Electric power material warehouse RFID checking and comprehensive risk fire monitoring method and system
By calculating the comprehensive risk coefficient and dynamically adjusting the transmission power, the problem of flexibility in material location and fire monitoring in power material warehouses was solved, enabling accurate location of materials and flexible fire monitoring in power material warehouses, and improving the efficiency and accuracy of fire rescue.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-10
- Publication Date
- 2026-03-10
AI Technical Summary
The existing RFID inspection robots in power material warehouses have blind spots during inventory checks, making it impossible to accurately locate the position of materials. Furthermore, fire monitoring can only provide a single alarm and cannot dynamically adjust the alarm strategy, resulting in a disconnect between inventory data and actual location, which hinders flexible rescue efforts in the event of a fire.
By calculating the comprehensive risk coefficient of each material and equipment, and combining inertial measurement device data and radio frequency signals, the transmission power and path planning are dynamically adjusted to achieve dynamic adjustment of fire alarm strategies for multiple types of materials. The inertial measurement device data is used to compensate for the radio frequency signals, and the extended Kalman filter is used for positioning. The transmission power and path are dynamically adjusted to improve positioning accuracy and the flexibility of rescue strategies.
It enables accurate location of materials in power material warehouses and flexible fire monitoring, improves the flexibility of rescue strategies in fire situations, solves the problem of dynamic adjustment of fire alarm strategies for various types of materials, and enhances the efficiency and accuracy of fire rescue.
Smart Images
Figure CN121639100A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of intelligent robot technology, and in particular relates to a method and system for RFID inventory and comprehensive risk fire monitoring in power material warehouses. Background Technology
[0002] The power materials warehouse stores a large number of critical power equipment and materials, such as transformers, high-voltage switchgear, relay protection devices and various cables. These materials are characterized by their wide variety, high value and dense layout. Moreover, most of the stored materials are flammable, and the electrical equipment also poses a risk of overheating and fire during long-term operation.
[0003] In terms of inventory management, RFID inspection robots based on fixed readers have serious blind spots when dealing with the massive and multi-dimensional static materials stored in warehouses. The tags of materials in the upper and deeper parts of the shelves are difficult to read effectively, resulting in a serious disconnect between inventory data and actual location. This means that existing inspection robots cannot deeply integrate the precise location information of materials with the accurate spatial positioning of fires. Furthermore, fire monitoring during the inventory process can only achieve a single alarm and cannot dynamically adjust the alarm strategy for multiple types of materials, which is not conducive to flexible rescue in the event of a fire. Summary of the Invention
[0004] To address the aforementioned problems, this invention proposes a method and system for RFID inventory management and comprehensive risk fire monitoring in power material warehouses. This invention determines the comprehensive risk coefficient of each material and equipment by summing the weights of its value, criticality, hazard, and distance from the fire source. The comprehensive risk coefficients of all materials and equipment are then ranked, improving the flexibility of rescue strategies in fire situations and solving the problem of dynamic adjustment of fire alarm strategies for multiple types of materials.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solution: In a first aspect, the present invention provides a method for RFID inventory and comprehensive fire risk monitoring in power material warehouses, comprising: Acquire the radio frequency signals of RFID electronic tags and the fire monitoring status; The system locates electrical equipment based on radio frequency signals, with the transmission power dynamically adjusted according to the distance to the shelf; when the fire monitoring status indicates a fire, the system identifies the source of the fire. Determine the influence radius of the fire source equipment. For all materials and equipment falling within the influence radius, sum the weights of each material and equipment based on its value, criticality, danger, and distance from the fire source to determine the comprehensive risk coefficient of each material and equipment. The overall risk coefficients of all materials and equipment are ranked to determine the recommended fire monitoring strategy.
[0006] Furthermore, when locating power equipment based on radio frequency signals, the original phase value is compensated using data from an inertial measurement unit: ; in, The phase value after compensation; The phase value before compensation; For radio frequency wavelengths; and The antenna displacement and attitude changes are obtained by integrating the data from the inertial measurement unit.
[0007] Furthermore, through iterative prediction and updating, the estimated location of the tag and its covariance are obtained. When the trace of the covariance is less than the threshold, the location is determined to be successful.
[0008] Furthermore, the overall risk coefficient for: ; in, , and Weights corresponding to value, criticality, danger, and distance from the fire source; The value coefficient after value normalization; The criticality coefficient is the criticality coefficient after criticality normalization; This is the hazard coefficient after hazard normalization; This is the distance coefficient from the fire source after normalization.
[0009] Furthermore, the value coefficient is determined by the ratio of the actual value of the corresponding equipment to the preset standard value; criticality is determined based on availability in the reliability index, and the criticality coefficient is determined by the ratio of the actual criticality of the corresponding equipment to the preset criticality; hazard = probability of an accident × severity of the accident consequences, and the hazard coefficient is determined by the ratio of the actual hazard of the corresponding equipment to the preset hazard; the distance coefficient from the fire source is determined by the ratio of the actual distance of the equipment from the fire source to the preset safe distance.
[0010] Furthermore, transmission power Distance from robot to shelf Dynamic adjustment: ; in, The minimum achievable transmit power; The maximum achievable transmission power; The distance from the robot to the shelf; This represents the maximum distance from the robot to the shelf. This is the minimum distance from the robot to the shelf; The robot uses a preset index to dynamically optimize its path based on real-time reading results, defining the shelf inventory value function U = (number of unread tags) / (estimated scanning time). At intersections, the robot tends to turn in the direction with a higher value function U to maximize inventory efficiency.
[0011] Secondly, the present invention also provides an RFID inventory and integrated fire risk monitoring system for power material warehouses, comprising: The data acquisition module is configured to acquire the radio frequency signals of RFID electronic tags and the fire monitoring status. The fire source identification module is configured to: locate electrical materials based on radio frequency signals, wherein the transmission power is dynamically adjusted according to the distance to the shelf; and identify the fire source equipment when the fire monitoring status indicates that a fire has occurred. The comprehensive risk coefficient determination module is configured to: determine the influence radius of the fire source equipment; and for all materials and equipment falling within the influence radius, sum the weights of each material and equipment's value, criticality, danger, and distance from the fire source to determine the comprehensive risk coefficient of each material and equipment. The fire monitoring module is configured to sort all materials and equipment by their comprehensive risk coefficients and determine the recommended fire monitoring strategy.
[0012] Thirdly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the RFID inventory and comprehensive risk fire monitoring method for power material warehouses described in the first aspect.
[0013] Fourthly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the steps of the RFID inventory and comprehensive risk fire monitoring method for power material warehouses described in the first aspect.
[0014] Fifthly, the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the RFID inventory and comprehensive risk fire monitoring method for power material warehouses described in the first aspect.
[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention innovatively provides a method for RFID inventory management and comprehensive risk fire monitoring in power material warehouses. By dynamically adjusting the transmission power and ranking the comprehensive risk coefficients, it achieves accurate location and fire monitoring of power materials. The comprehensive risk coefficient of each material / equipment is determined by summing the weights of its value, criticality, hazard, and distance from the fire source. Ranking the comprehensive risk coefficients of all materials / equipment improves the flexibility of rescue strategies in fire situations and solves the problem of dynamically adjusting fire alarm strategies for multiple types of materials. Attached Figure Description
[0016] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.
[0017] Figure 1 This is a block diagram of the overall modular architecture of the robot system according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of the inspection process according to Embodiment 1 of the present invention; Figure 3 This is a flowchart of the fire monitoring process in Embodiment 1 of the present invention. Detailed Implementation
[0018] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0019] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0020] Example 1: like Figure 1 As shown in the figure, this embodiment provides a method for RFID inventory and comprehensive risk fire monitoring in power material warehouses, including the following steps: S1. Dynamic RFID spatial positioning based on motion compensation and EKF: Traditional mobile RFID inventory checks suffer from positioning ambiguity due to interference from robot motion posture and environmental multipath effects. This embodiment proposes an Extended Kalman Filter (EKF) RF positioning model that incorporates inertial navigation compensation. Specifically: S1.1 Motion distortion compensation: The original RSSI (Received Signal Strength Indication) and phase values are compensated using inertial measurement unit (IMU) data. The model is as follows: ; in, The phase value is the compensated value; the RF wavelength is the uncompensated phase value. For radio frequency wavelengths; and The antenna displacement and attitude changes are obtained by integrating the IMU data.
[0021] S1.2, EKF positioning estimation: A state vector is defined, and the observation model is established based on path loss and phase-distance relationship. EKF outputs the optimal estimate of tag location and its covariance through iterative prediction and updating. When the trace of the covariance is less than a threshold, the location is considered successful and associated with the shelf GIS model.
[0022] S2, such as Figure 2 As shown, the material-fire linkage alarm and rescue decision support mechanism: S2.1 Modeling of the fire's impact range: Fire monitoring is conducted using existing fire monitoring systems within the warehouse, or independently installed image-based fire monitoring systems. When a fire occurs, the fire source is identified, and the impact range is dynamically calculated based on the fire source type and environmental parameters; for example, the impact radius of solid fires. for: ; in, and These are parameters related to the combustible material.
[0023] S2.1.1 Determination of initial parameter values: Optionally, in the fire impact range model In the middle, parameters and These factors collectively determine the speed and pattern of fire spread. Their determination is not fixed but rather based on an adaptive learning process of "initial empirical values + real-time observation and correction." The initial parameter values (based on prior knowledge) are determined during the initial system deployment or when encountering unknown materials. and Set initial values based on prior knowledge. This prior knowledge comes from combustion characteristic data of typical combustible materials (such as solid wood, plastics, cables, and oils) in relevant standards and specifications. For example: ordinary solid materials (such as cardboard boxes and wooden pallets): combustion is relatively stable with a moderate spread rate. (Settings can be made...) ≈0.8~1.0 (near linear growth) A moderate value is set based on its packing density and spatial layout. Power cables: Their insulation is typically made of PVC or PE, which has a high heat release rate when burning and may produce molten droplets, leading to rapid spread. [Setting is possible] ≈0.7~0.9, The value is relatively high.
[0024] Flammable liquids such as transformer oil: Once ignited, the fire spreads extremely rapidly. The model may be more inclined to... ≈1.0~1.2 (accelerated growth), and given a relatively large value. Initial values. Warehouse material database: This is a unique advantage of this embodiment. During system initialization, a "material-combustion characteristic" mapping table is imported or learned and established. When the robot identifies a "high-voltage cable" near a fire source via RFID or vision, it automatically retrieves the preset values for that type of material from the database. and As initial parameters. The initial parameter table is shown in Table 1: Table 1 Initial Parameters
[0025] S2.1.2 Real-time observation and adaptive correction of parameters (based on online learning): right and Online calibration is performed to make the model predictions increasingly closer to the actual fire situation. Optionally, this process can be achieved using a parameter identifier based on recursive least squares or Kalman filtering. The specific implementation steps are as follows: Data Acquisition: From the moment the fire is confirmed, the robot periodically (e.g., every second) records the following data: : Current time (starting from the time the fire was confirmed).
[0026] Determine the actual radius of the observed fire area. R_observed(k): Obtained by analyzing infrared thermal images - using image processing algorithms (such as edge detection and threshold segmentation) to identify "fire zones" with temperatures significantly higher than the ambient temperature, and calculate their circumcircle radius or equivalent radius.
[0027] Parameter correction: adjusting the observed data over a period of time ( ), ( ), ..., ( Substitute into the model .
[0028] Take the logarithm of both sides of the equation to linearize it: ln(R(t))=ln(α)+β*ln(t).
[0029] Let Y = ln(R(t)), X = ln(t), A = ln(α), and B = β, then the model is transformed into Y = A + B * X.
[0030] Using recursive least squares, it is possible to base new observation data on... The online estimation of parameters A and B is updated to obtain the updated values. and .
[0031] S2.1.3 Model Update and Prediction: The fire spread model will be rerun using the corrected parameters to predict the fire's impact range over a future period. This updated, more accurate prediction range will be used to: refresh the dynamic list of threatened assets, more precisely identifying high-value assets that are about to be affected; and provide more reliable dynamic obstacle information for robot firefighting path planning, preventing robots from entering areas that are about to be covered by fire.
[0032] In conclusion, and The determination is a dynamic and intelligent process: Initialization phase: Initial values are obtained through a "material identification → database query" mechanism. Operation phase: The "real-time observation → parameter identification algorithm" loop is used to... and Continuous calibration is performed. Safety precautions: For unidentified materials or during the initial calibration phase, the system uses conservative parameters (i.e., sets relatively large parameters). and This approach ensures comprehensive early warning coverage and prioritizes safety. The advantage of this method is that it transforms the fire spread model of this invention from a static formula into a self-learning and self-correcting intelligent agent. It can adapt to the specific environments of different power warehouses (such as ventilation conditions and material layout) and provide differentiated and increasingly precise responses to different types of fires, greatly improving the reliability and practicality of the entire system.
[0033] S2.2 Calculation of Asset Risk Coefficient: For each person falling into the danger zone (influence radius) Calculate the comprehensive risk coefficient of material i. : ; in, , and The weights corresponding to value, criticality, and risk can be determined through historical data or simulation. The value coefficient after value normalization can be determined by the ratio of the actual value of the corresponding equipment to the preset standard value. The criticality coefficient is the criticality coefficient after criticality normalization. Criticality can be determined based on availability in the reliability index. Criticality = Mean Time Between Failures / (Mean Time Between Failures + Mean Time to Repair). The criticality coefficient can be determined by the ratio of the actual criticality of the corresponding equipment to the preset criticality. The risk coefficient is the risk factor after risk normalization. Risk (risk degree) = probability of accident occurrence × severity of accident consequences. The probability of accident occurrence is determined by the ratio of the number of equipment failures to the total number of equipment put into operation in history. The severity of accident consequences is the comparison between the economic loss caused by the failure of the corresponding equipment and the planned output value. The risk factor can be determined by the ratio of the actual risk of the corresponding equipment to the preset risk. The distance to the fire source is the normalized distance coefficient. The distance coefficient can be determined based on the ratio of the actual distance between the equipment and the fire source to the preset safe distance.
[0034] S2.3, Regarding the comprehensive risk coefficient The system sorts and generates a dynamic list of threatened assets with priority, which is pushed out along with the fire alarm to provide data support for rescue decisions.
[0035] S3. Interference-resistant adaptive RFID inventory management for high-density shelving: To address signal interference in environments with dense metal shelving, this embodiment proposes a three-pronged strategy integrating environmental perception, parameter adaptation, and intelligent path design. Specifically, it includes: S3.1 Dynamic Power and Frequency Agility: Transmit power Distance from robot to shelf Dynamic adjustment; simultaneously, the reader automatically monitors and switches to the channel with the least background noise. Transmit power. for: ; in, The minimum achievable transmit power; The maximum achievable transmission power; The distance from the robot to the shelf; This represents the maximum distance from the robot to the shelf. Minimum distance from the robot to the shelf; This is the preset index.
[0036] S3.2 Data-driven adaptive path planning: The robot dynamically optimizes its path based on real-time data readings. The shelf inventory value function U is defined as (number of unread tags) / (estimated scan time). At intersections, the robot tends to turn in the direction with the higher value function U to maximize inventory efficiency.
[0037] S4, such as Figure 3 As shown, the model integrates thermal imaging semantic segmentation of material attributes with concealed fire point identification: To identify concealed fire points inside materials, this embodiment trains a deep learning model for thermal imaging semantic segmentation in warehouse environments. Specifically: S4.1 Network Model and Training: The U-Net++ network is used, with an infrared thermal image I_IR as input. The network outputs two branches: a) a material category semantic segmentation map of size HxWxC; b) an anomaly confidence map A of size HxWx1. End-to-end training is performed using the multi-task loss function: L_total = α*L_CE + β*L_BCE, where L_CE is the cross-entropy loss, used to supervise the first branch of the network, i.e., the material category semantic segmentation map of size HxWxC. It is a standard loss function in semantic segmentation tasks, used to measure the difference between the pixel category probability distribution predicted by the network and the true category label (the manually labeled material category of each pixel). The calculation method is as follows: for each pixel location in the image, the cross-entropy between its predicted probability and the true label is calculated, and then averaged over all pixels.
[0038] L_CE=-(1 / N)*Σ_i[Σ_c(Gt_i,c*log(P_i,c))]; Where: N is the total number of pixels. i represents the i-th pixel. c represents the category index (e.g., 0=background, 1=cable, 2=transformer, etc.). Gt_i,c are the ground truth labels (one-hot encoded, 1 if the ground truth category of pixel i is c, 0 otherwise). P_i,c are the probabilities predicted by the network that pixel i belongs to category c.
[0039] Minimizing L_CE enables the network to accurately classify each pixel in the image into the correct material category (such as cable, transformer, background, etc.), thereby achieving accurate material region segmentation.
[0040] L_BCE is the Binary Cross-Entropy Loss, used to supervise the second branch of the network, which outputs the anomaly confidence score with dimensions H x W x 1. The Binary Cross-Entropy Loss is the standard loss function for binary classification problems, measuring the difference between the network's predicted confidence score for each pixel as "abnormal" and the true anomaly label. It is calculated for each pixel and averaged. L_BCE=-(1 / N)*Σ_i[ Gt_i*log(A_i)+(1-Gt_i)*log(1-A_i)]; Where: N is the total number of pixels. i represents the i-th pixel. Gt_i is the true anomaly label of pixel i (1 represents "abnormal", 0 represents "normal"). A_i is the confidence level of the network predicting that pixel i is "abnormal" (range 0~1). Minimizing L_BCE allows the network to accurately identify which pixel regions in the image have temperature anomalies, regardless of the specific material of the region, focusing only on "whether it is abnormal". α and β: loss weight coefficients, two hyperparameters greater than 0, used to balance the relative importance of the two loss terms L_CE and L_BCE in the total loss L_total. α controls the weight of the material semantic segmentation task. If the α value is set relatively large, it means that during training, the model will focus more on learning how to accurately segment different types of materials. β controls the weight of the anomaly detection task. If the β value is set relatively large, the model will focus more on learning how to keenly detect abnormal temperature rise regions.
[0041] Settings and adjustments: S4.2 Online Reasoning and Early Warning: During online operation, the average anomaly confidence level Ā_Rc is calculated for each segmented material area R_c. If Ā_Rc > θ_c (a category-specific threshold), a targeted preventative warning is triggered, enabling the qualitative, location, and cause determination of potential hazards.
[0042] Example 2: The data acquisition module is configured to acquire the radio frequency signals of RFID electronic tags and the fire monitoring status. The fire source identification module is configured to: locate electrical materials based on radio frequency signals, wherein the transmission power is dynamically adjusted according to the distance to the shelf; and identify the fire source equipment when the fire monitoring status indicates that a fire has occurred. The comprehensive risk coefficient determination module is configured to: determine the influence radius of the fire source equipment; and for all materials and equipment falling within the influence radius, sum the weights of each material and equipment's value, criticality, danger, and distance from the fire source to determine the comprehensive risk coefficient of each material and equipment. The fire monitoring module is configured to sort all materials and equipment by their comprehensive risk coefficients and determine the recommended fire monitoring strategy.
[0043] The working method of the system is the same as that of the RFID inventory and comprehensive risk fire monitoring method for power material warehouse in Example 1, and will not be repeated here.
[0044] Example 3: This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the RFID inventory and comprehensive risk fire monitoring method for power material warehouses described in Embodiment 1.
[0045] Example 4: This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, it implements the steps of the RFID inventory and comprehensive risk fire monitoring method for power material warehouses described in Embodiment 1.
[0046] Example 5: This embodiment provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the RFID inventory and comprehensive risk fire monitoring method for power material warehouses described in Embodiment 1.
[0047] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.
Claims
1. A method for power material warehouse RFID inventory and integrated risk fire monitoring, characterized in that, The method comprises the following steps: acquiring a radio frequency signal of an RFID electronic tag and a fire monitoring state; positioning the power materials according to the radio frequency signal, wherein the transmission power is dynamically adjusted according to the distance to the shelf; when the fire monitoring state is a fire, determining the fire source equipment; determining the influence radius of the fire source equipment, and determining the comprehensive risk coefficient of each material equipment according to the weight sum of the value, criticality, danger and distance from the fire source of each material equipment for all material equipment falling within the influence radius; sorting the comprehensive risk coefficients of all material equipment, and determining the fire monitoring recommendation strategy.
2. The electric power asset warehouse RFID inventory and integrated risk fire monitoring method of claim 1, wherein, When the power materials are positioned according to the radio frequency signal, the original phase value is compensated by using the inertial measurement device data: ； wherein, is the compensated phase value; is the uncompensated phase value; is the radio frequency wavelength; and is the antenna displacement and attitude change resulting from integration of inertial measurement device data.
3. The electric power asset warehouse RFID inventory and integrated risk fire monitoring method of claim 2, wherein, Through iterative prediction and update, the estimation of the tag position and its covariance are obtained, and when the trace of the covariance is less than a threshold value, it is determined that the positioning is successful.
4. The electric power asset warehouse RFID inventory and integrated risk fire monitoring method of claim 1, wherein, Comprehensive risk coefficient is: ； wherein, , and are weights corresponding to the value, the criticality, the danger, and the distance from the fire source; is a value coefficient after value normalization; is a criticality coefficient after criticality normalization; is a danger coefficient after danger normalization; is a distance from the fire source coefficient after distance from the fire source normalization.
5. The electric power asset warehouse RFID inventory and integrated risk fire monitoring method of claim 4, wherein, The value coefficient is determined by the ratio of the actual value of the corresponding equipment to the preset standard value; the criticality is determined according to the availability in the reliability index, and the criticality coefficient is determined by the ratio of the actual criticality of the corresponding equipment to the preset criticality; the danger = the possibility of accident occurrence × the severity of accident consequence, and the danger coefficient is determined by the ratio of the actual danger of the corresponding equipment to the preset danger; the distance from the fire source coefficient is determined according to the ratio of the actual distance of the equipment from the fire source to the preset safe distance.
6. The electric power asset warehouse RFID inventory and integrated risk fire monitoring method of claim 1, wherein, Transmit power Random robot-to-shelf distance Dynamic adjustment: ； wherein, is the minimum achievable transmit power; is the maximum achievable transmit power; is the robot-to-shelf distance; is the maximum robot-to-shelf distance; is the minimum robot-to-shelf distance; is a preset index; the robot dynamically optimizes the path based on real-time reading results, defines a shelf inventory value function U = (number of unread labels) / (estimated scanning time); at the intersection, the robot tends to turn in the direction with a higher value of the value function U, maximizing the inventory efficiency.
7. A power materials warehouse RFID inventory and integrated risk fire monitoring system, characterized in that, The method comprises the following steps: a data acquisition module configured to acquire a radio frequency signal of an RFID electronic tag and a fire monitoring state; a fire source determination module configured to position the power materials according to the radio frequency signal, wherein the transmission power is dynamically adjusted according to the distance to the shelf; when the fire monitoring state is a fire, determining the fire source equipment; a comprehensive risk coefficient determination module configured to determine the influence radius of the fire source equipment, and determine the comprehensive risk coefficient of each material equipment according to the weight sum of the value, criticality, danger and distance from the fire source of each material equipment for all material equipment falling within the influence radius; a fire monitoring module configured to sort the comprehensive risk coefficients of all material equipment, and determine the fire monitoring recommendation strategy.
8. A computer-readable storage medium having stored thereon a computer program, characterized in that The program is executed by the processor to realize the steps of the power material warehouse RFID inventory and comprehensive risk fire monitoring method according to any one of claims 1-6.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and capable of running on the processor, characterized in that, The processor executes the program to realize the steps of the power material warehouse RFID inventory and comprehensive risk fire monitoring method according to any one of claims 1-6.
10. A computer program product, characterised in that, The computer program product comprises a computer program, which is executed by the processor to realize the steps of the power material warehouse RFID inventory and comprehensive risk fire monitoring method according to any one of claims 1-6.