Power plant operation and management tool internet-of-things supervision system

Abstract

The invention discloses a power plant operation and management tool internet-of-things supervision system, and relates to the technical field of industrial internet of things, and the method comprises the steps: collecting the real-time state data of a tool through a terminal sensor, packaging the data and an identity label through a preset protocol, and generating a LoRa uplink data package suitable for low-power-consumption transmission; and then the base station receives and demodulates the data packet, encapsulates the data packet into an IP data stream through a protocol adaptation layer, and uploads the data to a data center by using a high-speed channel with a built-in 5G module. And further, the server side carries out deep analysis and visualization processing on the original data to obtain an asset state view and a linkage alarm signal. Thus, a heterogeneous wireless communication network is constructed by fusing a 5G private network and the LoRa Internet of Things, low-cost, low-power-consumption and high-efficiency two-way communication and centralized supervision of Internet of Things terminal equipment in a factory are realized, the bottleneck problem of a downlink communication link is effectively solved, and finally, through a comprehensive management platform deployed at a cloud end, the Internet of Things terminal equipment in the factory can be managed. And data support is provided for management decision.

Description

Technical Field

[0001] This application relates to the field of industrial Internet of Things (IoT) technology, and more specifically, to an IoT monitoring system for power plant operation and management equipment. Background Technology

[0002] The daily operation and maintenance of large-scale energy facilities such as power plants and substations involve thousands of traditional tools and equipment, including safety visual signs, protective equipment (insulating boots, insulating gloves, safety ropes), and specialized kits (grounding wires). These assets are characterized by their large quantity, dispersed locations, high mobility, and low standardization; their management level directly affects the safety and efficiency of power production. With the advancement of the power Internet of Things (IoT) construction, how to achieve full lifecycle supervision of these massive amounts of materials has become a critical issue that the industry urgently needs to address.

[0003] However, current management of these assets largely relies on traditional manual recording, barcode, or passive RFID tag inventory methods, which have many drawbacks in practical applications. Firstly, status information is lacking; the management system cannot obtain real-time data on tool location, usage status (e.g., in stock, loaned, under maintenance, scrapped), temperature and humidity, and electrical status, posing serious safety hazards and management blind spots. Secondly, inventory efficiency is low; manual inventory is time-consuming, labor-intensive, error-prone, and lacks dynamic real-time monitoring, resulting in high asset loss rates and low utilization rates. Furthermore, existing technologies (such as passive RFID) are mostly one-way identification, lacking two-way interaction and the ability to issue commands to terminal devices or perform remote configuration, resulting in limited management functionality. In addition, there are significant economic challenges; deploying a pure cellular network (e.g., 4G / 5G) module for each terminal device would be prohibitively expensive for thousands of terminals due to power consumption, cost, and communication fees, making large-scale deployment economically unfeasible. While LoRa technology has been widely used in the Internet of Things (IoT) due to its low power consumption, long range, strong penetration, and low cost, its network capacity and uplink data transmission rate are limited. Although 5G technology boasts high bandwidth, low latency, and massive connectivity, and many power generation users have already built dedicated 5G networks covering their facilities, its terminal modules have higher costs and power consumption.

[0004] Therefore, there is an urgent need in this field for an optimized IoT monitoring system for power plant operation and management tools that can combine the technological advantages of LoRa and 5G, leveraging their strengths and compensating for their weaknesses, to build a monitoring system that can meet the economic requirements of massive terminal access while achieving stable, two-way, and real-time data interaction, in order to solve the problem of refined and intelligent management of traditional tools in industrial scenarios such as power plants. Summary of the Invention

[0005] This application is made in order to solve the above-mentioned technical problems.

[0006] According to one aspect of this application, a power plant operation and management equipment IoT monitoring system is provided, comprising: The status data acquisition module is used by the sensors within the terminal to collect current status data. The protocol packet module is used to package status data and its own unique identifier according to a preset protocol to obtain LoRa uplink data packets through the terminal main control chip; The protocol adaptation module is used to demodulate data packets in the processor inside the base station and encapsulate them into IP data streams through the protocol adaptation layer; The data transmission module is used to send IP data streams to the data center server through the 5G module built into the base station to obtain the raw data from the server. The visualization monitoring module is used to perform data analysis and visualization monitoring on the raw data from the server to obtain visualized asset status and linkage alarm signals.

[0007] Compared with existing technologies, this application provides a power plant operation and management equipment IoT monitoring system. First, it utilizes terminal sensors to collect real-time status data of the equipment and packages this data with identification identifiers using a preset protocol to generate a LoRa uplink data packet suitable for low-power transmission. Subsequently, the base station receives and demodulates the data packet, encapsulates it into an IP data stream through a protocol adaptation layer, and uploads the data to the data center using the high-speed channel of the built-in 5G module. Then, the server performs in-depth analysis and visualization processing on the raw data to obtain an asset status view and linked alarm signals. In this way, by integrating a 5G private network and LoRa IoT, a heterogeneous wireless communication network is constructed, enabling low-cost, low-power, and high-efficiency two-way communication and centralized monitoring of IoT terminal devices within the plant area. This effectively solves the bottleneck problem of the downlink communication link and ultimately provides data support for management decisions through a comprehensive management platform deployed in the cloud. Attached Figure Description

[0008] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0009] Figure 1 This is a block diagram of a power plant operation and management equipment IoT monitoring system according to an embodiment of this application.

[0010] Figure 2 This is a schematic diagram of data flow in the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application.

[0011] Figure 3 This is a block diagram of the protocol package module in the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application.

[0012] Figure 4 This is a block diagram of the visual monitoring module in the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application.

[0013] Figure 5 This is a block diagram of the cumulative risk early warning unit in the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application.

[0014] Figure 6 This is a block diagram of the overall architecture of the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application.

[0015] Figure 7 This is a schematic diagram illustrating the "one-to-many" downlink broadcast communication between a LoRa base station and a terminal in a power plant operation and management equipment IoT monitoring system according to an embodiment of this application.

[0016] Figure 8 This is a flowchart illustrating the specific implementation steps of the IoT monitoring method for power plant operation and management equipment according to an embodiment of this application. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] To address the problems mentioned above in the background technology, this application proposes an IoT monitoring system for power plant operation and management equipment. The purpose of this invention is to overcome the aforementioned deficiencies of the prior art and provide an IoT monitoring system for power plant operation and management equipment. This system aims to construct a heterogeneous wireless communication network by integrating 5G private networks and LoRa IoT, enabling low-cost, low-power, and high-efficiency two-way communication and centralized monitoring of thousands of IoT terminal devices within the plant area. This effectively solves the bottleneck problem of the downlink communication link and ultimately provides data support for management decisions through a comprehensive management platform deployed in the cloud. Figure 1 This is a block diagram of a power plant operation and management equipment IoT monitoring system according to an embodiment of this application. Figure 2 This is a schematic diagram of the data flow in the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application. Figure 1 and Figure 2As shown, the power plant operation and management equipment IoT monitoring system 100 includes: a status data acquisition module 110, used for sensors in the terminal to collect current status data; a protocol packet assembly module 120, used for packaging the status data and its own unique identifier according to a preset protocol through the terminal's main control chip to obtain LoRa uplink data packets; a protocol adaptation module 130, used for demodulating the data packets in the base station's internal processor and encapsulating them into IP data streams through a protocol adaptation layer; a data transmission module 140, used for sending the IP data streams to the data center server through the 5G module built into the base station to obtain the server's original data; and a visualization monitoring module 150, used for data parsing and visualization monitoring of the server's original data to obtain visualized asset status and linkage alarm signals.

[0019] In the aforementioned IoT monitoring system for power plant operation and management tools, the status data acquisition module 110 is used to collect current status data through sensors within the terminal. In a specific example of this application, the status data includes: timestamp, location coordinate data, triaxial acceleration data, remaining battery percentage, ambient temperature, and ambient humidity. It should be understood that due to the large spatial span and high mobility of tools in power plant operations, simple static ledgers cannot reflect the physical location, usage posture, and environmental safety status of tools in real time, leading to management blind spots and safety hazards. Therefore, this application integrates a multimodal sensor group to synchronously collect multi-dimensional data such as timestamps, location coordinates, triaxial acceleration, battery level, and ambient temperature and humidity, thereby comprehensively perceiving the real-time operating status and environmental characteristics of tools and providing accurate data support for subsequent risk coupling analysis. This effectively solves the problem of opaque asset status, achieving closed-loop monitoring of tools from trajectory tracking and behavior recognition to environmental monitoring, thereby significantly improving the safety and intelligence level of power plant operation and management.

[0020] Specifically, in one possible embodiment, the terminal's main control chip first responds to the system's preset acquisition cycle or an external trigger signal by sending wake-up commands to each sensor module and establishing data communication links. Subsequently, the main control chip drives the positioning module to parse satellite signals via a serial interface to obtain the current latitude and longitude coordinates, and reads the motion component data of the accelerometer in three orthogonal directions via a bus interface. Simultaneously, it uses an analog-to-digital converter to read the power supply voltage and convert it into a power percentage, while simultaneously acquiring environmental parameters through temperature and humidity sensors. Finally, the main control chip calls a real-time clock to generate corresponding timestamps, performs time-series alignment and formatting processing on all the aforementioned collected discrete physical quantities, and aggregates them into an internal buffer, thereby completing a standardized state data acquisition operation.

[0021] In the aforementioned IoT monitoring system for power plant operation and maintenance equipment, the protocol packetization module 120 is used to package status data and its unique identifier according to a preset protocol using the terminal main control chip to obtain LoRa uplink data packets. It should be understood that due to the large number of equipment in a power plant and the lack of attribution identifiers and unified formats for the raw physical data collected by sensors, direct transmission would lead to the receiving end being unable to identify the data source and content meaning, resulting in data confusion and loss. Therefore, this application further standardizes and packages status data and the device's unique identifier according to a preset communication protocol using the terminal main control chip to construct structured data packets with self-describing capabilities and identity traceability. This ensures the integrity and traceability of data during subsequent transmission, enabling the base station to accurately identify the status of each equipment in massive concurrent data, thereby guaranteeing the efficient and stable operation of heterogeneous network communication links.

[0022] In particular, in one specific embodiment, Figure 3 This is a block diagram of the protocol package module in the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application. Figure 3 As shown, the protocol packet assembly module 120 includes: a data frame encapsulation unit 121, used to encapsulate status data and its own unique identifier according to a preset protocol to obtain a data frame; and a spread spectrum modulation and amplification unit 122, used to map the data frame into a time-varying frequency signal using linear frequency modulation spread spectrum technology, and amplify its power to obtain a LoRa uplink data packet.

[0023] Specifically, the data frame encapsulation unit 121 is used to encapsulate the state data and its own unique identifier according to a preset protocol to obtain a data frame. It should be understood that simple data splicing cannot meet the stringent requirements of wireless communication protocols for data integrity verification and frame synchronization, and the lack of necessary control information makes it difficult for the receiver to extract the payload from noise. Therefore, this application further encapsulates the state data and its own unique identifier into a logical-level frame structure according to a preset protocol, thereby adding key control fields such as frame headers, frame lengths, and check bits to the original data. This provides the data stream with clear boundary definitions and error detection capabilities, ensuring high anti-interference and accuracy when transmitting data in complex electromagnetic environments, and providing a standard binary bitstream basis for physical layer signal modulation.

[0024] Specifically, in one possible embodiment, the processor first constructs a frame header preamble according to the communication protocol definition to indicate the start of data transmission and assist the receiver in achieving signal synchronization. Next, the system maps a unique identifier to the address field and fills the data field with serialized multidimensional state data. Based on this, the processor uses a specific verification algorithm to perform operations on the above fields, generating a verification sequence for detecting transmission errors and filling it into the frame tail. Specifically, the verification algorithm is a cyclic redundancy check algorithm, specifically adopting the CRC-16 / CCITT standard. This algorithm treats the data as a binary polynomial and compares it with a preset generator polynomial. Modulo-2 operations are performed to generate a 16-bit checksum, providing efficient error detection capabilities and accurately identifying bit errors during transmission, thus meeting the reliability requirements of low-power IoT scenarios. Finally, the processor combines the complete logical structure, including the synchronization header, address field, data field, and checksum field, into a continuous binary bit stream, thereby generating a standard data frame conforming to the link layer transmission specification, awaiting entry into the physical layer processing stage.

[0025] Specifically, the spread spectrum modulation and amplification unit 122 is used to map data frames into time-varying frequency signals using linear frequency modulation (LFM) spread spectrum technology, and then amplify the LFM signal to obtain LoRa uplink data packets. It should be understood that due to the presence of numerous metal obstructions and electromagnetic interference in power plant environments, traditional narrowband modulation techniques struggle to achieve reliable long-distance communication under low power consumption, easily leading to signal attenuation and packet loss. Therefore, this application further utilizes LFM spread spectrum technology to map logical data frames into time-varying frequency signals with strong anti-interference capabilities, and then amplifies the LFM signal to improve its power spectral density and penetration capability. This significantly expands the coverage of the wireless signal, ensuring that even under deep obstruction or strong noise backgrounds, the base station can accurately demodulate weak terminal signals, thereby achieving highly reliable physical layer uplink transmission.

[0026] Specifically, in one possible embodiment, after receiving a binary data frame, the RF transceiver encodes each group of bits into a linear frequency modulated pulse symbol with a specific slope according to a preset spreading factor (SF9-SF11). Subsequently, the modulation circuit generates a baseband signal whose frequency increases or decreases linearly with time and loads it onto a specified RF carrier frequency. Next, the power amplifier in the RF front-end amplifies the gain of the modulated RF signal to ensure its transmit power meets a preset requirement (e.g., 20dBm), thereby achieving a system link budget of 155-165dB. Finally, the electrical signal is converted into electromagnetic waves and radiated into space through an antenna via an impedance matching circuit, thus forming a LoRa physical layer uplink data packet with long-distance transmission capability.

[0027] In the aforementioned IoT monitoring system for power plant operation and management equipment, the protocol adaptation module 130 is used to demodulate data packets within the base station's internal processor and encapsulate them into IP data streams via a protocol adaptation layer. It should be understood that because the LoRa radio frequency protocol used by IoT terminals is a non-IP physical layer transmission standard, its data format cannot be directly recognized and processed by backbone networks or servers based on the TCP / IP protocol stack, resulting in severe communication barriers between heterogeneous networks. Therefore, this application further demodulates and restores the received radio frequency signals within the base station's internal processor and encapsulates the restored payload into a standard IP data stream via a protocol adaptation layer, thereby completing the format conversion from a private IoT protocol to a general network transmission protocol. This effectively eliminates protocol differences between heterogeneous networks, ensuring seamless access to the high-speed backhaul network for underlying sensed status data, and laying a standardized logical foundation for subsequent cross-network data transmission and centralized cloud processing.

[0028] Specifically, in one possible embodiment, the base station's radio frequency front-end first captures analog radio signals in the air and converts them into digital baseband signals using an analog-to-digital converter. Subsequently, the digital signal processor inside the base station uses a Fast Fourier Transform (FFT) algorithm to perform spectral analysis and demodulation on the signal. The efficient implementation of the Discrete Fourier Transform (DFT) can quickly decompose the signal spectrum, separate the effective signal from industrial electromagnetic noise, thereby extracting the original binary data frame from the spread spectrum signal and performing forward error correction to eliminate errors. Next, the processor calls a protocol adaptation middleware to strip the physical and link layer headers of the data frame, extracting the payload and device identifier. Finally, according to the User Datagram Protocol (UDP) or Transmission Control Protocol (TCP) specifications, the system adds network layer header information such as source IP address, destination IP address, and port number to the payload, reassembles it into a standard IP data packet, and temporarily stores it in a transmission queue awaiting scheduling.

[0029] In the aforementioned IoT monitoring system for power plant operation and maintenance equipment, the data transmission module 140 is used to send IP data streams to the data center server via the 5G module built into the base station to obtain the original server data. It should be understood that due to the complex environment and wide coverage area of ​​power plants, laying backhaul links using wired fiber optics presents challenges such as high construction difficulty, high cabling costs, and maintenance difficulties. Traditional wireless networks are also insufficient to meet the stringent requirements of low latency and high reliability for massive concurrent data. Therefore, this application further establishes a wireless connection with the core network via the 5G module built into the base station, utilizing the high-speed channel of the 5G private network to send IP data streams to the data center server in real time, thereby constructing a high-bandwidth, low-latency, and securely isolated data backhaul highway. This significantly reduces infrastructure construction costs while ensuring that monitoring data from massive amounts of equipment can be synchronized to the management platform in milliseconds, achieving real-time linkage between edge perception and cloud decision-making.

[0030] Specifically, in one possible embodiment, the 5G communication module within the base station first initiates an attach request to the 5G core network. After authentication, a secure data bearer channel is established, and a dedicated PDU session is established based on service priority. Subsequently, the module reads IP packets from the buffer queue, maps them to the corresponding quality of service stream, and uses orthogonal frequency division multiplexing (OFDM) technology to modulate the data onto a millimeter-wave or Sub-6GHz carrier. Next, the signal is directionally transmitted to a macro base station or indoor distribution system via a massive MIMO antenna array. The data is routed and forwarded through the 5G bearer network and core network, ultimately penetrating the firewall to reach the designated port of the data center server. The server-side network interface card receives and parses the data stream, thereby obtaining the server's raw data containing complete tool status information.

[0031] In the aforementioned IoT monitoring system for power plant operation and management equipment, the visualization monitoring module 150 is used to perform data analysis and visualization monitoring of the raw data from the server to obtain visualized asset status and linkage alarm signals. It should be understood that since the raw data received by the server is only a binary or hexadecimal encoded stream, lacking intuitive business semantics, and simply piling up data cannot directly assist managers in quickly identifying the spatial distribution and abnormal risks of equipment, leading to delayed regulatory decisions. Therefore, this application further performs in-depth business logic analysis and graphical rendering processing on the raw data from the server to transform the abstract underlying data into an intuitive digital twin view and monitor potential violations in real time. This enables a panoramic "one-map" control of the operational status of a massive number of equipment throughout the plant, ensuring that managers can immediately grasp asset dynamics and respond quickly to abnormal situations such as exceeding boundaries or failure to return equipment, thereby significantly improving the decision-making efficiency and safety early warning capabilities of power plant operation and management.

[0032] Specifically, in one possible embodiment, the system first receives raw data packets from the transport layer via a data interface and calls a parsing engine to extract the device's unique identifier, latitude and longitude coordinates, and timestamp information. Then, the system uses the device identifier as an index to retrieve the asset ledger database, obtains the static attributes of the tools, and projects the real-time location coordinates onto a high-precision electronic map model of the factory area, drawing device icons with status indicators at the corresponding coordinate points. Next, the background logic service performs a compliance scan based on static rules: on the one hand, it uses a point-to-surface inclusion algorithm to calculate whether the tool coordinates fall within a preset electronic fence polygon range to identify boundary violations; on the other hand, it calculates the continuous operating time of the tool based on the timestamp of the status change and compares it with the maximum allowable time limit. Once the monitoring results show that the tool's location has exceeded the boundary or its usage time has expired, the system immediately triggers an alarm interruption, marks the abnormal target on the map with a high-brightness flashing mark, and simultaneously generates a linked alarm signal.

[0033] Specifically, the alarm mechanism in the above embodiments is based on projecting updated tool information onto an electronic map and generating an alarm signal when a preset geofence or time threshold is triggered. The fundamental technical flaw of this mechanism is that its alarm logic relies entirely on static and isolated spatiotemporal coordinate judgments, completely ignoring the dynamic coupling relationship between the physical properties of tools and the spatial environment in the high-risk and complex scenario of a power plant. This oversight directly leads to two serious technical problems: First, it cannot effectively perform environmental compatibility analysis. When an ordinary metal tool with physical properties such as conductivity and magnetism is brought into a high-voltage or strong electromagnetic field area, even if its location does not cross the boundary, the inherent conflict between the tool and the environmental properties already constitutes a huge safety hazard, and the existing mechanism may fail to detect such potential risks. Second, the mechanism ignores the spatiotemporal cumulative effect of risks. It is permissible for certain tools to stay in a specific area for a short time, but prolonged stay will cause performance degradation or safety accidents. For example, if an insulated tool stays in a high-temperature area for too long, its insulation performance will decrease. Simple point-triggered alarms lack consideration of the risk exposure time integral and cannot effectively warn of such chronic safety hazards, and may even produce false alarms.

[0034] To overcome the aforementioned technical deficiencies, this technical solution proposes an algorithm based on a multidimensional spatiotemporal risk coupling field. Its core idea is to move beyond limiting risk assessment to geographic coordinate compliance checks. Instead, it calculates the mutual repulsion potential energy between the tool's own feature vector and the feature vector of its environment, and introduces a time dimension for risk integration, thereby achieving accurate early warning of implicit and cumulative risks. In one specific embodiment, Figure 4 This is a block diagram of the visual monitoring module in the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application. Figure 4 As shown, the visualization monitoring module 150 includes: a data parsing and decryption unit 151, used to parse the original data on the server to obtain decrypted status data; a spatial feature mapping unit 152, used to perform spatial mapping of heterogeneous environmental features on the decrypted status data based on the GIS environment database to obtain environmental attribute vectors and tool physical attribute vectors; a risk coupling estimation unit 153, used to estimate the risk coupling coefficients of the environmental attribute vectors and tool physical attribute vectors to obtain instantaneous risk coupling coefficients; and a cumulative risk early warning unit 154, used to perform cumulative risk judgment and dynamic early warning based on time integration of each instantaneous risk coupling coefficient in the historical risk cache queue based on data timestamps to obtain linkage alarm signals.

[0035] Specifically, the data parsing and decryption unit 151 is used to parse the server-side raw data to obtain decrypted status data. It should be understood that, to ensure the confidentiality and tamper-proof capability of critical power plant production data during wireless transmission, uplink data typically undergoes strict encryption encapsulation and compression encoding; direct reading only yields garbled text and fails to obtain the actual physical quantity information. Therefore, this application further utilizes a pre-set security key and protocol stack to perform decryption operations and formatted parsing on the server-side raw data, thereby stripping away the secure transmission layer and restoring the plaintext sensor sampling values. This ensures that, while maintaining a high level of data security protection, core business data such as timestamps, latitude and longitude, and environmental parameters are accurately extracted, providing reliable and standardized data input for subsequent spatial mapping and risk assessment, and ensuring the accuracy of the regulatory system's logical operations.

[0036] Specifically, in one possible embodiment, the data parsing and decryption unit first reads the header information of the original data packet to identify the encryption algorithm type and the corresponding key index identifier. Then, the unit calls the security authentication service module to obtain the corresponding session key from the key management center based on the device's unique identifier, and uses the Advanced Encryption Standard (AES) algorithm to decrypt the data payload, restoring it to an unencrypted binary stream. Next, the system performs an integrity check on the decrypted data. After confirming its integrity, it extracts the values ​​of each field sequentially according to the predefined communication protocol structure, byte by byte. Finally, the unit converts the extracted hexadecimal values ​​into decimal physical quantity readings, such as converting coordinate codes into standard latitude and longitude floating-point numbers, and voltage codes into electrical percentages, thereby outputting a clearly structured and semantically clear decrypted status data object.

[0037] Specifically, the spatial feature mapping unit 152 is used to perform spatial mapping of heterogeneous environmental features on the decrypted status data based on the GIS environmental database to obtain environmental attribute vectors and tool physical attribute vectors. It should be understood that, in order to overcome the limitation of traditional alarm mechanisms that can only sense location, it is necessary to quantitatively model the invisible, multi-dimensional environmental risk factors in space. Specifically, during execution, once the system receives the decrypted status data containing the real-time coordinates of the tools, it immediately calls the spatial indexing algorithm to accurately map it to the corresponding three-dimensional grid cell of the power plant's digital twin model. Immediately afterwards, the system synchronously retrieves the environmental attribute vector attached to that grid from the Geographic Information System (GIS) environmental database. This vector contains key information such as the voltage level, temperature field distribution, and electromagnetic intensity of the spatial point, and extracts the physical attribute vector of the tool itself from the asset database. Examples of properties include material conductivity, pressure resistance, and temperature resistance rating. This transforms a static electronic map into a dynamic, computable environmental potential field. By constructing a heterogeneous feature tensor that incorporates location, environmental, and tool attributes, a solid data foundation is laid for subsequent in-depth risk coupling analysis. This can be expressed by the formula: In the aforementioned formula, Represents an environment attribute vector; , , These represent the current voltage, current temperature, and current magnetic field strength at the current location, respectively. , , These represent the maximum value or danger threshold used for normalization of their respective physical quantities; The transpose symbol for a vector.

[0038] Specifically, the risk coupling estimation unit 153 is used to estimate the risk coupling coefficient of the environmental attribute vector and the tool physical attribute vector to obtain the instantaneous risk coupling coefficient. It should be understood that after obtaining the quantitative attributes of the tool and the environment respectively, a mathematical model capable of accurately measuring the degree of attribute conflict between the two must be established. Specifically, a non-negative definite hazard interaction matrix is ​​introduced, pre-calibrated by an expert system or trained by a machine learning algorithm. The training process for this matrix is ​​as follows: First, a training set containing a large amount of historical tool operation data is constructed, with each data point containing a tool attribute vector. , Environment attribute vector and the corresponding accident severity labels (Normalized to 0 to 1); secondly, construct the bilinear model loss function. Finally, the stochastic gradient descent algorithm is used to process the matrix. The elements in the matrix are iteratively updated until the loss function converges. Each element of the matrix defines a risk weight for a specific pair of physical properties of the tool and environmental properties when they interact. For example, this matrix can reflect that metal materials have extremely high risk weights when interacting with a high-voltage environment, while the weights for insulating materials interacting with a high-voltage environment are significantly reduced. By applying a bilinear form, the transpose of the tool physical property vector is... Danger Interaction Matrix and environment attribute vectors Matrix multiplication yields a scalar value, namely the instantaneous risk coupling coefficient. This approach abandons traditional if-then rule-based judgments and instead uses rigorous matrix operations to precisely quantify the hidden safety risks arising between tools with specific attributes and areas with specific attributes in specific industrial scenarios. The risk coupling coefficient between the environmental attribute vector and the physical attribute vector of the tools is estimated using the following formula: ;in, It is the transpose of the physical attribute vector of the tool; For pre-trained hazard weight matrix; This represents the instantaneous risk coupling coefficient; This is an environment attribute vector.

[0039] Specifically, the cumulative risk warning unit 154 is used to perform time-integral-based cumulative risk determination and dynamic warning on each instantaneous risk coupling coefficient in the historical risk cache queue based on data timestamps to obtain a linkage alarm signal. It should be understood that high instantaneous risks may be caused by non-continuous events such as signal drift or tools rapidly crossing dangerous areas; a time dimension must be introduced to distinguish between true lingering risks and brief transient risks. To address the problem of false alarms potentially caused by instantaneous risks, the system will perform time-integral-based cumulative risk determination and dynamic warning.

[0040] In particular, in one specific embodiment, Figure 5 This is a block diagram of a cumulative risk early warning unit in a power plant operation and management equipment IoT monitoring system according to an embodiment of this application. Figure 5 As shown, the cumulative risk warning unit 154 includes: a cumulative risk determination subunit 1541, used to perform time-integrated cumulative risk determination on each instantaneous risk coupling coefficient in the historical risk cache queue to obtain the cumulative risk index at the current moment; and a linkage alarm generation subunit 1542, used to determine whether to generate the linkage alarm signal based on the comparison between the cumulative risk index at the current moment and a preset threshold.

[0041] More specifically, the cumulative risk determination subunit 1541 is used to perform a time-integral-based cumulative risk determination on each instantaneous risk coupling coefficient in the historical risk cache queue to obtain the cumulative risk index at the current moment. Specifically, the system does not directly base its determination on... Instead of issuing an alarm, the risk is placed within a sliding time window and subjected to a weighted time integral calculation to obtain the cumulative risk index. This integral model introduces a time decay factor, giving higher weight to risk values ​​closer to the current moment. This perfectly simulates the process of heat accumulation or radiation dose absorption in a physical sense. Only when the accumulated risk index continuously exceeds a dynamically adjusted safety threshold will the system finally generate and issue an intelligent risk alarm signal. This cleverly solves the practical problem of whether a short stay should trigger an alarm in industrial site management. By modeling the cumulative effect of risk energy, the alarm mechanism can accurately identify chronic safety hazards caused by prolonged stays, thus achieving a full-cycle, high-precision closed-loop monitoring of the usage status of tools and equipment that considers both immediacy and continuity. In a specific example of this application, the cumulative risk determination of each instantaneous risk coupling coefficient in the historical risk cache queue is based on time integration using the following formula: ;in, This represents the cumulative risk index at the current moment; This is the size of the sliding time window, which can be set to 5 minutes. It is an integral variable, representing a past point in time; It is in the past moment The instantaneous risk coupling coefficient; This represents the time decay factor, used to adjust the weight of historical risk, and can be set to 0.02.

[0042] More specifically, the linked alarm generation subunit 1542 is used to determine whether to generate the linked alarm signal based on a comparison between the current cumulative risk index and a preset threshold. It should be understood that since high instantaneous risks are often caused by non-continuous events such as signal drift or tools rapidly crossing dangerous areas, directly triggering an alarm based on instantaneous values ​​would lead to an extremely high false alarm rate, making it impossible to distinguish between genuine loitering risks and brief transient risks. Therefore, this application further compares the calculated current cumulative risk index with a dynamically adjusted safety threshold in real time, using this as the decision-making basis for triggering the final alarm signal. This effectively filters out interference caused by short-term stays or data fluctuations, accurately identifies chronic safety hazards caused by prolonged exposure to incompatible environments, thereby ensuring that the generated linked alarm signal has extremely high reliability and business value, and achieving accurate early warning of the safety status of tools.

[0043] Specifically, in one possible embodiment, the linkage alarm generation subunit first receives the current cumulative risk index output by the cumulative risk determination subunit, such as 7.2 for high-voltage insulating gloves and 9.1 for ordinary metal wrenches. Based on the tool category, it retrieves the corresponding safety tolerance threshold from the database: 6.0 for high-voltage protective tools, 8.5 for general tools, and 5.0 for precision testing tools. Subsequently, the comparator logic module performs a numerical comparison operation, determining in real time whether the current cumulative risk index exceeds the set safety tolerance threshold. If the determination result is that it does not exceed the threshold (e.g., the cumulative risk index for precision testing instruments is 4.3, not exceeding the 5.0 threshold), the system maintains silent monitoring and continues to update the cache queue. If the determination result shows that the index has exceeded the threshold (e.g., 7.2 for high-voltage insulating gloves > 6.0, 9.1 for ordinary metal wrenches > 8.5), the logic module immediately generates a high-priority linkage alarm signal. The signal not only includes the identification and location information of the abnormal tools and equipment, but also carries the severity level of the accumulated risk. It also simultaneously triggers a pop-up warning on the visual interface and the action of the on-site audible and visual alarm devices, thus completing a closed-loop logic from risk calculation to intervention.

[0044] In summary, the fundamental purpose of the aforementioned visual monitoring module is to completely revolutionize the traditional alarm mode based on static geographical location. By introducing a multi-dimensional dynamic risk assessment model based on attribute conflicts and time accumulation, it achieves proactive and predictive safety early warning. This allows for the effective identification and early warning of hidden safety risks that traditional mechanisms cannot detect by quantifying the coupling relationship between tools and the inherent attributes of the environment, thus avoiding missed alarms that may result from environmental incompatibility. Simultaneously, by introducing a risk time integral model, it accurately distinguishes between instantaneous crossing and dangerous lingering, significantly reducing the false alarm rate and making the alarm system more intelligent and reliable. Ultimately, this mechanism elevates the safety monitoring level of power plant equipment from passive event response to proactive risk prevention, providing a more refined, intelligent, and deeply tailored risk early warning system for critical industrial facilities in complex application scenarios.

[0045] Furthermore, such as Figure 6 As shown, Figure 6This is a block diagram of the overall architecture of the IoT monitoring system for power plant operation and management equipment according to an embodiment of this application. The architecture clearly illustrates the closed-loop process from business requirement initiation to physical layer execution and data feedback. Specifically, the process begins with the initiation of a business requirement at the top level. The server-side IoT monitoring platform receives the business requirement, and the business layer, acting as the control center, initiates monitoring instructions for the equipment. Its management scope covers the management of monitored equipment and devices, IoT device facilities, and business relationship management. Subsequently, the instructions enter the downlink path, transmitted from the business layer to the network layer via a 5G wireless private network or a LoRa wireless IoT network. This process demonstrates the key technical characteristic of dual-network convergence, utilizing the complementarity of 5G and LoRa networks to balance high speed and wide coverage. After the instructions reach the gateway base station facility, they enter the protocol layer. Based on protocol compatibility, the system supports multiple protocols to adapt to different types of equipment (i.e., protocol 1 / 2 / 3), performing protocol conversion and adaptation. Intelligent scheduling, namely message queues and priority event mechanisms, ensures that critical instructions are processed first. Next, in the physical layer execution phase, the LoRa module's underlying communication mechanism is responsible for actual data transmission. It uses a data security shell to encrypt and decrypt wireless data, and combines channel planning, secure end-to-end encryption, anti-interference mechanisms, and low-power mechanisms. Its low-power design extends the battery life of the workpiece, reduces maintenance requirements, and ensures communication stability and long-term operation of the workpiece. Following this is the data uplink path, i.e., data transmission from the physical layer to the service layer. First, the physical layer collects the workpiece's status data, then encrypts and transmits the data via the wireless network. Next, the protocol layer performs protocol parsing to complete data parsing and format conversion, and finally, the data is sent to the server platform for service processing. Finally, the system implements a closed-loop service flow (parallel channel). This closed loop treats service flow as an independent channel for parallel processing, achieving end-to-end interactive management from service request initiation to completion of interaction, and ensuring real-time synchronization of service commands and data feedback through real-time monitoring.

[0046] Furthermore, such as Figure 7 As shown, Figure 7This diagram illustrates a "one-to-many" downlink broadcast communication between a LoRa base station and terminals in a power plant operation and management equipment IoT monitoring system according to an embodiment of this application. In the command initiation phase, the backend server management platform generates control commands, which are then transmitted at high speed to the base station location via a wired-to-5G network. The wired network provides a stable and reliable backend connection, while the 5G network enables high-speed remote transmission. Upon entering the base station processing phase, the base station performs a receive-to-transmit LoRa wireless transmission, converting the command data from the 5G network into LoRa wireless signals for broadcast transmission. This leverages the base station's wide coverage area to simultaneously connect multiple terminal devices. Regarding the addressing mechanism, the system uses ID addressing as the core method. Each terminal device has a unique identifier ID, and the base station filters target devices based on the ID. It supports unicast, multicast, and broadcast addressing modes to ensure accurate command delivery. During terminal device reception and processing, the terminal hardware can directly receive and parse commands. For long-distance or signal-obstructed areas, the network coverage can be extended through LoRa relays, allowing the terminal to receive and parse commands through relay nodes. This multi-path approach solves communication problems in long-distance or signal-obstructed areas. Finally, in the uplink communication phase of command execution and feedback, each terminal device first completes the execution operation, that is, executes the corresponding command function, and then transmits the result back. All terminal devices maintain a unified LoRa communication protocol and transmit the execution result as uplink data to the base station. The base station completes data aggregation, collects the feedback data from all terminal devices, and then enters the data transmission back to the server process. The base station processes the data and transmits the aggregated data back through the 5G network. The background server management platform is responsible for receiving and processing the result data, thereby monitoring the status and completing the entire communication loop to achieve remote monitoring and management.

[0047] Furthermore, to better understand the actual deployment and operation of this system, this application also provides a method for constructing a power plant operation and management equipment IoT monitoring system, such as... Figure 8 As shown, Figure 8This is a flowchart illustrating the specific implementation steps of the IoT monitoring method for power plant operation and management equipment according to an embodiment of this application. The method first deploys an IoT terminal layer, that is, installing or integrating an IoT terminal for each piece of equipment or device to be monitored. The core of this terminal is a low-power chip module with LoRa communication capabilities, and it can integrate various sensors and status detection circuits such as position sensors, pressure sensors, temperature and humidity sensors, as needed. All terminals are uniformly registered and assigned a unique identifier (ID). In addition to their respective functions, data transmission is handled by LoRa wireless. The second step is the construction of a heterogeneous wireless communication network layer, aiming to build a layered wireless communication network, specifically including the construction of a LoRa access subnet and a 5G backhaul subnet. In the LoRa access subnet, multiple LoRa base stations are deployed within the power plant area to form seamless signal coverage throughout the entire plant. These base stations are responsible for bidirectional data communication with all IoT terminals. In the uplink, IoT terminals periodically, or when triggered by events such as movement or status changes, transmit collected data such as ID, status, and sensor readings to the nearest LoRa base station via LoRa. Leveraging the low power consumption and long range of LoRa technology, this significantly extends terminal battery life and ensures coverage in remote areas. In the downlink, the powerful downlink broadcast capability of LoRa base stations solves the economic and efficiency issues of one-to-many downlink communication. Commands, query requests, or configuration information issued by the platform can be broadcast simultaneously from a single LoRa base station to tens of thousands of terminals. Terminals identify and respond to the corresponding commands based on their own IDs, avoiding the huge resource overhead of traditional point-to-point downlink communication. In the 5G backhaul subnet, a direct backhaul solution can be adopted, where LoRa base stations have built-in 5G communication modules or connect to 5GCPE via wired Ethernet to transmit the collected terminal data directly, securely, and at high speed to a remote data center server via a dedicated 5G wireless link. Alternatively, in complex or vast factory areas, a relay backhaul solution can be used, deploying dedicated LoRa repeaters or aggregation nodes to extend LoRa network coverage or aggregate data from more peripheral areas. These relay / aggregation nodes then use their built-in 5G modules to direct and transmit the data to the server. Finally, platform application layer deployment and management are performed. A comprehensive management platform software is deployed on the data center server. This platform receives all terminal data transmitted through the 5G network, stores, processes, and analyzes it, and provides functions such as electronic maps, asset ledgers, real-time status monitoring, lifecycle management, intelligent alarms, and report generation, thereby achieving visualized and intelligent supervision of all factory equipment.

[0048] Specifically, taking a large thermal power plant system as an example, the implementation of this system is as follows: First, in terms of network deployment, a central LoRa gateway base station is deployed at the center of the plant area. Multiple LoRa repeaters are deployed as needed in key areas such as the main plant building, maintenance workshop, and material warehouse to ensure that the signal strength in most areas of the plant meets the requirements, i.e., better than -110dBm. All LoRa base stations and repeaters access the 5G private network jointly built by the power plant and the operator through built-in 5G modules and obtain IP addresses. Next, in terms of terminal deployment, smart tags for LoRa communication modules, batteries, and sensors are built into 3,000 safety tools and commonly used power maintenance tools throughout the plant, along with smart tags affixed to each device, and other IoT kits. Each device is written with a unique ID at the factory and bound to the tool information in the platform database. Finally, in terms of platform deployment, a smart tool management platform is deployed on the power plant's private cloud server, and firewalls and security policies are set up to allow only LoRa base station IP addresses accessing the data interface via the 5G private network. The system operates in scenarios including status monitoring, downlink command inventory, and alarm functions. For example, in status monitoring, sensors on tools detect movement every minute. Once a tool is moved, it immediately reports its outbound status and its own ID to the base station via a LoRa link. The base station transmits the data to the platform via the 5G network, and the platform then updates the tool's status to "in use" on the electronic map and records the user's information. This process can be integrated with access control systems. In the warehouse inventory scenario, when a manager clicks the "Warehouse Inventory" button on the platform, the platform sends a "broadcast query" command to the LoRa base station covering the warehouse. The base station broadcasts this command to all tool terminals within the warehouse. Upon receiving the broadcast, each terminal immediately reports its own ID and status. The platform can automatically count all tools and generate an inventory report within seconds. Regarding the alarm function, if an insulated glove is taken out of its authorized area, such as the factory gate, and the LoRa base station connected to its terminal changes, the platform uses a positioning algorithm to determine that it has crossed the boundary, immediately triggering an alarm and notifying security personnel. This embodiment fully verifies the effectiveness and superiority of the construction method described in this application in achieving large-scale, low-cost, high-efficiency, and two-way interactive industrial IoT supervision.

[0049] In summary, the IoT monitoring system for power plant operation and management equipment based on the embodiments of this application is explained. It first utilizes terminal sensors to collect real-time status data of the equipment, and packages this data with identification identifiers using a preset protocol to generate LoRa uplink data packets suitable for low-power transmission. Subsequently, the base station receives and demodulates the data packets, encapsulates them into IP data streams through a protocol adaptation layer, and uploads the data to the data center using the high-speed channel of the built-in 5G module. Then, the server performs in-depth analysis and visualization processing on the raw data to obtain an asset status view and linked alarm signals. In this way, by integrating a 5G private network and LoRa IoT, a heterogeneous wireless communication network is constructed, enabling low-cost, low-power, and high-efficiency two-way communication and centralized monitoring of IoT terminal devices within the plant area. This effectively solves the bottleneck problem of the downlink communication link and ultimately provides data support for management decisions through a comprehensive management platform deployed in the cloud. Compared with existing technologies, this application has significant beneficial effects. First, it boasts exceptional cost-effectiveness. The terminal side utilizes extremely low-cost LoRa modules, overcoming the economic bottleneck of equipping massive numbers of devices with communication capabilities. The network side leverages the high reliability of 5G private networks, avoiding the cost of building a large number of wired networks. Second, it features an efficient communication architecture. It innovatively utilizes the powerful downlink broadcast capabilities of LoRa base stations to efficiently solve the "one-to-many" communication challenges of issuing commands and updating configurations for massive numbers of terminals, significantly reducing network signaling overhead and latency. Third, it offers comprehensive two-way interaction, enabling bidirectional data exchange from the platform to any terminal device. It can not only collect data but also remotely control, configure, and upgrade terminals, giving tools true data interaction capabilities. Simultaneously, it possesses powerful access capabilities and low power consumption. LoRa technology naturally supports group transmission and management connections, with a single base station capable of connecting thousands to tens of thousands of terminals. Terminal power consumption is extremely low, with battery life reaching several years, making it ideal for large-scale deployment of distributed, non-standard equipment. In terms of reliability and security, the 5G private network provides a low-latency, high-bandwidth, high-security, and isolated data backhaul channel, ensuring the reliability and security of critical production data transmission, meeting the stringent requirements of industrial scenarios. Finally, there is broad applicability. This construction method is not only applicable to tool management in power plants, but can also be extended to any industrial IoT scenario that requires data collection and status monitoring of a large number of dispersed, edge, and non-standard devices, such as petrochemicals, rail transportation, and large-scale warehousing.

[0050] As described above, the IoT monitoring system for power plant operation and management equipment according to embodiments of this application can be implemented in various wireless terminals. In one possible implementation, the IoT monitoring system for power plant operation and management equipment according to embodiments of this application can be integrated into the wireless terminal as a software module and / or hardware module. For example, the IoT monitoring system for power plant operation and management equipment can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the IoT monitoring system for power plant operation and management equipment can also be one of many hardware modules of the wireless terminal.

[0051] Alternatively, in another example, the power plant operation and maintenance equipment IoT monitoring system and the wireless terminal can also be separate devices, and the power plant operation and maintenance equipment IoT monitoring system can connect to the wireless terminal via wired and / or wireless networks and transmit interactive information in accordance with an agreed data format.

Claims

1. A power plant pipe walker instrumented supervision system, characterized in that, The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device.

2. The power plant runner tool internet-of-things monitoring system of claim 1, wherein, The application relates to a terminal state data acquisition and transmission method and device.

3. The power plant runner tool IoT supervisory system of claim 2, wherein, The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device.

4. The power plant runner tool IoT supervisory system of claim 1, wherein, The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device.

5. The power plant runner tool IoT supervisory system of claim 4, wherein, The risk coupling estimation unit comprises: estimating the risk coupling coefficient of the environment attribute vector and the tool physical attribute vector by the following formula: ; wherein, is the transpose vector of the tool physical attribute vector; is the pre-trained danger weight matrix; represents the instantaneous risk coupling coefficient; is the environment attribute vector.

6. The power plant runner tool IoT supervisory system of claim 4, wherein, The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data acquisition and transmission method and device. The application relates to a terminal state data 7. The power plant runner tool IoT supervisory system of claim 6, wherein, The cumulative risk judgment subunit comprises: cumulative risk judgment based on time integration of each instantaneous risk coupling coefficient in the historical risk cache queue according to the following formula: ; wherein, represents the cumulative risk index at the current moment; is the size of the sliding time window; is the integral variable, representing the past time point; is the instantaneous risk coupling coefficient at the past moment ; and represents the time attenuation factor.

Images