Intelligent protective glasses equipment management method and system based on cloud platform

Abstract

The invention relates to the technical field of intelligent equipment management, in particular to an intelligent protective glasses equipment management method and system based on a cloud platform. The method comprises the following steps: monitoring corresponding dial scanning data, gas monitoring data and equipment external environment data in real time through a corresponding sensor built in intelligent protective glasses equipment, and uploading the data to a cloud platform; acquiring an equipment dial plate scanning use frequency, and performing dial plate scanning fault analysis and gas reading abnormity evaluation to obtain an equipment dial plate scanning fault probability and an equipment gas reading abnormity index; and carrying out equipment intelligent management analysis on the intelligent protective glasses equipment based on the equipment dial scanning fault probability and the equipment gas reading abnormal index so as to generate a cloud platform equipment abnormity maintenance management plan corresponding to the intelligent protective glasses equipment. According to the invention, comprehensive equipment state monitoring and accurate maintenance management work can be provided for the intelligent protective glasses, so that the use performance and user experience of the intelligent protective glasses can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent device management, and particularly to a method and system for managing intelligent protective glasses devices based on a cloud platform. Background Art

[0002] With the increasing industrial safety requirements, traditional personal protective equipment (PPE) has gradually been unable to meet the safety protection needs in modern high-risk environments. As a new type of safety protection technology, intelligent protective equipment has gradually entered high-risk fields such as industry, elevators, and chemical engineering. As an advanced device integrating various sensors, communication modules, and data processing capabilities, the intelligent protective glasses can scan instrument dials such as pressure gauges and flow meters, identify the data on the dials, and upload the data to the backend server, effectively improving the safety guarantee in the elevator operation environment and has become an indispensable safety protection tool in many fields. However, most of the existing intelligent protective glasses rely on local management systems, and there are often information islands in the analysis of dial data, gas concentration data, and leakage location data monitored in real time, which cannot be analyzed and utilized in a timely and accurate manner, resulting in the inability of the device to make intelligent adjustments according to the actual situation and it is also difficult to timely feedback effective information to the cloud platform and relevant personnel. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for managing intelligent protective glasses devices based on a cloud platform to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for managing intelligent protective glasses devices based on a cloud platform includes the following steps: Step S1: Real-time monitor the corresponding dial scan data, gas monitoring data, and device external environment data through the sensors built in the intelligent protective glasses device, where the device external environment data includes temperature data and humidity data, and upload them to the cloud platform using wireless communication technology; Step S2: Obtain the usage frequency of the device dial scan, and perform dial scan fault analysis on the corresponding dial scan sensors in the intelligent protective glasses device based on the temperature data, dial scan data, and device dial scan usage frequency on the cloud platform to obtain the device dial scan fault probability; Step S3: Obtain the calibration data and usage duration corresponding to the gas sensors in the intelligent protective glasses device through the cloud platform, and perform sensing aging prediction based on the calibration data and usage duration to obtain the gas sensor aging time; perform gas reading anomaly evaluation on the corresponding gas sensors based on the gas sensor aging time, humidity data, and gas monitoring data to obtain the device gas reading anomaly index; Step S4: Based on the device dial scan failure probability and the device gas reading anomaly index, perform device intelligent management analysis on the intelligent protective glasses device to generate a cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

[0005] Further, step S1 includes the following steps: Step S11: Use the built-in dial scan sensor of the intelligent protective glasses device to continuously monitor the dial scan pictures corresponding to the pressure gauge and the flow meter; Step S12: Use image recognition technology to perform dial recognition analysis on the dial scan pictures corresponding to the pressure gauge and the flow meter to obtain dial scan data; Step S13: Use the built-in gas sensor of the intelligent protective glasses device to continuously monitor the gas corresponding to the impending leakage, and convert the gas leakage condition into a visual corresponding color display intensity to obtain gas monitoring data; Step S14: Use the built-in environment sensor of the intelligent protective glasses device to continuously monitor the surrounding environment corresponding temperature data and humidity data to obtain device external environment data; Step S15: Denoise, filter, and normalize the dial scan data, gas monitoring data, and device external environment data, and upload the preprocessed dial scan data, gas monitoring data, and device external environment data to the cloud platform using wireless communication technology.

[0006] Further, step S2 includes the following steps: Step S21: Obtain the usage times of the dial scan sensor on the intelligent protective glasses device, and perform frequency quantization calculation based on the usage times of the dial scan sensor to obtain the device dial scan usage frequency; Step S22: Perform life attenuation assessment on the battery inside the intelligent protective glasses device based on the temperature data on the cloud platform to obtain the device battery life attenuation rate; Step S23: Perform accurate assessment of scan recognition on the dial scan data based on the device dial scan usage frequency to obtain the device dial scan recognition accuracy rate; Step S24: Perform dial scan failure analysis on the dial scan sensor inside the intelligent protective glasses device based on the device battery life attenuation rate and the device dial scan recognition accuracy rate to obtain the device dial scan failure probability.

[0007] Further, step S22 includes the following steps: Perform time series feature analysis on the temperature data on the cloud platform to analyze and extract the change trend, periodicity, and mutation point features of the temperature to obtain the temperature time series change features; Based on the temperature time - series variation characteristics, perform temperature frequency distribution statistics on temperature data to obtain the temperature time - series frequency distribution; Based on the temperature time - series frequency distribution, simulate the battery life attenuation of the corresponding battery in the intelligent protective glasses device to generate the life attenuation process of the battery under the corresponding temperature frequency distribution; Perform battery prediction and capacity attenuation analysis on the life attenuation process of the battery under the corresponding temperature frequency distribution to obtain the predicted capacity and capacity attenuation amount of the battery at each time point; Obtain the initial capacity of the battery, and perform life attenuation calculation based on the predicted capacity and capacity attenuation amount of the battery at each time point and in combination with the initial capacity of the battery to obtain the battery life attenuation rate of the device.

[0008] Further, step S23 includes the following steps: Step S231: Obtain the actual data corresponding to the dial; Step S232: Based on the actual data corresponding to the dial, calculate the difference between the dial scan data to obtain the deviation of the dial scan data; Step S233: Based on the usage frequency of the device dial scan, analyze the scan usage limit of the corresponding dial scan sensor to obtain the attenuation degree of the dial scan performance limit; Step S234: Based on the attenuation degree of the dial scan performance limit and in combination with the deviation of the dial scan data, accurately evaluate the scan recognition of the corresponding dial scan sensor to obtain the dial scan recognition accuracy rate of the device.

[0009] Further, step S24 includes the following steps: Step S241: Conduct a comparative analysis of the mathematical relationship based on the battery life attenuation rate of the device and the dial scan recognition accuracy rate of the device to obtain the mathematical relationship between battery life attenuation and scan recognition; Step S242: Based on the dial scan recognition accuracy rate of the device, evaluate the scan response of the corresponding dial scan sensor in the intelligent protective glasses device to obtain the dial scan response interval under the corresponding recognition accuracy rate; Step S243: According to the dial scan response interval under the corresponding recognition accuracy rate, perform statistical calculation on the scan indicators of the scan pictures corresponding to the dial scan sensor to obtain the dial scan resolution and dial scan contrast under the corresponding recognition accuracy rate; Step S244: Based on the mathematical relationship between battery life attenuation and scan recognition and in combination with the battery life attenuation rate of the device and the dial scan recognition accuracy rate of the device, perform a dial scan fault assessment calculation on the dial scan resolution and dial scan contrast under the corresponding recognition accuracy rate to obtain the dial scan fault probability of the device.

[0010] Furthermore, step S3 includes the following steps: Step S31: Obtain the calibration data corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform; Step S32: Obtain the usage duration corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform; Step S33: Perform sensing aging prediction based on the calibration data and the usage duration to obtain the aging time of the gas sensor; Step S34: Perform gas reading anomaly assessment on the corresponding gas sensor based on the gas sensor aging time, humidity data, and gas monitoring data to obtain the device gas reading anomaly index.

[0011] Furthermore, step S34 includes the following steps: Step S341: Perform monitoring accuracy impact assessment on the corresponding gas sensor based on the humidity data to obtain the impact degree of humidity on the accuracy of the gas sensor; Step S342: Perform reading anomaly fluctuation coupling analysis on the gas monitoring data based on the impact degree of humidity on the accuracy of the gas sensor to obtain the gas sensor reading anomaly fluctuation amplitude; Step S343: Perform gas reading anomaly assessment on the corresponding gas sensor based on the gas sensor aging time and the gas sensor reading anomaly fluctuation amplitude to obtain the device gas reading anomaly index.

[0012] Furthermore, step S4 includes the following steps: Step S41: Perform device safety response warning on the intelligent protective glasses device based on the device dial scanning failure probability and the device gas reading anomaly index. If both the device dial scanning failure probability and the device gas reading anomaly index exceed the preset threshold, then generate a corresponding maintenance instruction through the corresponding safety warning module in the intelligent protective glasses device to generate a device safety warning maintenance instruction; Step S42: Apply the device safety warning maintenance instruction to the intelligent protective glasses device for device intelligent management analysis, automatically send a maintenance reminder to the corresponding maintenance terminal of the maintenance personnel, and formulate a corresponding maintenance time, maintenance content, and maintenance personnel arrangement push plan to generate a cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

[0013] Furthermore, the present invention also provides a cloud platform-based intelligent protective glasses device management system for executing the above-mentioned cloud platform-based intelligent protective glasses device management method. The cloud platform-based intelligent protective glasses device management system includes: The device data real-time monitoring module is used to real-time monitor the corresponding dial scan data, gas monitoring data, and device external environment data through the sensors built in the intelligent protective glasses device. The device external environment data includes temperature data and humidity data, and uploads them to the cloud platform using wireless communication technology; The dial scan fault analysis module is used to obtain the usage frequency of the device dial scan, and perform dial scan fault analysis on the corresponding dial scan sensors in the intelligent protective glasses device based on the temperature data, dial scan data, and device dial scan usage frequency on the cloud platform, so as to obtain the device dial scan fault probability; The gas reading anomaly evaluation module is used to obtain the calibration data and usage duration corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform, and perform sensing aging prediction according to the calibration data and usage duration to obtain the gas sensor aging time; perform gas reading anomaly evaluation on the corresponding gas sensor based on the gas sensor aging time, humidity data, and gas monitoring data, so as to obtain the device gas reading anomaly index; The device intelligent management module is used to perform device intelligent management analysis on the intelligent protective glasses device based on the device dial scan fault probability and the device gas reading anomaly index, so as to generate the cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

[0014] Advantages of the present invention: 1. Compared with the prior art, the beneficial effect of the intelligent protective glasses device management method based on the cloud platform proposed by the present invention lies in the real-time monitoring of multiple key data through the built-in sensors, such as dial scanning data, gas monitoring data, temperature data, and humidity data. These data can comprehensively reflect the usage status of the device and the changes in the external environment. The application of sensors not only improves the monitoring accuracy of the device but also ensures that in the actual use process, users can obtain accurate real-time feedback. And through wireless communication technology, these data are uploaded to the cloud platform. The device can send its working status and environmental parameters to the cloud at any time, enabling the cloud platform to timely grasp the device operation situation, thereby providing a reliable information source for subsequent data analysis and fault prediction. Through the collection and upload of real-time data, the device can more flexibly and intelligently adapt to environmental changes, improving the device's working ability in complex environments. Most importantly, the cloud storage and processing of all data not only improve the accessibility and security of the data but also provide data support for subsequent artificial intelligence analysis and optimization, promoting the intelligent management of the device. Secondly, through the temperature data, dial scanning data, and the usage frequency of the device on the cloud platform, fault analysis can be carried out on the dial scanning sensor in the intelligent protective glasses device. The faults of the device's dial scanning sensor usually affect the user experience and safety, so the prediction and analysis of its fault probability are crucial. Temperature and humidity are the key factors affecting the accuracy and performance of the sensor, while the dial scanning data and the usage frequency of the device are important indicators for understanding the health status of the sensor. By combining these data, the cloud platform can evaluate the probability of the sensor failing, thereby providing forward-looking information for the maintenance of the device. In this way, the corresponding data can be analyzed and utilized in a timely and accurate manner, and accurate fault prediction can be made according to the actual situation to help users perform maintenance or replace the sensor in a timely manner. Then, the aging of the gas sensor is an inevitable phenomenon during the long-term use of the device. In this step, by obtaining the calibration data and usage duration of the device's gas sensor, the cloud platform can predict the aging time of the gas sensor and evaluate its abnormal gas readings. The calibration data of the gas sensor can reflect its initial performance, while the usage duration can reveal the aging process of the sensor. By combining the humidity data and the gas monitoring data, the cloud platform can conduct an abnormal evaluation of the gas readings of the sensor, thereby obtaining an abnormal gas reading index. In this way, the performance degradation of the gas sensor can be effectively evaluated and a response can be made. As the sensor ages, the gas readings will become inaccurate, which not only affects the usage effect of the device but also can be intelligently adjusted according to the actual situation. This data-based prediction can greatly improve the predictability and accuracy of device maintenance, reduce ineffective device inspections and maintenance, and improve the overall operation efficiency of the device.Finally, based on the previously analyzed dial scan failure probability and gas reading anomaly index, the cloud platform will perform intelligent management analysis. Through intelligent algorithms, it comprehensively evaluates the device status. The cloud platform can provide personalized maintenance suggestions for the device, including specific measures such as repair, calibration, and sensor replacement. Through precise management analysis, the cloud platform can not only minimize the occurrence of device failures but also ensure the long-term stable operation of the device. This enables targeted scheduling and repair according to the status of different devices, ensuring that each task can address the specific problems of the device, and thus can timely feedback effective information to the cloud platform and relevant personnel.

[0015] 2. The intelligent protective glasses device management system based on the cloud platform proposed by the present invention is generally composed of a device data real-time monitoring module, a dial scan failure analysis module, a gas reading anomaly evaluation module, and a device intelligent management module. It can implement any of the intelligent protective glasses device management methods based on the cloud platform described in the present invention, and is used to realize the intelligent protective glasses device management method based on the cloud platform through the operation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower investment, and can quickly and effectively provide a more accurate and efficient intelligent protective glasses device management process based on the cloud platform, thereby simplifying the operation process of the intelligent protective glasses device management system based on the cloud platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects, and advantages of the present invention will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings: Figure 1 It is a schematic flow chart of the steps of the intelligent protective glasses device management method based on the cloud platform of the present invention; Figure 2 For Figure 1 a detailed schematic flow chart of step S1 in Figure 3 For Figure 1 a detailed schematic flow chart of step S2 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0018] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0019] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0020] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for managing an intelligent protective glasses device based on a cloud platform, and the method includes the following steps: Step S1: Real-time monitor the corresponding dial scan data, gas monitoring data, and device external environment data through sensors built in the intelligent protective glasses device, where the device external environment data includes temperature data and humidity data, and upload them to the cloud platform using wireless communication technology; Step S2: Obtain the usage frequency of the device dial scan, and perform dial scan fault analysis on the corresponding dial scan sensor in the intelligent protective glasses device based on the temperature data, dial scan data, and device dial scan usage frequency on the cloud platform to obtain the device dial scan fault probability; Step S3: Obtain the calibration data and usage duration corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform, and perform sensing aging prediction based on the calibration data and usage duration to obtain the gas sensor aging time; perform gas reading anomaly evaluation on the corresponding gas sensor based on the gas sensor aging time, humidity data, and gas monitoring data to obtain the device gas reading anomaly index; Step S4: Perform device intelligent management analysis on the intelligent protective glasses device based on the device dial scan fault probability and the device gas reading anomaly index to generate a cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

[0021] In the embodiments of the present invention, please refer to Figure 1As shown in the figure, it is a schematic flow chart of the steps of the intelligent protective glasses device management method based on the cloud platform of the present invention. In this example, the intelligent protective glasses device management method based on the cloud platform includes the following steps: Step S1: The corresponding dial scan data, gas monitoring data, and device external environment data are continuously monitored in real time through the sensors built in the intelligent protective glasses device. The device external environment data includes temperature data and humidity data, and they are uploaded to the cloud platform using wireless communication technology; In the embodiment of the present invention, the dial scan sensor, gas sensor, and environment sensor built in the intelligent protective glasses device work continuously. The dial scan sensor is a high-resolution image acquisition device, which scans the dials such as pressure gauges and flow meters 3 times per second. The dial image is converted into an electrical signal through the principle of optical imaging, and after analog-to-digital conversion, it is temporarily stored in the device cache. The gas sensor uses the electrochemical principle to continuously monitor the surrounding gas. When gas molecules react with the sensor electrode, the change in the generated electrical signal is recorded. The temperature sensor in the environment sensor uses the characteristics of a thermistor, and the humidity sensor is based on the capacitance change detection principle to collect temperature and humidity data at a frequency of 1 time per minute. The wireless communication module built in the device, such as a Wi-Fi or 4G module, packages and uploads the dial scan data (including the digital information of the dial image), gas monitoring data (gas type, concentration, etc.), and device external environment data (temperature and humidity values) in the cache to the cloud platform every 5 minutes according to the MQTT communication protocol. On the cloud platform, a data receiving program written in Python listens to the corresponding topic of the MQTT server and accurately stores the received data in a relational database, using the device number and timestamp as the primary key for convenient subsequent query and analysis. For example, for an intelligent protective glasses device numbered 001, the data uploaded at 10:05 am includes the matrix data after digitalization of the dial scan image, the detected methane concentration of 5 ppm, and the temperature of 25 °C and humidity of 50%, etc., which are completely stored in the database.

[0022] Step S2: Obtain the usage frequency of the device dial scan, and perform dial scan fault analysis on the corresponding dial scan sensor in the intelligent protective glasses device based on the temperature data, dial scan data, and device dial scan usage frequency on the cloud platform to obtain the device dial scan fault probability; In an embodiment of the present invention, on the cloud platform, the usage frequency of the device dial scan is obtained from the log records of the intelligent protective glasses device. The logs are stored in the cloud platform database. Through an SQL query statement such as "SELECT COUNT (*) FROM scan_log WHERE device_id = '001' AND scan_type = 'dial' GROUP BY device_id", the number of dial scans of a certain device (such as device number 001) within the past day is counted. Assuming that the number of scans obtained is 2000 times, the converted usage frequency is approximately 83 times per hour. Using Python to write an analysis program, the temperature data of the device (stored in a DataFrame structure of pandas, with the index being the timestamp and the column name being "temperature"), the dial scan data (including the recognized dial values, etc.), and the calculated usage frequency are read from the cloud platform database. Based on a pre-established dial scan fault analysis model, this model considers the influence of temperature on the sensor performance (such as for every 5°C increase in temperature, the scan accuracy decreases by 3%) and the relationship between the usage frequency and the fault probability (for every 100 times / hour increase in usage frequency, the fault probability increases by 5%). For example, the average temperature of the device on that day is 28°C, which is 3°C higher than the standard working temperature of 25°C, and the scan accuracy is expected to decrease by 1.8%; the usage frequency is 83 times / hour, which is 33 times / hour higher than the reference frequency of 50 times / hour, and the fault probability is expected to increase by 1.65%. Through comprehensive calculation by the model, the device dial scan fault probability is obtained as 15%, and this data is stored in the cloud platform database and associated with the device number.

[0023] Step S3: Obtain the calibration data and usage duration corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform, and perform sensing aging prediction based on the calibration data and usage duration to obtain the gas sensor aging time; perform gas reading anomaly assessment on the corresponding gas sensor based on the gas sensor aging time, humidity data, and gas monitoring data to obtain the device gas reading anomaly index; In an embodiment of the present invention, the cloud platform obtains calibration data corresponding to the gas sensor from the built-in storage module or the device management system of the device through a communication connection with the intelligent protective glasses device. The calibration data is stored after the sensor is calibrated and includes standard output signal values at different gas concentrations. At the same time, the usage duration of the gas sensor is obtained. The device starts timing from when the sensor is enabled and regularly uploads the usage duration data to the cloud platform through wireless communication and stores it in the database. A sensing aging prediction program is written in Python. According to the calibration data and the usage duration, in the model, for every 10,000 seconds increase in the usage duration, the deviation between the sensor output voltage and the actual gas concentration increases by 0.1V. If the usage duration of the gas sensor of a certain device is 50,000 seconds and the output voltage corresponding to a gas concentration of 10 ppm in the initial calibration data is 0.5V, according to the model calculation, the output voltage deviation at this time is 0.5V. Based on the humidity data, the abnormal fluctuation amplitude of the corresponding readings of the gas monitoring data is analyzed, and an abnormal evaluation model is set. For example, the abnormal index = abnormal fluctuation amplitude of readings / standard fluctuation amplitude + aging influence coefficient × (1 - remaining aging time ratio (i.e., the ratio between the aging time and the usage duration)), where the standard fluctuation amplitude is determined according to the performance indicators of the sensor in the normal working state, and the aging influence coefficient is determined through experiments or experience. For example, the standard fluctuation amplitude is 0.2 ppm, the aging influence coefficient is 0.3, and the remaining aging time ratio is 0.4 (i.e., the remaining aging time is 40% of the expected aging time). Assuming that the abnormal fluctuation amplitude of the readings at a certain moment is 0.4 ppm, substituting it into the model calculation gives the abnormal index = 0.4 / 0.2 + 0.3 × (1 - 0.4) = 2 + 0.18 = 2.18. This index is stored in the cloud platform database corresponding to the device number.

[0024] Step S4: Based on the device dial scanning failure probability and the device gas reading abnormal index, perform device intelligent management analysis on the intelligent protective glasses device to generate a cloud platform device abnormal maintenance management plan corresponding to the intelligent protective glasses device.

[0025] In an embodiment of the present invention, by using Python to write a device intelligent management and analysis program on a cloud platform, device dial scan failure probability data and device gas reading anomaly index data read from the cloud platform database are obtained. At the same time, maintenance personnel information (stored in a DataFrame structure of pandas, with columns such as "maintenance personnel name", "contact information", "expertise field", etc.) and maintenance task priority setting data in the device management system are read. For device number 001, its dial scan failure probability is 15% and the gas reading anomaly index is 0.13. According to the pre-set rules, when the dial scan failure probability exceeds 10% or the gas reading anomaly index exceeds 0.1, the maintenance process is triggered. The program, based on the maintenance instruction content (such as "perform performance detection and calibration on the dial scan sensor, and perform maintenance and recalibration on the gas sensor"), matches maintenance personnel proficient in the corresponding fields through data analysis. Suppose it is determined that maintenance personnel Wang Wu is proficient in maintaining the dial scan sensor and Zhao Liu is proficient in maintaining the gas sensor. According to the work arrangements of the maintenance personnel and the task priorities, the maintenance time is determined. For example, it is arranged that Wang Wu will maintain the dial scan sensor at 10 am the day after tomorrow, and Zhao Liu will maintain the gas sensor at 3 pm the day after tomorrow. The maintenance time, maintenance content, and maintenance personnel arrangements are sorted into a push plan, and a text message "Please perform performance detection and calibration on the dial scan sensor of device number 001 at 10 am the day after tomorrow" is sent to Wang Wu through the SMS gateway, and a message "Please perform maintenance and recalibration on the gas sensor of device number 001 at 3 pm the day after tomorrow" is sent to Zhao Liu through the instant messaging software. At the same time, the detailed cloud platform device anomaly maintenance management plan corresponding to the entire intelligent protective glasses device is recorded in the cloud platform database, including a maintenance task progress tracking field, which is convenient for subsequent viewing and updating of the maintenance status. Further, step S1 includes the following steps: Step S11: Real-time monitor the dial scan pictures corresponding to the pressure gauge and flow meter through the dial scan sensor built in the intelligent protective glasses device; Step S12: Perform dial recognition and analysis on the dial scan pictures corresponding to the pressure gauge and flow meter through image recognition technology to obtain dial scan data; Step S13: Real-time monitor the gas corresponding to the impending leakage through the gas sensor built in the intelligent protective glasses device, and convert the gas leakage condition into a visual corresponding color display intensity to obtain gas monitoring data; Step S14: Real-time monitor the surrounding environment corresponding temperature data and humidity data through the environmental sensor built in the intelligent protective glasses device to obtain device external environment data; Step S15: Denoise, filter, and normalize the dial scan data, gas monitoring data, and device external environment data, and upload the preprocessed dial scan data, gas monitoring data, and device external environment data to the cloud platform using wireless communication technology.

[0026] As an embodiment of the present invention, refer to Figure 2 shown in Figure 1 the detailed step flow diagram of step S1 in Step S11: Use the built-in corresponding dial scan sensor in the intelligent protective glasses device to continuously monitor the dial scan pictures corresponding to the pressure gauge and flow meter in real time; In the embodiment of the present invention, the dial scan sensor built in the intelligent protective glasses device is a high-precision image acquisition module, which has high resolution and fast focusing functions. In the industrial production site, such as a chemical workshop, the dial scan sensor scans the dials of the pressure gauge and flow meter at a frequency of 5 times per second. For example, for a circular pressure gauge dial, the sensor captures its complete circular contour, scale markings, and pointer position. Each time it scans, the sensor focuses the light of the dial onto the image sensor through the built-in optical lens, converts the optical signal into an electrical signal, and then generates a dial scan picture. These pictures are temporarily stored in the local cache of the intelligent protective glasses device in a specific image format, such as JPEG format, for subsequent processing.

[0027] Step S12: Use image recognition technology to perform dial recognition and analysis on the dial scan pictures corresponding to the pressure gauge and flow meter to obtain dial scan data; In the embodiment of the present invention, the intelligent protective glasses device is equipped with a dedicated image recognition chip, and an image recognition program based on deep learning algorithms runs in the chip. The previously cached dial scan pictures are sequentially input into the image recognition chip one by one. The algorithm first performs edge detection on the pictures to identify the contour of the dial. For example, for a square flow meter dial, it can accurately identify the positions of the four sides. Then, through the character recognition algorithm, it recognizes the numbers on the scale markings, and uses the template matching algorithm to determine the position of the pointer on the dial. By calculating the relative position relationship between the pointer and the scale markings, the specific pressure value or flow value is obtained. For example, when the pointer points to the position of the flow meter scale "50", the algorithm can output the dial scan data with a flow rate of 50 units. These data are organized into a structured format and stored in the temporary data storage area of the device.

[0028] Step S13: Use the built-in corresponding gas sensor in the intelligent protective glasses device to continuously monitor the gas about to leak in real time, and convert the gas leakage situation into a visual corresponding color display intensity to obtain gas monitoring data; In an embodiment of the present invention, the gas sensor built into the intelligent protective glasses device is an electrochemical gas sensor, which has high sensitivity to a variety of easily leaked gases. In an environment where there may be a risk of gas leakage, such as a natural gas transmission station, the gas sensor continuously operates. When gas molecules about to leak come into contact with the induction electrode of the sensor, an electrochemical reaction occurs, causing a change in the current between the electrodes. The circuit inside the sensor converts this current change into a voltage signal, and through an analog-to-digital conversion module, the analog voltage signal is converted into a digital signal. According to the pre-set correspondence between the gas concentration and the color display intensity, for example, low-concentration natural gas leakage corresponds to a weak green display intensity, and high concentration corresponds to a strong red display intensity, the gas leakage situation is converted into a visually corresponding color display intensity. For example, when the detected natural gas concentration reaches a certain threshold, the display screen of the device shows red and has a high brightness, and at the same time, corresponding gas monitoring data is generated, such as "natural gas leakage, color display intensity: high", and is stored in the data storage area of the device.

[0029] Step S14: The corresponding ambient sensors built into the intelligent protective glasses device are used to continuously monitor the corresponding temperature data and humidity data of the surrounding environment to obtain the external environment data of the device. In an embodiment of the present invention, the ambient sensor of the intelligent protective glasses device integrates a temperature sensor and a humidity sensor. The temperature sensor uses a thermistor-type sensor, and the humidity sensor uses a capacitive humidity sensor. In daily use scenarios, such as outdoor construction sites, the ambient sensor collects data at a frequency of once per minute. The temperature sensor converts the temperature signal into an electrical signal through the characteristic that the resistance value of the thermistor changes with temperature, and after being processed by the signal conditioning circuit, accurate temperature data is obtained. The humidity sensor obtains the humidity data by detecting the change in capacitance value with the ambient humidity, and also through signal conditioning and analog-to-digital conversion. For example, at a certain moment, the temperature sensor collects an ambient temperature of 30 °C, and the humidity sensor collects a humidity of 60%. These temperature data and humidity data are integrated into the external environment data of the device and stored in the temporary storage area of the device.

[0030] Step S15: Denoising, filtering, and normalization processing are performed on the dial scan data, gas monitoring data, and external environment data of the device, and the pre-processed dial scan data, gas monitoring data, and external environment data of the device are uploaded to the cloud platform using wireless communication technology.

[0031] In an embodiment of the present invention, a data preprocessing program is running in the microprocessor inside the intelligent protective glasses device. For the dial scan data, gas monitoring data, and external environment data of the device, denoising processing is first performed. The median filtering algorithm is used to smooth the data and remove the random noise in the data. For example, for a set of pressure value data [2.1, 2.3, 2.0, 10.5, 2.2] obtained from dial scanning, 10.5 is obviously a noise point. After median filtering, this data point is corrected to 2.2. Then, filtering processing is performed. A low-pass filter is used to remove high-frequency interference signals. Finally, normalization processing is performed to map data in different ranges to the [0, 1] interval. For example, the pressure value range of 0-10 MPa is normalized to [0, 1]. The preprocessed data is uploaded to the cloud platform through the built-in wireless communication module of the device, such as a Wi-Fi module or a 4G module, according to a specific communication protocol, such as the MQTT protocol, for subsequent data analysis and processing.

[0032] Further, step S2 includes the following steps: Step S21: Obtain the usage times corresponding to the dial scan sensor on the intelligent protective glasses device, and perform frequency quantization calculation according to the usage times corresponding to the dial scan sensor to obtain the device dial scan usage frequency; Step S22: Evaluate the life attenuation of the corresponding battery in the intelligent protective glasses device based on the temperature data on the cloud platform to obtain the device battery life attenuation rate; Step S23: Perform an accurate evaluation of the dial scan data based on the device dial scan usage frequency to obtain the device dial scan recognition accuracy rate; Step S24: Perform a dial scan fault analysis on the corresponding dial scan sensor in the intelligent protective glasses device based on the device battery life attenuation rate and the device dial scan recognition accuracy rate to obtain the device dial scan fault probability.

[0033] As an embodiment of the present invention, refer to Figure 3 shown, for Figure 1 the detailed step flow schematic diagram of step S2 in Step S21: Obtain the usage times corresponding to the dial scan sensor on the intelligent protective glasses device, and perform frequency quantization calculation according to the usage times corresponding to the dial scan sensor to obtain the device dial scan usage frequency; In the embodiment of the present invention, a counter variable is preset in the firmware of the intelligent protective glasses device to record the usage times of the dial scanning sensor. Each time the dial scanning sensor performs a scanning operation, the microcontroller of the device will automatically increment the value of the counter variable by 1. For example, when the intelligent protective glasses scan the pressure gauge dial in a chemical workshop, after the scanning action is triggered, the microcontroller executes an addition instruction to change the value of the counter variable from 100 to 101. The intelligent protective glasses device sends the value of the counter variable to the cloud platform at a set time interval (such as every hour) through the built-in wireless communication module. On the cloud platform, a data processing program is written in Python to receive and store these usage times data. Assuming that data is received once an hour within a day, a total of 24 data are received, which are 100, 105, 110... 340 respectively. By calculating the change amount of the usage times within a certain period, frequency quantization calculation is performed. For example, to calculate the dial scanning usage frequency in the past 24 hours, subtract the initial usage times 100 from the last recorded usage times 340 to get 240 times, and then divide by the number of time intervals 24 to obtain the device dial scanning usage frequency of 10 times per hour. This frequency data is stored in the cloud platform database.

[0034] Step S22: Evaluate the life attenuation of the corresponding battery in the intelligent protective glasses device based on the temperature data on the cloud platform to obtain the battery life attenuation rate of the device; In the embodiment of the present invention, on the cloud platform, Python is used in combination with a professional battery life evaluation library, such as the BatteryLifeEval library, to evaluate the life attenuation of the corresponding battery in the intelligent protective glasses device based on the temperature data. The temperature data of the surrounding environment of the intelligent protective glasses device uploaded is read from the cloud platform database. Assuming that the temperature data is stored in a pandas DataFrame structure with the index being the timestamp and the column name being "temperature", in the Python program, according to the type of the battery (such as a lithium-ion battery), the corresponding life attenuation evaluation model in the BatteryLifeEval library is called. This model considers the influence of temperature on the chemical reaction rate inside the battery. For example, for a lithium-ion battery, an increase in temperature will accelerate the dissolution of the battery's positive electrode material and the decomposition of the solid electrolyte interface film on the negative electrode surface, resulting in battery life attenuation. By sequentially inputting the temperature data at different time points into the model, the model calculates the battery life attenuation situation under this temperature condition according to the internal algorithm. For example, within a certain period, the temperature remains at 35°C, and the model calculates that the battery life attenuation rate per hour at this temperature is 0.1%. The temperature data at all time points is processed, and the life attenuation rate of the device battery during the entire monitoring period is comprehensively calculated. Assuming that the final calculated battery life attenuation rate of the device is 5%, this attenuation rate data is stored in the cloud platform database.

[0035] Step S23: Based on the usage frequency of device dial scanning, accurately evaluate the dial scanning data through scanning recognition to obtain the accuracy rate of device dial scanning recognition. In the embodiment of the present invention, by using Python to write an evaluation program on the cloud platform, accurately evaluate the dial scanning data based on the usage frequency of device dial scanning. Read the device dial scanning usage frequency data, dial scanning data, and obtained actual dial data from the cloud platform database. Assume that the dial scanning usage frequency is stored in a variable, such as freq = 10 times / hour; the dial scanning data and actual data are stored in the DataFrame structure of pandas and aligned by timestamp. Set an evaluation model, for example, scanning recognition accuracy rate = number of correct recognitions / total number of scans. By comparing the dial scanning data with the actual data, determine whether each scan recognition is correct. For example, among 100 scan data, after comparing with the actual data, 80 scan data are within the allowable error range (assuming the allowable error is ±5%) of the actual data, then the number of correct recognitions is 80 times. The total number of scans can be calculated based on the dial scanning usage frequency and monitoring time. Assume the monitoring time is 10 hours, and according to the usage frequency of 10 times per hour, the total number of scans is 10×10 = 100 times. Substitute the data into the evaluation model to obtain the scanning recognition accuracy rate of 80 / 100 = 80%, and store this accuracy rate data in the cloud platform database.

[0036] Step S24: Based on the device battery life attenuation rate and the accuracy rate of device dial scanning recognition, conduct a dial scanning fault analysis on the corresponding dial scanning sensor in the intelligent protective glasses device to obtain the device dial scanning fault probability.

[0037] In the embodiment of the present invention, by using Python to write a fault analysis program on the cloud platform, conduct a dial scanning fault analysis on the corresponding dial scanning sensor in the intelligent protective glasses device based on the device battery life attenuation rate and the accuracy rate of device dial scanning recognition. Read the device battery life attenuation rate data (assuming it is 5%) and device dial scanning recognition accuracy rate data (assuming it is 80%) from the cloud platform database. Set a fault analysis model, for example, fault probability = 1 - [(scanning resolution / standard resolution) × (scanning contrast / standard contrast) × (1 - battery life attenuation rate) × (dial scanning recognition accuracy rate)]. By performing the same calculation on the data at multiple different time points or different intelligent protective glasses devices, and statistically analyzing statistics such as the average value of the fault probability, obtain the overall evaluation result of the device dial scanning fault probability, and finally obtain the device dial scanning fault probability, providing a basis for the maintenance and fault warning of the dial scanning sensor of the intelligent protective glasses device.

[0038] Further, step S22 includes the following steps: By analyzing the time series characteristics of temperature data on the cloud platform, the change trend, periodicity and mutation point characteristics corresponding to the temperature are analyzed and extracted, and the temperature time series change characteristics are obtained; In an embodiment of the present invention, by using Python data analysis libraries such as pandas and numpy on a cloud platform, a time series feature analysis is performed on the temperature data uploaded from the smart protective glasses device. It is assumed that the temperature data is stored in a pandas DataFrame structure, the index is the timestamp, and the column name is "temperature". First, the rolling function of pandas is used to calculate the moving average to analyze the temperature change trend. For example, the window size is set to 10 time points, and the average temperature of every 10 consecutive time points is calculated. By observing the change in the moving average, it can be determined whether the temperature is rising, falling, or remaining stable. For periodic analysis, Fourier transform is used to convert the temperature data in the time domain to the frequency domain with the help of numpy's fft function. Whether there is an obvious periodic peak in the spectrum diagram is analyzed to determine whether the temperature is periodic and the duration of the cycle. For the mutation point feature, the diff function of pandas is used to calculate the difference in temperature between adjacent time points. If a certain difference exceeds a preset threshold (such as 5°C), the time point is marked as a mutation point. Through these operations, the change trend, periodicity, and mutation point features corresponding to the temperature are extracted and organized into a new data set, and finally the temperature time series change feature is obtained.

[0039] Preferably, temperature frequency distribution statistics are performed on the temperature data based on the temperature time series variation characteristics to obtain the temperature time series frequency distribution; In an embodiment of the present invention, based on the previously obtained temperature time series variation characteristics, the temperature frequency distribution statistics are continued to be performed using Python's data analysis tools on the cloud platform, and the temperature data is statistically analyzed by using numpy's histogram function. First, the temperature range is determined, such as from 0°C to 50°C, and this range is divided into several intervals, for example, each 5°C is an interval, and then the frequency of occurrence of temperature data in each interval is counted. For example, in the 0-5°C interval, the temperature data appears 100 times, in the 5-10°C interval, it appears 150 times, etc., and these statistical results are organized into a frequency distribution table, in which one column records the temperature interval and the other column records the frequency of the corresponding interval, to obtain the temperature time series frequency distribution. By analyzing the frequency distribution, the frequency of occurrence of different temperature intervals can be understood, providing data support for subsequent battery life decay simulation.

[0040] Preferably, a battery life decay simulation is performed on a corresponding battery in the smart protective glasses device based on the temperature time series frequency distribution to generate a corresponding life decay process of the battery under the corresponding temperature frequency distribution; In an embodiment of the present invention, by using a professional battery life simulation software, such as BatteryLifeSimulator, a battery life decay simulation is performed on the corresponding battery in the intelligent protection glasses device based on the temperature time series frequency distribution. In the software, the temperature time series frequency distribution data obtained from the previous analysis is imported, and parameters such as the type of the battery (such as a lithium-ion battery) and the initial capacity are set. According to the pre-established relationship model between battery life and temperature, the software simulates the life decay process of the battery at different temperature frequencies. For example, for a lithium-ion battery, when the temperature is in a relatively high range (such as 35 - 40°C) and the occurrence frequency is high, the software will calculate according to the model that the chemical reaction rate inside the battery accelerates, resulting in a faster decay of the battery capacity. Through simulation, a series of data is generated, including the change of the battery capacity at different time points, so as to generate the corresponding life decay process of the battery under the corresponding temperature frequency distribution, and the simulation results are stored in the database of the cloud platform.

[0041] Preferably, a battery prediction and capacity decay analysis are performed on the corresponding life decay process of the battery under the corresponding temperature frequency distribution to obtain the predicted capacity and capacity decay amount of the battery at each time point. In an embodiment of the present invention, by using Python to write a data analysis program on the cloud platform, a battery prediction and capacity decay analysis are performed on the corresponding life decay process of the battery under the corresponding temperature frequency distribution. The previously generated battery life decay simulation data is read from the cloud platform database, and according to the change of the battery capacity with time in the simulation data, the linear interpolation method or other appropriate algorithms are used to calculate the predicted capacity of the battery at each time point. For example, it is known that the battery capacity is C1 at time point t1 and C2 at time point t2, and the predicted capacity at any time point between t1 and t2 can be calculated by linear interpolation. For the capacity decay amount, it is obtained by calculating the difference between the predicted capacity at the current time point and the initial capacity. For example, if the initial capacity of the battery is 1000 mAh and the predicted capacity at a certain time point is 800 mAh, then the capacity decay amount at this time point is 200 mAh. The predicted capacity and capacity decay amount corresponding to each time point are organized into a new data set to prepare for calculating the battery life decay rate.

[0042] Preferably, the initial capacity of the battery is obtained, and a life decay calculation is performed based on the predicted capacity and capacity decay amount of the battery at each time point and in combination with the initial capacity of the battery to obtain the battery life decay rate of the device.

[0043] In the embodiment of the present invention, the initial capacity corresponding to the battery is obtained from the product manual of the intelligent protective glasses device or the device management system. A calculation program is written in Python on the cloud platform. Based on the estimated capacity and the capacity attenuation at each time point of the battery and combined with the initial capacity of the battery, the life attenuation calculation is carried out. Assuming that the initial capacity of the battery is C0, the estimated capacity at time point t is Ct, and the capacity attenuation is ΔC, the calculation formula for the battery life attenuation rate is: life attenuation rate = ΔC / C0 × 100% = (C0 - Ct) / C0 × 100%. For example, if the initial capacity of the battery is 1000 mAh, and after a period of time, the estimated capacity at a certain time point is 700 mAh, then the life attenuation rate = (1000 - 700) / 1000 × 100% = 30%. By calculating and organizing the life attenuation rates at each time point, the life attenuation rate of the device battery in different usage stages is finally obtained, providing an important basis for the battery management and maintenance of the intelligent protective glasses device.

[0044] Further, step S23 includes the following steps: Step S231: Obtain the actual data corresponding to the dial. In the embodiment of the present invention, the actual data corresponding to the dial is obtained from the automation control system of the industrial device or the manual regular calibration records. In the chemical production workshop, various dial data such as pressure and flow are connected to the automation control system. For example, through the OPC (OLE for Process Control) server connected to the workshop automation control system, using special OPC client software, according to specific data reading protocols, the real-time pressure value of the pressure gauge and the real-time flow value of the flow meter are read from the system. Assuming that a certain pressure gauge is connected to the pipeline, the automation control system monitors and stores its pressure data in real time. The current actual pressure value of 3.5 MPa can be obtained through the OPC client software. For some dials that are not connected to the automation control system, the actual data is obtained based on the manual calibration records. The staff regularly calibrates the dials and records the accurate data after calibration in paper documents or spreadsheets. For example, a certain flow meter is calibrated monthly, and the latest calibration record shows that the actual flow value is 40 cubic meters per hour. The actual dial data obtained from different channels is organized into a structured data table for convenient subsequent analysis.

[0045] Step S232: Calculate the difference between the dial scan data based on the actual data corresponding to the dial to obtain the deviation of the dial scan data. In an embodiment of the present invention, a data processing program is written in Python on a cloud platform to calculate the difference in dial data for dial scan data based on the actual data corresponding to the dial. The previously processed and stored dial scan data and the obtained actual dial data are read from the cloud platform database. Assume that the dial scan data is stored in a pandas DataFrame structure with column names such as "scanned pressure value" and "scanned flow value", and the index is the scan timestamp; the actual data is stored in another DataFrame structure with column names such as "actual pressure value" and "actual flow value", and the index is also the timestamp. By aligning the two DataFrames according to the timestamp, the difference in the corresponding data is calculated using the numpy library in Python. For example, for pressure data, the difference between the scanned pressure value and the actual pressure value is calculated, i.e., deviation = scanned pressure value - actual pressure value. If the scanned pressure value at a certain time point is 3.7 MPa and the actual pressure value is 3.5 MPa, then the pressure data deviation at this point is 3.7 - 3.5 = 0.2 MPa. The same calculation is performed for the pressure, flow, and other data at all time points to obtain a series of data deviation values. These deviation values are organized into a new data set to obtain the dial scan data deviation, which is used to evaluate the accuracy of the dial scan data.

[0046] Step S233: Analyze the scanning usage limit of the corresponding dial scan sensor based on the usage frequency of the device dial scan to obtain the attenuation degree of the dial scan performance limit. In an embodiment of the present invention, the usage frequency of the device dial scan is obtained by querying the log records of the intelligent protective glasses device on the cloud platform. The device log records are stored in the cloud platform database and record each dial scan operation in a time series manner. For example, through an SQL query statement, it is counted that a certain intelligent protective glasses device scanned the pressure gauge dial 1000 times and the flow meter dial 800 times in the past week. According to the pre-set performance attenuation model of the dial scan sensor, which is established based on the physical characteristics and usage experience of the sensor, such as the relationship between the number of scans and the performance attenuation degree being a linear relationship. Assume that for every 1000 scans, the sensor scan performance attenuates by 10%. For the above-mentioned pressure gauge dial scan situation, its scanning usage frequency is 1000 times / week. According to the model calculation, the attenuation degree of the scanning performance limit is 10%. The scanning usage frequencies corresponding to different types of dials and the calculated attenuation degrees of the scanning performance limits are organized into a table to provide data support for subsequent evaluation of the scanning recognition accuracy.

[0047] Step S234: Based on the attenuation degree of the dial scan performance limit and combined with the dial scan data deviation, accurately evaluate the scanning recognition of the corresponding dial scan sensor to obtain the device dial scan recognition accuracy.

[0048] In the embodiment of the present invention, an evaluation program is written in Python on the cloud platform to accurately evaluate the scanning and recognition of the corresponding dial scanning sensor based on the attenuation degree of the dial scanning performance limit and in combination with the deviation of the dial scanning data. The deviation of the previously obtained dial scanning data and the data of the attenuation degree of the dial scanning performance limit are read from the cloud platform database. For each dial scanning data point, the scanning and recognition accuracy rate is calculated according to the deviation value and the attenuation degree of the scanning performance limit. For example, an accuracy rate calculation formula is set: scanning and recognition accuracy rate = (1 - |deviation| / maximum allowable deviation value) × (1 - attenuation degree of scanning performance limit). Suppose for pressure data, the maximum allowable deviation value is 0.5 MPa, the deviation of a certain scanning data point is 0.2 MPa, and the attenuation degree of the scanning performance limit is 10%, then the scanning and recognition accuracy rate of this point = (1 - 0.2 / 0.5) × (1 - 0.1) = 0.54, that is, 54%. The same calculation is performed for all scanning data points to obtain a series of scanning and recognition accuracy rate values. By statistically analyzing statistics such as the average value and median of these values, an overall evaluation result of the device's dial scanning and recognition accuracy rate is obtained. For example, the average scanning and recognition accuracy rate is 60%, providing a basis for the maintenance and performance optimization of the dial scanning sensor of the intelligent protective glasses device.

[0049] Further, step S24 includes the following steps: Step S241: Conduct a comparative analysis of the mathematical relationship based on the battery life attenuation rate of the device and the accuracy rate of the device's dial scanning and recognition to obtain the mathematical relationship between the battery life attenuation and the scanning and recognition. In the embodiment of the present invention, a data analysis program is written in Python on the cloud platform. Based on the battery life attenuation rate of the device and the accuracy rate of the device's dial scanning and recognition, a comparative analysis of the mathematical relationship is conducted. The data of the battery life attenuation rate of the device and the accuracy rate of the device's dial scanning and recognition calculated previously are read from the cloud platform database. Suppose the battery life attenuation rate is stored in a Series structure of pandas with the index being the time point; the accuracy rate of the dial scanning and recognition is stored in another Series structure with the same index being the time point. By using the curve fitting function in the scipy library of Python, such as the curve_fit function, different mathematical models (such as linear models, quadratic function models, etc.) are tried to fit the relationship between these two sets of data. For example, first assume the relationship between the two is a linear relationship y = ax + b, where y is the accuracy rate of the dial scanning and recognition and x is the battery life attenuation rate. The data is fitted and calculated through the curve_fit function to obtain the values of parameters a and b. After calculation, if a = -0.8 and b = 0.9 are obtained, then the mathematical relationship is that the accuracy rate of the dial scanning and recognition = -0.8 × battery life attenuation rate + 0.9. The fitted mathematical relationship is stored in the cloud platform database to provide a basis for subsequent analysis.

[0050] Step S242: Based on the scanning recognition accuracy of the device dial, evaluate the scanning response of the corresponding dial scanning sensor in the intelligent protective glasses device to obtain the corresponding dial scanning response interval at the corresponding recognition accuracy; In the embodiment of the present invention, by using Python to write an evaluation program on the cloud platform, based on the scanning recognition accuracy of the device dial, evaluate the scanning response of the corresponding dial scanning sensor in the intelligent protective glasses device. Read the device dial scanning recognition accuracy data obtained from the cloud platform database. According to the pre-established correspondence table between scanning recognition accuracy and scanning response time, this table is established based on a large amount of experimental data and actual use experience. For example, when the scanning recognition accuracy is between 50% - 60%, the scanning response time is between 0.5 - 1 second; when the scanning recognition accuracy is between 60% - 70%, the scanning response time is between 0.3 - 0.5 second, etc. For each recognition accuracy data point, find the accuracy interval it belongs to, so as to determine the corresponding scanning response time interval. Assume that at a certain moment, the device dial scanning recognition accuracy is 55%. By looking up the correspondence table, determine that its corresponding dial scanning response interval is 0.5 - 1 second. Organize the scanning response intervals corresponding to all recognition accuracies into a new data set and store it in the cloud platform database for subsequent analysis of the performance of the dial scanning sensor.

[0051] Step S243: According to the corresponding dial scanning response interval at the corresponding recognition accuracy, perform statistical calculation on the scanning indicators of the scanning pictures corresponding to the dial scanning sensor to obtain the corresponding dial scanning resolution and dial scanning contrast at the corresponding recognition accuracy; In the embodiment of the present invention, an image processing program is written in Python on the cloud platform. According to the dial scan response interval corresponding to the corresponding recognition accuracy, statistical calculation of scan metrics is performed on the scanned pictures corresponding to the dial scan sensor. The scanned picture data and the obtained scan response interval data corresponding to the corresponding recognition accuracy are read from the cloud platform database. For the scanned pictures within this scan response interval, the OpenCV library of Python is used for image processing. For the calculation of scan resolution, by detecting the number of pixel points in the picture and the actual size of the picture (assuming it is known), the number of pixels per inch (PPI) is calculated. For example, for a picture with a size of 2 inches × 2 inches and a pixel point number of 1000 × 1000, the scan resolution is 1000 / 2 = 500 PPI. For the calculation of dial scan contrast, the functions of OpenCV are used to calculate the maximum and minimum pixel values in the picture, and the contrast is calculated through the formula (maximum value - minimum value) / (maximum value + minimum value). Assuming that the maximum pixel value of a certain picture is 200 and the minimum value is 50, the contrast is (200 - 50) / (200 + 50) = 0.6. The scan resolution and scan contrast data of the scanned pictures corresponding to different recognition accuracies are sorted into a table and stored in the cloud platform database, providing data support for evaluating the performance of the dial scan sensor.

[0052] Step S244: Based on the mathematical relationship between battery life decay and scan recognition, and in combination with the device battery life decay rate and the device dial scan recognition accuracy, perform dial scan fault assessment calculation on the dial scan resolution and dial scan contrast corresponding to the corresponding recognition accuracy, and obtain the device dial scan fault probability.

[0053] In the embodiment of the present invention, a fault assessment program is written in Python on the cloud platform. Based on the mathematical relationship between battery life attenuation and scan recognition, combined with the device battery life attenuation rate and the device dial scan recognition accuracy, the dial scan fault assessment calculation is carried out for the corresponding dial scan resolution and dial scan contrast at the corresponding recognition accuracy. The mathematical relationship, device battery life attenuation rate, device dial scan recognition accuracy, and corresponding scan resolution and scan contrast data read from the cloud platform database are used to set up a fault assessment model. For example, fault probability = 1 - [(scan resolution / standard resolution) × (scan contrast / standard contrast) × (1 - battery life attenuation rate) × (dial scan recognition accuracy)]. Assuming the standard resolution is 600 PPI and the standard contrast is 0.8, for each data point, the corresponding values are substituted for calculation. For example, at a certain moment, the battery life attenuation rate is 0.2, the dial scan recognition accuracy is 0.5, the scan resolution is 400 PPI, and the scan contrast is 0.5. Then the fault probability = 1 - [(400 / 600) × (0.5 / 0.8) × (1 - 0.2) × 0.5] ≈ 0.67. The same calculation is performed for all data points to obtain a series of fault probability values. By statistically analyzing statistics such as the average value of these values, the overall assessment result of the device dial scan fault probability is obtained. For example, the average fault probability is 0.7, which provides a basis for the maintenance and fault warning of the dial scan sensor of the intelligent protective glasses device.

[0054] Further, step S3 includes the following steps: Step S31: Obtain the calibration data corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform; In the embodiment of the present invention, a stable data transmission channel is established between the cloud platform and the intelligent protective glasses device. After the gas sensor of the intelligent protective glasses device completes the calibration operation, the calibration data will be automatically stored in the local storage module of the device. For example, in a laboratory environment, the gas sensor is calibrated to determine the corresponding relationship between the output signal and the actual concentration of a specific gas (such as methane) at different concentrations, and these calibration parameters are stored in the flash chip inside the device. According to the set communication protocol, such as the MQTT protocol, the intelligent protective glasses device regularly (such as at 2 am every day) sends the calibration data of the gas sensor to the cloud platform through the built-in wireless communication module. On the cloud platform, a data receiving program is written in Python to monitor the topic of the corresponding device on the MQTT server. When the calibration data is received, the program stores the data in a relational database on the cloud platform (such as MySQL), using the device number and timestamp as the composite primary key for convenient subsequent query and management. For example, an intelligent protective glasses device has a device number of 001, and the calibration data includes the sensor output voltage values corresponding to different concentrations of methane. For example, when the concentration is 10 ppm, the output voltage is 0.5 V, and these data are accurately stored in the database.

[0055] Step S32: Obtain the usage duration corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform; In the embodiment of the present invention, by setting a timer variable in the firmware program of the intelligent protective glasses device, the timer starts timing from when the gas sensor is enabled. Each time the device is powered on and runs, the microcontroller reads the value of the timer variable and continuously updates it during the device operation. For example, the device is powered on at 8 am, and the timer starts timing from the current time. Every 1 second, the value of the timer variable increases by 1. The intelligent protective glasses device sends the usage duration data of the gas sensor recorded by the timer to the cloud platform at a certain time interval (such as every 12 hours) through the wireless communication module. On the cloud platform, a data receiving and processing program is written in Python. When the usage duration data is received, the program associates it with the device number and stores it in the database on the cloud platform. Assuming the device number is 002, and the usage duration of its gas sensor is received at 8 pm on the same day as 43200 seconds (12 hours), the program accurately enters this data into the database to provide a basis for subsequent analysis.

[0056] Step S33: Perform sensing aging prediction based on the calibration data and the usage duration to obtain the aging time of the gas sensor; In the embodiments of the present invention, a sensing aging prediction program is written in Python on a cloud platform, and sensing aging prediction is performed according to calibration data and usage duration. The stored gas sensor calibration data and usage duration data are read from the cloud platform database. It is assumed that the calibration data is stored in a DataFrame structure of pandas, with column names such as "gas concentration" and "output voltage"; the usage duration data is stored in another DataFrame structure, with column names "device number" and "usage duration". According to a pre-established gas sensor aging model, which is constructed based on the physical characteristics of the sensor and a large amount of experimental data. For example, there is a linear relationship between the usage duration and the degree of sensor aging, and the degree of aging will affect the correspondence between the output voltage and the gas concentration in the calibration data. By substituting the usage duration data of different devices into the model and combining the calibration data, the degree of sensor aging is calculated. For example, for a certain type of gas sensor, in the model, for every 10,000 seconds increase in the usage duration, the deviation between the sensor output voltage and the actual gas concentration increases by 0.1V. If the usage duration of the gas sensor of a certain device is 50,000 seconds, and the output voltage corresponding to a gas concentration of 10 ppm in the initial calibration data is 0.5V, according to the model calculation, the output voltage deviation at this time is 0.5V. Through further calculation and analysis, it is obtained that the aging time of this gas sensor is expected to be 20,000 seconds later, when it needs to be replaced or deeply calibrated. The aging time data is stored in the cloud platform database.

[0057] Step S34: Based on the gas sensor aging time, humidity data, and gas monitoring data, perform an abnormal gas reading assessment on the corresponding gas sensor to obtain the device gas reading abnormal index.

[0058] In an embodiment of the present invention, a gas reading anomaly assessment program is written in Python on a cloud platform. Based on the aging time of the gas sensor, humidity data, and gas monitoring data, the corresponding gas sensor is evaluated for gas reading anomalies. The gas sensor aging time data, uploaded humidity data, and gas monitoring data are read from the cloud platform database. Assume that the gas sensor aging time is stored in a variable, such as aging_time = 20000 seconds; the humidity data is stored in a DataFrame structure of pandas, with the index being the timestamp and the column name being "humidity"; the gas monitoring data is stored in another DataFrame structure, with column names such as "gas concentration" and "color display intensity". First, based on the humidity data, the corresponding reading anomaly fluctuation range of the gas monitoring data is analyzed, and an anomaly assessment model is set. For example, anomaly index = reading anomaly fluctuation range / standard fluctuation range + aging influence coefficient × (1 - remaining aging time ratio (i.e., the ratio between the aging time and the usage duration)). Among them, the standard fluctuation range is determined according to the performance indicators of the sensor in the normal working state, and the aging influence coefficient is determined through experiments or experience. For example, the standard fluctuation range is 0.2 ppm, the aging influence coefficient is 0.3, and the remaining aging time ratio is 0.4 (i.e., the remaining aging time is 40% of the expected aging time). Assume that the reading anomaly fluctuation range at a certain moment is 0.4 ppm. Substituting it into the model, the calculated anomaly index = 0.4 / 0.2 + 0.3 × (1 - 0.4) = 2 + 0.18 = 2.18. By performing the same calculation on the data of multiple time points or different devices and statistically analyzing statistics such as the average value of the anomaly index, the overall assessment result of the gas reading anomaly index of the device is obtained. For example, the average anomaly index is 2.0, providing a basis for the maintenance and fault warning of the gas sensor of the intelligent protective glasses device.

[0059] Further, step S34 includes the following steps: Step S341: Evaluate the influence of humidity on the monitoring accuracy of the corresponding gas sensor to obtain the influence degree of humidity on the accuracy of the gas sensor; In an embodiment of the present invention, a monitoring accuracy impact assessment program is written in Python on a cloud platform to assess the impact of humidity data on the monitoring accuracy of corresponding gas sensors. The uploaded humidity data is read from the cloud platform database. Assume that the humidity data is stored in a pandas DataFrame structure with a timestamp as the index and a column named "humidity". At the same time, relevant data on the accuracy change of gas sensors under different humidity conditions is obtained from sensor technical documents or previous experimental data to construct a humidity-accuracy impact relationship table. For example, when the humidity is 40%, the monitoring accuracy deviation of the gas sensor for methane concentration is ±2%; when the humidity is 60%, the accuracy deviation is ±5%, etc. In the Python program, each humidity value in the humidity data DataFrame is traversed, and according to the humidity-accuracy impact relationship table, through linear interpolation or other appropriate algorithms, the impact degree of accuracy corresponding to each humidity value is determined. Assume that the currently read humidity value is 50%, and the impact degree of humidity on the gas sensor accuracy at this time is calculated by linear interpolation to be ±3.5%. The impact degrees corresponding to all humidity values are organized into a new data set and stored in the cloud platform database to provide a basis for subsequent analysis.

[0060] Step S342: Perform a coupling analysis on the abnormal fluctuations in the readings of gas monitoring data based on the impact degree of humidity on the accuracy of the gas sensor to obtain the abnormal fluctuation amplitude of the gas sensor readings. In an embodiment of the present invention, a coupling analysis program for abnormal fluctuations in readings is written in Python on a cloud platform to perform a coupling analysis on the abnormal fluctuations in the readings of gas monitoring data based on the impact degree of humidity on the accuracy of the gas sensor. The data on the impact degree of humidity on the accuracy of the gas sensor and the gas monitoring data obtained from the cloud platform database are read. Assume that the gas monitoring data is stored in a pandas DataFrame structure with columns named "gas concentration", "color display intensity", etc. For each gas monitoring data point, the abnormal fluctuation amplitude of the reading is calculated by combining the impact degree of humidity on the accuracy corresponding to this time point. For example, if the gas monitoring concentration at a certain moment is 10 ppm and the impact degree of humidity on the accuracy is ±3.5%, then the abnormal fluctuation amplitude of the gas sensor readings at this moment is 10 ppm × 3.5% = ±0.35 ppm. By performing the same calculation on all gas monitoring data points, a series of abnormal fluctuation amplitude values are obtained, and these values are organized into a new data set and stored in the cloud platform database, such as using the timestamp as the index and the column named "abnormal fluctuation amplitude of readings" to provide data support for evaluating abnormal gas readings.

[0061] Step S343: Perform an abnormal gas reading assessment on the corresponding gas sensor based on the aging time of the gas sensor and the abnormal fluctuation amplitude of the gas sensor readings to obtain the abnormal gas reading index of the device.

[0062] In an embodiment of the present invention, a gas reading anomaly evaluation program is written in Python on a cloud platform. Based on the aging time of the gas sensor and the abnormal fluctuation amplitude of the gas sensor readings, the corresponding gas sensor is evaluated for gas reading anomalies. The gas sensor aging time data and the abnormal fluctuation amplitude data of the gas sensor readings are read from the cloud platform database. Assume that the gas sensor aging time is stored in a variable, such as aging_time = 20000 seconds; the abnormal fluctuation amplitude data of the gas sensor readings is stored in a DataFrame structure of pandas, with the index being the timestamp and the column name being "abnormal fluctuation amplitude of readings". Set an anomaly evaluation model, for example, anomaly index = abnormal fluctuation amplitude of readings / standard fluctuation amplitude + aging influence coefficient × (1 - remaining aging time ratio), where the standard fluctuation amplitude is determined according to the performance indicators of the sensor under normal working conditions, and the aging influence coefficient is determined through experiments or experience. For example, the standard fluctuation amplitude is 0.2 ppm, the aging influence coefficient is 0.3, and the remaining aging time ratio is 0.4 (i.e., the remaining aging time is 40% of the expected aging time). Assume that the abnormal fluctuation amplitude of readings at a certain moment is 0.4 ppm. Substituting it into the model, the calculated anomaly index = 0.4 / 0.2 + 0.3 × (1 - 0.4) = 2 + 0.18 = 2.18. By performing the same calculation on the data of multiple time points or different devices and statistically analyzing statistics such as the average value of the anomaly index, the overall evaluation result of the gas reading anomaly index of the device is obtained. For example, the average anomaly index is 2.0, providing a basis for the maintenance and fault warning of the gas sensor of the intelligent protective glasses device.

[0063] Further, step S4 includes the following steps: Step S41: Based on the device dial scanning failure probability and the device gas reading anomaly index, conduct a device safety response warning for the intelligent protective glasses device. If both the device dial scanning failure probability and the device gas reading anomaly index exceed the preset threshold, then a corresponding maintenance instruction is generated through the corresponding safety warning module in the intelligent protective glasses device to generate a device safety warning maintenance instruction; In an embodiment of the present invention, by using Python to write a device security response warning program on a cloud platform, device security response warning is performed on the intelligent protective glasses device based on the device dial scan failure probability and the device gas reading anomaly index. The device dial scan failure probability data and the device gas reading anomaly index data are read from the cloud platform database. Assume that the device dial scan failure probability is stored in a Series structure of pandas, with the index being the device number; the device gas reading anomaly index is stored in another Series structure, and the index is also the device number. By traversing the failure probability and anomaly index data corresponding to each device number, conditional judgments are made. For example, for the intelligent protective glasses device with the device number 001, its device dial scan failure probability is 60%, and the device gas reading anomaly index is 0.15. Both exceed the set thresholds (the device dial scan failure probability exceeds 10%, and the device gas reading anomaly index exceeds 0.1). At this time, the program sends an instruction to the device by calling the API interface of the security warning module in the intelligent protective glasses device. After receiving the instruction, the security warning module generates a corresponding maintenance instruction according to the pre-set template, such as "repair the dial scan sensor of the device with the device number 001, calibrate and check the gas sensor", and stores the generated device security warning maintenance instruction in the cloud platform database, associating it with the device number for subsequent query and processing.

[0064] Step S42: Apply the device security warning maintenance instruction to the intelligent protective glasses device for device intelligent management analysis, automatically send a maintenance reminder to the corresponding maintenance terminal of the maintenance personnel, and formulate a corresponding maintenance time, maintenance content, and maintenance personnel arrangement push plan to generate a cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

[0065] In an embodiment of the present invention, by using Python to write a device intelligent management and analysis program on the cloud platform, the device security warning and maintenance instructions are applied to the intelligent protective glasses device for device intelligent management and analysis. The device security warning and maintenance instruction data generated is read from the cloud platform database, combined with data such as maintenance personnel information and maintenance task priorities in the device management system. Assume that the maintenance personnel information is stored in a DataFrame structure of pandas, with column names such as "Maintenance Personnel Name", "Contact Information", "Specialized Field", etc.; the maintenance task priorities are preset according to the device type and the severity of the failure. For the device with device number 001, its maintenance instruction is "Overhaul the dial scan sensor and calibrate and check the gas sensor". The program matches the maintenance personnel who are good at this field according to the task content in the maintenance instruction. Assume that through data analysis, it is determined that Zhang San is good at overhauling the dial scan sensor and Li Si is good at calibrating the gas sensor. According to the work arrangements of the maintenance personnel and the task priorities, the maintenance time is determined. For example, Zhang San is arranged to overhaul the dial scan sensor at 9 am tomorrow, and Li Si is arranged to calibrate the gas sensor at 2 pm tomorrow. The maintenance time, maintenance content, and maintenance personnel arrangements are sorted out into a push plan, and through the API interface of the SMS gateway or instant messaging software, maintenance reminders are automatically sent to the maintenance terminals (mobile phones or tablets) corresponding to maintenance personnel Zhang San and Li Si. For example, a text message "Please overhaul the dial scan sensor of device number 001 at 9 am tomorrow" is sent to Zhang San, and an instant messaging message "Please calibrate the gas sensor of device number 001 at 2 pm tomorrow" is sent to Li Si. At the same time, the cloud platform device exception maintenance management plan corresponding to the entire intelligent protective glasses device is stored in the cloud platform database for convenient subsequent viewing and tracking of the maintenance progress.

[0066] Further, the present invention also provides a cloud platform-based intelligent protective glasses device management system for executing the cloud platform-based intelligent protective glasses device management method as described above. The cloud platform-based intelligent protective glasses device management system includes: A device data real-time monitoring module for real-time monitoring the corresponding dial scan data, gas monitoring data, and device external environment data through the sensors built in the intelligent protective glasses device, where the device external environment data includes temperature data and humidity data, and uploading them to the cloud platform using wireless communication technology; A dial scan fault analysis module for obtaining the usage frequency of the device dial scan and performing dial scan fault analysis on the corresponding dial scan sensor in the intelligent protective glasses device based on the temperature data, dial scan data, and device dial scan usage frequency on the cloud platform to obtain the device dial scan fault probability; A gas reading anomaly evaluation module is used to obtain calibration data and usage duration corresponding to a gas sensor in an intelligent protective glasses device through a cloud platform, and perform sensing aging prediction based on the calibration data and usage duration to obtain the aging time of the gas sensor; perform gas reading anomaly evaluation on the corresponding gas sensor based on the gas sensor aging time, humidity data, and gas monitoring data, so as to obtain the device gas reading anomaly index; A device intelligent management module is used to perform device intelligent management analysis on the intelligent protective glasses device based on the device dial scanning failure probability and the device gas reading anomaly index, so as to generate a cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

[0067] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent protective glasses device management method based on a cloud platform, characterized in that, Including the following steps: Step S1: Use the corresponding sensors built into the intelligent protective glasses device to continuously monitor the corresponding dial scan data, gas monitoring data, and device external environment data in real time. The device external environment data includes temperature data and humidity data, and upload them to the cloud platform using wireless communication technology; Step S2: Obtain the usage frequency of the device dial scan, and perform dial scan fault analysis on the corresponding dial scan sensor in the intelligent protective glasses device based on the temperature data, dial scan data, and device dial scan usage frequency on the cloud platform to obtain the device dial scan fault probability; Step S3: Obtain the calibration data and usage duration of the gas sensor in the intelligent protective glasses device through the cloud platform, and perform sensing aging prediction based on the calibration data and usage duration to obtain the gas sensor aging time; Based on the gas sensor aging time, humidity data, and gas monitoring data, perform gas reading anomaly evaluation on the corresponding gas sensor to obtain the device gas reading anomaly index; Among them, the gas reading anomaly evaluation includes the following steps: Step S341: Evaluate the influence of humidity data on the monitoring accuracy of the corresponding gas sensor to obtain the influence degree of humidity on the accuracy of the gas sensor; Step S342: Perform reading anomaly fluctuation coupling analysis on the gas monitoring data based on the influence degree of humidity on the accuracy of the gas sensor to obtain the gas sensor reading anomaly fluctuation amplitude; Step S343: Perform gas reading anomaly evaluation on the corresponding gas sensor based on the gas sensor aging time and the gas sensor reading anomaly fluctuation amplitude to obtain the device gas reading anomaly index; Step S4: Perform device intelligent management analysis on the intelligent protective glasses device based on the device dial scan fault probability and the device gas reading anomaly index to generate a cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

2. The method for managing an intelligent protective glasses device based on a cloud platform according to claim 1, wherein, Step S1 includes the following steps: Step S11: Use the corresponding dial scan sensor built into the intelligent protective glasses device to continuously monitor the dial scan pictures of the pressure gauge and flow meter in real time; Step S12: Perform dial recognition analysis on the dial scan pictures of the pressure gauge and flow meter through image recognition technology to obtain the dial scan data; Step S13: Use the corresponding gas sensor built into the intelligent protective glasses device to continuously monitor the gas about to leak, and convert the gas leakage condition into a visual corresponding color display intensity to obtain the gas monitoring data; Step S14: Use the corresponding environmental sensor built into the intelligent protective glasses device to continuously monitor the surrounding environment corresponding temperature data and humidity data to obtain the device external environment data; Step S15: Denoise, filter, and normalize the dial scan data, gas monitoring data, and device external environment data, and upload the preprocessed dial scan data, gas monitoring data, and device external environment data to the cloud platform using wireless communication technology.

3. The method for managing an intelligent protective glasses device based on a cloud platform according to claim 1, wherein, Step S2 includes the following steps: Step S21: Obtain the usage times corresponding to the dial scanning sensor on the intelligent protective glasses device, and perform frequency quantization calculation based on the usage times corresponding to the dial scanning sensor to obtain the device dial scanning usage frequency; Step S22: Evaluate the life attenuation of the corresponding battery in the intelligent protective glasses device based on the temperature data on the cloud platform to obtain the device battery life attenuation rate; Step S23: Accurately evaluate the dial scanning data based on the device dial scanning usage frequency to obtain the device dial scanning recognition accuracy rate; Step S24: Analyze the dial scanning faults of the corresponding dial scanning sensor in the intelligent protective glasses device based on the device battery life attenuation rate and the device dial scanning recognition accuracy rate to obtain the device dial scanning fault probability.

4. The method for managing an intelligent protective glasses device based on a cloud platform according to claim 3, wherein, Step S22 includes the following steps: Perform time series feature analysis on the temperature data on the cloud platform to analyze and extract the change trend, periodicity, and mutation point features corresponding to the temperature, and obtain the temperature time series change features; Statistically analyze the temperature frequency distribution of the temperature data based on the temperature time series change features to obtain the temperature time series frequency distribution; Simulate the battery life attenuation of the corresponding battery in the intelligent protective glasses device based on the temperature time series frequency distribution to generate the life attenuation process corresponding to the battery under the corresponding temperature frequency distribution; Perform battery prediction and capacity attenuation analysis on the life attenuation process corresponding to the battery under the corresponding temperature frequency distribution to obtain the predicted capacity and capacity attenuation amount corresponding to the battery at each time point; Obtain the initial capacity corresponding to the battery, and perform life attenuation calculation based on the predicted capacity and capacity attenuation amount corresponding to the battery at each time point and in combination with the initial capacity corresponding to the battery to obtain the device battery life attenuation rate.

5. The method for managing an intelligent protective glasses device based on a cloud platform according to claim 3, characterized in that, Step S23 includes the following steps: Step S231: Obtain the actual data corresponding to the dial; Step S232: Calculate the difference between the dial scanning data and the dial data based on the actual data corresponding to the dial to obtain the dial scanning data deviation; Step S233: Analyze the scanning usage limit of the corresponding dial scanning sensor based on the device dial scanning usage frequency to obtain the attenuation degree of the dial scanning performance limit; Step S234: Accurately evaluate the scanning recognition of the corresponding dial scanning sensor based on the attenuation degree of the dial scanning performance limit and in combination with the dial scanning data deviation to obtain the device dial scanning recognition accuracy rate.

6. The method for managing an intelligent protective glasses device based on a cloud platform according to claim 3, wherein Step S24 includes the following steps: Step S241: Conduct a comparative analysis of the mathematical relationship based on the device battery life attenuation rate and the device dial scanning recognition accuracy rate to obtain the mathematical relationship between the battery life attenuation and the scanning recognition; Step S242: Evaluate the scanning response of the corresponding dial scanning sensor in the intelligent protective glasses device based on the device dial scanning recognition accuracy rate to obtain the corresponding dial scanning response interval under the corresponding recognition accuracy rate; Step S243: Statistically calculate the scanning metrics of the scanning picture corresponding to the dial scanning sensor according to the corresponding dial scanning response interval at the corresponding recognition accuracy rate, so as to obtain the corresponding dial scanning resolution and dial scanning contrast at the corresponding recognition accuracy rate; Step S244: Based on the mathematical relationship between battery life attenuation and scanning recognition, and in combination with the device battery life attenuation rate and the device dial scanning recognition accuracy rate, perform a dial scanning fault assessment calculation on the corresponding dial scanning resolution and dial scanning contrast at the corresponding recognition accuracy rate, and obtain the device dial scanning fault probability.

7. The method for managing an intelligent protective glasses device based on a cloud platform according to claim 1, wherein, Step S3 includes the following steps: Step S31: Obtain the calibration data corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform; Step S32: Obtain the usage duration corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform; Step S33: Perform sensing aging prediction according to the calibration data and the usage duration to obtain the gas sensor aging time; Step S34: Based on the gas sensor aging time, humidity data, and gas monitoring data, perform an abnormal gas reading assessment on the corresponding gas sensor to obtain the device gas reading abnormal index.

8. The method for managing an intelligent protective glasses device based on a cloud platform according to claim 1, wherein, Step S4 includes the following steps: Step S41: Based on the device dial scanning fault probability and the device gas reading abnormal index, perform a device safety response warning on the intelligent protective glasses device. If both the device dial scanning fault probability and the device gas reading abnormal index exceed the preset threshold, then generate a corresponding maintenance instruction through the corresponding safety warning module in the intelligent protective glasses device to generate a device safety warning maintenance instruction; Step S42: Apply the device safety warning maintenance instruction to the intelligent protective glasses device for device intelligent management analysis, automatically send a maintenance reminder to the corresponding maintenance terminal of the maintenance personnel, and formulate a corresponding maintenance time, maintenance content, and maintenance personnel arrangement push plan to generate a cloud platform device abnormal maintenance management plan corresponding to the intelligent protective glasses device.

9. An intelligent protective glasses device management system based on a cloud platform, characterized in that, For implementing the cloud platform-based intelligent protective glasses device management method as described in claim 1, the cloud platform-based intelligent protective glasses device management system includes: A device data real-time monitoring module, configured to real-time monitor the corresponding dial scanning data, gas monitoring data, and device external environment data through the sensors built in the intelligent protective glasses device, where the device external environment data includes temperature data and humidity data, and upload them to the cloud platform using wireless communication technology; A dial scanning fault analysis module, configured to obtain the device dial scanning usage frequency, and perform dial scanning fault analysis on the corresponding dial scanning sensor in the intelligent protective glasses device based on the temperature data, dial scanning data, and device dial scanning usage frequency on the cloud platform, so as to obtain the device dial scanning fault probability; The gas reading anomaly evaluation module is used to obtain the calibration data and usage duration corresponding to the gas sensor in the intelligent protective glasses device through the cloud platform, and perform sensing aging prediction based on the calibration data and usage duration to obtain the aging time of the gas sensor; perform gas reading anomaly evaluation on the corresponding gas sensor based on the gas sensor aging time, humidity data, and gas monitoring data, so as to obtain the device gas reading anomaly index; The device intelligent management module is used to perform device intelligent management analysis on the intelligent protective glasses device based on the device dial scanning failure probability and the device gas reading anomaly index, so as to generate a cloud platform device anomaly maintenance management plan corresponding to the intelligent protective glasses device.

Images