to different inspection areas, and the inspection area can be set according to the environmental characteristics of the nuclear power plant integrated pipe corridor. For example, the pipeline facilities of the nuclear power plant integrated pipe corridor in a certain inspection area are more complex, and for this inspection area, an inspection robot with richer detection accuracy and sensor equipment is configured. Or the pipelines in the nuclear power plant integrated pipe corridor in a certain inspection area transmit radioactive materials, and a high-precision radiation detection device is configured for this inspection area. Or based on the location of the pipeline facilities in the nuclear power plant integrated pipe corridor, the tracks are set at different locations. For example, when the pipeline facilities in a certain inspection area are all set on one side of the nuclear power plant integrated pipe corridor, the tracks can be set on the other side relative to the pipeline facilities, so that the inspection robot can inspect the pipeline facilities more comprehensively.

[0074] In step S101 of some embodiments, the inspection robot obtains an inspection start instruction and performs an inspection operation based on the inspection start instruction. The inspection start instruction is used to instruct the inspection robot to perform an inspection operation. It may be sent from a local server. Exemplarily, relevant personnel send an inspection start instruction to the inspection robot through data information in the local server. It may also be preset in the inspection robot, such as a preset instruction to perform an inspection operation in a certain time period. It may also be that relevant personnel input the inspection start instruction to the inspection robot through a control device.

[0075] In step S102 of some embodiments, the inspection robot collects corresponding environmental sound data in real time during the inspection operation, and the environmental sound data refers to the sound collected in the environment of the nuclear power plant integrated pipe gallery. The environmental sound data includes the sound of the equipment or items in the nuclear power plant integrated pipe gallery when they are operating normally, and also includes the sound generated by the abnormality of the equipment or items in the nuclear power plant integrated pipe gallery.

[0076] In some embodiments, in step S103 to step S104, the inspection robot transmits the environmental sound data to the local server, and the local server receives the environmental sound data transmitted by the inspection robot, wherein the inspection robot can transmit the environmental sound data through its own communication module, or through an intermediate end, and illustratively, wireless communication devices are set at a certain interval in the integrated pipe gallery of a nuclear power plant, and the inspection robot first transmits the environmental sound data to the wireless communication device, and then the wireless communication device transmits it to the local server, thereby ensuring that the environmental sound data can be smoothly and in real time transmitted to the local server in the complex environment of the integrated pipe gallery of the nuclear power plant. Among them, the wireless communication device is preferably set at the connection position of multiple pipe galleries in the integrated pipe gallery of the nuclear power plant, so as to receive the data transmission of the inspection robot to the greatest extent, and can avoid the signal transmission problem caused by the complex environment of the integrated pipe gallery of the nuclear power plant.

[0077] In step S105 of some embodiments, the local server inputs the environmental sound data into a pre-trained sound analysis model, performs an abnormality recognition analysis, and obtains an abnormality recognition result. The sound analysis model is used to predict whether the environmental sound data contains features revealed by abnormal problems, and the abnormality recognition result is used to indicate the type of abnormal problem predicted by the environmental sound data.

[0078] It should be noted that the environment of the nuclear power plant's integrated pipeline corridor is complex, with poor visual conditions, and most items are arranged overlappingly in a relatively small space. Therefore, analyzing abnormal problems only through video, infrared and other data can easily lead to misjudgment or omission of abnormal problems.

[0079] And usually, not only do we need to find the abnormality, but we also need to judge the type of the abnormality. This is very important, because it can make the relevant personnel more targeted when they enter the site for maintenance, and it can also avoid the relevant personnel from entering the site multiple times, reducing the possibility of safety problems. If the abnormal problems in the nuclear power plant integrated pipe corridor will lead to serious dangerous problems, such as a fire in the nuclear power plant integrated pipe corridor, it can also remind the relevant personnel to take preventive measures when entering the site for maintenance. However, conventional detection methods are difficult to accurately judge, especially for abnormal problems such as pipeline steam leakage and abnormal vibration. It is a relatively reliable technical means to identify the type of abnormal problems by acquiring and processing sound signals.

[0080] In some embodiments, before the environmental sound data is input into the sound analysis model, the environmental sound data is preprocessed in the local server, including eliminating noise through low-pass filtering, and forming information data in a unified format through pre-emphasis, framing and windowing, so as to obtain preprocessed data for easy processing. The preprocessed data is then feature extracted, the preprocessed data is converted into a Mel-spectrogram, the time-frequency feature information is extracted, and then input into the sound analysis model for abnormal identification analysis. Through preprocessing and feature extraction, the influence of normal sound in the integrated pipe gallery of a nuclear power plant on abnormal identification analysis can be reduced, so that more accurate abnormal identification results can be obtained.

[0081] In step S106 of some embodiments, the local server obtains the inspection position data of the inspection robot in real time, and determines the inspection abnormal area based on the abnormal identification result and the inspection position data of the inspection robot. The inspection abnormal area indicates the approximate area where the abnormal problem exists, and is used for the inspection robot to conduct a more detailed inspection and determine the target abnormal source. The target abnormal source indicates the source of the abnormal problem and the specific location of the abnormal problem. Among them, the local server can obtain the inspection position data by transmitting the position information of the inspection robot in real time, or by combining the motion information of the inspection robot and the map information of the nuclear power plant integrated pipe gallery to obtain the inspection position data. For example, the inspection robot moves on the track at a fixed speed, and the start time of the inspection robot is known. Then, the movement distance of each inspection robot can be calculated by time and speed, and then combined with the map information of the nuclear power plant integrated pipe gallery, the inspection position data can be obtained. The local server can also determine the inspection position data of the inspection robot through the camera, locator and other equipment set in the nuclear power plant integrated pipe gallery.

[0082] When one of the inspection robots transmits environmental sound data to the local server, and the abnormal recognition result obtained by the sound analysis model indicates that there is an abnormal problem, the inspection abnormal area is determined based on the inspection position data of the inspection robot obtained through implementation.

[0083] Among them, the inspection abnormal area can be determined based on the characteristic strength of the abnormal recognition result. For example, after the abnormal recognition result is obtained from the environmental sound data, the distance of the target abnormal source relative to the inspection robot is determined by the obviousness of the sound characteristics representing the abnormal problem in the abnormal recognition result, so as to determine the approximate inspection abnormal area. The inspection abnormal area can also be determined based on the type of abnormal problem represented by the abnormal recognition result. For example, when the abnormal recognition result represents the abnormal problem of equipment vibration around the corresponding inspection robot, and when the abnormal recognition result represents the abnormal problem of pipeline steam leakage around the corresponding inspection robot, the determined inspection abnormal area is different.

[0084] When multiple inspection robots transmit environmental sound data to the local server, and the abnormal identification results obtained by the sound analysis model all indicate the same abnormal problem, the inspection abnormal area is determined based on the inspection position data of multiple inspection robots obtained in real time. It is understandable that sound will be transmitted through the integrated pipe gallery of the nuclear power plant, so the approximate range of the target abnormal source can be located through the inspection position data of multiple inspection robots, thereby determining the inspection abnormal area.

[0085] In steps S107 to S109 of some embodiments, the local server transmits the abnormal identification results and the abnormal inspection area to the corresponding inspection robot. The inspection robot receives the abnormal identification results and the abnormal inspection area transmitted by the local server, and then performs precise positioning in the abnormal inspection area based on the abnormal identification results, finds the location of the target abnormal source, and determines the target abnormal source. In some embodiments, the inspection robot can determine the position of the inspection robot relative to the target abnormal source by the size of the sound emitted by the target abnormal source. In some embodiments, relevant personnel can use the remote control terminal of the local server to control the inspection robot to find the target abnormal source through the local server. The inspection robot is equipped with a camera, and the inspection robot can move relative to the track to adjust the position of the inspection robot, so as to find the target abnormal source in the complex environment of the nuclear power plant integrated pipeline corridor.

[0086] See also Figure 2 In some embodiments, the inspection robot includes a sound sensor array, and step S102 may include but is not limited to step S201:

[0087] Step S201, collecting sound through a single sound sensor in the sound sensor array to obtain environmental sound data;

[0088] Step S109 may include but is not limited to steps S202 to S204:

[0089] Step S202, starting each sound sensor of the sound sensor array to collect sound in the inspection abnormal area to obtain sound array data;

[0090] Step S203, transmitting the sound array data to the local server in real time, so that the local server performs phase difference distance analysis based on the sound array data and the inspection position data to determine the location where the abnormality occurs;

[0091] Step S204, receiving the abnormality occurrence location transmitted from the local server, and determining the target abnormality source according to the abnormality occurrence location.

[0092] In step S201 of some embodiments, the inspection robot may be provided with a sound sensor array, and when performing an inspection operation, sound is collected only through a single sound sensor in the sound sensor array to obtain environmental sound data.

[0093] In step S202 of some embodiments, after determining the abnormal inspection area, all sound sensors of the sound sensor array are started to collect sound in the abnormal inspection area to obtain sound array data. The sound array data is also environmental sound data, but the difference is that the sound array data is environmental sound data collected by multiple sound sensors at the same time, which can reflect the phase difference of sound propagation.

[0094] In step S203 of some embodiments, the inspection robot transmits the sound array data to the local server in real time, and the local server performs phase difference distance analysis based on the sound array data and the inspection position data to determine the direction of sound propagation and the position where the abnormality occurs. The position where the abnormality occurs is used to indicate the position of the target abnormality source relative to the inspection robot.

[0095] The local server will perform arithmetic averaging of the audio amplitude for the collected sound array data, and compare the average values ​​of the sound array data collected at different times to determine the location of the abnormality. For example, the position of the target abnormality source relative to the inspection robot is determined by the positive or negative difference between the volume average value at time t and the volume average value at time t+1, and the distance of the target abnormality source relative to the inspection robot is determined by the difference between the volume average value at time t and the volume average value at time t+1.

[0096] In step S204 of some embodiments, the inspection robot receives the abnormality occurrence location transmitted from the local server, and determines the location of the target abnormality source according to the abnormality occurrence location.

[0097] Through steps S201 to S204, by using a sound array sensor, environmental sound data is collected through a single sound sensor during inspection, which can reduce the energy consumption of the inspection robot. When precise positioning is required in the inspection abnormal area, all sound sensors are turned on to collect the phase difference of the sound, and the target abnormal source is located, thereby accurately determining the position of the target abnormal source.

[0098] See also Figure 3 In some embodiments, before step S105, the local server may also pre-train the sound analysis model, which may include but is not limited to steps S301 to S304:

[0099] Step S301, obtaining a model training set; wherein the model training set includes a plurality of sound training samples, each sound training sample is configured with a corresponding sound sample label;

[0100] Step S302, inputting the sound training sample into the original sound analysis model for sample recognition training to obtain a sample recognition result;

[0101] Step S303, comparing the sample recognition result corresponding to the sound training sample with the sound sample label to obtain comparison deviation data;

[0102] Step S304, updating the model parameters of the sound analysis model based on the comparison deviation data, returning to execute inputting the sound training sample into the sound analysis model for sample recognition training, until the sound analysis model meets the preset training termination condition, and obtaining the pre-trained sound analysis model.

[0103] In step S301 of some embodiments, a model training set is obtained, wherein the model training set includes multiple sound training samples, and each sound training sample is configured with a corresponding sound sample label. The sound training samples include normal audio samples during normal operation of the nuclear power plant and abnormal audio samples under abnormal conditions. In some embodiments, abnormal audio samples are divided into 7 categories, corresponding to 7 different types of abnormal problems, and are assigned specific sound sample labels, including: fan abnormality (label 1), pump operation abnormality (label 2), steam pipe leakage (label 3), liquid medium leakage (label 4), valve vibration (label 5), pipeline vibration (label 6) and equipment vibration (label 7). Normal audio samples are assigned a sound sample label of label 0.

[0104] In steps S302 to S304 of some embodiments, the sound training sample is input into the original sound analysis model for sample recognition training to obtain a sample recognition result, and a comparison is performed based on the sample recognition result corresponding to the sound training sample and the sound sample label to obtain comparison deviation data, and the model parameters of the sound analysis model are updated based on the comparison deviation data. The comparison deviation data is the loss function calculation data. Then the execution returns again to input the sound training sample into the sound analysis model for sample recognition training until the sound analysis model meets the preset training termination condition, which is that the accuracy of the sound analysis model no longer improves and tends to be stable. The iterative training can be stopped to obtain a pre-trained sound analysis model.

[0105] In some embodiments, the loss function of the sound analysis model may use a cross entropy function, which is as follows:

[0106]

[0107] Where N is the number of sound training samples, K is the sound sample label (label 0 to label 7), y ik represents the label value of the kth label classification of the ith sound training sample, P ik represents the predicted value of the kth label classification of the ith sound training sample, and L is used to represent the damage function value of the cross entropy function.

[0108] Through steps S301 to S304, the original sound analysis model is trained by using sound training samples of different abnormal problems and normal audio samples under normal conditions, so that the final pre-trained sound analysis model can perform abnormality recognition analysis based on environmental sound data to obtain abnormality recognition results corresponding to different abnormal problem types.

[0109] In some embodiments, the sound analysis model after pre-training will also be trained based on the environmental analysis data obtained during the routine inspection process to continuously improve the sound analysis model and update the model parameters to improve the recognition accuracy of the model.

[0110] See also Figure 4 In some embodiments, the inspection robot further includes an image sensor, a temperature sensor, and an infrared sensor. Step S109 may include but is not limited to steps S401 to S404:

[0111] Step S401, collecting images through an image sensor to obtain environmental image data;

[0112] Step S402, collecting temperature through a temperature sensor to obtain ambient temperature data;

[0113] Step S403, collecting infrared data through an infrared sensor to obtain infrared image data;

[0114] Step S404, transmitting the environmental image data, the environmental temperature data and the infrared image data to the local server, so that the local server inputs the environmental image data into a pre-trained image analysis model for abnormality recognition analysis to obtain an image recognition result; and verifies the abnormality recognition result based on the image recognition result, the environmental temperature data and the infrared image data, and performs a hazard level assessment on the target abnormality source to obtain a comprehensive assessment result.

[0115] In steps S401 to S403 of some embodiments, after determining the abnormal inspection area, image acquisition can be performed through an image sensor to obtain environmental image data, temperature acquisition can be performed through a temperature sensor to obtain environmental temperature data, and infrared data acquisition can be performed through an infrared sensor to obtain infrared image data. This is because part of the environment of the nuclear power plant integrated pipe corridor is dim, but most of the pipeline facilities therein have certain temperature characteristics, and some conditions of the pipeline facilities can be observed through infrared image data. And when a fire occurs in the nuclear power plant integrated pipe corridor, the infrared sensor can accurately detect the fire situation.

[0116] In step S404 of some embodiments, the inspection robot can transmit the environmental image data, the environmental temperature data and the infrared image data to the local server, and the local server inputs the environmental image data into the pre-trained image analysis model for abnormality recognition analysis to obtain image recognition results. The image analysis model is pre-trained like the sound analysis model, and the specific training process is not discussed here.

[0117] Afterwards, the local server verifies the abnormality recognition results based on the image recognition results, ambient temperature data, and infrared image data, and evaluates the danger level of the target abnormal source to obtain a comprehensive evaluation result. The local server will reconfirm the target abnormal source based on the image recognition results, ambient temperature data, and infrared image data, and verify the abnormality recognition results. After verification of multi-dimensional data, the local server will evaluate the danger level of the target abnormal source based on the image recognition results, ambient temperature data, infrared image data, and abnormality recognition results to obtain a comprehensive evaluation result, and at the same time, send a warning message to relevant personnel. The comprehensive evaluation result represents the dangerousness evaluation of the target abnormal source through multi-dimensional data.

[0118] Through steps S401 to S404, the abnormality recognition results can be verified through environmental image data, environmental temperature data, and infrared image data, thereby increasing the reliability of patrol inspections of the nuclear power plant integrated pipeline corridor. Based on the image recognition results, environmental temperature data, infrared image data, and abnormality recognition results, the target abnormality source is evaluated for its danger level to obtain a comprehensive evaluation result, thereby evaluating the criticality and danger level of the target abnormality source, so that relevant personnel can better arrange processing tasks based on the comprehensive evaluation results.

[0119] In some embodiments, the inspection robot will simultaneously collect environmental image data, environmental temperature data, infrared image data and environmental sound data during inspection operations, wherein the environmental image data includes infrared image data. The inspection robot transmits the environmental image data, environmental temperature data, infrared image data and environmental sound data to a local server, and inputs them into a corresponding pre-trained neural network model for analysis to obtain a multi-dimensional analysis result, and determines whether there is an abnormal condition in the nuclear power plant's integrated pipeline corridor based on the multi-dimensional analysis result, and locates the target abnormal source based on the multi-dimensional analysis result and the inspection position data, and processes the target abnormal source.

[0120] See also Figure 5 In some embodiments, the local server further includes resource distribution data, wherein the resource distribution data records the distribution of various resources in the integrated pipe gallery. Step S109 may also include but is not limited to steps S501 to S502:

[0121] Step S501, based on the target abnormal source and the resource distribution data corresponding to the inspection abnormal area, the target abnormal source is evaluated for the danger level to obtain a comprehensive evaluation result;

[0122] Step S502: issuing an alarm message based on the target abnormal source and the comprehensive evaluation result to notify relevant personnel to handle the target abnormal source.

[0123] In step S501 of some embodiments, the local server will target the abnormal source and the resource distribution data corresponding to the inspection abnormal area, perform a danger level assessment on the target abnormal source, and obtain a comprehensive assessment result, so as to determine which resource has the abnormal problem and determine the degree of danger and urgency of the target abnormal source.

[0124] In some embodiments, in step S404, the abnormality recognition result is verified based on the image recognition result, the ambient temperature data, and the infrared image data, and the hazard level of the target abnormality source is evaluated. When a comprehensive evaluation result is obtained, the hazard level is also evaluated based on the resource distribution data corresponding to the inspection abnormal area to obtain a comprehensive evaluation result. This allows a more comprehensive understanding of the abnormality of the target abnormality source, which resource it is.

[0125] In step S502 of some embodiments, an alarm message is issued based on the target abnormal source and the comprehensive evaluation result to notify relevant personnel to handle the target abnormal source.

[0126] See also Figure 6 In some embodiments, after step S109, the local server may further include but is not limited to steps S601 to S603:

[0127] Step S601, selecting an adapted target response plan from a plurality of candidate response plans based on the abnormality recognition result; wherein the candidate response plan represents a pre-prepared processing plan corresponding to the abnormality recognition result;

[0128] Step S602, controlling the inspection robot to go to the emergency processing tool station closest to the target abnormality source, and automatically equipping the corresponding emergency processing equipment based on the target response plan;

[0129] Step S603, control the inspection robot to go to the inspection abnormal area, and use emergency processing equipment to perform emergency processing on the target abnormal source.

[0130] In step S601 of some embodiments, after the inspection robot determines the target abnormal source, the local server selects an adapted target response plan from multiple candidate response plans based on the abnormal identification result. The candidate response plan represents a pre-prepared processing plan corresponding to the abnormal identification result. For each type of abnormal problem in the abnormal identification result, a corresponding processing plan is prepared.

[0131] In steps S602 to S603 of some embodiments, the local server issues a control instruction to control the inspection robot to go to the emergency processing tool station closest to the target abnormal source, and automatically assemble the corresponding emergency processing equipment based on the target response plan. In the integrated pipe gallery of a nuclear power plant, the track for the movement of the inspection robot is set with an emergency processing tool station at a certain distance. The emergency processing tool station can provide tools and equipment to relevant personnel and assemble tools and equipment to the inspection robot. Since the inspection robot runs on the track, it has a certain load-bearing capacity and can carry some emergency processing equipment. Exemplarily, when a fire occurs in the cable of the integrated pipe gallery of a nuclear power plant, the local server can call other nearby inspection robots to go to the nearest emergency processing tool station, assemble fire-fighting tools, and then go to the target abnormal source for emergency treatment. The inspection robot that finds the target abnormal source can remain in place and keep observing the target abnormal source. The inspection robot can transmit the video screen to the local server in real time, so that the relevant personnel can understand the status of the target abnormal source in time. If there is a surveillance camera near the target abnormality source, the target abnormality source can be kept under observation. Then the inspection robot that finds the target abnormality source can also choose to go to the emergency processing tool station to assemble the corresponding emergency processing equipment.

[0132] It is understandable that the inspection robot can be equipped with lighting equipment to better perform inspections or determine target abnormality sources in the integrated pipeline corridor of a nuclear power plant with poor lighting conditions.

[0133] The inspection robot goes to the inspection abnormal area and uses the emergency processing equipment to perform emergency processing on the target abnormal source. This can be done by the inspection robot itself, for example, through a neural network model, or by relevant personnel controlling the inspection robot through a local server to perform emergency processing. At the same time, relevant personnel must be notified to prepare to enter the nuclear power plant integrated pipeline corridor to perform subsequent processing on the target abnormal source.

[0134] In some embodiments, after the inspection robot finds the target abnormal source, if it finds that the inspection robot cannot perform emergency treatment on the target abnormal source, the local server can control the inspection robot to go to the emergency treatment tool station to equip the tools required by the relevant personnel for treatment. For example, the inspection robot can carry maintenance tools for the relevant personnel, emergency supplies such as flashlights, masks, radiation meters or medical supplies.

[0135] Through steps S601 to S603, after the inspection robot determines the target abnormality source, it selects an adapted target response plan from multiple candidate response plans based on the abnormality identification results, and controls the inspection robot through the local server to go to the emergency processing tool station closest to the target abnormality source to automatically assemble the corresponding emergency processing equipment, and go to the inspection abnormal area to perform emergency processing on the target abnormality source, thereby achieving timely emergency processing of the target abnormality source, preventing the target abnormality source from further deteriorating, and reducing the possibility of danger when relevant personnel enter the nuclear power plant integrated pipeline corridor for processing.

[0136] The embodiment of the present application sets a track in the integrated pipe corridor of a nuclear power plant, and the inspection robot is installed on the track so that the inspection robot travels on the track, thereby avoiding the inspection robot from being affected by the complex environment of the integrated pipe corridor of the nuclear power plant, and can perform inspection operations more reliably. The inspection robot performs inspection operations on the integrated pipe corridor of the nuclear power plant, which reduces the number of times relevant personnel enter the integrated pipe corridor of the nuclear power plant, thereby reducing the possibility of injury to relevant personnel and improving the safety of inspection of the integrated pipe corridor of the nuclear power plant. The inspection robot obtains the inspection start instruction, performs inspection operations on the integrated pipe corridor, collects the corresponding environmental sound data of the inspection robot in real time during the inspection operation, and transmits the environmental sound data to the local server, so that the local server inputs the environmental sound data into the pre-trained sound analysis model for abnormal recognition analysis, obtains the abnormal recognition result, and determines the inspection abnormal area based on the abnormal recognition result and the inspection position data of the inspection robot. The inspection robot receives the abnormal recognition result and the inspection abnormal area transmitted from the local server, and accurately locates in the inspection abnormal area based on the abnormal recognition result to determine the target abnormal source. By collecting environmental sound data, the sounds generated by abnormal problems can be collected in the complex environment of the nuclear power plant's integrated pipeline corridor, and input into the sound analysis model pre-trained on the local server to obtain abnormal recognition results, thereby predicting abnormal problems existing in the nuclear power plant's integrated pipeline corridor, and by accurately locating the abnormal area during inspection, the target abnormal source can be reliably determined, thereby achieving safe and reliable inspection of the nuclear power plant's integrated pipeline corridor.

[0137] The embodiment of the present application also provides a nuclear power plant integrated pipe gallery inspection system, which can implement the above-mentioned nuclear power plant integrated pipe gallery inspection method. The system includes an inspection robot and a local server, specifically including:

[0138] The inspection robot obtains the inspection start instruction and performs the inspection operation based on the inspection start instruction; the inspection robot collects the corresponding environmental sound data in real time during the inspection operation; the inspection robot transmits the environmental sound data to the local server, and the local server inputs the environmental sound data into a pre-trained sound analysis model for anomaly recognition and analysis to obtain anomaly recognition results, and the local server determines the inspection abnormality area based on the inspection position data of the inspection robot; wherein the inspection position data is obtained by the local server in real time; the inspection robot receives the anomaly recognition results and inspection abnormality area transmitted by the local server; the inspection robot performs precise positioning in the inspection abnormality area based on the anomaly recognition results to determine the target abnormality source.

[0139] The specific implementation method of the nuclear power plant integrated pipeline corridor inspection system is basically the same as the specific implementation method of the nuclear power plant integrated pipeline corridor inspection method mentioned above, and will not be repeated here.

[0140] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned nuclear power plant integrated pipeline corridor inspection method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0141] See also Figure 7 , Figure 7 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0142] The processor 701 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0143] The memory 702 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 702, and the processor 701 calls and executes the nuclear power plant integrated pipeline corridor inspection method of the embodiment of this application;

[0144] Input / output interface 703, used to implement information input and output;

[0145] Communication interface 704, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);

[0146] A bus 705 that transmits information between the various components of the device (e.g., the processor 701, the memory 702, the input / output interface 703, and the communication interface 704);

[0147] The processor 701 , the memory 702 , the input / output interface 703 and the communication interface 704 are connected to each other in communication within the device via a bus 705 .

[0148] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned nuclear power plant integrated pipeline corridor inspection method is implemented.

[0149] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0150] The nuclear power plant integrated pipe corridor inspection method, system, electronic device and storage medium provided in the embodiment of the present application are provided with a track in the nuclear power plant integrated pipe corridor, and the inspection robot is installed on the track so that the inspection robot travels on the track, thereby avoiding the inspection robot from being affected by the complex environment of the nuclear power plant integrated pipe corridor, and can perform inspection operations more reliably. The inspection robot performs inspection operations on the nuclear power plant integrated pipe corridor, which reduces the number of times relevant personnel enter the nuclear power plant integrated pipe corridor, thereby reducing the possibility of relevant personnel being injured and improving the safety of inspecting the nuclear power plant integrated pipe corridor. The inspection robot obtains the inspection start instruction, performs the inspection operation on the integrated pipe corridor, collects the corresponding environmental sound data of the inspection robot in the process of performing the inspection operation in real time, and transmits the environmental sound data to the local server, so that the local server inputs the environmental sound data into the pre-trained sound analysis model for abnormal recognition analysis, obtains the abnormal recognition result, and determines the inspection abnormal area based on the abnormal recognition result and the inspection position data of the inspection robot. The inspection robot receives the abnormal identification results and inspection abnormal areas transmitted from the local server, and accurately locates the inspection abnormal area based on the abnormal identification results to determine the target abnormal source. By collecting environmental sound data, the sound generated by abnormal problems can be collected in the complex environment of the nuclear power plant integrated pipe corridor, and input into the sound analysis model pre-trained on the local server to obtain abnormal identification results, thereby predicting abnormal problems in the nuclear power plant integrated pipe corridor, and by accurately locating the inspection abnormal area, the target abnormal source can be reliably determined, and the nuclear power plant integrated pipe corridor can be safely and reliably inspected.

[0151] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0152] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0153] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0154] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0155] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0156] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0157] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0158] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0160] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0161] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A nuclear power plant integrated pipe gallery inspection method, applied to an inspection robot, characterized in that: A track is provided in the integrated pipe gallery, the inspection robot is installed on the track, and the method includes: Obtaining a patrol inspection start instruction, and performing a patrol inspection operation based on the patrol inspection start instruction; Real-time collection of environmental sound data corresponding to the process of performing the inspection operation; The environmental sound data is transmitted to a local server, so that the local server inputs the environmental sound data into a pre-trained sound analysis model for abnormality recognition analysis to obtain an abnormality recognition result, and determines the abnormal inspection area based on the abnormality recognition result and the inspection position data of the inspection robot; wherein the inspection position data is obtained by the local server in real time; Receiving the abnormality identification result and the abnormal inspection area transmitted from the local server; Based on the abnormality identification result, precise positioning is performed in the inspection abnormal area to determine the target abnormality source.

2. The method according to claim 1, characterized in that: The inspection robot includes a sound sensor array, and the real-time collection of corresponding environmental sound data during the inspection operation includes: Acquiring the environmental sound data by collecting sound through a single sound sensor in the sound sensor array; The performing precise positioning in the inspection abnormal area based on the abnormality identification result to determine the target abnormality source includes: Start each sound sensor of the sound sensor array to collect sound in the abnormal inspection area to obtain sound array data; Transmitting the sound array data to the local server in real time, so that the local server performs phase difference distance analysis based on the sound array data and the inspection position data to determine the location where the abnormality occurs; The abnormality occurrence location transmitted from the local server is received, and the target abnormality source is determined according to the abnormality occurrence location.

3. The method according to claim 1 or 2, characterized in that: The inspection robot further includes an image sensor, a temperature sensor and an infrared sensor, and the method further includes: Acquire images through the image sensor to obtain environmental image data; Collecting temperature through the temperature sensor to obtain ambient temperature data; Collect infrared data through the infrared sensor to obtain infrared image data; The environmental image data, the environmental temperature data and the infrared image data are transmitted to the local server, so that the local server inputs the environmental image data into a pre-trained image analysis model for abnormality recognition analysis to obtain an image recognition result; and based on the image recognition result, the environmental temperature data and the infrared image data, the abnormality recognition result is verified, and the danger level of the target abnormality source is assessed to obtain a comprehensive assessment result.

4. A nuclear power plant integrated pipe gallery inspection method, applied to a local server, characterized in that: The method comprises: Receive environmental sound data transmitted by the inspection robot; Inputting the environmental sound data into a pre-trained sound analysis model for abnormality recognition analysis to obtain an abnormality recognition result; Acquire the inspection position data of the inspection robot in real time, and determine the inspection abnormal area based on the abnormality recognition result and the inspection position data of the inspection robot; The abnormality identification result and the abnormal inspection area are transmitted to the corresponding inspection robot, so that the inspection robot can accurately locate the abnormal inspection area based on the abnormality identification result and determine the target abnormality source.

5. The method according to claim 4, characterized in that The step of inputting the environmental sound data into a pre-trained sound analysis model for abnormality identification analysis and obtaining an abnormality identification result further includes pre-training the sound analysis model, specifically including: Obtain a model training set; wherein the model training set includes a plurality of sound training samples, each sound training sample is configured with a corresponding sound sample label; Inputting the sound training sample into the original sound analysis model for sample recognition training to obtain a sample recognition result; Comparing the sample recognition result corresponding to the sound training sample with the sound sample label to obtain comparison deviation data; The model parameters of the sound analysis model are updated based on the comparison deviation data, and the sound training sample is input into the sound analysis model for sample recognition training until the sound analysis model meets the preset training termination condition, thereby obtaining the pre-trained sound analysis model.

6. The method according to claim 4, characterized in that The abnormality identification result and the abnormal inspection area are transmitted to the corresponding inspection robot, so that the inspection robot can accurately locate the abnormal inspection area based on the abnormality identification result and determine the target abnormality source, and further includes: Selecting an adapted target response plan from a plurality of candidate response plans based on the abnormality identification result; wherein the candidate response plan represents a pre-prepared processing plan corresponding to the abnormality identification result; Control the inspection robot to go to the emergency processing tool station closest to the target abnormality source, and automatically equip the corresponding emergency processing equipment based on the target response plan; The inspection robot is controlled to go to the inspection abnormal area, and the emergency processing equipment is used to perform emergency processing on the target abnormal source.

7. The method according to any one of claim 4, characterized in that: The local server also includes resource distribution data, wherein the resource distribution data records the distribution of various resources in the integrated pipe gallery, and the abnormal identification result and the abnormal inspection area are transmitted to the corresponding inspection robot, so that the inspection robot can accurately locate the abnormal inspection area based on the abnormal identification result. After determining the target abnormal source, it also includes: Based on the target abnormal source and the resource distribution data corresponding to the inspection abnormal area, a hazard level assessment is performed on the target abnormal source to obtain a comprehensive assessment result; An alarm message is issued based on the target abnormal source and the comprehensive evaluation result to notify relevant personnel to handle the target abnormal source.

8. A nuclear power plant integrated pipe gallery inspection system, characterized in that: The system includes an inspection robot and a local server, specifically including: The inspection robot obtains an inspection start instruction and performs an inspection operation based on the inspection start instruction; the inspection robot collects corresponding environmental sound data in real time during the execution of the inspection operation; the inspection robot transmits the environmental sound data to the local server, and the local server inputs the environmental sound data into a pre-trained sound analysis model for abnormality recognition and analysis to obtain an abnormality recognition result, and the local server determines the inspection abnormality area based on the inspection position data of the inspection robot; wherein the inspection position data is obtained by the local server in real time; the inspection robot receives the abnormality recognition result and the inspection abnormality area transmitted by the local server; the inspection robot performs precise positioning in the inspection abnormality area based on the abnormality recognition result to determine the target abnormality source.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the nuclear power plant integrated pipeline corridor inspection method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the nuclear power plant integrated pipeline corridor inspection method described in any one of claims 1 to 7 is implemented.

Images