Power plant security patrol intelligent management method and system based on Internet of Things technology

Abstract

The invention provides a power plant security patrol intelligent management method and system based on the Internet of Things technology. The method comprises the following steps: acquiring a digital map of a marked forbidden area, acquiring initial data of each equipment object in a power plant through a sensor, and preprocessing the initial data through each corresponding edge processor; receiving the preprocessed data through the cloud, detecting an abnormal equipment object as a first patrol point by using a depth recognition model, and taking the first patrol point and a configured second patrol point as a patrol set; using a path search algorithm to generate a traversal sequence of the patrol set, using a next patrol point traversing to the current patrol point as an attraction field, using a forbidden area as a repulsive force field, using a virtual fluid mechanics path planning method to solve a patrol path, and marking the patrol path in a digital map; and importing the digital map marked with the patrol path into a mobile device of the patrol security guard, and monitoring the position of the patrol security guard in real time in the patrol process.

Description

Technical Field

[0001] The present application relates to the technical fields of industrial path planning and power plant inspection, and particularly relates to an intelligent management method and system for power plant security patrol based on Internet of Things technology. Background Art

[0002] The management of power plant security patrol based on the Internet of Things mainly refers to an intelligent solution that uses Internet of Things technology to optimize the security patrol route, efficiency, and safety. Its core goal is dynamic analysis and decision-making to improve the accuracy and response speed of patrol.

[0003] In related technologies, the traditional patrol path planning method is usually static and fixed. However, there are a large number of high-risk prohibited areas in power plants, such as high-voltage equipment, radiation areas, and high-temperature pipelines. The above technical means have the following defects: The traditional method explicitly defines the obstacle boundary, and the results generated by ordinary search algorithms such as the A* algorithm and the JSP (Jump Point Search) algorithm are very likely to be close to dangerous areas and cannot avoid mechanical sharp turns. There are still potential safety hazards in the paths close to the edge of the danger to a certain extent; in addition, the traditional algorithm requires static and accurate modeling and the computational cost of re-planning and solving is relatively large. Summary of the Invention

[0004] The embodiments of the present application provide an intelligent management method and system for power plant security patrol based on Internet of Things technology.

[0005] According to the first aspect of the embodiments of the present application, an intelligent management method for power plant security patrol based on Internet of Things technology is provided, including:

[0006] Obtain a digital map of the power plant, where the no-go areas are marked on the digital map;

[0007] Obtain the initial data of each equipment object in the power plant within the sensing range of each sensor through the respective sensors, and preprocess the initial data through the edge processor corresponding to each sensor to obtain the sensing data of each equipment object;

[0008] Receive the sensing data of each equipment object through the cloud, and detect abnormal equipment objects as the first patrol points based on the sensing data, and use the first patrol points and the configured second patrol points as a patrol set;

[0009] Use a path search algorithm to generate the traversal order of the patrol set, use the next patrol point reached when traversing to the current patrol point as the attraction field, use the no-go area as the repulsion field, and use the virtual hydrodynamics path planning method to solve the patrol path, and mark the patrol path on the digital map;

[0010] Import the digital map marking the patrol route into the mobile device of the patrol security guard, and monitor the position of the patrol security guard in real time during the patrol.

[0011] According to the second aspect of the embodiments of the present application, there is provided an intelligent management system for power plant security patrol based on Internet of Things technology, including:

[0012] A perception preprocessing module, configured to obtain the digital map of the power plant, obtain the initial data of each device object within the perception range of each sensor in the power plant through each sensor, and preprocess the initial data through the edge processor corresponding to each sensor to obtain the perception data of each device object; the no-go area is marked on the digital map;

[0013] A patrol point determination module, configured to receive the perception data of each device object through the cloud, and detect abnormal device objects as the first patrol points based on the perception data, and use the first patrol points and the configured second patrol points as a patrol set;

[0014] A path solving module, configured to use a path search algorithm to generate the traversal order of the patrol set, use the next patrol point reached when traversing to the current patrol point as the attraction field, use the no-go area as the repulsion field, and use the virtual hydrodynamics path planning method to solve the patrol path, and mark the patrol path on the digital map;

[0015] An application patrol module, configured to import the digital map marking the patrol path into the mobile device of the patrol security guard, and monitor the position of the patrol security guard in real time during the patrol.

[0016] According to the third aspect of the embodiments of the present application, there is provided an electronic device, including:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the foregoing first aspect.

[0020] According to the fourth aspect of the embodiments of the present application, there is provided a storage medium storing instructions, which when run on an electronic device, cause the electronic device to execute the method described in the foregoing first aspect.

[0021] According to a fifth aspect of the embodiments of the present application, a program product is provided, including at least one of a program and instructions, and when at least one of the program and instructions is executed by a processor, the steps of the method described in the foregoing first aspect are implemented.

[0022] According to the technical solution of the present application, abnormal equipment objects in the power plant are detected by sensors and deep recognition models in the power plant as the first patrol points, the first patrol points and the configured second patrol points are used as a patrol set, and based on a digital map marked with restricted areas, the virtual hydrodynamics path planning method is used to solve and automatically form a continuous patrol path for the patrol set. While reducing the possibility of mechanical sharp turns, it can always maintain a safe distance from the restricted area naturally; and when the digital map is adjusted, it can adapt in time, and the patrol path can be automatically generated without complex global calculations, which can greatly reduce the planning cost and calculation amount of the patrol path.

[0023] Additional aspects and advantages of the present application will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and / or additional aspects and advantages of the present application will become apparent and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0025] Figure 1 is a schematic flowchart of a power plant security patrol intelligent management method based on Internet of Things technology provided by an embodiment of the present application;

[0026] Figure 2 is a block diagram of a power plant security patrol intelligent management system provided by an embodiment of the present application;

[0027] Figure 3 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0029] The terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present application. The singular forms "a", "the", and "said" used in one or more embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0030] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0031] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.), and signals involved in the present application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0032] It is worth noting that in the embodiments of the present application, certain industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be considered exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0033] The intelligent management method and system for power plant security patrol based on Internet of Things technology in the embodiments of the present application will be described below with reference to the accompanying drawings.

[0034] Among them, it should be noted that the execution subject of the intelligent management method for power plant security patrol based on Internet of Things technology in the embodiments of the present application can be an intelligent management system for power plant security patrol based on Internet of Things technology. This system can be implemented in the form of software and / or hardware, and this system can be configured in an electronic device. Exemplarily, the electronic device can include but not be limited to a terminal, a server, etc.

[0035] Figure 1 It is a schematic flowchart of the intelligent management method for power plant security patrol based on Internet of Things technology provided for the embodiments of the present application. As Figure 1 shown, the intelligent management method for power plant security patrol based on Internet of Things technology may include but not be limited to the following steps.

[0036] In step 101, a digital map of the power plant is obtained, and no-go areas are marked on the digital map.

[0037] Exemplarily, no-go areas are marked in a specific color (such as red) on the digital map. No-go areas are not within the scope of the security patrol of the power plant and are the responsibility of the department that specifically deals with dangerous scenario situations, or are the responsibility of robots. Other immovable parts such as walls also belong to no-go areas.

[0038] In step 102, initial data of each device object within the sensing range of the sensors in the power plant is obtained through each sensor, and the initial data is preprocessed by the edge processor corresponding to each sensor to obtain the sensing data of each device object.

[0039] Exemplarily, sensors are installed at key positions in the power plant, and various types of initial data are obtained through sensors installed at the positions of device objects, which include temperature sensors, humidity sensors, smoke detectors, vibration sensors, infrared thermal imaging devices, and cameras.

[0040] In some embodiments, each type of initial data can be sequentially subjected to missing value filling, abnormal and duplicate data removal, and normalization processing by each edge processor to obtain preprocessed data, that is, the sensing data of each device object. Using the edge processor to perform preliminary processing on the initial data can reduce the amount of data uploaded to the cloud, thereby accelerating the response speed.

[0041] In step 103, the sensing data of each device object is received through the cloud, and an abnormal device object is detected as the first patrol point based on the sensing data using a deep recognition model, and the first patrol point and the configured second patrol point are used as a patrol set.

[0042] In some embodiments, a pre-trained deep autoencoder is obtained as the deep recognition model; the sensing data is input into the deep recognition model, and the data is reconstructed through the deep recognition model; a reconstruction error is calculated based on the sensing data and the reconstructed data output by the deep recognition model, and the difference between the reconstruction error and a preset threshold is determined, and the device object whose difference is outside the preset interval is used as the first patrol point.

[0043] It should be noted that in the embodiments of the present application, the deep autoencoder has different parameters for different device objects, that is, different deep autoencoders can also be used in different situations; in the embodiments of the present invention, the structure of the deep autoencoder is not limited.

[0044] In an embodiment of the present application, after detecting an abnormal device object as the first patrol point from the device objects in the power plant based on the perception data using a depth recognition model, the first patrol point and the configured second patrol point can be used as a patrol set, that is, the objects to be patrolled. The first patrol point can refer to a device object point regarded as deviating from the normal mode; the second patrol point can be a device object point configured in advance (such as manually configured), for example, it can be determined according to the key device objects in the actual patrol.

[0045] In step 104, a path search algorithm is used to generate the traversal order of the patrol set. Taking the next patrol point traversed to the current patrol point as the attractive force field and the no-go area as the repulsive force field, the virtual hydrodynamics path planning method is used to solve the patrol path, and the patrol path is marked on the digital map.

[0046] It should be noted that the path planning of virtual hydrodynamics directly moves along a single negative gradient and usually can only converge to the nearest or the lowest potential energy patrol point. However, for the embodiments of the present application that include multiple patrol points, it is necessary to ensure that the path passes through all the patrol points in the patrol set. Therefore, the patrol set can be abstracted as a complete graph connected by straight-line distances to pre-generate a processing order, that is, the traversal order. Since the paths between the patrol point nodes are not originally straight lines, but processing them as straight-line distance connections is convenient for calculation, so the executable path with bends can be solved by the virtual hydrodynamics path planning method.

[0047] In some embodiments, the patrol set can be abstracted as a complete graph connected by straight-line distances, and the minimum spanning tree algorithm (Prim algorithm or Kruskal algorithm) is used to start traversing from the node closest to the starting point of the patrol security until all the nodes in the complete graph are traversed to obtain the traversal order.

[0048] It should be noted that when using the virtual hydrodynamics path planning method for each solution, only the next patrol point is included in the attractive force field, and all no-go areas can be used as the repulsive force field to construct a phased solution model. After reaching the next patrol point along the negative gradient direction, the attractive force field is switched while the repulsive force field remains unchanged, and the process is repeated until all the patrol points in the traversal order are visited. Optionally, in some embodiments, the above-mentioned optional implementation manner of using the virtual hydrodynamics path planning method to solve the patrol path by taking the next patrol point traversed to the current patrol point as the attractive force field and the no-go area as the repulsive force field includes: taking the next patrol point currently solved as the target point, and constructing the attractive force field based on the target point using the attractive force field function Constructing the repulsive force field U based on all no-go areas using the repulsive force field function rep (P), based on the attractive force field and the repulsive force field U rep Determining the total potential field U (k)(P); Move along the negative gradient direction of the total potential field U at the current patrol point to the target point, which is used as the patrol path from the current patrol point to the target point until the traversal order is solved. As an example, the formula of the attraction field function is as follows: (k) (P) to the target point along the negative gradient direction of (P), which is used as the patrol path from the current patrol point to the target point until the traversal order is solved. As an example, the formula of the attraction field function is expressed as follows:

[0049] The formula of the repulsive force field function is expressed as follows:

[0050] The formula of the total potential field function is expressed as follows:

[0051] Among them, P represents the coordinates of the current patrol point, A k represents the attraction intensity of the target point, t k represents the coordinates of the target point, σ k represents the action range of the attraction force, n represents the number of no-go zones, B i represents the repulsive force intensity of the no-go zone i, d i (P) represents the shortest distance from the current patrol point to the no-go zone i, and ∈ represents the prevention of zero infinitesimal.

[0052] When obtaining the total potential field U (k) (P) of the current patrol point, the gradient vector of this total potential field can be determined Based on this gradient vector, the movement in the negative gradient direction of the total potential field is η > 0 represents dynamic adjustment of the step size until the traversal order is solved.

[0053] For example, taking the patrol points in the patrol set including a control room, b transformer, and c fire station as an example, using the path search algorithm to generate the traversal order of this patrol set as b transformer, a controller, c fire station. Taking the next patrol point (a controller) after traversing to the current patrol point (b transformer) as the target point, using the attraction field function to construct the attraction field based on the target point (a controller), using the repulsive force field function to construct the repulsive force field based on all no-go zones, using the total potential field function to calculate the total potential field, moving from the current patrol point (b transformer) along the negative gradient direction of this total potential field to the target point (a controller), which is used as the patrol path from b transformer to a controller, and so on, the patrol path from a controller to c fire station can be obtained, thus obtaining the entire patrol path of the patrol set.

[0054] It should be noted that in path planning, the low point of the total potential field corresponds to the strongest attraction of the target point, and vice versa for the strongest repulsive force. The negative gradient direction is the direction in which the potential energy drops the fastest, which can naturally generate a continuous path and avoid the principle no-go zone, and always naturally maintain a safe distance without sticking to the edge of the no-go zone.

[0055] In step 105, the digital map marking the patrol path is imported into the mobile device of the patrol security guard, and the position of the patrol security guard is monitored in real time during the patrol.

[0056] In some embodiments, when obtaining the digital map marking the patrol path, the digital map marking the patrol path can be sent to the mobile device of the patrol security guard, and the mobile device displays the digital map to guide the patrol security guard to conduct the patrol. During the patrol, if the patrol security guard is inside the power plant building, Bluetooth technology is used to locate the position of the patrol security guard, and when the Bluetooth signal strength is lower than the preset strength, a laser SLAM (Simultaneous Localization and Mapping) positioning layer is used to detect positioning anomalies and correct the Bluetooth positioning result; if the patrol security guard is outside the power plant building, GNSS technology is used to locate the position of the patrol security guard.

[0057] That is to say, since the power plant patrol scenario has high requirements for safety performance, and due to the multipath effect in the indoor enclosed space affecting communication, it is more necessary to improve the high-precision positioning indoors. When the patrol security guard is inside the power plant building, Bluetooth technology is used for positioning. When the Bluetooth signal strength is lower than the preset strength, a laser SLAM positioning layer is used to detect positioning anomalies and correct the Bluetooth positioning result. The specific correction method is as follows: a state space model is established, and the data of the two positioning systems are used as observation inputs, and the optimal estimation is achieved through Kalman filtering; when the patrol security guard is outside the power plant building, GNSS technology is used for positioning. Thus, high-precision positioning without dead angles in the entire power plant area can be achieved.

[0058] Regardless of whether the patrol security guard is inside or outside the power plant building, when the moving distance of the patrol security guard exceeds the preset alarm range, an alarm can be activated and a prompt can be given within the mobile device, such as at least one of voice prompt and vibration prompt.

[0059] Optionally, in some embodiments, identity verification of the patrol security guard can also be performed. In a possible implementation manner, the facial features and voice features of the patrol security guard are collected; based on the facial features and the voice features, identity verification of the patrol security guard is performed. In the embodiments of the present application, a dual method of facial verification and voice verification can be used to verify the identity of the patrol security guard. For example: the facial features of the patrol security guard are collected and compared with the pre-stored file. After the comparison passes, the voice features of the patrol security guard are collected for voice recognition (such as voiceprint feature recognition verification), and after the recognition is successful, the identity verification ends. Thus, losses caused by the possible acquisition of a single password input method by others can be avoided.

[0060] Optionally, in some embodiments, facial verification can use the ArcFace high-precision model to enhance the discrimination effect through angular margin loss; when the identity verification is qualified, the digital map marking the patrol path is imported into the mobile device of the patrol security guard.

[0061] In summary, the present application uses sensors and a depth recognition model in a power plant to detect abnormal equipment objects in the power plant as the first patrol points, takes the first patrol points and the configured second patrol points as a patrol set, and uses the Prim algorithm or the Kruskal algorithm to solve the traversal order of the patrol set, ensuring that all patrol points are passed through and the order is as reasonable as possible when solving the patrol path; based on a digital map with marked no-go areas, uses the virtual hydrodynamics path planning method to automatically form a continuous patrol path. The negative gradient direction naturally bypasses the no-go areas, reducing the possibility of mechanical sharp turns and always maintaining a certain safe distance from the no-go areas to avoid patrolling along the edge; when the digital map is adjusted, it can adapt in a timely manner, and the patrol path can be automatically generated adaptively without complex global calculations, improving the computational performance and greatly reducing the planning cost and computational volume of the patrol path.

[0062] Figure 2 FIG. is a block diagram of an intelligent management system for power plant security patrol based on Internet of Things technology provided by an embodiment of the present application. As Figure 2 shown, the intelligent management system for power plant security patrol based on Internet of Things technology may include: a sensing preprocessing module 201, a patrol point determination module 202, a path solving module 203, and an applied patrol module 204.

[0063] Among them, the sensing preprocessing module 201 is configured to obtain a digital map of the power plant, obtain initial data of each equipment object within the sensing range of the sensors in the power plant through each sensor, and perform preprocessing on the initial data through the edge processor corresponding to each sensor to obtain the sensing data of each equipment object; the no-go areas are marked on the digital map.

[0064] The patrol point determination module 202 is configured to receive the sensing data of each equipment object through the cloud, and detect abnormal equipment objects as the first patrol points based on the sensing data, and take the first patrol points and the configured second patrol points as a patrol set.

[0065] The path solving module 203 is configured to use a path search algorithm to generate the traversal order of the patrol set, use the next patrol point reached when traversing to the current patrol point as the attraction field, use the no-go area as the repulsion field, use the virtual hydrodynamics path planning method to solve the patrol path, and mark the patrol path on the digital map.

[0066] The applied patrol module 204 is configured to import the digital map marked with the patrol path into the mobile device of the patrol security guard, and monitor the position of the patrol security guard in real time during the patrol process.

[0067] In some embodiments, the patrol point determination module 202 is configured to: obtain a pre-trained deep autoencoder as a depth recognition model, where the deep autoencoder has different parameters for different device objects; input the perception data into the depth recognition model and reconstruct the data through the depth recognition model; calculate a reconstruction error based on the perception data and the reconstructed data output by the depth recognition model, and determine the difference between the reconstruction error and a preset threshold, and use the device objects outside the preset interval as the first patrol points.

[0068] In some embodiments, the path solving module 203 is configured to: abstract the patrol set into a complete graph connected by straight-line distances, and use the Prim algorithm or the Kruskal algorithm to traverse starting from the node closest to the starting point of the patrol security until all nodes in the complete graph are traversed to obtain the traversal order.

[0069] In some embodiments, the path solving module 203 is configured to: use the next patrol point to be solved currently as the target point, and construct an attraction field based on the target point using the attraction field function Use the repulsion field function to construct a repulsion field U rep (P) based on all no-go areas, and determine the total potential field U and the repulsion field U rep (P); move from the current patrol point along the negative gradient direction of the total potential field U (k) (P) to the target point as the patrol path from the current patrol point to the target point until the traversal order is solved. (k) (P) until the traversal order is solved.

[0070] In some embodiments, the formula of the attraction field function is expressed as follows: The formula of the repulsion field function is expressed as follows: where P represents the coordinates of the current patrol point, A k represents the attraction intensity of the target point, t k represents the coordinates of the target point, σ k represents the attraction range, n represents the number of no-go areas, B i represents the repulsion intensity of the no-go area i, d i (P) represents the shortest distance from the current patrol point to the no-go area i, and ∈ represents a small quantity for preventing division by zero.

[0071] In some embodiments, the application patrol module 204 is further configured to: collect the facial features and voice features of the patrol security; perform identity verification on the patrol security based on the facial features and voice features.

[0072] In some embodiments, the application patrol module 204 is configured to: during the patrol, if the patrolling security guard is inside the power plant, use Bluetooth technology to locate the position of the patrolling security guard, and when the Bluetooth signal strength is lower than the preset strength, use the laser SLAM positioning layer to detect positioning anomalies and correct the Bluetooth positioning result; if the patrolling security guard is outside the power plant, use GNSS technology to locate the position of the patrolling security guard.

[0073] It should be noted that the foregoing explanation of the embodiments of the intelligent management method for power plant security patrol based on the Internet of Things technology also applies to the intelligent management system for power plant security patrol based on the Internet of Things technology in this embodiment, and will not be elaborated here.

[0074] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0075] As Figure 3 shown, it is a block diagram of an electronic device according to an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0076] As Figure 3 shown, the electronic device includes: one or more processors 301, a memory 302, and an interface for connecting the components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and can be installed on a common motherboard or otherwise installed as needed. The processor can process instructions executed within the electronic device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, each device providing some necessary operations (such as, as a server array, a group of blade servers, or a multi-processor system). Figure 3 One processor 301 is taken as an example herein.

[0077] The memory 302 is the non-transitory computer-readable storage medium provided by this application. Among them, the memory stores instructions executable by at least one processor, so that the at least one processor executes the intelligent management method for power plant security patrol based on the Internet of Things technology provided by this application. The non-transitory computer-readable storage medium of this application stores computer instructions, and these computer instructions are used to make a computer execute the intelligent management method for power plant security patrol based on the Internet of Things technology provided by this application.

[0078] As a non-transitory computer-readable storage medium, the memory 302 can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the intelligent management method for power plant security patrol based on the Internet of Things technology in the embodiments of this application (for example, the perception preprocessing module 201, the patrol point determination module 202, the path solving module 203, and the application patrol module 204 shown in the appendix). By running the non-transitory software programs, instructions, and modules stored in the memory 302, the processor 301 executes various functional applications and data processing of the server, that is, implements the intelligent management method for power plant security patrol based on the Internet of Things technology in the above method embodiments. Figure 2 The memory 302 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the electronic device. In addition, the memory 302 can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 302 may optionally include a memory remotely set relative to the processor 301, and these remote memories can be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and their combinations.

[0079]

[0080] The electronic device may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303, and the output device 304 can be connected through a bus or other means, Figure 3 Taking the connection through the bus as an example.

[0081] ​The input device 303 can receive input digital or character information and generate key signal inputs related to user settings and function controls of the electronic device, such as input devices like touchscreens, keypads, mice, trackpads, touchpads, pointing sticks, one or more mouse buttons, trackballs, joysticks, etc. The output device 304 can include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), etc. The display device can include, but is not limited to, liquid crystal displays (LCDs), light emitting diode (LED) displays, and plasma displays. In some embodiments, the display device can be a touchscreen.

[0082] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0083] These computing programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, device, and / or apparatus (e.g., disks, optical disks, memories, programmable logic devices (PLDs)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term “machine-readable signal” refers to any signal for providing machine instructions and / or data to a programmable processor.

[0084] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input received from the user can be in any form (including acoustic input, voice input, or tactile input).

[0085] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), the Internet, and blockchain networks.

[0086] A computer system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The server can also be a server of a distributed system, or a server combined with blockchain.

[0087] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved, and no limitation is made herein.

[0088] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub - combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. An intelligent management method for the security patrol of a power plant based on Internet of Things technology, characterized in that, Including: Obtain a digital map of the power plant, where a no-go area is marked on the digital map; Obtain initial data of each device object within the sensing range of each sensor in the power plant through each sensor, and preprocess the initial data through the edge processor corresponding to each sensor to obtain the sensing data of each device object; Receive the sensing data of each device object through the cloud, and use a deep recognition model based on the sensing data to detect abnormal device objects as the first patrol points, and use the first patrol points and the configured second patrol points as a patrol set; Use a path search algorithm to generate the traversal order of the patrol set, use the next patrol point reached at the current patrol point as the attraction field, use the no-go area as the repulsion field, and use the virtual hydrodynamics path planning method to solve the patrol path, and mark the patrol path on the digital map; Import the digital map marked with the patrol path into the mobile device of the patrol security guard, and monitor the position of the patrol security guard in real time during the patrol.

2. The method according to claim 1, characterized in that, The using a deep recognition model based on the sensing data to detect abnormal device objects as the first patrol points includes: Obtain a pre-trained deep autoencoder as the deep recognition model, where the deep autoencoder has different parameters for different device objects; Input the sensing data into the deep recognition model and reconstruct the data through the deep recognition model; Calculate the reconstruction error based on the sensing data and the reconstructed data output by the deep recognition model, determine the difference between the reconstruction error and a preset threshold, and use the device object outside the preset interval of the difference as the first patrol point.

3. The method according to claim 1, characterized in that The using a path search algorithm to generate the traversal order of the patrol set includes: Abstract the patrol set into a complete graph connected by straight-line distances, and use the Prim algorithm or Kruskal algorithm to start traversing from the node closest to the starting point of the patrol security guard until all nodes in the complete graph are traversed to obtain the traversal order.

4. The method according to claim 1, wherein The using the next patrol point reached at the current patrol point as the attraction field, using the no-go area as the repulsion field, and using the virtual hydrodynamics path planning method to solve the patrol path includes: Take the next patrol point to be solved currently as the target point, and construct an attraction field based on the target point using the attraction field function Use the repulsion field function to construct a repulsion field U based on all no-go zones rep (p), based on the attraction field and the repulsion field U rep Determine the total potential field U (k) (P); Move along the negative gradient direction of the total potential field U (k) (P) at the current patrol point to the target point, which is used as the patrol path from the current patrol point to the target point until the traversal order is solved.

5. The method according to claim 4, wherein The formula of the attraction field function is expressed as follows: The formula of the repulsive force field function is expressed as follows: Among them, P represents the coordinates of the current patrol point, and A k represents the attraction intensity of the target point, and t k represents the coordinates of the target point, and σ k represents the range of the attraction effect, n represents the number of no-go zones, and B i represents the repulsion intensity of the no-go zone i, and d i (P) represents the shortest distance from the current patrol point to the no-go zone i, and ∈ represents the prevention of zero infinitesimal quantity.

6. The method according to claim 1, wherein The method further includes: Collect the facial features and voice features of the patrol security guard; Authenticate the identity of the patrol security guard based on the facial features and the voice features.

7. The method according to any one of claims 1-6, characterized in that, The monitoring the position of the patrol security guard in real time during the patrol includes: During the patrol, if the patrol security guard is inside the power plant, use Bluetooth technology to locate the position of the patrol security guard, and when the Bluetooth signal strength is lower than the preset strength, use the laser SLAM positioning layer to detect positioning anomalies and correct the Bluetooth positioning result; If the patrol security guard is outside the power plant, use GNSS technology to locate the position of the patrol security guard.

8. An intelligent management system for security patrol in a power plant based on Internet of Things technology, characterized in that, Including: A perception preprocessing module, configured to obtain the digital map of the power plant, acquire the initial data of each device object within the sensing range of the respective sensors in the power plant through the sensors, and preprocess the initial data through the edge processors corresponding to the respective sensors to obtain the perception data of each device object; The no-go area is marked in the digital map; A patrol point determination module, configured to receive the perception data of each device object through the cloud, and detect abnormal device objects as the first patrol points based on the perception data using a deep recognition model, and use the first patrol points and the configured second patrol points as a patrol set; A path solving module, configured to use a path search algorithm to generate the traversal order of the patrol set, use the next patrol point reached when traversing to the current patrol point as the attraction field, use the no-go area as the repulsion field, and use the virtual hydrodynamics path planning method to solve the patrol path, and mark the patrol path in the digital map; An applied patrol module, configured to import the digital map marked with the patrol path into the mobile device of the patrol security, and monitor the position of the patrol security in real time during the patrol.

9. An electronic device, characterized in that, Comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-7.

10. A storage medium, the storage medium stores instructions, characterized in that, When the instructions run on the electronic device, the electronic device executes the method according to any one of claims 1-7.

Images