Safety tool regular inspection intelligent management method and system based on RFID technology

Abstract

The invention discloses an intelligent management method and system for regular inspection of safety tools and instruments based on the RFID technology, and the method comprises the steps: collecting the RFID tag information, sensor data, use frequency, time and environment conditions of the tools and instruments, and forming a tool and instrument state data set; performing data analysis by utilizing the characteristic values of the tool state data set, predicting potential fault points of the tool according to historical data, and dynamically adjusting the reading frequency and power of the RFID tag; the tool state sensing precision of the system is improved through a data fusion technology; performing anomaly detection according to a data fusion result, and giving an alarm when an abnormal condition is detected; and according to the feedback of the user and the operation data of the system, regularly updating the machine learning model, and adjusting the system configuration. The scientificity and reliability of tool management can be effectively improved, and production pause and economic loss caused by tool faults can be greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to an intelligent management method and system for scheduled inspection of safety tools using RFID technology. Background Art

[0002] With the rapid development of modern industrial production, higher requirements have been put forward for the management and maintenance of various tools. Traditional tool management mainly relies on manual regular inspection and maintenance, which is not only inefficient, but also difficult to ensure that the tools are always in the best working condition. In recent years, with the rapid development of Internet of Things technology, radio frequency identification technology RFID has been widely used in the field of tool management due to its advantages of non-contact, long-distance and rapid identification. The application of RFID technology makes it possible to track tools in real time and monitor their status, which greatly improves the automation level and work efficiency of tool management.

[0003] However, the existing tool management systems based on RFID technology still have certain limitations. On the one hand, most systems can only realize basic RFID tag information reading and recording, lack the ability to deeply analyze the use environment and status of tools, and cannot actively discover potential failure risks; on the other hand, the existing systems are relatively simple in data processing, usually relying on only a single data source, and fail to make full use of multiple sensor data for comprehensive judgment, resulting in the perception of tool status is not comprehensive and accurate enough. In addition, the existing systems do not make full use of user feedback, and lack an effective mechanism to optimize system configuration and improve management level according to the actual user experience. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing tool management system based on RFID technology still has certain limitations. On the one hand, most systems can only realize basic RFID tag information reading and recording, lack the ability to deeply analyze the use environment and status of the tools, and cannot actively discover potential failure risks; on the other hand, the existing systems are relatively simple in data processing, usually relying only on a single data source, and fail to make full use of multiple sensor data for comprehensive judgment, resulting in insufficiently comprehensive and accurate perception of the tool status. In addition, the existing systems do not make sufficient use of user feedback, and lack an effective mechanism to optimize system configuration and improve management level based on the user's actual usage experience.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent management method for scheduled inspection of safety tools using RFID technology, comprising:

[0007] Collect RFID tag information, sensor data, usage frequency, time and environmental conditions of tools to form a tool status data set;

[0008] Using the characteristic values ​​of the tool status data set, data analysis is performed to predict potential failure points of the tool based on historical data, and the reading frequency and power of the RFID tag are dynamically adjusted;

[0009] Improve the system's accuracy in sensing tool status through data fusion technology;

[0010] Based on the results of data fusion, anomaly detection is performed and an alarm is issued when an abnormal situation is detected;

[0011] Based on user feedback and system operation data, the machine learning model is updated regularly and the system configuration is adjusted.

[0012] As a preferred solution of the RFID technology safety tool inspection intelligent management method of the present invention, wherein: the tool status data set includes installing RFID tags on the tools and arranging RFID readers in the warehouse;

[0013] The data of ambient temperature T and ambient humidity H are collected through the environmental sensors installed in the warehouse;

[0014] The RFID reader is used to record the timestamp Ti of each entry and exit of tools, and the usage frequency F and cumulative usage time CUT of tools are calculated. The usage frequency F is expressed as:

[0015]

[0016] Among them, N represents the number of times of entering and leaving the warehouse, and ΔT represents the time interval;

[0017] Cumulative usage time CUT, expressed as:

[0018]

[0019] Where n is the total number of times the tool is used, T out,i Indicates the timestamp of the end of the i-th use, T in,i Indicates the timestamp of the start of the i-th use;

[0020] The data acquisition module integrates RFID tag information, sensor data, usage frequency, and cumulative usage time into a tool status data set D, which is expressed as:

[0021] D=[CUT,Pv,Av,T,H,F]

[0022] Among them, Pv represents the tool pressure value, and Av represents the tool acceleration value.

[0023] As a preferred solution of the RFID technology safety tool inspection intelligent management method of the present invention, wherein: the characteristic value of the tool status data set includes the use mode and environmental changes of the tool analyzed by the machine learning algorithm based on the tool status data set, specifically,

[0024] The characteristic value is calculated based on the tool status data set, and the expression is:

[0025]

[0026] in, represents the average pressure value of the tool, θ represents the number of pressure data points collected during the time period, Pv i Represents the pressure value at the i-th time point, i represents the index variable, Indicates the average acceleration value of the tool. Indicates the number of acceleration data points collected during this time period, Av q represents the acceleration value at the qth time point, q represents the index variable, represents the average frequency of use of tools, m represents the number of collected frequency data points, and F j represents the usage frequency at the jth time point, j represents the index variable, ΔT represents the rate of change of ambient temperature over time, ΔH represents the rate of change of ambient humidity over time, ΔF represents the rate of change of usage frequency over time, final represents the final time point, and initial represents the initial time point;

[0027] Use the support vector machine (SVM) model as the basis of the machine learning model. ΔT, ΔH, and ΔF are input into the machine learning model for training to predict the tool usage pattern and environmental changes, as well as the corresponding RFID tag reading frequency and power;

[0028]

[0029] Where X represents the feature vector set;

[0030] Using the SVM model as the basis for building a fault prediction model, the feature vector is input into the fault prediction model, and the expression is:

[0031]

[0032] Among them, P f represents the predicted potential failure probability of the tool, e represents the exponential function, ε is the adjustment coefficient, β is the adjustment coefficient, P max Indicates the maximum allowable pressure value, A max Indicates the maximum permissible acceleration value, Fmax Indicates the maximum allowable frequency of use, T range Indicates the allowable temperature fluctuation range, H range Indicates the allowable humidity fluctuation range.

[0033] As a preferred solution of the intelligent management method for scheduled inspection of safety tools using RFID technology described in the present invention, the specific steps of dynamically adjusting the reading frequency and power of the RFID tag are as follows:

[0034] Based on the prediction of the potential failure probability P of the tool f , set the threshold TP;

[0035] When P f >TP, it indicates that the tool has a high probability of potential failure points, and the reading frequency and power of the RFID tag are dynamically adjusted;

[0036] When P f When ≤TP, it means that the probability of potential failure points in the tool is low, and daily inspection work should be maintained;

[0037] The reading frequency and power of the RFID tag are expressed as:

[0038]

[0039] Wherein, f represents the reading frequency of the RFID tag, and p represents the power of the RFID tag.

[0040] As a preferred solution of the RFID technology safety tool inspection intelligent management method of the present invention, wherein: the improvement of the system's accuracy of tool status perception through data fusion technology includes standardizing the data from the RFID tag and the environmental sensor;

[0041] The data from different sensors are fused by weighted averaging, and the expression is:

[0042] D fusion =α·RFIDA+β·ENV

[0043] Among them, D fusion represents the fused data set, RFIDA represents the data value provided by the RFID tag, α represents the weight factor of RFIDA, ENV represents the data value provided by the environmental sensor, and β represents the weight factor of ENV;

[0044] The weight factors α and β are obtained by learning from historical data, and the optimal weights are determined by the least squares method;

[0045] Compare the fused data with the actual tool status and calculate the deviation between the fused data and the actual status. The expression is:

[0046] ΔD=D fusion -D actual

[0047] Among them, ΔD represents the deviation value, which is used to measure the gap between the fused data and the actual tool status; D fusion represents the fused data set; D actual A data set representing the actual tool status.

[0048] As a preferred solution of the RFID technology safety tool inspection intelligent management method of the present invention, the data fusion technology includes constructing a comprehensive index Z to evaluate the status of the tool, which is expressed as:

[0049]

[0050] Among them, Z represents the health status score, CUT max Indicates the maximum value of the accumulated usage time.

[0051] Taking the health status score Z as the standard, a threshold is set;

[0052] When Z exceeds the preset threshold, it is considered that there is a potential fault point in the tool; when the system detects an abnormal change in Z, the system will automatically issue an alarm;

[0053] Determine the replacement of parts based on the status of the tool;

[0054] Update the reading frequency and power of RFID tags.

[0055] As a preferred solution of the RFID technology safety tool inspection intelligent management method of the present invention, wherein: the collected feedback data is standardized;

[0056] based on The six features ΔT, ΔH, and ΔF construct the feedback function, which is expressed as follows:

[0057]

[0058] Among them, U represents the feedback evaluation score, and the value range of U is [0,6]; U f Represents the quantitative value of user feedback, U max Indicates the maximum value of user feedback;

[0059] Based on the updated model, the system configuration parameters are adjusted according to the prediction results, and the reading frequency and power of the RFID tag are recalculated after the adjustment.

[0060] An intelligent management system for scheduled inspection of safety tools based on RFID technology using the method of the present invention is characterized by:

[0061] The data acquisition module is responsible for collecting the RFID tag information, sensor data, usage frequency, time and environmental conditions of the tools to form a tool status data set;

[0062] Adaptive learning module, which analyzes tool usage patterns and environmental changes based on tool status datasets through machine learning algorithms;

[0063] The intelligent prediction module uses data analysis models to predict potential failure points of tools based on historical data and dynamically adjust the reading frequency and power of RFID tags;

[0064] Multi-sensor fusion module integrates RFID data with data from multiple sensors, and improves the system's accuracy in sensing tool status through data fusion technology;

[0065] The decision support module is responsible for comprehensively analyzing the data from the adaptive learning module, the intelligent prediction module, and the multi-sensor fusion module, formulating maintenance plans for tools, and issuing alarms when abnormal conditions are detected;

[0066] User interaction module, which provides a user interface and allows users to submit usage feedback;

[0067] The system optimization module regularly updates the machine learning model and adjusts the configuration of the entire system based on user feedback and system operation data.

[0068] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein: the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0069] A computer-readable storage medium stores a computer program, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0070] Beneficial effects of the present invention: The intelligent management method for scheduled inspection of safety tools using RFID technology provided by the present invention realizes comprehensive monitoring and intelligent analysis of the status of tools by integrating advanced data collection, adaptive learning, intelligent prediction, and multi-sensor fusion technologies. A machine learning algorithm is introduced to analyze the usage patterns and environmental changes of tools, and potential fault points are predicted using data analysis models. The reading strategy of RFID tags can be dynamically adjusted according to actual conditions. In addition, the system also provides a user interaction module, allowing users to directly submit usage feedback, and regularly update the machine learning model through the system optimization module to ensure continuous improvement and enhanced adaptability of the system. This intelligent management system based on big data and artificial intelligence technology can not only effectively improve the scientificity and reliability of tool management, but also significantly reduce production stoppages and economic losses caused by tool failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0072] Figure 1 An overall flow chart of an intelligent management method for scheduled inspection of safety tools using RFID technology provided by the first embodiment of the present invention;

[0073] Figure 2 A framework diagram of an intelligent management system for scheduled inspection of safety tools using RFID technology provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0074] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0075] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a method for intelligent management of scheduled inspection of safety tools using RFID technology, comprising:

[0076] S1: Collect RFID tag information, sensor data, usage frequency, time and environmental conditions of tools to form a tool status data set.

[0077] The RFID tag information, sensor data, usage frequency, time and environmental conditions of tools are collected to form a tool status data set. The specific steps are: install RFID tags on tools and arrange RFID readers in the warehouse; collect data on ambient temperature T and ambient humidity H through environmental sensors installed in the warehouse; record the timestamp Ti of each entry and exit of tools through RFID readers, and calculate the usage frequency F and cumulative usage time CUT of tools. The usage frequency F is expressed as:

[0078]

[0079] Among them, N represents the number of times of entering and leaving the warehouse, and ΔT represents the time interval. The cumulative usage time CUT is expressed as:

[0080]

[0081] Where n is the total number of times the tool is used, T out,i Indicates the timestamp of the end of the i-th use, T in,i Indicates the timestamp of the start of the i-th use. The RFID tag information, sensor data, usage frequency and cumulative usage time are integrated into the tool status data set D through the data acquisition module, and the expression is:

[0082] D=[CUT,Pv,Av,T,H,F]

[0083] Among them, Pv represents the tool pressure value, and Av represents the tool acceleration value.

[0084] S2: Perform data analysis using the characteristic values ​​of the tool status data set, predict potential failure points of the tool based on historical data, and dynamically adjust the reading frequency and power of the RFID tag.

[0085] The characteristic value of the tool status data set includes analyzing the tool usage mode and environmental changes based on the tool status data set through a machine learning algorithm, specifically, calculating its characteristic value based on the tool status data set, and the expression is:

[0086]

[0087] in, represents the average pressure value of the tool, θ represents the number of pressure data points collected during the time period, Pv i Represents the pressure value at the i-th time point, i represents the index variable, Indicates the average acceleration value of the tool. Indicates the number of acceleration data points collected during this time period, Av q represents the acceleration value at the qth time point, q represents the index variable, represents the average frequency of use of tools, m represents the number of collected frequency data points, and F j represents the usage frequency at the jth time point, j represents the index variable, ΔT represents the rate of change of ambient temperature over time, ΔH represents the rate of change of ambient humidity over time, ΔF represents the rate of change of usage frequency over time, final represents the final time point, and initial represents the initial time point.

[0088] Use the support vector machine (SVM) model as the basis of the machine learning model. ΔT, ΔH, and ΔF are input into the machine learning model for training to predict the tool usage pattern and environmental changes, as well as the corresponding RFID tag reading frequency and power.

[0089]

[0090] Among them, X represents the feature vector set. Using the SVM model as the basis for building a fault prediction model, the feature vector is input into the fault prediction model, and the expression is:

[0091]

[0092] Among them, P f represents the predicted potential failure probability of the tool, e represents the exponential function, ε is the adjustment coefficient, β is the adjustment coefficient, P max Indicates the maximum allowable pressure value, A max Indicates the maximum permissible acceleration value, F max Indicates the maximum allowable frequency of use, T range Indicates the allowable temperature fluctuation range, H range Indicates the allowable humidity fluctuation range.

[0093] The dynamic adjustment of the reading frequency and power of the RFID tag is specifically performed as follows: based on the predicted potential failure probability P of the tool f , set the threshold TP. When P f >TP, it indicates that the tool has a high probability of potential failure points, and the reading frequency and power of the RFID tag are dynamically adjusted. f When ≤TP, it indicates that the probability of potential failure points in the tool is low, and daily inspection work should be maintained.

[0094] The reading frequency and power of the RFID tag are expressed as:

[0095]

[0096] Wherein, f represents the reading frequency of the RFID tag, and p represents the power of the RFID tag.

[0097] S3: Improve the accuracy of the system’s perception of tool status through data fusion technology.

[0098] Specifically, the data from the RFID tags and environmental sensors are standardized.

[0099] The data from different sensors are fused by weighted averaging, and the expression is:

[0100] D fusion =α·RFIDA+β·ENV

[0101] Among them, D fusion represents the fused data set, RFIDA represents the data value provided by the RFID tag, α represents the weight factor of RFIDA, ENV represents the data value provided by the environmental sensor, and β represents the weight factor of ENV.

[0102] The weight factors α and β are obtained by learning from historical data, and the optimal weights are determined by the least squares method. The fused data is compared with the actual tool status, and the deviation between the fused data and the actual status is calculated. The expression is:

[0103] ΔD=D fusion -D actual

[0104] Among them, ΔD represents the deviation value, which is used to measure the gap between the fused data and the actual tool status; D fusion represents the fused data set; D actual A data set representing the actual tool status.

[0105] S4: Based on the results of data fusion, anomaly detection is performed and an alarm is issued when an abnormal situation is detected.

[0106] Construct a comprehensive indicator Z to evaluate the status of the tool, the expression is:

[0107]

[0108] Among them, Z represents the health status score, CUT max Indicates the maximum value of the accumulated usage time.

[0109] Take the health status score Z as the standard and set the threshold. When Z exceeds the preset threshold, it is considered that there is a potential failure point in the tool; when the system detects an abnormal change in Z, the system will automatically issue an alarm. Determine the maintenance of replacement parts based on the status of the tool. Update the reading frequency and power of the RFID tag to ensure system performance and reduce energy consumption.

[0110] S5: Regularly update the machine learning model and adjust the system configuration based on user feedback and system operation data.

[0111] Standardize the collected feedback data; The six features ΔT, ΔH, and ΔF construct the feedback function, which is expressed as follows:

[0112]

[0113] Among them, U represents the feedback evaluation score, and the value range of U is [0,6]; U f Represents the quantitative value of user feedback, U max Indicates the maximum value of user feedback.

[0114] Based on the updated model, the system configuration parameters are adjusted according to the prediction results, and the reading frequency and power of the RFID tag are recalculated after the adjustment.

[0115] Embodiment 2: This embodiment also provides an intelligent management system for scheduled inspection of safety tools based on RFID technology, which includes:

[0116] The data acquisition module is responsible for collecting the RFID tag information, sensor data, usage frequency, time and environmental conditions of the tools to form a tool status data set.

[0117] The adaptive learning module analyzes the tool usage patterns and environmental changes based on the tool status dataset through machine learning algorithms.

[0118] The intelligent prediction module uses data analysis models to predict potential failure points of tools based on historical data and dynamically adjust the reading frequency and power of RFID tags.

[0119] The multi-sensor fusion module integrates RFID data with data from multiple sensors, and improves the accuracy of the system's perception of tool status through data fusion technology.

[0120] The decision support module is responsible for comprehensively analyzing the data from the adaptive learning module, intelligent prediction module and multi-sensor fusion module, formulating maintenance plans for tools and equipment, and issuing alarms when abnormal conditions are detected.

[0121] The user interaction module provides a user interface and allows users to submit usage feedback.

[0122] The system optimization module regularly updates the machine learning model and adjusts the configuration of the entire system based on user feedback and system operation data.

[0123] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0124] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0125] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0126] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0127] Example 3 is an embodiment of the present invention, which provides an intelligent management method for scheduled inspection of safety tools using RFID technology. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0128] During the experiment, the RFID reader recorded the timestamp of each tool entering and leaving the warehouse, and calculated the tool usage frequency F and cumulative usage time CUT based on these timestamps; at the same time, the environmental sensor collected data on ambient temperature T and humidity H, which helped to evaluate the usage of tools in specific environments; the data acquisition module integrated the RFID tag information, sensor data, usage frequency and cumulative usage time into a tool status data set D; then, the data was processed through the adaptive learning module, intelligent prediction module and multi-sensor fusion module.

[0129] In the adaptive learning module, the support vector machine (SVM) model is used to analyze the usage patterns and environmental changes of tools. The intelligent prediction module uses the data analysis model to predict the potential failure points of tools and dynamically adjusts the reading frequency and power of RFID tags according to the prediction results. The multi-sensor fusion module fuses RFID data with environmental sensor data to improve the accuracy of the system's perception of tool status.

[0130] During the experiment, the decision support module comprehensively analyzed the data of the adaptive learning module, intelligent prediction module and multi-sensor fusion module, formulated a maintenance plan for the tools, and issued an alarm when an abnormal situation was detected; in addition, the user interaction module allowed users to submit usage feedback. These feedback data were collected and used to regularly update the machine learning model, thereby adjusting the configuration of the entire system.

[0131] The details are shown in Table 1 below:

[0132] Table 1 Experimental record table

[0133]

[0134] As can be seen from Table 1, different tools have differences in usage frequency, cumulative usage time, average pressure value and average acceleration value. By analyzing these data, it can be found that:

[0135] Frequency of use F: The electric drill is used most frequently, reaching 40 times / week, while the pliers are used least frequently, only 15 times / week, which means that the electric drill may be one of the most frequently used tools, while pliers are used less frequently.

[0136] Cumulative usage time CUT: The cumulative usage time of the electric drill is 25 hours, which is much higher than other tools, while the cumulative usage time of the screwdriver is the lowest, only 10 hours, which shows that the electric drill is used more intensively per unit time.

[0137] Average pressure value Pv: The average pressure value of the electric drill is the highest, which is 200 Newtons, while the average pressure value of the screwdriver is the lowest, which is 80 Newtons. This is because the electric drill needs to exert a greater torque during use.

[0138] Average acceleration value Av: The average acceleration value of the electric drill is also the highest, reaching 0.8m / s 2 , while the average acceleration of the screwdriver is the lowest, only 0.3m / s 2 , which indicates that the electric drill generates greater vibration and impact during use.

[0139] By comparing these data, it can be found that the proposed safety tool inspection intelligent management system based on RFID technology has significant advantages over the traditional manual management method:

[0140] High degree of intelligence: This system uses RFID technology and sensors to monitor the status of tools in real time, and can automatically collect and analyze data, reducing errors caused by human intervention.

[0141] Accurate fault prediction: The intelligent prediction module uses data analysis models to predict potential failure points of tools based on historical data, which helps to detect and prevent failures in advance and reduce maintenance costs.

[0142] Accurate data fusion: The multi-sensor fusion module fuses data from multiple sensors, improving the system's accuracy in perceiving tool status and making maintenance plans more scientific and reasonable.

[0143] Timely user feedback: The user interaction module allows users to submit usage feedback. These feedback data are collected and used to optimize system configuration, improving the system's adaptability and practicality.

[0144] Therefore, through the data analysis of this embodiment, we can clearly see the innovation and superiority in tool management, especially in improving management efficiency, reducing the occurrence of failures and enhancing user experience.

[0145] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent management method for scheduled inspection of safety tools using RFID technology, characterized in that: include: Collect RFID tag information, sensor data, usage frequency, time and environmental conditions of tools to form a tool status data set; Using the characteristic values ​​of the tool status data set, data analysis is performed to predict potential failure points of the tool based on historical data, and the reading frequency and power of the RFID tag are dynamically adjusted; Improve the system's accuracy in sensing tool status through data fusion technology; Based on the results of data fusion, anomaly detection is performed and an alarm is issued when an abnormal situation is detected; Based on user feedback and system operation data, the machine learning model is updated regularly and the system configuration is adjusted.

2. The RFID technology safety tool inspection intelligent management method according to claim 1, characterized in that: The tool status data set includes installing RFID tags on tools and arranging RFID readers in the warehouse; The data of ambient temperature T and ambient humidity H are collected through the environmental sensors installed in the warehouse; The RFID reader is used to record the timestamp Ti of each entry and exit of tools, and the usage frequency F and cumulative usage time CUT of tools are calculated. The usage frequency F is expressed as: Among them, N represents the number of times of entering and leaving the warehouse, and ΔT represents the time interval; Cumulative usage time CUT, expressed as: Where n is the total number of times the tool is used, T out,i Indicates the timestamp of the end of the i-th use, T in,i Indicates the timestamp of the start of the i-th use; The data acquisition module integrates RFID tag information, sensor data, usage frequency, and cumulative usage time into a tool status data set D, which is expressed as: D=[CUT,Pv,Av,T,H,F] Among them, Pv represents the tool pressure value, and Av represents the tool acceleration value.

3. The RFID technology safety tool inspection intelligent management method according to claim 2, characterized in that: The characteristic values ​​of the tool status data set include the use mode and environmental changes of the tool analyzed by the machine learning algorithm based on the tool status data set, specifically, The characteristic value is calculated based on the tool status data set, and the expression is: in, Indicates the average pressure value of the tool. Indicates the number of pressure data points collected during this time period, Pv i Represents the pressure value at the i-th time point, i represents the index variable, Indicates the average acceleration value of the tool. Indicates the number of acceleration data points collected during this time period, Av q represents the acceleration value at the qth time point, q represents the index variable, represents the average frequency of use of tools, m represents the number of collected frequency data points, and F j represents the usage frequency at the jth time point, j represents the index variable, ΔT represents the rate of change of ambient temperature over time, ΔH represents the rate of change of ambient humidity over time, ΔF represents the rate of change of usage frequency over time, final represents the final time point, and initial represents the initial time point; Use the support vector machine (SVM) model as the basis of the machine learning model. ΔT, ΔH, and ΔF are input into the machine learning model for training to predict the tool usage pattern and environmental changes, as well as the corresponding RFID tag reading frequency and power; Where X represents the feature vector set; The SVM model is used as the basis for building a fault prediction model, and the feature vector is input into the fault prediction model. The expression is: Among them, P f represents the predicted potential failure probability of the tool, e represents the exponential function, ε is the adjustment coefficient, β is the adjustment coefficient, P max Indicates the maximum allowable pressure value, A max Indicates the maximum permissible acceleration value, F max Indicates the maximum permissible frequency of use, T range Indicates the allowable temperature fluctuation range, H range Indicates the allowable humidity fluctuation range.

4. The RFID technology safety tool inspection intelligent management method according to claim 3, characterized in that: The specific steps of dynamically adjusting the reading frequency and power of the RFID tag are as follows: Based on the prediction of the potential failure probability P of the tool f , set the threshold TP; When P f >TP, indicating that the tool has a high probability of potential failure points, and the reading frequency and power of the RFID tag are dynamically adjusted; When P f When ≤TP, it means that the probability of potential failure points in the tool is low, and daily inspection work should be maintained; The reading frequency and power of the RFID tag are expressed as: Wherein, f represents the reading frequency of the RFID tag, and p represents the power of the RFID tag.

5. The intelligent management method for scheduled inspection of safety tools based on RFID technology as claimed in claim 4, characterized in that: Improving the accuracy of the system's perception of the tool status through data fusion technology includes standardizing the data from the RFID tag and the environmental sensor; The data from different sensors are fused by weighted averaging, and the expression is: D fusion =a·RFIDA+b·ENV Among them, D fusion represents the fused data set, RFIDA represents the data value provided by the RFID tag, α represents the weight factor of RFIDA, ENV represents the data value provided by the environmental sensor, and β represents the weight factor of ENV; The weight factors α and β are obtained by learning from historical data, and the optimal weights are determined by the least squares method; Compare the fused data with the actual tool status and calculate the deviation between the fused data and the actual status. The expression is: ΔD=D fusion -D actual Among them, ΔD represents the deviation value, which is used to measure the gap between the fused data and the actual tool status; D fusion represents the fused data set; D actual A data set representing the actual tool status.

6. The RFID technology safety tool inspection intelligent management method according to claim 5, characterized in that: The data fusion technology includes constructing a comprehensive index Z to evaluate the status of the tool, which is expressed as: Among them, Z represents the health status score, CUT max Indicates the maximum value of the accumulated usage time. Taking the health status score Z as the standard, a threshold is set; When Z exceeds the preset threshold, it is considered that there is a potential fault point in the tool; when the system detects an abnormal change in Z, the system will automatically issue an alarm; Determine the replacement of parts based on the status of the tool; Update the reading frequency and power of RFID tags.

7. The intelligent management method for scheduled inspection of safety tools based on RFID technology as claimed in claim 6, characterized in that: Standardize the collected feedback data; based on The six features ΔT, ΔH, and ΔF construct the feedback function, which is expressed as follows: Among them, U represents the feedback evaluation score, and the value range of U is [0,6]; U f Represents the quantitative value of user feedback, U max Indicates the maximum value of user feedback; Based on the updated model, the system configuration parameters are adjusted according to the prediction results, and the reading frequency and power of the RFID tag are recalculated after the adjustment.

8. An intelligent management system for scheduled inspection of safety tools based on RFID technology using the method as described in any one of claims 1 to 7, characterized in that: The data acquisition module is responsible for collecting the RFID tag information, sensor data, usage frequency, time and environmental conditions of the tools to form a tool status data set; Adaptive learning module, which analyzes tool usage patterns and environmental changes based on tool status datasets through machine learning algorithms; The intelligent prediction module uses data analysis models to predict potential failure points of tools based on historical data and dynamically adjust the reading frequency and power of RFID tags; Multi-sensor fusion module integrates RFID data with data from multiple sensors, and improves the system's accuracy in sensing tool status through data fusion technology; The decision support module is responsible for comprehensively analyzing the data from the adaptive learning module, the intelligent prediction module, and the multi-sensor fusion module, formulating maintenance plans for tools, and issuing alarms when abnormal conditions are detected; User interaction module, which provides a user interface and allows users to submit usage feedback; The system optimization module regularly updates the machine learning model and adjusts the configuration of the entire system based on user feedback and system operation data.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any method as claimed in claim 1 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images