Warehouse safety management platform and method based on wireless radio frequency technology

Abstract

The invention discloses a warehouse safety management platform and method based on the wireless radio frequency technology, and relates to the technical field of monitoring analysis, and the method comprises the steps: collecting environment sensing data and radio frequency signal data, carrying out the three-dimensional space topology construction of a warehouse, generating a warehouse three-dimensional dynamic environment model, and carrying out the monitoring of the environment sensing data and the radio frequency signal data. Performing correlation analysis on temperature and humidity data in the environment sensing data and warehouse material attributes in the warehouse, generating material abnormal vibration trajectory data, and determining an environment parameter correlation matrix; inputting the environmental parameter incidence matrix and the material abnormal vibration trajectory data into a preset dynamic risk model for security threat probability assessment, generating an equipment abnormal operation characteristic spectrum, and outputting a warehouse regional risk grade distribution diagram; and fusing the warehouse regional risk level distribution diagram and the equipment abnormal operation characteristic spectrum, constructing a potential safety hazard identification optimization model, and pushing the model to a terminal to execute real-time safety early warning and equipment linkage management. The method has the effect of improving the safety management efficiency of the storeroom.

Description

Technical Field

[0001] The present application relates to the field of monitoring and analysis technology, and in particular to a warehouse safety management platform and method based on wireless radio frequency technology. Background Art

[0002] Radio frequency (RF) is a contactless automatic identification technology that emerged in the 1990s. Compared to traditional magnetic and IC card technologies, RF technology boasts non-contact, fast reading speeds, and zero wear. RF technology enables contactless, bidirectional data transmission between the reader and the RFID card, enabling target identification and data exchange. Compared to traditional barcodes, magnetic and IC cards, RF cards offer non-contact, fast reading speeds, environmental resistance, long lifespan, ease of use, anti-collision capabilities, and the ability to process multiple cards simultaneously.

[0003] In the related technologies, in traditional warehouse safety management, most solutions rely on manual inspections, video surveillance and combined monitoring of temperature and humidity sensors. In addition, the existing technology has a single monitoring dimension for environmental parameters, making it difficult to dynamically associate the potential risks between the properties of stored materials and changes in temperature and humidity, resulting in delayed warnings for accidents such as fire and corrosion. Secondly, abnormal state detection mainly relies on vibration sensor threshold alarms, but it cannot effectively distinguish between normal handling operations and abnormal vibrations caused by safety hazards, and lacks analysis of the spatiotemporal characteristics of vibration trajectories. The false alarm rate is high, which in turn reduces the efficiency of warehouse safety management and leaves room for improvement. Summary of the Invention

[0004] In response to the deficiencies of the existing technology, the present application provides a warehouse safety management platform and method based on wireless radio frequency technology.

[0005] In a first aspect, the present application provides a warehouse safety management method based on wireless radio frequency technology, comprising the following steps: Step S1: Parameter collection is performed through a wireless radio frequency sensor network deployed in the warehouse, including environmental perception data and radio frequency signal data. The radio frequency signal data includes radio frequency signal strength characteristic data, radio frequency tag displacement characteristic data, and radio frequency signal attenuation characteristic data. The environmental perception data includes temperature data, humidity data, and vibration parameter data. The three-dimensional spatial topology of the warehouse is then constructed to generate a three-dimensional dynamic environment model of the warehouse. Step S2: performing correlation analysis on the temperature and humidity data in the environmental sensing data and the properties of the stored materials in the warehouse, and detecting abnormal vibration states of the stored materials based on the displacement characteristic data of the radio frequency tags to generate abnormal vibration trajectory data of the materials, and then confirming the environmental parameter correlation matrix based on the correlation analysis results and the abnormal vibration trajectory data of the materials; Step S3: Input the environmental parameter association matrix and the material abnormal vibration trajectory data into a preset dynamic risk model to perform a safety threat probability assessment. Based on the radio frequency signal attenuation characteristic data, the equipment operation status is diagnosed to generate an abnormal equipment operation characteristic spectrum. Based on the safety threat probability assessment results and the abnormal equipment operation characteristic spectrum, a risk level distribution map for each warehouse area is output. Step S4: Integrate the warehouse area risk level distribution map and the equipment abnormal operation characteristic spectrum to build a safety hazard identification optimization model, and push the safety hazard identification optimization model to the terminal through the radio frequency communication network to implement real-time safety warning and equipment linkage management.

[0006] Preferably, the step S1 specifically includes the following steps: Deploy a wireless RF sensor network consisting of RF readers, temperature sensors, humidity sensors, and vibration sensors in the warehouse; The radio frequency tag signal strength data of the stored materials is collected in real time through the radio frequency reader, and the temperature data, humidity data and vibration parameter data are collected through the temperature sensor, humidity sensor and vibration sensor; Performing spatial filtering on the radio frequency tag signal strength data, thereby extracting radio frequency signal strength feature data after spatial filtering; The three-dimensional coordinate system of the equipment and storage materials in the warehouse is calibrated based on the radio frequency signal strength characteristic data after spatial filtering processing, and then a three-dimensional dynamic environment model of the warehouse is generated through point cloud registration technology based on the calibration results and environmental perception data.

[0007] Preferably, the step S2 specifically includes the following steps: Establishing a database of storage material properties, wherein the storage material properties include material ignition point threshold, material moisture absorption coefficient and material stability coefficient; Identify the spatiotemporal distribution of temperature and humidity data in the warehouse, and then divide the areas into different temperature and humidity risk levels based on the identification results. Then, match and analyze the storage material attributes in the storage material attribute database to generate a temperature and humidity-material attribute mapping relationship; The displacement characteristic data of the radio frequency tag is processed by wavelet transformation to separate the normal vibration parameter signal from the abnormal vibration parameter signal, and the spatiotemporal distribution characteristics corresponding to the abnormal vibration parameter signal are extracted. The spatiotemporal distribution characteristics of the abnormal vibration parameter signal are then mapped to the three-dimensional dynamic environment model of the warehouse to generate abnormal vibration trajectory data of the material; The temperature, humidity and material property mapping relationship is combined with the material abnormal vibration trajectory data for data fusion analysis to determine the environmental parameter correlation matrix.

[0008] Preferably, the step S3 specifically includes the following steps: Obtaining an environmental parameter correlation matrix, extracting temperature and humidity deviation, material ignition point proximity index, and vibration cumulative value from the environmental parameter correlation matrix, inputting the temperature and humidity deviation, material ignition point proximity index, and vibration cumulative value into a preset dynamic risk model, and thereby confirming a safety threat probability assessment result; Based on the safety threat probability assessment results, the risk propagation paths of the warehouse areas are modeled, and combined with the historical accident data stored in the cloud database, a risk propagation probability map is generated; Extract frequency domain features from the equipment's abnormal operation characteristic spectrum. The frequency domain features include harmonic distortion rate, signal attenuation rate, and noise floor change rate. An equipment status evaluation index system is constructed based on the harmonic distortion rate, signal attenuation rate, and noise floor change rate. Furthermore, an equipment status evaluation coefficient is determined based on the equipment status evaluation index system. The risk propagation probability map and the equipment status evaluation coefficient are superimposed and analyzed to generate a risk level distribution map for each warehouse area.

[0009] Preferably, the device operation status diagnosis based on the radio frequency signal attenuation characteristics to generate the device abnormal operation characteristic spectrum specifically further includes: Acquire radio frequency signal attenuation characteristic data, extract carrier frequency offset and phase noise parameters from the radio frequency signal attenuation characteristic data, and then construct device operation status baseline data based on the carrier frequency offset and phase noise parameters; The deviation between the RF signal attenuation characteristic data and the equipment operation status baseline data is monitored in real time. When the deviation is detected to exceed the preset deviation threshold, the abnormal operation characteristic spectrum of the equipment is generated based on the carrier frequency offset and phase noise parameters.

[0010] Preferably, the step S4 specifically includes the following steps: A safety hazard identification model is established based on the warehouse area risk level distribution map and the equipment abnormal operation characteristic spectrum, and the optimization factors corresponding to the safety hazard identification model are determined. The optimization factors include the risk level false alarm rate, early warning response time and linkage control accuracy; Dynamically adjust the safety hazard identification model and update the weight allocation strategy based on historical warning records and actual accident data feedback. Then, optimize the safety hazard identification model based on the weight allocation strategy to build a safety hazard identification optimization model. Design a graded warning strategy based on the safety hazard identification optimization model. The graded warning strategy includes yellow warning, orange warning, and red warning. Different levels of linkage control instructions are matched according to the abnormal operation characteristic spectrum of the equipment. The optimized safety hazard identification optimization model and graded warning strategy are pushed to the terminal through the radio frequency communication network, thereby executing real-time safety warning and equipment linkage management.

[0011] In a second aspect, the present application provides a warehouse safety management platform based on wireless radio frequency technology, including: The data acquisition module is used to collect parameters through the wireless radio frequency sensor network deployed in the warehouse, including environmental perception data and radio frequency signal data. The radio frequency signal data includes radio frequency signal strength characteristic data, radio frequency tag displacement characteristic data, and radio frequency signal attenuation characteristic data. The environmental perception data includes temperature data, humidity data, and vibration parameter data, and then constructs the three-dimensional spatial topology of the warehouse and generates a three-dimensional dynamic environment model of the warehouse; A data analysis module is used to perform correlation analysis on the temperature and humidity data in the environmental sensing data and the properties of the stored materials in the warehouse, and to detect abnormal vibration states of the stored materials based on the displacement characteristic data of the radio frequency tags, generate abnormal vibration trajectory data of the materials, and further determine the environmental parameter correlation matrix based on the correlation analysis results and the abnormal vibration trajectory data of the materials; The safety risk assessment module is used to input the environmental parameter correlation matrix and the material abnormal vibration trajectory data into a preset dynamic risk model to conduct a safety threat probability assessment. It also diagnoses the equipment operation status based on the radio frequency signal attenuation characteristic data and generates an abnormal equipment operation characteristic spectrum. Based on the safety threat probability assessment results and the abnormal equipment operation characteristic spectrum, it outputs a risk level distribution map for each warehouse area. The optimization management module is used to integrate the risk level distribution map of each warehouse area with the characteristic spectrum of abnormal equipment operation to build a safety hazard identification optimization model. This model is then pushed to the terminal through the radio frequency communication network to implement real-time safety warnings and equipment linkage management.

[0012] In a third aspect, the present application provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes any one of the above-mentioned warehouse safety management methods based on wireless radio frequency technology.

[0013] In summary, this application has the following beneficial technical effects: The present application provides a warehouse safety management method based on wireless radio frequency technology, which collects parameters through a wireless radio frequency sensor network deployed in the warehouse, thereby effectively reducing the occurrence of a single dimension of environmental parameter monitoring, and performs correlation analysis on environmental temperature and humidity data and the properties of stored materials in the warehouse, and detects abnormal vibration states of stored materials based on radio frequency tag displacement feature data, generates abnormal vibration trajectory data of materials, and then confirms an environmental parameter correlation matrix based on the correlation analysis results and the abnormal vibration trajectory data of materials, and inputs the environmental parameter correlation matrix and the abnormal vibration trajectory data of materials into a preset dynamic risk model for security threat probability assessment, diagnoses the equipment operation status based on radio frequency signal attenuation feature data to generate an abnormal operation feature spectrum of equipment, and then outputs a risk level distribution map of the warehouse area, thereby effectively analyzing the potential risks between the properties of stored materials and temperature and humidity changes, effectively reducing the occurrence of delayed warnings of accidents such as fire and corrosion, and analyzing the spatiotemporal characteristics of the vibration trajectory, thereby effectively improving the efficiency of warehouse safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 This is a flow chart of a method for warehouse safety management based on wireless radio frequency technology according to an embodiment of the present application.

[0016] Figure 2 It is a schematic diagram of a platform for warehouse safety management based on wireless radio frequency technology in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following is combined with Figure 1-2 This application is described in further detail.

[0018] Example 1 The embodiment of the present application discloses a warehouse safety management method based on wireless radio frequency technology.

[0019] Reference Figure 1 , a warehouse safety management method based on wireless radio frequency technology, comprising the following steps: Step S1: Parameter collection is performed through a wireless radio frequency sensor network deployed in the warehouse, including environmental perception data and radio frequency signal data. The radio frequency signal data includes radio frequency signal strength characteristic data, radio frequency tag displacement characteristic data, and radio frequency signal attenuation characteristic data. The environmental perception data includes temperature data, humidity data, and vibration parameter data. The three-dimensional spatial topology of the warehouse is then constructed to generate a three-dimensional dynamic environment model of the warehouse. Step S2: performing correlation analysis on the temperature and humidity data in the environmental sensing data and the properties of the stored materials in the warehouse, and detecting abnormal vibration states of the stored materials based on the displacement characteristic data of the radio frequency tags to generate abnormal vibration trajectory data of the materials, and then confirming the environmental parameter correlation matrix based on the correlation analysis results and the abnormal vibration trajectory data of the materials; Step S3: Input the environmental parameter association matrix and the material abnormal vibration trajectory data into a preset dynamic risk model to perform a safety threat probability assessment. Based on the radio frequency signal attenuation characteristic data, the equipment operation status is diagnosed to generate an abnormal equipment operation characteristic spectrum. Based on the safety threat probability assessment results and the abnormal equipment operation characteristic spectrum, a risk level distribution map for each warehouse area is output. Step S4: Integrate the warehouse area risk level distribution map and the equipment abnormal operation characteristic spectrum to build a safety hazard identification optimization model, and push the safety hazard identification optimization model to the terminal through the radio frequency communication network to implement real-time safety warning and equipment linkage management.

[0020] It should be noted that the step S1 specifically includes the following steps: Deploy a wireless RF sensor network consisting of RF readers, temperature sensors, humidity sensors, and vibration sensors in the warehouse; The radio frequency tag signal strength data of the stored materials is collected in real time through the radio frequency reader, and the temperature data, humidity data and vibration parameter data are collected through the temperature sensor, humidity sensor and vibration sensor; Performing spatial filtering on the radio frequency tag signal strength data, thereby extracting radio frequency signal strength feature data after spatial filtering; The three-dimensional coordinate system of the equipment and storage materials in the warehouse is calibrated based on the radio frequency signal strength characteristic data after spatial filtering processing, and then a three-dimensional dynamic environment model of the warehouse is generated through point cloud registration technology based on the calibration results and environmental perception data.

[0021] Specifically, deploy a wireless RF sensor network: Deploy a wireless sensor network consisting of RF readers, temperature sensors, humidity sensors, and vibration sensors at key locations in the warehouse (such as top of shelves, aisle corners, and entrances and exits); RFID readers: Multi-band devices are used to cover the entire warehouse area, ensuring comprehensive scanning of stored materials with RFID tags. For example, in a large e-commerce warehouse, a reader is installed at each end of each shelf to simultaneously read the tag signals of materials on both the upper and lower shelves. Environmental sensors: Temperature and humidity sensors are evenly distributed on warehouse walls or between shelves (approximately 5-10 meters apart). Vibration sensors are fixed to the bases of heavy equipment (such as stackers and conveyor belts) to detect equipment operating status or abnormal vibrations in real time. For example, a smart warehousing center deployed 50 radio frequency readers, 30 temperature and humidity sensors, and 10 vibration sensors in a 1,000-square-meter warehouse to form a high-density sensing network.

[0022] Real-time collection of multi-source data: The following data is collected in real time through various sensors: RFID tag signal strength data: RFID readers continuously scan material tags to obtain signal strength values. For example, when a forklift carrying tagged goods passes by a reader, the reader records the signal strength curve over time. Environmental perception data: The temperature sensor collects the real-time temperature in the warehouse; Humidity sensor monitors air humidity; Vibration sensors capture equipment vibration frequency, amplitude and other parameters (e.g. the vibration frequency of a stacker crane is 20Hz when it is running); Data transmission: All sensors transmit data to the terminal in real time via the Wi-Fi network, forming a raw data stream.

[0023] RF signal spatial filtering and feature extraction: Perform spatial filtering on the original RFID tag signal strength data to remove noise interference and extract effective features: Filtering algorithms: Use Kalman filtering or median filtering to filter out signal fluctuations caused by multipath effects, metal interference, and other factors. Feature extraction: Extract features such as mean, variance, and signal attenuation rate from the filtered signal. For example, if a certain area is densely populated with materials and the signal attenuation rate is rapid, the material density can be determined using the feature values.

[0024] 3D coordinate system calibration and point cloud registration: Three-dimensional coordinate system calibration: With the lower left corner of the warehouse as the origin (0,0,0), establish a three-dimensional coordinate system (X axis: length direction of the warehouse, Y axis: width direction, Z axis: height direction); The coordinates of materials and equipment are calculated based on RF signal strength characteristic data through triangulation or fingerprint matching. For example, if the signal strengths of a material detected by three readers are -50dBm, -55dBm, and -48dBm, respectively, the coordinates are calculated through trilateration to be (15, 8, 3) meters (the third shelf layer).

[0025] Generate a 3D dynamic environment model: The calibrated equipment and material coordinates are converted into point cloud data, and the environmental perception data (temperature, humidity, vibration) is integrated for weighted processing. For example, when the vibration sensor detects abnormal vibration of equipment in a certain area, the corresponding point cloud is marked as a red alert. Based on the deep learning point cloud registration model, the point cloud data at different times are aligned and spliced ​​to generate a three-dimensional dynamic environment model of the warehouse.

[0026] It should be noted that step S2 specifically includes the following steps: Establishing a database of storage material properties, wherein the storage material properties include material ignition point threshold, material moisture absorption coefficient and material stability coefficient; Identify the spatiotemporal distribution of temperature and humidity data in the warehouse, and then divide the areas into different temperature and humidity risk levels based on the identification results. Then, match and analyze the storage material attributes in the storage material attribute database to generate a temperature and humidity-material attribute mapping relationship; The displacement characteristic data of the radio frequency tag is processed by wavelet transformation to separate the normal vibration parameter signal from the abnormal vibration parameter signal, and the spatiotemporal distribution characteristics corresponding to the abnormal vibration parameter signal are extracted. The spatiotemporal distribution characteristics of the abnormal vibration parameter signal are then mapped to the three-dimensional dynamic environment model of the warehouse to generate abnormal vibration trajectory data of the material; The temperature, humidity and material property mapping relationship is combined with the material abnormal vibration trajectory data for data fusion analysis to determine the environmental parameter correlation matrix.

[0027] Specifically, establish a warehouse material attribute database: Based on the physical and chemical properties of stored materials, a property database including ignition threshold, moisture absorption coefficient, and stability coefficient is constructed; Temperature and humidity risk area division and attribute matching: Identify the spatiotemporal distribution of temperature and humidity. This involves performing grid aggregation on real-time data collected by temperature and humidity sensors by time (e.g., every 10 minutes) and space (e.g., dividing a warehouse into 5m x 5m grids). Risk level classification: Temperature risk level: Set three thresholds, such as low temperature (<5°C), normal temperature (5-30°C), and high temperature (>30°C). High temperature areas trigger ignition risk warnings. Humidity risk levels: low humidity (<30%RH), medium humidity (30%-60%RH), and high humidity (>60%RH). High humidity areas trigger moisture absorption risk warnings. For example, in the northwest corner of a warehouse, due to its proximity to a heat source, the temperature is consistently above 35°C (high temperature risk zone) and the humidity is 55%RH (medium humidity). Materials with flash points below 35°C require special monitoring. Temperature and humidity-material property matching analysis: Spatial association: Match the temperature and humidity levels of each grid area with the properties of the materials stored in that area. For example, if the flash point threshold of a material stored in a high-temperature area is less than 35°C (such as ethanol's flash point of 12.78°C), it is determined to be "high flash point risk." If the moisture absorption coefficient of a material stored in a high-humidity area is greater than 0.2 (such as white sugar's moisture absorption coefficient of 0.3), it is determined to be "high moisture absorption risk." Mapping relationship generation: record the matching results of temperature and humidity levels and material properties in matrix form; RF signal vibration feature analysis and trajectory generation Wavelet transform separates vibration signals. The original signal collected by the vibration sensor contains both normal equipment vibration and abnormal vibration. Wavelet transform processing uses the db4 wavelet basis function to perform multi-layer decomposition on the signal to separate different frequency components. For example, normal vibration signals are mainly concentrated in the low-frequency range of 10-50Hz, while abnormal vibration signals have peaks in the high-frequency range of 80-150Hz. For example, if the vibration signal of the stacker crane suddenly increases by 30% in the high-frequency range after wavelet transform, it is judged as abnormal vibration. Spatiotemporal feature extraction and trajectory mapping Spatiotemporal positioning uses RFID tag displacement data (calculating material location based on changes in RFID reader signal strength) to determine the material coordinates (X, Y, Z) and timestamp corresponding to abnormal vibrations. For example, when material A was located at (20, 15, 4) meters at 2:00 PM, the vibration frequency suddenly increased from the normal 20 Hz to 100 Hz. Trajectory generation: Continuous abnormal vibration points are linked together in time and space, and the trajectory is marked with a red curve in the 3D dynamic environment model. For example, when a pallet of cargo tilts on a conveyor belt, an abnormal vibration upward trajectory is generated from (10, 5, 2) meters to (12, 5, 2.2) meters, indicating a possible tipping risk. Data fusion and environmental parameter correlation matrix generation Multi-source data fusion: Time alignment: Align the temperature and humidity-material attribute mapping data with the abnormal vibration trajectory data by timestamp, and filter out related data within the same time period. For example, between 2:00 PM and 2:05 PM, abnormal vibrations occurred simultaneously in a material (ignition point 25°C) in a high-temperature area (35°C). Spatial correlation: Matching temperature and humidity risks with vibration anomalies within the same grid area. For example, the shelf area at coordinates (20, 15, 4) meters is both a high-temperature risk zone and has detected abnormal material vibration, making it a high-risk overlapping area. Taking the temperature and humidity risk level (rows) and vibration anomaly type (columns) as dimensions, the frequency of risk occurrence and the degree of impact under each combination are counted, and then the environmental parameter correlation matrix is ​​confirmed.

[0028] It should be noted that step S3 specifically includes the following steps: Obtaining an environmental parameter correlation matrix, extracting temperature and humidity deviation, material ignition point proximity index, and vibration cumulative value from the environmental parameter correlation matrix, inputting the temperature and humidity deviation, material ignition point proximity index, and vibration cumulative value into a preset dynamic risk model, and thereby confirming a safety threat probability assessment result; Based on the safety threat probability assessment results, the risk propagation paths of the warehouse areas are modeled, and combined with the historical accident data stored in the cloud database, a risk propagation probability map is generated; Extract frequency domain features from the equipment's abnormal operation characteristic spectrum. The frequency domain features include harmonic distortion rate, signal attenuation rate, and noise floor change rate. An equipment status evaluation index system is constructed based on the harmonic distortion rate, signal attenuation rate, and noise floor change rate. Furthermore, an equipment status evaluation coefficient is determined based on the equipment status evaluation index system. The risk propagation probability map and the equipment status evaluation coefficient are superimposed and analyzed to generate a risk level distribution map for each warehouse area.

[0029] Specifically, the environmental parameter correlation matrix analysis: Three core parameters are extracted from the environmental parameter correlation matrix: temperature and humidity deviation, which measures the degree of deviation between the real-time temperature and humidity and the material safe storage threshold; material ignition point proximity index, which reflects the degree to which the ambient temperature approaches the material's ignition point; and vibration accumulation value, which calculates the energy of abnormal vibration signals per unit time by summing the squares of high-frequency coefficients after wavelet transformation. These three parameters are input into a preset dynamic risk model to output a safety threat probability (ranging from 0 to 1). Risk propagation path modeling and probability map generation: Divide the warehouse into N areas according to a grid (e.g., 10m x 10m), and assign each area a unique ID (e.g., A1, B3); Based on historical data, we analyze risk propagation patterns. For example, risks in high-temperature areas can spread to adjacent areas through air flow, and abnormal vibrations can trigger chain reactions due to equipment linkage. For example, historical data shows that after an ignition risk occurs in area A1 (high temperature), the probability of temperature increases in adjacent areas A2 and B1 within 30 minutes is 60% and 40%, respectively. Combined with historical accident data in the cloud database, the Bayesian network is used to calculate the risk propagation probability in each region; Bayesian network structure: With the temperature of area A1 and the vibration of area A2 as parent nodes, and the ignition point risk of area B1 as child nodes, the conditional probability table is trained through historical data; Visualization results: Generate a heat map showing the risk transmission probability of each area. For example, the transmission probability of the three adjacent areas around area A1 is marked as 50%-70%. The darker the color, the higher the risk. To build an equipment status evaluation index system, perform a fast Fourier transform (FFT) on the equipment's abnormal operation characteristic spectrum to extract three frequency domain features. Weights are assigned to the three indicators (e.g., harmonic distortion rate 0.5, attenuation rate 0.3, and noise floor 0.2). The equipment status evaluation coefficient is calculated as follows: 0.5 × distortion rate score + 0.3 × attenuation rate score + 0.2 × noise floor score. Data overlay analysis and risk level distribution map generation are carried out, and the risk propagation probability map and equipment status evaluation coefficient are transferred to the warehouse three-dimensional dynamic environment model through the coordinate system.

[0030] The weighted summation method is used to generate the comprehensive risk index of each area. The comprehensive risk index = 0.6 × security threat probability + 0.3 × risk propagation probability + 0.1 × (10-equipment status evaluation coefficient). For example, area B2 has a security threat probability of 0.85, a propagation probability of 0.65, and an equipment status coefficient of 3.7. The calculated risk index = 0.6 × 0.85 + 0.3 × 0.65 + 0.1 × (10-3.7) = 0.51 + 0.195 + 0.63 = 1.335, which is considered high risk. High risk: risk index > 0.7, marked in red; Medium risk: risk index 0.4-0.7, marked in yellow; Low risk: Risk index < 0.4, marked in green, generates a risk level distribution map for each warehouse area, marking the risk level, main risk factors and related material information of each area. You can click on the area to view detailed parameters, such as temperature 38°C, material ignition point proximity index 85%, equipment vibration distortion rate 15%, and trigger the emergency plan (such as starting the cooling system and suspending equipment operation).

[0031] It should be noted that the device operation status diagnosis based on the RF signal attenuation characteristics generates the device abnormal operation characteristic spectrum, which specifically includes: Acquire radio frequency signal attenuation characteristic data, extract carrier frequency offset and phase noise parameters from the radio frequency signal attenuation characteristic data, and then construct device operation status baseline data based on the carrier frequency offset and phase noise parameters; The deviation between the RF signal attenuation characteristic data and the equipment operation status baseline data is monitored in real time. When the deviation is detected to exceed the preset deviation threshold, the abnormal operation characteristic spectrum of the equipment is generated based on the carrier frequency offset and phase noise parameters.

[0032] It should be noted that step S4 specifically includes the following steps: A safety hazard identification model is established based on the warehouse area risk level distribution map and the equipment abnormal operation characteristic spectrum, and the optimization factors corresponding to the safety hazard identification model are determined. The optimization factors include the risk level false alarm rate, early warning response time and linkage control accuracy; Dynamically adjust the safety hazard identification model and update the weight allocation strategy based on historical warning records and actual accident data feedback. Then, optimize the safety hazard identification model based on the weight allocation strategy to build a safety hazard identification optimization model. Design a graded warning strategy based on the safety hazard identification optimization model. The graded warning strategy includes yellow warning, orange warning, and red warning. Different levels of linkage control instructions are matched according to the abnormal operation characteristic spectrum of the equipment. The optimized safety hazard identification optimization model and graded warning strategy are pushed to the terminal through the radio frequency communication network, thereby executing real-time safety warning and equipment linkage management.

[0033] Specifically, through the above process, the transformation of safety hazard identification from "experience-based judgment" to "data-driven" has been achieved. The combination of the safety hazard identification optimization model and the graded warning strategy not only improves the accuracy of risk identification, but also achieves the management goal of "prevention first, prevention and control combined" through equipment linkage control.

[0034] Example 2 The embodiment of the present application also discloses a warehouse safety management platform based on wireless radio frequency technology.

[0035] Reference Figure 2 , a warehouse safety management platform based on wireless radio frequency technology, including: The data acquisition module is used to collect parameters through the wireless radio frequency sensor network deployed in the warehouse, including environmental perception data and radio frequency signal data. The radio frequency signal data includes radio frequency signal strength characteristic data, radio frequency tag displacement characteristic data, and radio frequency signal attenuation characteristic data. The environmental perception data includes temperature data, humidity data, and vibration parameter data, and then constructs the three-dimensional spatial topology of the warehouse and generates a three-dimensional dynamic environment model of the warehouse; A data analysis module is used to perform correlation analysis on the temperature and humidity data in the environmental sensing data and the properties of the stored materials in the warehouse, and to detect abnormal vibration states of the stored materials based on the displacement characteristic data of the radio frequency tags, generate abnormal vibration trajectory data of the materials, and further determine the environmental parameter correlation matrix based on the correlation analysis results and the abnormal vibration trajectory data of the materials; The safety risk assessment module is used to input the environmental parameter correlation matrix and the material abnormal vibration trajectory data into a preset dynamic risk model to conduct a safety threat probability assessment. It also diagnoses the equipment operation status based on the radio frequency signal attenuation characteristic data and generates an abnormal equipment operation characteristic spectrum. Based on the safety threat probability assessment results and the abnormal equipment operation characteristic spectrum, it outputs a risk level distribution map for each warehouse area. The optimization management module is used to integrate the risk level distribution map of each warehouse area with the characteristic spectrum of abnormal equipment operation to build a safety hazard identification optimization model. This model is then pushed to the terminal through the radio frequency communication network to implement real-time safety warnings and equipment linkage management.

[0036] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in similar ways. As long as they do not deviate from the concept of the invention, they should all fall within the scope of protection of the present invention.

[0037] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0038] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention.

Claims

1. A warehouse safety management method based on wireless radio frequency technology, characterized in that: The following steps are involved: Step S1: Parameter collection is performed through a wireless radio frequency sensor network deployed in the warehouse, including environmental perception data and radio frequency signal data. The radio frequency signal data includes radio frequency signal strength characteristic data, radio frequency tag displacement characteristic data, and radio frequency signal attenuation characteristic data. The environmental perception data includes temperature data, humidity data, and vibration parameter data. The three-dimensional spatial topology of the warehouse is then constructed to generate a three-dimensional dynamic environment model of the warehouse. Step S2: performing correlation analysis on the temperature and humidity data in the environmental sensing data and the properties of the stored materials in the warehouse, and detecting abnormal vibration states of the stored materials based on the displacement characteristic data of the radio frequency tags to generate abnormal vibration trajectory data of the materials, and then confirming the environmental parameter correlation matrix based on the correlation analysis results and the abnormal vibration trajectory data of the materials; Step S3: Input the environmental parameter association matrix and the material abnormal vibration trajectory data into a preset dynamic risk model to perform a safety threat probability assessment. Based on the radio frequency signal attenuation characteristic data, the equipment operation status is diagnosed to generate an abnormal equipment operation characteristic spectrum. Based on the safety threat probability assessment results and the abnormal equipment operation characteristic spectrum, a risk level distribution map for each warehouse area is output. Step S4: Integrate the warehouse area risk level distribution map and the equipment abnormal operation characteristic spectrum to build a safety hazard identification optimization model, and push the safety hazard identification optimization model to the terminal through the radio frequency communication network to implement real-time safety warning and equipment linkage management.

2. A warehouse safety management method based on wireless radio frequency technology according to claim 1, characterized in that: The step S1 specifically includes the following steps: Deploy a wireless RF sensor network consisting of RF readers, temperature sensors, humidity sensors, and vibration sensors in the warehouse; The radio frequency tag signal strength data of the stored materials is collected in real time through the radio frequency reader, and the temperature data, humidity data and vibration parameter data are collected through the temperature sensor, humidity sensor and vibration sensor; Performing spatial filtering on the radio frequency tag signal strength data, thereby extracting radio frequency signal strength feature data after spatial filtering; The three-dimensional coordinate system of the equipment and storage materials in the warehouse is calibrated based on the radio frequency signal strength characteristic data after spatial filtering processing, and then a three-dimensional dynamic environment model of the warehouse is generated through point cloud registration technology based on the calibration results and environmental perception data.

3. The warehouse safety management method based on wireless radio frequency technology according to claim 1 is characterized in that: The step S2 specifically includes the following steps: Establishing a database of storage material properties, wherein the storage material properties include material ignition point threshold, material moisture absorption coefficient and material stability coefficient; Identify the spatiotemporal distribution of temperature and humidity data in the warehouse, and then divide the areas into different temperature and humidity risk levels based on the identification results. Then, match and analyze the storage material attributes in the storage material attribute database to generate a temperature and humidity-material attribute mapping relationship; The displacement characteristic data of the radio frequency tag is processed by wavelet transformation to separate the normal vibration parameter signal from the abnormal vibration parameter signal, and the spatiotemporal distribution characteristics corresponding to the abnormal vibration parameter signal are extracted. The spatiotemporal distribution characteristics of the abnormal vibration parameter signal are then mapped to the three-dimensional dynamic environment model of the warehouse to generate abnormal vibration trajectory data of the material; The temperature, humidity and material property mapping relationship is combined with the material abnormal vibration trajectory data for data fusion analysis to determine the environmental parameter correlation matrix.

4. The warehouse safety management method based on wireless radio frequency technology according to claim 1 is characterized in that: The step S3 specifically includes the following steps: Obtaining an environmental parameter correlation matrix, extracting temperature and humidity deviation, material ignition point proximity index, and vibration cumulative value from the environmental parameter correlation matrix, inputting the temperature and humidity deviation, material ignition point proximity index, and vibration cumulative value into a preset dynamic risk model, and thereby confirming a safety threat probability assessment result; Based on the safety threat probability assessment results, the risk propagation path of each warehouse area is modeled, and combined with the historical accident data stored in the cloud database, a risk propagation probability map is generated; Extract frequency domain features from the equipment's abnormal operation characteristic spectrum. The frequency domain features include harmonic distortion rate, signal attenuation rate, and noise floor change rate. An equipment status evaluation index system is constructed based on the harmonic distortion rate, signal attenuation rate, and noise floor change rate. Furthermore, an equipment status evaluation coefficient is determined based on the equipment status evaluation index system. The risk propagation probability map and the equipment status evaluation coefficient are superimposed and analyzed to generate a risk level distribution map for each warehouse area.

5. The warehouse safety management method based on wireless radio frequency technology according to claim 4 is characterized in that: The device operation status is diagnosed based on the RF signal attenuation characteristics to generate the device abnormal operation characteristic spectrum, which specifically includes: Acquire radio frequency signal attenuation characteristic data, extract carrier frequency offset and phase noise parameters from the radio frequency signal attenuation characteristic data, and then construct device operation status baseline data based on the carrier frequency offset and phase noise parameters; The deviation between the RF signal attenuation characteristic data and the equipment operation status baseline data is monitored in real time. When the deviation is detected to exceed the preset deviation threshold, the abnormal operation characteristic spectrum of the equipment is generated based on the carrier frequency offset and phase noise parameters.

6. The warehouse safety management method based on wireless radio frequency technology according to claim 1 is characterized in that: The step S4 specifically includes the following steps: A safety hazard identification model is established based on the warehouse area risk level distribution map and the equipment abnormal operation characteristic spectrum, and the optimization factors corresponding to the safety hazard identification model are determined. The optimization factors include the risk level false alarm rate, early warning response time and linkage control accuracy; Dynamically adjust the safety hazard identification model and update the weight allocation strategy based on historical warning records and actual accident data feedback. Then, optimize the safety hazard identification model based on the weight allocation strategy to build a safety hazard identification optimization model. Design a graded warning strategy based on the safety hazard identification optimization model. The graded warning strategy includes yellow warning, orange warning, and red warning. Different levels of linkage control instructions are matched according to the abnormal operation characteristic spectrum of the equipment. The optimized safety hazard identification optimization model and graded warning strategy are pushed to the terminal through the radio frequency communication network, thereby executing real-time safety warning and equipment linkage management.

7. A warehouse safety management platform based on wireless radio frequency technology, applied to a warehouse safety management method based on wireless radio frequency technology as described in any one of claims 1 to 6, characterized in that: include: The data acquisition module is used to collect parameters through the wireless radio frequency sensor network deployed in the warehouse, including environmental perception data and radio frequency signal data. The radio frequency signal data includes radio frequency signal strength characteristic data, radio frequency tag displacement characteristic data, and radio frequency signal attenuation characteristic data. The environmental perception data includes temperature data, humidity data, and vibration parameter data, and then constructs the three-dimensional spatial topology of the warehouse and generates a three-dimensional dynamic environment model of the warehouse; A data analysis module is used to perform correlation analysis on the temperature and humidity data in the environmental sensing data and the properties of the stored materials in the warehouse, and to detect abnormal vibration states of the stored materials based on the displacement characteristic data of the radio frequency tags, generate abnormal vibration trajectory data of the materials, and further determine the environmental parameter correlation matrix based on the correlation analysis results and the abnormal vibration trajectory data of the materials; The safety risk assessment module is used to input the environmental parameter correlation matrix and the material abnormal vibration trajectory data into a preset dynamic risk model to conduct a safety threat probability assessment. It also diagnoses the equipment operation status based on the radio frequency signal attenuation characteristic data and generates an abnormal equipment operation characteristic spectrum. Based on the safety threat probability assessment results and the abnormal equipment operation characteristic spectrum, it outputs a risk level distribution map for each warehouse area. The optimization management module is used to integrate the risk level distribution map of each warehouse area with the characteristic spectrum of abnormal equipment operation to build a safety hazard identification optimization model. This model is then pushed to the terminal through the radio frequency communication network to implement real-time safety warnings and equipment linkage management.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer is caused to execute a warehouse safety management method based on wireless radio frequency technology as claimed in any one of claims 1 to 6.

Images