Electronic tag wireless radio frequency intelligent identification system based on Internet of Things

Abstract

The invention relates to the technical field of wireless radio frequency identification, in particular to an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things, which binds multi-dimensional data collected by various types of RFID electronic tags in the whole process of a cigarette making process to obtain an environment dynamic parameter set, a processing quality feature set and an anti-counterfeiting traceability identification set; a process composite prediction model is constructed to analyze the environment dynamic parameter set and the processing quality feature set, first abnormal data are obtained and recognized, and a baking temperature lag compensation coefficient and a flavoring pressure dynamic adjustment parameter are generated; the temperature is adjusted according to the baking temperature lag compensation coefficient; adjusting the perfuming amount according to the perfuming pressure dynamic adjusting parameters; label data are obtained through the built-in RFID label of the seal paper; constructing a quality tracing model to identify and analyze the label data, and obtaining a label detection result; and analyzing the label detection result and the anti-counterfeiting traceability identification set to obtain a quality traceability result.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless radio frequency identification, in particular to an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things. Background Art

[0002] In the tobacco production industry, the drying, fermentation, and seasoning of tobacco leaves play a vital role in product quality, while the anti-counterfeiting and integrity of the seal in the packaging process are directly related to the safety of the product. However, the traditional production method faces the following technical problems: First, data collection in the production process is often discrete and intermittent, and real-time and continuous monitoring cannot be achieved, resulting in incomplete data and difficulty in truly reflecting the production status. Secondly, the regulation of equipment parameters mostly relies on manual experience, lacks automation and intelligent support, and the timeliness and accuracy of regulation are insufficient, which in turn affects production efficiency and product quality. Thirdly, the anti-counterfeiting and integrity detection methods of packaging seals are relatively traditional, usually limited to anti-counterfeiting labels or anti-counterfeiting codes, and it is difficult to achieve automated real-time verification, and there is a high risk of tampering. Finally, the data of each production link is relatively scattered, lacks an effective integration mechanism, and the collaborative operation ability between equipment is insufficient, which limits the intelligent management and optimization of the entire production process. With the rise of the Internet of Things and wireless radio frequency identification (RFID) technology, intelligent production has gradually become the development direction of the industry, but the existing technology still has obvious deficiencies in realizing the real-time collection of process parameters, automatic regulation of equipment, and comprehensive integration of packaging integrity detection, and has failed to form a systematic and efficient solution.

[0003] Therefore, an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things, which binds multi-dimensional data collected by multiple types of RFID electronic tags in the whole process of cigarette making process to obtain an environmental dynamic parameter set, a processing quality feature set and an anti-counterfeiting traceability identification set; constructs a process composite prediction model to analyze the environmental dynamic parameter set and the processing quality feature set, obtains and identifies the first abnormal data, generates a baking temperature hysteresis compensation coefficient and a flavoring pressure dynamic adjustment parameter; adjusts the temperature according to the baking temperature hysteresis compensation coefficient; adjusts the flavoring amount by the flavoring pressure dynamic adjustment parameter; obtains tag data by building an RFID tag into the sealing paper; constructs a quality traceability model to identify and analyze the tag data to obtain tag detection results; obtains quality traceability results by analyzing the tag detection results and the anti-counterfeiting traceability identification set.

[0005] To achieve the above object, the present invention provides the following technical solutions: An electronic tag wireless radio frequency intelligent identification system based on the Internet of Things, comprising: The data collection module uses the industrial Internet of Things to bind the process parameters collected by various RFID electronic tags in the entire process of cigarette making with the production batch, equipment number and timestamp in multiple dimensions, and obtain the environmental dynamic parameter set, processing quality feature set and anti-counterfeiting traceability identification set; The process parameter optimization module builds a composite prediction model to analyze the environmental dynamic parameter set and the processing quality feature set, obtains and identifies the first abnormal data, generates the baking temperature hysteresis compensation coefficient and the dynamic adjustment parameter of the flavoring pressure; adjusts the temperature according to the baking temperature hysteresis compensation coefficient; adjusts the flavoring amount through the dynamic adjustment parameter of the flavoring pressure; obtains data through RFID electronic tags to verify the temperature and pressure, and iteratively optimizes the equipment parameters; The quality traceability verification module integrates a dedicated RFID reading device and an automatic sealing device on the tobacco packaging line, obtains label data through the built-in RFID tag in the sealing paper; builds a quality traceability model to identify and analyze label data to obtain label detection results; and obtains quality traceability results by analyzing label detection results and anti-counterfeiting traceability identification sets.

[0006] Preferably, the environmental dynamic parameter set includes temperature and humidity sensor and gas composition sensor data based on the fermentation link to generate temperature field distribution thermogram, humidity gradient change curve, target temperature curve and oxygen concentration attenuation matrix; the processing quality feature set includes integrated shredded thickness fluctuation spectrum, baking hot air velocity field vector diagram and flavoring atomization pressure timing waveform; the anti-counterfeiting traceability identification set includes a microstructure optical fingerprint map of the storage packaging seal and its blockchain hash binding relationship with the production batch; the label data includes front-end data and seal feature data; the front-end data stream includes production batch number, equipment number and process parameters; the seal feature data: optical fingerprint map and microstructure three-dimensional coordinates.

[0007] Preferably, the process composite prediction model includes: a data preprocessing layer obtains smoothed environmental dynamic parameter data and processing quality feature data by preprocessing the environmental dynamic parameter set and the processing quality feature set; a feature extraction layer generates temperature conduction features and pressure waveform features by extracting features from the environmental dynamic parameter data and the processing quality feature data; a timing analysis layer obtains process parameter evolution trends by extracting spatial features from the environmental dynamic parameter data and timing features from the processing quality feature data, and analyzing the spatial features and timing features; an anomaly detection layer obtains first quality data and first anomaly data by performing anomaly detection on temperature conduction features and pressure waveform features; a decision optimization layer obtains a baking temperature lag compensation coefficient and a flavoring pressure dynamic adjustment parameter by analyzing the first anomaly data and the process parameter evolution trend.

[0008] Preferably, the specific generation process of the baking temperature lag compensation coefficient includes: by analyzing the first abnormal data, obtaining the baking temperature data and tobacco leaf quality data, and obtaining the mapping relationship between temperature and quality; using the support vector regression algorithm to train the model to predict the tobacco leaf quality under different temperature lag conditions; according to the prediction results, calculating the baking temperature lag compensation coefficient with the optimal tobacco leaf quality; the specific generation process of the dynamic adjustment parameter of the flavoring pressure includes: by analyzing the first abnormal data, obtaining the relationship between the flavoring pressure data and the aroma uniformity, obtaining the function of pressure and uniformity, and calculating the dynamic adjustment parameter of the flavoring pressure that optimizes the aroma uniformity under different production conditions.

[0009] Preferably, the calculation formula of the baking temperature hysteresis compensation coefficient is: ; in, is the temperature hysteresis compensation coefficient, is the target temperature curve, is the actual temperature measurement value, is the lag time, is the spatial gradient of the temperature field distribution thermal map, is the thermal diffusion coefficient of tobacco leaves, is the maximum temperature deviation, is the baking area, It is the vector diagram of the hot air velocity field for baking; The calculation formula of the dynamic adjustment parameter of aromatherapy pressure is: ; in, To dynamically adjust the pressure value, is the base pressure, is the nozzle gain coefficient, is the time window, The pressure timing waveform The window standard deviation, For the The main frequency phase angle of the window, is the instantaneous spice flow rate, is the target average flow rate, For the uniformity of fragrance, is the uniformity standard threshold.

[0010] Preferably, the quality traceability model includes a feature digital extraction layer, a blockchain anchoring layer, a smart contract verification layer and a label detection result output layer; the feature digital extraction layer obtains a reflectivity matrix by scanning a microstructure optical fingerprint, and obtains a first eigenvector by analyzing the reflectivity matrix; the blockchain anchoring layer obtains a mixed hash value by performing a double hash operation on the first eigenvector and the production batch; the smart contract verification layer automatically verifies the matching of the label data with the production batch number and the equipment number in the anti-counterfeiting traceability identification set by using a smart contract to determine the authenticity of the label; the label detection result output layer analyzes the authenticity of the label and outputs a judgment result.

[0011] Preferably, the specific steps for obtaining the quality traceability results are: Cartesian product matching of the production batch number in the front-end data and the blockchain hash value of the anti-counterfeiting traceability identification set; if there is a temperature-related abnormality, tracing back to the baking equipment; if there is a pressure-related abnormality, locating the flavoring machine nozzle; through the three-dimensional coordinates of the microstructure and the process parameters, generating a traceability report including a thermodynamic simulation animation, a material transfer path diagram and an encrypted audit log.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention adopts the fusion technology of Internet of Things and RFID electronic tags to realize the real-time data collection and multi-dimensional information binding of tobacco production process. Through the industrial Internet of Things, the data collected by various sensors in the tobacco making process are associated with information such as production batch, equipment number, timestamp, etc., to form environmental dynamic parameters, processing quality characteristics and anti-counterfeiting traceability identification sets, which can accurately capture key process data such as temperature and humidity, gas composition, temperature field distribution, and generate auxiliary analysis graphics such as thermal maps, gradient curves, and target temperature curves, thereby significantly improving data processing efficiency and intelligent monitoring level.

[0013] 2. The present invention constructs a composite prediction model for the process, integrating multi-layer processing such as data preprocessing, feature extraction, time series analysis and anomaly detection, to achieve accurate prediction of the evolution trend of tobacco process parameters. The support vector regression algorithm is used to train the model, and the baking temperature compensation coefficient is calculated according to the temperature lag and quality mapping relationship. The flavoring pressure parameters are adjusted according to the pressure characteristics to eliminate fluctuations. This improves the stability of tobacco quality and process consistency, promotes adaptive adjustment of equipment, reduces the risk of manual intervention, and ensures efficient, accurate and safe production process.

[0014] 3. In terms of quality traceability verification, the present invention integrates a dedicated RFID reading device and an automatic sealing device, and uses the built-in electronic tag of the seal to obtain the front-end data and seal features, thereby realizing the dual functions of packaging anti-counterfeiting and traceability. The system constructs a feature digital extraction, blockchain anchoring and smart contract verification process, automatically matches the production batch and equipment number, and generates a traceability report containing a thermodynamic simulation animation, a material transfer path diagram and an encrypted audit log, ensuring product authenticity and quality traceability, and improving overall traceability efficiency and safety protection level. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the structure of an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things provided by the present invention; Figure 2 A schematic diagram of the process composite prediction model structure provided by an embodiment of the present invention; Figure 3 A schematic diagram of the quality traceability model structure provided by an embodiment of the present invention; Figure 4 This is a schematic diagram of the wireless radio frequency intelligent identification structure of an electronic tag provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] In the tobacco production process, existing technologies mostly use decentralized sensors and manual monitoring methods, which have many deficiencies in the collection, regulation and quality traceability of key parameters of the production process. Traditional systems can usually only monitor a single process parameter, and data collection relies on local environmental monitoring. It is impossible to achieve real-time comprehensive analysis of multi-dimensional parameters such as temperature and humidity, gas composition, temperature field distribution, shred thickness, hot air speed and atomization pressure in the entire tobacco production process. Due to the lack of a unified information management platform, process control mainly relies on experience, resulting in delayed equipment parameter optimization, low accuracy of temperature compensation and flavoring pressure adjustment, which ultimately affects the stability of tobacco leaf quality. In addition, the existing anti-counterfeiting and traceability technical means are relatively single, and there is a lack of effective binding mechanism between anti-counterfeiting data and production batches. There are data islands and tampering risks, which are difficult to meet the high requirements of the modern tobacco market for product quality and traceability security.

[0018] Embodiment 1: In order to solve the above technical problems, this solution proposes an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things. The technical solution is as follows, refer to Figure 1 : The data collection module uses the industrial Internet of Things to bind the process parameters collected by various RFID electronic tags in the entire process of cigarette making with the production batch, equipment number and timestamp in multiple dimensions, and obtain the environmental dynamic parameter set, processing quality feature set and anti-counterfeiting traceability identification set; Furthermore, the environmental dynamic parameter set includes data from temperature and humidity sensors and gas composition sensors based on the fermentation process to generate a temperature field distribution thermogram, a humidity gradient change curve, a target temperature curve and an oxygen concentration attenuation matrix; the processing quality feature set includes an integrated shredded thickness fluctuation spectrum, a baking hot air velocity field vector diagram and a flavoring atomization pressure timing waveform; the anti-counterfeiting and traceability identification set includes a microstructure optical fingerprint map of the storage packaging seal and its blockchain hash binding relationship with the production batch.

[0019] In this embodiment, by integrating the industrial Internet of Things and RFID electronic tags, multi-dimensional data collection and intelligent binding of environmental dynamic parameters, processing quality characteristics and anti-counterfeiting traceability identification in the whole process of tobacco manufacturing process are realized. Specifically, the temperature field distribution thermogram, humidity gradient change curve, target temperature curve and oxygen concentration attenuation matrix are generated by sensor data, which can intuitively reflect the environmental changes during the fermentation process; at the same time, by integrating the shredded thickness fluctuation spectrum, baking hot air velocity field vector diagram and flavoring atomization pressure timing waveform, real-time monitoring and precise control of processing quality are realized. More importantly, the anti-counterfeiting traceability identification set stores the microstructure optical fingerprint map built into the packaging seal, and uses blockchain technology to hash and bind with the production batch information, ensuring the reliability of product anti-counterfeiting and quality traceability. It greatly improves the efficiency of process data collection and processing, optimizes the real-time control and intelligent regulation of the tobacco production process, significantly improves product quality and safety, and effectively reduces production risks and manual intervention costs.

[0020] The process parameter optimization module builds a composite prediction model to analyze the environmental dynamic parameter set and the processing quality feature set, obtains and identifies the first abnormal data, generates the baking temperature hysteresis compensation coefficient and the dynamic adjustment parameter of the flavoring pressure; adjusts the temperature according to the baking temperature hysteresis compensation coefficient; adjusts the flavoring amount through the dynamic adjustment parameter of the flavoring pressure; obtains data through RFID electronic tags to verify the temperature and pressure, and iteratively optimizes the equipment parameters; Furthermore, the process composite prediction model includes a data preprocessing layer, a feature extraction layer, a time series analysis layer, an anomaly detection layer and a decision optimization layer, see Figure 2; The data preprocessing layer obtains smoothed environmental dynamic parameter data and processing quality feature data by preprocessing the environmental dynamic parameter set and the processing quality feature set; the feature extraction layer generates temperature conduction features and pressure waveform features by extracting features from the environmental dynamic parameter data and the processing quality feature data; the timing analysis layer obtains the process parameter evolution trend by extracting spatial features from the environmental dynamic parameter data and timing features from the processing quality feature data, and analyzing the spatial features and timing features; the anomaly detection layer obtains the first quality data and the first anomaly data by performing anomaly detection on the temperature conduction features and the pressure waveform features; the decision optimization layer obtains the baking temperature lag compensation coefficient and the flavoring pressure dynamic adjustment parameter by analyzing the first anomaly data and the process parameter evolution trend.

[0021] In this embodiment, by constructing a composite prediction model for the process, comprehensive processing and accurate analysis of environmental dynamic parameters and processing quality characteristic data are achieved, effectively improving the intelligent control level of the tobacco making process. First, the data preprocessing layer smoothes the collected data to ensure the accuracy of subsequent analysis; the feature extraction layer extracts key features from the temperature conduction and pressure waveforms, so that the timing analysis layer can accurately capture the evolution trend of the process parameters and promptly identify the first abnormal data. Subsequently, the decision optimization layer generates the baking temperature lag compensation coefficient and the dynamic adjustment parameters of the flavoring pressure based on the abnormal data and trend analysis results, so as to achieve precise control of temperature and pressure. Through RFID electronic tag data verification, the system can provide real-time feedback and iterative optimization of equipment parameters, thereby effectively reducing production risks, ensuring the stability of tobacco leaf quality, and greatly improving production efficiency, providing an efficient, intelligent and automated technical solution for the tobacco making process.

[0022] Furthermore, the specific generation process of the baking temperature lag compensation coefficient includes: by analyzing the first abnormal data, obtaining the baking temperature data and tobacco leaf quality data, and obtaining the mapping relationship between temperature and quality; using the support vector regression algorithm to train the model to predict the tobacco leaf quality under different temperature lag conditions; based on the prediction results, calculating the baking temperature lag compensation coefficient with optimal tobacco leaf quality; the specific generation process of the dynamic adjustment parameter of the flavoring pressure includes: by analyzing the first abnormal data, obtaining the relationship between the flavoring pressure data and the aroma uniformity, obtaining the function of pressure and uniformity, and calculating the dynamic adjustment parameter of the flavoring pressure that optimizes the aroma uniformity under different production conditions.

[0023] In this embodiment, by using the support vector regression algorithm to establish the mapping relationship between the baking temperature and the tobacco leaf quality, the accurate prediction of the tobacco leaf quality under different temperature hysteresis conditions is achieved, and the optimal baking temperature hysteresis compensation coefficient is calculated accordingly, thereby ensuring the accuracy of the baking temperature regulation. This can effectively reduce the tobacco leaf quality fluctuation caused by temperature hysteresis and improve the overall quality and production stability of tobacco leaves. At the same time, by deeply analyzing the relationship between the flavoring pressure and the uniformity of the flavor, the optimal dynamic adjustment parameters of the flavoring pressure under various production conditions are accurately calculated, and the fine regulation of the flavoring amount is achieved to ensure a more uniform distribution of the flavor. Not only does it achieve intelligent optimization and real-time adjustment of process parameters, it also greatly improves the automation level of the production process and product consistency, providing an efficient, accurate and reliable technical support for tobacco production.

[0024] Furthermore, the baking temperature hysteresis compensation coefficient calculation formula is: ; in, is the temperature hysteresis compensation coefficient, is the target temperature curve, is the actual temperature measurement value, is the lag time, is the spatial gradient of the temperature field distribution thermal map, is the thermal diffusion coefficient of tobacco leaves, is the maximum temperature deviation, is the baking area, It is the vector diagram of the hot air velocity field for baking; The calculation formula of the dynamic adjustment parameter of aromatherapy pressure is: ; in, To dynamically adjust the pressure value, is the base pressure, is the nozzle gain coefficient, is the time window, The pressure timing waveform The window standard deviation, For the The main frequency phase angle of the window, is the instantaneous spice flow rate, is the target average flow rate, For the uniformity of fragrance, is the uniformity standard threshold.

[0025] In this embodiment, two formulas, temperature hysteresis compensation coefficient and dynamic adjustment parameter of flavoring pressure, are used to realize intelligent adjustment of temperature control and flavoring addition in the tobacco making process. Through the temperature hysteresis compensation coefficient formula, the system can capture the deviation between the target temperature and the actual temperature in real time, and combine the spatial gradient of the temperature field, the thermal diffusion characteristics of tobacco leaves and the hot air distribution in the baking area to accurately compensate for the temperature hysteresis effect, thereby effectively eliminating the process error caused by temperature fluctuations, ensuring the stability and uniformity of the baking temperature, and improving the quality of tobacco leaves. At the same time, the dynamic adjustment parameter formula of flavoring pressure comprehensively considers key factors such as pressure fluctuations, nozzle gain, flavor flow and flavor uniformity. By dynamically adjusting the pressure value, fine control of the flavoring process is achieved to ensure balanced distribution of flavor. The two technologies cooperate with each other, not only optimizing the adaptive regulation of production process parameters, reducing quality defects caused by unstable process parameters, but also greatly improving production efficiency and product consistency, providing efficient, accurate and intelligent technical support for tobacco production.

[0026] The quality traceability verification module integrates a dedicated RFID reading device and an automatic sealing device on the tobacco packaging line, obtains label data through the built-in RFID tag of the sealing paper; constructs a quality traceability model to identify and analyze the label data to obtain the label detection results; obtains the quality traceability results by analyzing the label detection results and the anti-counterfeiting traceability identification set; the label data includes front-end data and sealing feature data; the front-end data stream includes production batch number, equipment number and process parameters; the sealing feature data: optical fingerprint map and microstructure three-dimensional coordinates.

[0027] Furthermore, the quality traceability model includes a feature digital extraction layer, a blockchain anchoring layer, a smart contract verification layer, and a label detection result output layer, see Figure 3 ; The feature digital extraction layer obtains the reflectivity matrix by scanning the microstructure optical fingerprint, and obtains the first feature vector by analyzing the reflectivity matrix; the blockchain anchoring layer obtains the mixed hash value by performing double hash operation on the first feature vector and the production batch; the smart contract verification layer automatically verifies the matching of the label data with the production batch number and the equipment number in the anti-counterfeiting traceability identification set by using smart contracts to determine the authenticity of the label; the label detection result output layer analyzes the authenticity of the label and outputs the judgment result.

[0028] In this embodiment, a quality traceability verification module is adopted to integrate the RFID reading device and the automatic sealing device on the tobacco packaging line to realize the real-time collection and accurate analysis of the built-in RFID tag data of the sealing paper. By constructing a quality traceability model including a feature digital extraction layer, a blockchain anchoring layer, a smart contract verification layer and a label detection result output layer, the system first obtains the reflectivity matrix by scanning the microstructure optical fingerprint spectrum, and further extracts the first feature vector; then, the feature vector is mixed and hashed with the production batch through a double hash operation to achieve data tamper-proof and safe traceability; the smart contract automatically verifies whether the label data matches the production batch number and equipment number in the anti-counterfeiting traceability identification set, thereby determining the authenticity of the label and outputting the test results. The closed-loop traceability system not only greatly improves the reliability of product anti-counterfeiting and quality traceability, but also realizes an efficient and automated detection process, effectively reduces the risk of manual intervention, and enhances the safety of tobacco products and consumer trust. In order to compare the performance of this application with the existing anti-counterfeiting technology, Table 1 shows the quantitative data of the anti-counterfeiting verification success rate, batch matching success rate, data tampering protection rate and verification time consumption, highlighting the technical advantages of this application in anti-counterfeiting verification.

[0029] Table 1 Comparison of anti-counterfeiting verification success rates index Quality traceability model Anti-counterfeiting system based on QR code Tag verification success rate 99.5% 90% Batch matching success rate 99.8% 85% Data tampering protection rate 100% 70% Verification time 0.3s 1.5s Furthermore, the specific steps to obtain the quality traceability results are as follows: Cartesian product matching of the production batch number in the front-end data and the blockchain hash value of the anti-counterfeiting traceability identification set; if there is a temperature-related anomaly, trace it back to the baking equipment; if there is a pressure-related anomaly, locate the flavoring machine nozzle; through the three-dimensional coordinates of the microstructure and the process parameters, generate a traceability report including a thermodynamic simulation animation, a material transfer path diagram and an encrypted audit log.

[0030] In this embodiment, by matching the production batch number in the front-end data with the blockchain hash value of the anti-counterfeiting traceability identification set by Cartesian product, the traceability information is closely bound to the product data, greatly improving the data security and anti-tampering capabilities. In the event of temperature-related anomalies, the system can quickly trace back to the baking equipment; and pressure-related anomalies can locate the flavoring machine nozzle to ensure the rapid location and processing of abnormal problems. This precise fault tracking can not only detect problems in the production process in a timely manner, but also provide strong data support for subsequent equipment maintenance and process optimization. By combining the three-dimensional coordinates of the microstructure with the process parameters, the traceability report generated by the system includes thermodynamic simulation animations, material transfer path diagrams, and encrypted audit logs, providing intuitive and detailed records for each link of the production process. The accuracy and efficiency of product quality traceability are significantly improved, product safety and consumer trust are enhanced, while reducing maintenance costs and production risks for enterprises, and realizing intelligent management and continuous optimization of the production process.

[0031] The present invention realizes the real-time collection, precise analysis and intelligent control of multi-parameter data in the whole process of cigarette making by constructing an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things. The system uses RFID electronic tags and industrial sensors to perform multi-dimensional data binding on key indicators such as temperature and humidity, gas composition, temperature field distribution and processing quality, and generates an environmental dynamic parameter set, a processing quality feature set and an anti-counterfeiting traceability identification set. Using the process composite prediction model, the data is preprocessed, feature extracted, time series analyzed and anomaly detected, and the baking temperature hysteresis compensation coefficient and the dynamic adjustment parameters of the flavoring pressure are accurately calculated to effectively suppress the adverse effects of temperature and pressure fluctuations on the quality of tobacco leaves. At the same time, a dedicated RFID reading device and an automatic sealing device are integrated on the tobacco packaging line, and product anti-counterfeiting and quality traceability are achieved by scanning the microstructure optical fingerprint map, using blockchain double hash binding and smart contract verification. When a process abnormality is found, the system can quickly locate the baking equipment or the flavoring machine nozzle, and generate thermodynamic simulation animations, material transfer path diagrams and encrypted audit logs through the three-dimensional coordinates of the microstructure and the process parameters, providing a detailed basis for fault tracking and production optimization. For details, please refer to Figure 4 The present invention greatly improves the automation and intelligence level of the production process, not only ensuring the quality and safety of tobacco products, but also reducing production risks and labor costs.

[0032] Embodiment 2: This solution proposes an electronic tag wireless radio frequency intelligent identification system based on the Internet of Things. The technical solution is as follows: The data collection module uses the industrial Internet of Things to bind the process parameters collected by various RFID electronic tags in the entire process of cigarette making with the production batch, equipment number and timestamp in multiple dimensions, and obtain the environmental dynamic parameter set, processing quality feature set and anti-counterfeiting traceability identification set; Furthermore, the environmental dynamic parameter set includes data from temperature and humidity sensors and gas composition sensors based on the fermentation process to generate a temperature field distribution thermogram, a humidity gradient change curve, a target temperature curve and an oxygen concentration attenuation matrix; the processing quality feature set includes an integrated shredded thickness fluctuation spectrum, a baking hot air velocity field vector diagram and a flavoring atomization pressure timing waveform; the anti-counterfeiting and traceability identification set includes a microstructure optical fingerprint map of the storage packaging seal and its blockchain hash binding relationship with the production batch.

[0033] The process parameter optimization module builds a composite prediction model to analyze the environmental dynamic parameter set and the processing quality feature set, obtains and identifies the first abnormal data, generates the baking temperature hysteresis compensation coefficient and the dynamic adjustment parameter of the flavoring pressure; adjusts the temperature according to the baking temperature hysteresis compensation coefficient; adjusts the flavoring amount through the dynamic adjustment parameter of the flavoring pressure; obtains data through RFID electronic tags to verify the temperature and pressure, and iteratively optimizes the equipment parameters; Furthermore, the process composite prediction model includes a data preprocessing layer, a feature extraction layer, a time series analysis layer, an anomaly detection layer and a decision optimization layer, see Figure 2 ; The data preprocessing layer obtains smoothed environmental dynamic parameter data and processing quality feature data by preprocessing the environmental dynamic parameter set and the processing quality feature set; the feature extraction layer generates temperature conduction features and pressure waveform features by extracting features from the environmental dynamic parameter data and the processing quality feature data; the timing analysis layer obtains the process parameter evolution trend by extracting spatial features from the environmental dynamic parameter data and timing features from the processing quality feature data, and analyzing the spatial features and timing features; the anomaly detection layer obtains the first quality data and the first anomaly data by performing anomaly detection on the temperature conduction features and the pressure waveform features; the decision optimization layer obtains the baking temperature lag compensation coefficient and the flavoring pressure dynamic adjustment parameter by analyzing the first anomaly data and the process parameter evolution trend.

[0034] Furthermore, the specific generation process of the baking temperature lag compensation coefficient includes: by analyzing the first abnormal data, obtaining the baking temperature data and tobacco leaf quality data, and obtaining the mapping relationship between temperature and quality; using the support vector regression algorithm to train the model to predict the tobacco leaf quality under different temperature lag conditions; based on the prediction results, calculating the baking temperature lag compensation coefficient with optimal tobacco leaf quality; the specific generation process of the dynamic adjustment parameter of the flavoring pressure includes: by analyzing the first abnormal data, obtaining the relationship between the flavoring pressure data and the aroma uniformity, obtaining the function of pressure and uniformity, and calculating the dynamic adjustment parameter of the flavoring pressure that optimizes the aroma uniformity under different production conditions.

[0035] Furthermore, the baking temperature hysteresis compensation coefficient calculation formula is: ; in, is the temperature hysteresis compensation coefficient, is the target temperature curve, is the actual temperature measurement value, is the lag time, is the spatial gradient of the temperature field distribution thermal map, is the thermal diffusion coefficient of tobacco leaves, is the maximum temperature deviation, is the baking area, It is the vector diagram of the hot air velocity field for baking; The spatial gradient of the temperature field distribution thermogram is obtained by collecting real-time temperature data through the temperature and humidity sensors and gas composition sensors in the fermentation process, and combining the heat conduction model to generate the temperature field distribution thermogram; the thermogram is spatially analyzed by using image processing or numerical differential methods (such as the central difference method), and the rate of change of temperature in space is calculated to obtain the spatial gradient; the thermal diffusion coefficient of tobacco leaves is calculated by measuring the thermophysical properties of tobacco leaves in the laboratory, such as density, specific heat capacity and thermal conductivity, and combining it with Fourier's heat conduction law; the baking area uses a laser ranging sensor to measure the effective area of ​​the baking area in real time; the baking hot air velocity field vector diagram collects hot air velocity data through the wind speed sensor array installed in the baking equipment, and generates a velocity field vector diagram in combination with the fluid dynamics model; The theoretical derivation of this formula is based on the physical model of heat conduction: The temperature field equation is established according to Fourier's law: ; in, Input heat to the hot air system, and the velocity field vector Related, is the temperature, is the tobacco leaf mass density, is the specific heat capacity at constant pressure; Define the time-lagged error function: ; in, is the time lag error; Considering the influence of hot air velocity field on temperature distribution, a compensation weight function is established: ; in, is the compensation weight function; Construct the compensation coefficients by integrating in the time domain: ; The surface integral normalization factor was introduced to ensure dimensional consistency, and finally the calculation formula of the baking temperature hysteresis compensation coefficient was obtained.

[0036] The calculation formula of the dynamic adjustment parameter of aromatherapy pressure is: ; in, Dynamically adjust the pressure value for aromatherapy, is the base pressure, is the nozzle gain coefficient, is the time window, The pressure timing waveform The window standard deviation, For the The main frequency phase angle of the window, is the instantaneous spice flow rate, is the target average flow rate, For the uniformity of fragrance, is the uniformity standard threshold; Among them, the nozzle gain coefficient is calculated by experimentally calibrating the nozzle flow-pressure characteristic curve and combining it with the flavor atomization efficiency test; the flavor uniformity deviation is detected by the sensor on the tobacco leaf surface. The root mean square error between the actual distribution and the target distribution is calculated; The theoretical derivation of this formula is based on the physical model of heat conduction: The calculation formula for the pressure fluctuation characteristics within the time window is: ; in, The time window Pressure value, is the average pressure in the time window; The calculation formula of the main frequency phase angle is: ; in, is a discrete pressure sequence, is an imaginary unit; Flow stability index The calculation formula is: ; The various parameters are integrated to obtain the calculation formula for the dynamic adjustment parameters of the aromatherapy pressure.

[0037] The quality traceability verification module integrates a dedicated RFID reading device and an automatic sealing device on the tobacco packaging line, obtains label data through the built-in RFID tag of the sealing paper; builds a quality traceability model to identify and analyze label data and obtain label test results; obtains quality traceability results by analyzing label test results and anti-counterfeiting traceability identification sets; Furthermore, the quality traceability model includes a feature digital extraction layer, a blockchain anchoring layer, a smart contract verification layer, and a label detection result output layer, see Figure 3 ; The feature digital extraction layer obtains the reflectivity matrix by scanning the microstructure optical fingerprint, and obtains the first feature vector by analyzing the reflectivity matrix; the blockchain anchoring layer obtains the mixed hash value by performing double hash operation on the first feature vector and the production batch; the smart contract verification layer automatically verifies the matching of the label data with the production batch number and the equipment number in the anti-counterfeiting traceability identification set by using smart contracts to determine the authenticity of the label; the label detection result output layer analyzes the authenticity of the label and outputs the judgment result.

[0038] Detection result output layer: Output three-state judgment results: passed (feature similarity ≥ 95% and hash match), questionable (85% ≤ similarity < 95%) and failed (similarity < 85% or hash mismatch); Furthermore, the specific steps to obtain the quality traceability results are: Cartesian product matching of the production batch number in the front-end data and the blockchain hash value of the anti-counterfeiting traceability identification set; if there is a temperature-related anomaly, trace it back to the baking equipment; if there is a pressure-related anomaly, locate the flavoring machine nozzle; through the three-dimensional coordinates of the microstructure and the process parameters, generate a traceability report including a thermodynamic simulation animation, a material transfer path diagram, and an encrypted audit log. In order to demonstrate the advantages of this application in quality traceability efficiency, Table 2 lists the comparative data of batch matching time, anomaly location time, traceability report generation time, and data processing throughput, reflecting the significant improvement of this application in traceability efficiency and intelligence level.

[0039] Table 2 Comparison of quality traceability efficiency index The efficiency of this application traceability result Database traceability Batch matching time 0.5s 2s Abnormal location time 1s 5s Time for generating traceability report 2s 10s Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An electronic tag wireless radio frequency intelligent identification system based on the Internet of Things, characterized in that: include: The data collection module uses the industrial Internet of Things to bind the process parameters collected by various RFID electronic tags in the entire process of cigarette making with the production batch, equipment number and timestamp in multiple dimensions, and obtain the environmental dynamic parameter set, processing quality feature set and anti-counterfeiting traceability identification set; The process parameter optimization module builds a process composite prediction model to analyze the environmental dynamic parameter set and the processing quality feature set, obtains and identifies the first abnormal data, generates the baking temperature hysteresis compensation coefficient and the flavoring pressure dynamic adjustment parameter; adjusts the temperature according to the baking temperature hysteresis compensation coefficient; adjusts the flavoring amount through the flavoring pressure dynamic adjustment parameter; The data obtained through RFID electronic tags are used to verify the temperature and pressure, and the equipment parameters are optimized iteratively; The quality traceability verification module integrates a dedicated RFID reading device and an automatic sealing device on the tobacco packaging line, obtains label data through the built-in RFID tag in the sealing paper; builds a quality traceability model to identify and analyze label data to obtain label detection results; and obtains quality traceability results by analyzing label detection results and anti-counterfeiting traceability identification sets.

2. According to the Internet of Things-based electronic tag wireless radio frequency intelligent identification system according to claim 1, it is characterized by: The environmental dynamic parameter set includes data from temperature and humidity sensors and gas composition sensors based on the fermentation process, generating temperature field distribution thermograms, humidity gradient change curves, target temperature curves and oxygen concentration attenuation matrices; the processing quality feature set includes integrated shredded thickness fluctuation spectrum, baking hot air velocity field vector diagram and flavoring atomization pressure timing waveform; the anti-counterfeiting traceability identification set includes a microstructure optical fingerprint map of the storage packaging seal and its blockchain hash binding relationship with the production batch; the label data includes front-end data and seal feature data; the front-end data stream includes production batch number, equipment number and process parameters; the seal feature data: optical fingerprint map and microstructure three-dimensional coordinates.

3. The electronic tag wireless radio frequency intelligent identification system based on the Internet of Things according to claim 1 is characterized in that: The process composite prediction model includes: a data preprocessing layer obtains smoothed environmental dynamic parameter data and processing quality feature data by preprocessing the environmental dynamic parameter set and the processing quality feature set; a feature extraction layer generates temperature conduction features and pressure waveform features by extracting features from the environmental dynamic parameter data and the processing quality feature data; a timing analysis layer obtains the process parameter evolution trend by extracting spatial features from the environmental dynamic parameter data and timing features from the processing quality feature data, and analyzing the spatial features and timing features; an anomaly detection layer obtains first quality data and first anomaly data by performing anomaly detection on the temperature conduction features and the pressure waveform features; a decision optimization layer obtains the baking temperature lag compensation coefficient and the flavoring pressure dynamic adjustment parameter by analyzing the first anomaly data and the process parameter evolution trend.

4. The electronic tag wireless radio frequency intelligent identification system based on the Internet of Things according to claim 3 is characterized by: The specific generation process of the baking temperature lag compensation coefficient includes: by analyzing the first abnormal data, obtaining the baking temperature data and tobacco leaf quality data, and obtaining the mapping relationship between temperature and quality; using the support vector regression algorithm to train the model to predict the tobacco leaf quality under different temperature lag conditions; based on the prediction results, calculating the baking temperature lag compensation coefficient with the optimal tobacco leaf quality; the specific generation process of the dynamic adjustment parameter of the flavoring pressure includes: by analyzing the first abnormal data, obtaining the relationship between the flavoring pressure data and the aroma uniformity, obtaining the function of pressure and uniformity, and calculating the dynamic adjustment parameter of the flavoring pressure that optimizes the aroma uniformity under different production conditions.

5. The electronic tag wireless radio frequency intelligent identification system based on the Internet of Things according to claim 4 is characterized in that: The calculation formula of the baking temperature hysteresis compensation coefficient is: ； in, is the temperature hysteresis compensation coefficient, is the target temperature curve, is the actual temperature measurement value, is the lag time, is the spatial gradient of the temperature field distribution thermal map, is the thermal diffusion coefficient of tobacco leaves, is the maximum temperature deviation, is the baking area, It is the vector diagram of the hot air velocity field for baking; The calculation formula of the dynamic adjustment parameter of aromatherapy pressure is: ； in, To dynamically adjust the pressure value, is the base pressure, is the nozzle gain coefficient, is the time window, The pressure timing waveform The window standard deviation, For the The main frequency phase angle of the window, is the instantaneous spice flow rate, is the target average flow rate, For the uniformity of fragrance, is the uniformity standard threshold.

6. The electronic tag wireless radio frequency intelligent identification system based on the Internet of Things according to claim 1 is characterized in that: The quality traceability model includes a feature digital extraction layer, a blockchain anchoring layer, a smart contract verification layer, and a label detection result output layer; The feature digital extraction layer obtains the reflectivity matrix by scanning the microstructure optical fingerprint, and obtains the first feature vector by analyzing the reflectivity matrix; the blockchain anchoring layer obtains the mixed hash value by performing double hash operation on the first feature vector and the production batch; the smart contract verification layer automatically verifies the matching of the label data with the production batch number and the equipment number in the anti-counterfeiting traceability identification set by using smart contracts to determine the authenticity of the label; the label detection result output layer analyzes the authenticity of the label and outputs the judgment result.

7. The electronic tag wireless radio frequency intelligent identification system based on the Internet of Things according to claim 1 is characterized by: Specific steps to obtain quality traceability results: Cartesian product matching of the production batch number in the front-end data and the blockchain hash value of the anti-counterfeiting traceability identification set; if there is a temperature-related anomaly, trace it back to the baking equipment; if there is a pressure-related anomaly, locate the flavoring machine nozzle; through the three-dimensional coordinates of the microstructure and the process parameters, generate a traceability report including a thermodynamic simulation animation, a material transfer path diagram and an encrypted audit log.

Images