Pearlescent material production quality safety traceability-oriented data fusion method and system

Abstract

The invention relates to the technical field of pearlescent material production quality traceability, in particular to a pearlescent material production quality safety traceability-oriented data fusion method and a pearlescent material production quality safety traceability-oriented data fusion system. The method comprises the following steps: acquiring data of the whole production process of the pearlescent material, and determining the initial property of the pearlescent material in combination with the operation state of a production workshop; analyzing a dynamic fatigue growth trend based on production equipment operation data, and evaluating an equipment coupling degradation condition in combination with raw material properties; monitoring the dynamic stability of the finished product based on degradation conditions; evaluating the deterioration trend of the finished product and detecting the quality safety risk of the finished product through packaging and transportation simulation; and finally, fusing the quality safety data and the stability data of the finished product, identifying defects of the production process, and completing optimization processing of the data in the whole process to obtain optimized data which can be used for tracing and adjusting the process. According to the invention, the production quality of the pearlescent material is traced, so that the production quality of the pearlescent material is more perfect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of quality traceability of pearl material production, and particularly relates to a data fusion method and system for quality and safety traceability of pearl material production. BACKGROUND

[0002] As a functional material with unique optical effects, pearl material is widely used in coatings, cosmetics, plastics, printing inks and other fields. Due to its wide use in visual performance, human contact and high-end decoration, the quality stability and safety of the product have become the focus of the industry. The quality of pearl material is affected by many factors, including impurity composition of raw materials, particle size distribution, surface coating layer stability, production equipment running state, workshop environment parameters and packaging structure sealing. In the actual production process, due to problems such as high impurity content of raw materials, oxidation and decomposition of coating layer, particle agglomeration, production equipment coupling attenuation, running frequency drift or packaging structure damage, the finished product of pearl material has increased irritation, decreased stability and even deteriorated. However, the traditional quality and safety traceability of pearl material production has the problems of inaccurate monitoring of dynamic stability of pearl material finished product and inaccurate quality and safety detection of pearl material. SUMMARY

[0003] Therefore, it is necessary to provide a data fusion method and system for quality and safety traceability of pearl material production to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a data fusion method for quality and safety traceability of pearl material production comprises the following steps: Step S1: acquiring pearl material production whole process data; collecting pearl material production workshop data based on the pearl material production whole process data; and determining pearl raw material initial property data based on the pearl material production workshop data and the pearl material production whole process data; Step S2: determining material production equipment dynamic fatigue growth trend according to the pearl material production workshop data; determining material production equipment coupling degradation condition according to the pearl raw material initial property data and the material production equipment dynamic fatigue growth trend; and monitoring dynamic stability of pearl material finished product based on the material production equipment coupling degradation condition; Step S3: simulating pearl material packaging and transportation based on the dynamic stability of pearl material finished product to obtain pearl material packaging and transportation simulation data; monitoring deterioration trend of pearl material finished product according to the pearl material packaging and transportation simulation data; and detecting quality and safety data of pearl material based on the deterioration trend of pearl material finished product. Step S4: based on the quality safety data of the pearlescent material and the dynamic stability property evaluation of the finished pearlescent material, the defect data of the pearlescent material production process is evaluated; based on the defect data of the pearlescent material production process, the production process optimization data of the whole process of the pearlescent material production is obtained.

[0005] The application fuses the whole process data of the pearlescent material production with the production workshop data, improves the identification accuracy of the initial properties of the raw materials, and strengthens the controllability of the material quality from the source; combines the workshop data to monitor the fatigue growth trend, effectively evaluates the coupling degradation condition of the equipment, improves the dynamic perception ability of the equipment running state, ensures the production continuity and product consistency; based on the dynamic stability of the finished product, the influence of the packaging structure on the product performance is identified in advance, and the product stability and quality safety in the transportation process are ensured; through the fusion of the deterioration trend and the quality safety data, the potential defect points in the production are deeply mined, and the accuracy and reaction speed of the quality traceability are improved; further, the whole process data is reversely optimized by using the defect data, a data closed loop mechanism is constructed, the flexible adjustment ability and optimization efficiency of the production process are improved, the whole process quality safety traceability and production process intelligent optimization are realized, and the stability, reliability and safety of the pearlescent material production system are enhanced. Therefore, the application is an optimization processing of the traditional pearlescent material production quality safety traceability, solves the problems of inaccurate monitoring of the dynamic stability property of the finished pearlescent material and inaccurate quality safety detection of the pearlescent material in the traditional pearlescent material production quality safety traceability, improves the accuracy of the dynamic stability property monitoring of the finished pearlescent material and the accuracy of the quality safety detection of the pearlescent material.

[0006] The application also provides a data fusion system for pearlescent material production quality safety traceability, which is used for executing the data fusion method for pearlescent material production quality safety traceability as described above, and comprises: The raw material initial property determination module is used for acquiring the whole process data of the pearlescent material production, collecting the pearlescent material production workshop data based on the whole process data of the pearlescent material production, and determining the initial property data of the raw material based on the pearlescent material production workshop data and the whole process data of the pearlescent material production; The finished product dynamic stability property monitoring module is used for determining the dynamic fatigue growth trend of the material production equipment according to the pearlescent material production workshop data, determining the coupling degradation condition of the material production equipment according to the initial property data of the raw material and the dynamic fatigue growth trend of the material production equipment, and monitoring the dynamic stability property of the finished pearlescent material based on the coupling degradation condition of the material production equipment. The pearl material quality safety detection module is used for simulating the pearl material packaging and transportation based on the pearl material production whole process data, obtaining the pearl material packaging and transportation simulation data, monitoring the deterioration trend of the pearl material finished product according to the pearl material packaging and transportation simulation data, and detecting the pearl material quality safety data based on the deterioration trend of the pearl material finished product. The production process optimization processing module is used for evaluating the pearl material production process defect data based on the pearl material quality safety data and the dynamic stability property of the pearl material finished product, and performing production process optimization processing on the pearl material production whole process data based on the pearl material production process defect data, so as to obtain the pearl material production process optimization data.

[0007] The data fusion system for the pearl material production quality safety traceability can realize any data fusion method for the pearl material production quality safety traceability, and is used as a medium for joint operation and signal transmission between modules to complete the data fusion method for the pearl material production quality safety traceability. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 It is a step flowchart of a data fusion method for pearl material production quality safety traceability. Figure 2 It is a detailed implementation step flowchart of step S3. Figure 1 Figure 3 It is a production equipment coupling degradation condition detection diagram in the application. The implementation, functional characteristics and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0009] The technical method of the application will be described clearly and completely in combination with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor belong to the protection scope of the application.

[0010] ​Furthermore, the accompanying drawings are included to provide a further understanding of the present application, and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments of the present application and, together with the description, serve to explain the principles of the present application. In the drawings:

[0011] It should be understood that, although terms such as "first", "second", and the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element without departing from the scope of the example embodiments. The term "and / or" as used herein encompasses any and all combinations of one or more of the associated associated items.

[0012] To achieve the above object, there is provided Figures 1 to 3 A data fusion method for quality safety traceability of production of pearlescent materials, comprising the following steps: Step S1: acquiring data of the whole process of production of the pearlescent materials; acquiring data of a workshop for production of the pearlescent materials based on the data of the whole process of production of the pearlescent materials; and determining initial property data of raw materials for the pearlescent materials based on the data of the workshop for production of the pearlescent materials and the data of the whole process of production of the pearlescent materials; In the embodiment of the present application, in the production process of pearlescent material, the whole process data of the production of pearlescent material is obtained based on the industrial data acquisition system deployed by the manufacturing enterprise in each link of the production. The data includes but is not limited to raw material batch information, feeding time, stirring speed, heating temperature, drying time, surface treatment process number, quality detection result, process alarm record, etc., and the data format is uniformly recorded in the form of time series database (TSDB). Then, combined with the workshop environment monitoring system configured on the production line, the pearlescent material production workshop data is collected, which includes the temperature and humidity, air cleanliness, particle concentration, electrostatic potential change, motor current, equipment switching frequency and other indicators of the workstations in each production section (such as mixing, coating, drying), which are collected to a unified edge collection terminal by Modbus protocol and transmitted to the central data platform through OPC UA interface. Then, by establishing data fusion processing logic, the above workshop data is associated and paired with the whole process process parameters. Specifically, the batch number and storage time of rutile titanium dioxide in the pearlescent raw material data are timestamped and compared, combined with the change of workshop temperature interval and electrostatic level, and the activity evolution of the raw material under actual environmental conditions is analyzed. Further, for the wet content, pH value, specific surface area and other characterization parameters of the raw material, the workshop running state data corresponding to the production time point is segmented and calibrated, forming the initial property data set of the pearlescent raw material, including the initial particle size distribution, surface potential level and potential agglomeration trend index of the material, etc., providing basic support for subsequent equipment state and finished product performance analysis.

[0013] Step S2: determining the dynamic fatigue growth trend of the material production equipment according to the pearlescent material production workshop data; determining the coupled degradation status of the material production equipment according to the initial property data of the pearlescent raw material and the dynamic fatigue growth trend of the material production equipment; monitoring the dynamic stability of the finished pearlescent material based on the coupled degradation status of the material production equipment; In the embodiment of the present application, based on the aforementioned collected data of the pearl material production workshop, the operation log of each key processing equipment in the workshop is structured and analyzed. The on-off state, frequency adjustment instruction, speed change, load current and other fields in the log text are normalized in a time axis manner to form the operation sequence data of the pearl material production workshop. Subsequently, by constructing a workshop operation intensity monitoring model, the frequency of various operation commands and the concurrent operation rate of the equipment within a unit time are counted, and the workshop production intensity fluctuation curve is calculated accordingly. The curve extracts the rising slope by calculating the mean and variance of the difference in operation intensity between adjacent time periods. When the slope exceeds 0.87 for 3 consecutive periods, it is determined that the workshop is in a high-intensity pressurized operation state. At the same time, combined with the cooperative operation relationship between the equipment, a Pearson correlation coefficient matrix is constructed to analyze the correlation of the load change trend of multiple devices in the same production line, and the coupled operation interference data is obtained. The high-intensity fluctuation and coupled interference risk are fused to form the dynamic fatigue growth trend of the material production equipment. Then, the particle size distribution information and humidity content data in the initial property data of the pearl raw material are retrieved, and a physical dispersion resistance calculation model is established to predict the viscous force that the raw material slurry needs to overcome during the stirring stage. According to the viscous force trend, the torque load growth process of the stirring system is deduced, and combined with the real-time acquisition data of the stirring equipment torque and stress sensor data, the abnormal fluctuation of the device shear stress is monitored. At the same time, based on the rotational speed fluctuation data obtained by the angular velocity sensor arranged in the equipment transmission system, combined with the viscous load rising trend, the growth process of torque jitter frequency and intensity is deduced, so as to comprehensively estimate the coupled degradation condition of the equipment. Finally, according to the coupled degradation condition of the equipment, the dynamic stability of the finished pearl material is monitored. Specifically, after drying is completed, the particle size deviation degree of the finished product is monitored in real time by an online particle size detector (such as a laser particle size analyzer), and a particle size deviation-color difference drift response relationship model is established combined with the color difference data collected by an online color difference instrument. When the mean particle size deviation is greater than ±0.15 μm or the color difference ΔE is greater than 1.2, it is determined that the dynamic stability of the finished product has a significant fluctuation.

[0014] Step S3: Based on the pearl material production process data, the dynamic stability of the finished pearl material is simulated for pearl material packaging and transportation, to obtain pearl material packaging and transportation simulation data; the deterioration trend of the finished pearl material is monitored according to the pearl material packaging and transportation simulation data; and the quality and safety data of the pearl material are detected based on the deterioration trend of the finished pearl material; In the embodiments of the present application, after the monitoring of the dynamic stability of the finished product is completed, a multi-factor simulation model of the packaging and transportation process of the pearlescent material is constructed based on the data of the entire production process of the pearlescent material and the physical property parameters of the finished product. The model considers the mechanical vibration frequency (10,200 Hz) during transportation, the peak value of vehicle acceleration (up to 5g), air pressure fluctuation (10,101 kPa), and environmental humidity change (30%~95%RH). Through the finite element analysis method, the stress distribution and structural deformation of the pearlescent material under different packaging structures (such as single-layer plastic sealing + paper box, double-layer aluminum film composite packaging) are simulated, and the simulation data of the packaging and transportation of the pearlescent material are formed. Based on the above simulation data, the time domain analysis of the change of the packaging sealing performance is carried out, the decline rate of the sealing parameters of the packaging structure (such as the change rate of the permeability is more than 0.03g / m²·d) is calculated, and the damage risk level of the packaging structure is determined. Then, combined with the particle size and color difference change trend in the dynamic stability of the finished product, the material deterioration process under the damage condition is calculated, including: the increase of the oxidation rate of the surface coating layer (>0.05mg / cm²·d) caused by air permeation induced by packaging damage, the decrease of the material adhesion caused by water vapor penetration, the increase of the probability of microbial proliferation, etc. Further, according to the weighted fusion of each risk factor, the deterioration trend prediction curve is constructed, the safety performance decline threshold of the material at different time nodes is extracted, and the quality safety data of the pearlescent material is formed, covering the failure mode classification (oxidation type, moisture type, infection type) and the time-performance degradation relationship.

[0015] Step S4: evaluating the defect data of the production process of the pearlescent material based on the quality safety data of the pearlescent material and the dynamic stability of the finished product of the pearlescent material; and performing production process optimization processing on the data of the entire production process of the pearlescent material based on the defect data of the production process of the pearlescent material, to obtain the optimized data of the production process of the pearlescent material.

[0016] In the embodiment of the present application, after obtaining the quality safety data of the pearlescent material, field-level data fusion processing is performed on the quality safety data and the dynamic stability of the finished product. Specifically, the particle size change rate, oxidation decomposition trend curve, and packaging damage index in the quality safety data are matched with the particle size deviation, color difference fluctuation amplitude, and stirring viscosity change rate in the dynamic stability data in the field, and the unified material behavior trajectory is constructed using the DTW (Dynamic Time Warping) algorithm. Subsequently, based on the behavior trajectory data, the failure event occurrence probability under different time periods and different equipment working conditions is calculated by associating and mining the whole process process parameters (such as drying temperature, mixing time, stirring rate, equipment start-stop frequency, etc.), and the whole process tracking data of the pearlescent material production is formed. The tracking data identifies high-frequency defect modes (such as the "high-humidity batch-high-slope operation-sticky aggregation" path) through cluster analysis, and outputs the defect data of the pearlescent material production process accordingly. Finally, according to the defect data, the key process parameter setting interval is reconstructed in the whole process data management system, and the parameter optimization table based on the defect suppression mechanism is formed. The system automatically generates adjustment suggestions, including reducing the stirring intensity by 5-10%, increasing the drying temperature by 3°C, controlling the workshop temperature within ±1.5°C, etc., to form the optimization data of the pearlescent material production process. The data is transmitted to the MES system as the basis for subsequent batch production control, realizing the closed-loop optimization of quality safety based on data fusion.

[0017] Preferably, step S1 comprises the following steps: Step S11: acquiring whole process data of the pearlescent material production; In the embodiment of the present application, in the process of acquiring the whole process data of the pearlescent material production, a unified industrial data acquisition architecture is set up in the pearlescent material manufacturing factory. The architecture relies on PLC controllers, distributed data acquisition devices (such as Siemens S7-1200 and NI CompactDAQ), industrial cameras, environmental sensing nodes, RFID reading and writing equipment, and online data relay gateways to continuously acquire various key data in the production process. The specific contents of the acquisition include but are not limited to: raw material storage time, batch number, supplier code, transportation conditions (temperature and humidity, vibration data, etc.), raw material unloading time, storage area and storage conditions, sampling information, input ratio data, stirring uniformity parameters, real-time temperature and humidity records, production rhythm, operation time, equipment running status and alarm logs, and product composition, packaging time, test results, etc. After preliminary preprocessing by the edge computing module, all the above data is uploaded to the centralized database deployed on the local server or industrial cloud platform, and is standardized and archived according to the unified timestamp, field naming, and data type, to form the complete whole process data of the pearlescent material production.

[0018] Step S12: acquiring pearlescent raw material data based on the whole process data of the pearlescent material production; In the embodiment of the present application, based on the acquired data of the whole production process of the pearlescent material, the data of the pearlescent raw material is collected. This step filters the data fields associated with the raw material storage and use links in the data set by identifying the corresponding storage time stamp, supplier identification information and batch number of the raw material. This includes the physicochemical properties of the raw material (such as particle size distribution range, surface modifier type, heavy metal content detection data, pH value, water absorption rate, surface potential), packaging conditions (sealing bag material, vacuum level), storage inspection report (quantitative data generated by laser particle size analyzer, ICP-MS spectrometer, SEM scanning electron microscope, etc. detection equipment), and time axis data such as actual delivery time, feeding section number, reaction kettle time recorded in the material flow sheet. All raw material data needs to be bound with production data according to unique batch code after collection, forming a traceable raw material sub-database for subsequent steps.

[0019] Step S13: Collecting data of the pearlescent material production workshop based on the data of the whole production process of the pearlescent material; In the process of collecting data of the pearlescent material production workshop, the environmental monitoring devices (such as temperature and humidity sensors, wind speed and volume recorders, aerosol monitoring probes) deployed in the key areas of the workshop, production equipment state collection modules (including torque sensors, current and voltage sensors, vibration sensors, shaft temperature sensors) and video collection systems are used to record the production conditions throughout the period. The specific collection contents include: temperature variation curve, humidity variation record, running power, load variation, fault alarm frequency, downtime record of key nodes such as stirring kettle, coating reaction kettle and other equipment in different sections. The device operation log is standardized uploaded to the unified database through OPC-UA protocol, and the time node is corrected combined with the task scheduling table in the MES system, so that the workshop data can be matched with the raw material use data and process data. At the same time, the actual feeding time, work team, shift personnel ID and other information recorded by the operation platform are also stored synchronously to perfect the boundary conditions for subsequent analysis.

[0020] Step S14: Determining the initial property data of the pearlescent raw material based on the data of the pearlescent material production workshop and the data of the pearlescent raw material.

[0021] In the embodiment of the present application, based on the pearl raw material data obtained in step S12 and the pearl material production workshop data obtained in step S13, the nature state of the raw material in the initial stage is analyzed. In the implementation, a data fusion algorithm (such as multi-channel time series clustering, attribute cross analysis method) is used to perform feature-level fusion on the two types of data, and the particle size data of the raw material and the workshop temperature and humidity fluctuation data are compared to identify the coupling effect of the material surface charge fluctuation and the environmental factor. Secondly, according to the impurity and heavy metal content in the raw material, combined with the recorded stirring torque change and reactant pH value change in the workshop, the catalytic oxidation reaction sensitivity index is analyzed. Then, by analyzing the position where the shear resistance fluctuation frequently occurs in the operation of the workshop equipment, the raw material high molecular chain fracture sensitivity index is compared, and the initial structure stability is inferred. The above analysis results are summarized as the initial property data of the pearl raw material, which includes but is not limited to: reaction catalytic oxidation sensitivity index, electrostatic repulsion drop value, impurity critical threshold, rest angle fluctuation degree, particle size drift probability index, etc. These data will flow into the subsequent device dynamic fatigue and product dynamic stability analysis module as input conditions to ensure the integrity of the data chain.

[0022] Preferably, step S14 comprises the following steps: Step S141: detecting the impurity component content of the pearl raw material to obtain the impurity component content data of the pearl raw material; In the embodiment of the present application, after the raw material sample is pretreated by the pretreatment equipment (such as acidolysis treatment of the sample by the full-automatic digestion instrument), it is sent into the inductively coupled plasma optical emission spectrometer (ICP-OES) and the gas chromatograph-mass spectrometer (GC-MS) for component analysis. In this process, the detection target focuses on inorganic impurities (such as silicon, calcium, aluminum, iron, etc. Oxides) and organic impurities (such as residual reaction byproducts, polymer monomer residues, etc.). The mass fraction of each type of impurity is calculated according to the standard curve method, and the data is collected in ppm as a unit to generate the impurity component content data of the pearl raw material.

[0023] Step S142: determining the heavy metal content data of the pearl raw material according to the impurity component content data of the pearl raw material; In the embodiment of the present application, the heavy metal related elements (such as Pb, Cd, Cr, Hg, As, Ni, Cu, Zn, etc.) are screened out from the impurity component content data obtained in step S141, and each data is classified and summarized. In the specific implementation, the contents of Pb and Cd are respectively summarized according to the raw material batch, the time of entering the factory and the sampling point to ensure the consistency of batch tracking. The heavy metal content data is composed of a structured data table in the form of element name + mass fraction, which is used as the input of subsequent analysis.

[0024] Step S143: According to the heavy metal content data of the pearl raw material, the pearl raw material data is analyzed and detected by the pearl raw material reaction catalytic oxidation analysis, and the pearl raw material reaction catalytic oxidation condition is obtained; In the embodiment of the present application, a constant temperature reaction kettle (set temperature 80°C, stirring rate 600 rpm) is used in combination with an oxidation-reduction potential (ORP) online detection module and a UV-Vis ultraviolet visible spectrophotometer to analyze the catalytic oxidation reaction behavior of the pearl raw material in the presence of hydrogen peroxide. During the measurement process, the oxidation potential change curve, the hydrogen peroxide decomposition rate and the active intermediate generation are recorded. Combined with the heavy metal content data of the pearl raw material, the intervention degree of metal ion catalytic reaction process is evaluated. According to the active change characteristics of the reaction time node, the pearl raw material reaction catalytic oxidation condition parameters are obtained, including the initial reaction rate, the reaction stable period length, the maximum ORP change amplitude, etc.

[0025] Step S144: Detecting the surface charge change trend of the pearl raw material data of the pearl raw material; In the embodiment of the present application, a Zeta potential analyzer (such as Malvern Zetasizer Ultra) is used to detect the surface charge characteristics of the pearl raw material particles in different pH value buffers. The raw material sample is dispersed in a standard dispersion medium for 5 minutes before detection, and the Zeta potential distribution curve of the sample in the pH=3-11 range is recorded. The detection results are used to analyze the charging trend and stability, especially the downward trend of the absolute value of the Zeta potential and the position offset of the isoelectric point, as the core basis of the surface charge change trend data of the pearl raw material.

[0026] Step S145: Measuring the temperature change trend of the pearl material production workshop based on the pearl material production workshop data; In the embodiment of the present application, the temperature change trend of the pearl material production workshop is collected in real time by a distributed industrial temperature and humidity sensor node network. The sensor model is selected from the Honeywell HIH series, which is installed at key positions such as the inlet and outlet of the reaction kettle, the feeding platform, the upper part of the drying section transmission line, and the stirring system. The sampling frequency is set to 5 seconds / time, and after the data is uploaded to the local OPC server, the mean value, fluctuation amplitude, maximum gradient and trend inflection point position in the temperature curve are extracted using a time series analysis algorithm to generate the temperature change trend data of the pearl material production workshop.

[0027] Step S146: When the temperature change trend of the pearl material production workshop exceeds ±3.2°C, the surface charge change trend of the pearl raw material is determined to determine the decrease of the electrostatic repulsion of the raw material particles; In the embodiment of the present application, the surface charge variation trend data obtained in step S144 is combined with the workshop temperature variation trend data obtained in step S145 for joint analysis. The threshold of ±3.2°C in the temperature variation trend is focused on, and a judgment is made based on whether the Zeta potential decreases by more than 15% within 5 minutes before and after the temperature crosses the threshold. When the condition is met, the electrostatic repulsion decrease index is calculated, and the electrostatic repulsion decrease of the raw material particles is confirmed in combination with the particle size distribution change.

[0028] Step S147: Estimate the spontaneous grouping condition of the pearlescent raw material according to the electrostatic repulsion decrease of the raw material particles; In the embodiment of the present application, according to the confirmed electrostatic repulsion decrease, the grouping trend of the raw material in a static state is further measured. The specific method is to place the sample in a transparent cuvette, and use a light scattering imaging system (such as Turbiscan Lab) to record the light intensity distribution change within 0-30 minutes, and through the increase of the bottom scattering light intensity and the increase trend of the top clear liquid transmittance, the grouping rate and the grouping particle size growth rate are quantified, and the spontaneous grouping condition data of the pearlescent raw material is output in the form of average grouping rate μg / min and volume distribution shift index.

[0029] Step S148: Determine the initial property data of the pearlescent raw material based on the spontaneous grouping condition of the pearlescent raw material and the catalytic oxidation reaction condition of the pearlescent raw material.

[0030] In the embodiment of the present application, the catalytic oxidation reaction condition of the pearlescent raw material obtained in step S143 is fused with the spontaneous grouping condition data obtained in step S147 for analysis, and an attribute weight proportioning analysis method is used to standardize and weightedly average process the two groups of indexes, and the initial property data of the pearlescent raw material is output. The data contains index items including: reaction sensitivity score, particle size drift index, repulsion decrease risk coefficient, grouping rate level, etc., forming a set of structured initial property description fields, which are used as the data basis for subsequent equipment degradation analysis and product stability evaluation.

[0031] Preferably, the determination of the material production equipment dynamic fatigue growth trend according to the pearlescent material production workshop data in step S2 comprises: Determine the structural complexity of the pearlescent material production workshop according to the pearlescent material production workshop data; In the embodiment of the present application, the structural complexity of the pearl material production workshop is quantitatively analyzed based on the building information model (BIM) data of the workshop, the sensor deployment map and the function structure diagram of the station. The structural complexity parameters are obtained by calculating the spatial distribution density of the workshop, the number of key equipment connection nodes, the function coupling index of the station, etc. The specific method includes: using three-dimensional point cloud reconstruction technology to scan and model the workshop space, combining with the process flow diagram of the workshop to extract the connection path, function chain and operation link redundancy between each device, the structural complexity is represented by the structural coupling index (SCI), and the numerical range is set to 0~1, the higher the value, the more complex the structure.

[0032] According to the data of the pearl material production workshop, the operation log of the pearl material production workshop is extracted; In the embodiment of the present application, the operation log of the pearl material production workshop is extracted by using the industrial internet collection node (such as OPC UA communication interface). The log content covers device start-stop record, temperature and pressure alarm information, feeding time point, maintenance period, shutdown reason and other contents. The time stamp alignment mechanism is set in the collection process to ensure that the time accuracy of the log data reaches millisecond level, and the real-time collection and unified storage are realized through Kafka message queue system. After the repeated items, invalid items and format error items are removed in the preprocessing process, the original log data enters the time series analysis stage.

[0033] The operation log of the pearl material production workshop is analyzed in time sequence to obtain the time sequence data of the pearl material production workshop; In the embodiment of the present application, in the time sequence analysis process, a multi-scale feature extraction method based on sliding window mechanism is used to model the time series of the workshop operation log. The window width is set to 30 minutes and the step is set to 5 minutes. The event frequency, operation type conversion number, shutdown alarm interval and other parameters in the window are extracted to generate the time sequence data of the pearl material production workshop. The data structure includes time stamp, event label, operation category, operation intensity and other fields, which are used for subsequent dynamic trend analysis.

[0034] Based on the time sequence data of the pearl material production workshop, the material production demand change data of the workshop is obtained; In the embodiment of the present application, based on the generated time sequence data of the workshop, the material production demand change data of the workshop is extracted by comparing the job plan data with the actual feeding / running time. The method includes comparing the time between the daily plan and the running log, the increase / decrease ratio change of the number of started devices per unit time, etc. The dynamic evolution process of the actual running load is determined in the form of data such as the average production request number per unit hour, the fluctuation frequency and the maximum load difference.

[0035] Draw a workshop production running strength fluctuation chart based on the material production demand change data, and calculate the workshop running strength rising slope value according to the workshop running strength fluctuation chart; In the embodiment of the application, further, the aforementioned material production demand change data is used to draw a workshop production running strength fluctuation chart through a visualization library such as Matplotlib or Plotly, the horizontal axis is set as time, and the vertical axis is set as the total number of started processes or the running time proportion in a unit time. The rising slope of the curve is calculated through a linear fitting algorithm to obtain the workshop running strength rising slope value. OLS (least squares method) linear fitting is used, and the slope of different time periods is statistically segmented to output an important parameter for judging the fatigue growth trend.

[0036] Based on the time series data of the pearlescent material production workshop, the running state correlation between devices is analyzed to obtain workshop device cooperative running data; In the embodiment of the application, the correlation between the state signals (such as running, standby, and alarm) of each key device in the time series data of the pearlescent material production workshop is calculated, and the Pearson correlation coefficient and mutual information index are used to evaluate the correlation strength between the running state sequences of the device pairs. The analysis objects include reaction kettles, drying systems, conveying pumps, and screening devices, etc. After standardizing the running timestamp sequences, the synchronization trend between different devices is analyzed to generate the workshop device cooperative running data.

[0037] Based on the workshop device cooperative running data, the coupling interference risk data between devices is determined; In the embodiment of the application, according to the workshop device cooperative running data, the mutual interference relationship in the high-frequency cooperative group is identified, the conflict matrix and statistical anomaly detection method are used to identify the abnormal coupling frequency, state switching lag time, and conflict rate between key devices, and the coupling interference risk data between devices is extracted. The data is composed of a risk assessment table with risk levels (L1-L5) and frequency scores (coupling anomaly times per hour) as core indexes.

[0038] When the workshop running strength rising slope value exceeds 0.87, and the coupling interference risk data between devices determines the dynamic fatigue growth trend of the material production device.

[0039] In the embodiment of the application, the obtained workshop running strength rising slope value and the coupling interference risk data between devices are jointly judged. When the rising slope value exceeds the set threshold value 0.87, and the corresponding coupling interference risk level is greater than or equal to L3, the dynamic fatigue growth trend of the material production device is obtained as "growth" state according to the logic threshold judgment method, an evaluation report of the trend is generated, which is used as the input of the subsequent coupling degradation analysis.

[0040] Please refer to Figure 3 , which is a schematic diagram of the production device coupling degradation condition detection in the application. Preferably, determining the coupling degradation status of the material production equipment in step S2 according to the initial property data of the pearl material and the dynamic fatigue growth trend of the material production equipment comprises: measuring the initial water content of the raw material according to the initial property data of the pearl material; In the embodiment of the present application, the initial water content of the raw material is measured according to the water sensor reading and the weighing difference method results contained in the initial property data of the pearl material. In the operation process, an infrared moisture meter is used to heat the raw material sample at a constant temperature (the heating temperature is set to 120°C, and the duration is 8 minutes), and the initial water content of the raw material is calculated in combination with the mass change before and after heating the sample, with the unit being mass percentage (%). The sample amount is uniformly 10g, and the average value is obtained after repeating three times for each group.

[0041] determining the particle size distribution of the pearl material according to the initial property data of the pearl material; In the embodiment of the present application, a laser particle size analyzer is used to detect the particle size of the pearl material at high resolution to determine the particle size distribution. The measurement method uses a static light scattering method to collect data on particle signals with a scattering angle range of 0.02° to 130°, and the particle size distribution interval is set to 0.1μm to 100μm, with a sampling frequency of 1000 times per second. After data collection is completed, the D10, D50 and D90 particle size parameters are analyzed through the integral particle size distribution curve, and the particle size distribution data of the pearl material is output.

[0042] predicting the processing viscosity growth trend of the raw material based on the particle size distribution of the pearl material and the initial water content of the raw material; In the embodiment of the present application, the processing viscosity growth trend of the raw material is calculated based on the previously obtained water content and particle size distribution data of the raw material. A rheometer (shear rate range 0.01 to 100s^-1) is used to test the rheological behavior of the raw material slurry under different water content conditions. After the raw material is adjusted into a slurry, it is placed on a temperature-controlled (25°C) rheological platform for shear testing, the shear stress-shear rate curve is recorded and the viscosity growth curve is fitted. By comparing the change gradient of the water content and the particle size influence factor, the viscosity growth trend in the processing process is predicted.

[0043] estimating the stirring resistance rising trend of the material stirring equipment based on the processing viscosity growth trend of the raw material; In the embodiment of the present application, the viscosity growth trend data is used to estimate the stirring resistance rising trend of the material stirring equipment by calculating the change of the driving force of the stirring equipment per unit time. The operation is performed by collecting the torque sensor data on the control panel of the equipment. The strain gauge torque sensor is installed on the stirring paddle shaft of the equipment. The starting torque, stable running torque and peak torque change are recorded during the processing of different batches of materials. After fitting the change trend with the viscosity change, the stirring resistance rising curve is obtained.

[0044] According to the initial property data of the pearlescent raw material, the dynamic fluctuation of the angle of repose of the pearlescent raw material is estimated. In the embodiment of the present application, according to the particle size, surface charge and moisture index and other indicators in the initial property data of the pearlescent raw material, the dynamic fluctuation of the angle of repose of the raw material is measured by the plate tilt experiment. The inclination is set to gradually increase from 0° to 60°. The maximum stable angle of the powder in the natural accumulation and static state is recorded as the static angle of repose of the batch of raw materials. The experiment is repeated three times under different temperature and humidity environments and particle size processing conditions to form a sequence of raw material angle of repose fluctuation data.

[0045] According to the dynamic fluctuation of the angle of repose of the pearlescent raw material and the stirring resistance rising trend of the material stirring equipment, the abnormal situation of the shear stress of the equipment is detected. In the embodiment of the present application, the dynamic fluctuation of the angle of repose of the raw material and the stirring resistance rising trend are coupled to analyze the shear resistance fluctuation behavior caused by the change of the accumulation performance of the raw material, and the abnormal situation of the shear stress of the equipment is detected. The abnormality is determined according to the mutation point change rate of the shear resistance curve exceeding the set threshold (Δτ / Δt>3.5 Pa / s), which is regarded as the shear abnormal behavior. The data is obtained by real-time synchronous analysis of the equipment torque controller and the PLC acquisition system.

[0046] Based on the abnormal situation of the shear stress of the equipment and the dynamic fatigue growth trend of the material production equipment, the torque fluctuation growth trend of the equipment is estimated. In the embodiment of the present application, based on the abnormal situation of the shear stress and the dynamic fatigue growth trend of the material production equipment, the energy consumption fluctuation and torque instability of the equipment are jointly analyzed to estimate the torque fluctuation growth trend of the equipment. The analysis method is to perform FFT (Fast Fourier Transform) spectrum analysis on the torque time sequence in the historical running data of the stirring motor to identify the main vibration frequency band and the growth rate of the fluctuation amplitude, and obtain the equipment fluctuation frequency amplitude curve.

[0047] According to the torque fluctuation growth trend of the equipment, the coupling degradation condition of the material production equipment is determined.

[0048] In the embodiment of the present application, according to the fluctuation amplitude index (VFI) in the device torque jitter growth trend curve and its growth slope value, the device fatigue growth trend data is compared, when the VFI growth rate in three periods is more than 0.4, and the corresponding fatigue trend level is greater than or equal to 2, the comprehensive judgment is that the material production equipment coupling degradation state enters the enhancement stage, and the coupling degradation evaluation data report is generated. The data is used as the input reference for subsequent finished product dynamic stability property monitoring.

[0049] Preferably, the step S2 of monitoring the dynamic stability property of the pearl material product based on the coupling degradation state of the material production equipment comprises: Detecting the coordination imbalance of the material production equipment based on the coupling degradation state of the material production equipment; In the embodiment of the present application, the coordination imbalance of the material production equipment is detected based on the coupling degradation state of the material production equipment. This operation is completed by collecting real-time running parameters of multiple key stirring, conveying and mixing devices, including torque, speed, power and vibration signals. Using a synchronous data acquisition system, the time series of parameters collected by each device are compared, the correlation coefficient (Pearson correlation coefficient) of the running parameters between devices is calculated, and the time sequence deviation of the device response is detected through time delay correlation analysis. When the correlation coefficient between devices is less than 0.85 and the time sequence deviation exceeds the set threshold (such as 500ms), it is determined that the device has coordination imbalance. The detection result is output as the device coordination imbalance state data.

[0050] Estimating the load abnormal accumulation state of the material production equipment according to the coordination imbalance state of the material production equipment; In the embodiment of the present application, the load abnormal accumulation state of the material production equipment is estimated according to the coordination imbalance state of the material production equipment. Using the collected device load current data and torque curve, the device load exceeding time ratio and exceeding amplitude are calculated by integration, and the load abnormal accumulation curve is generated. The specific indicators of the load abnormal accumulation state include the peak load ratio (actual load / rated load) and the cumulative overload time, and the overload threshold is set to 110% of the rated load. Cumulative overload time exceeding 30 minutes is considered as significant load abnormal accumulation. The load abnormal accumulation curve provides a basis for subsequent frequency drift detection.

[0051] Detecting the running frequency drift state of the production equipment based on the load abnormal accumulation state of the production equipment; In the embodiment of the present application, based on the abnormal accumulation of production equipment load, a high-precision spindle speed sensor is used to continuously collect the real-time speed of the production equipment. The installation position of the sensor ensures that the speed signal of the equipment spindle can be accurately captured. The data acquisition frequency is set to at least 100 times per second to ensure that the subtle fluctuations in the speed change are recorded completely. The collected real-time speed data is preprocessed, including denoising filtering and outlier rejection, to ensure the data quality for subsequent analysis. The average speed value of the calculation equipment during normal operation is obtained by statistical analysis of historical operation data, which is used as a reference. Then, for each second of collected speed data, the deviation rate from the average speed is calculated, and the deviation rate is expressed in percentage form to quantify the instantaneous speed fluctuation amplitude. To more comprehensively analyze the frequency drift characteristics of the equipment speed, the collected speed time series data is processed by discrete Fourier transform to convert the time domain signal to the frequency domain, extract the frequency component, and identify the frequency drift amplitude and its trend. The detection threshold of frequency drift is set to ±0.5 Hz. If the frequency drift amplitude exceeds this threshold in any time period and the duration exceeds 5 minutes, it is determined as a frequency drift abnormal event. This abnormality determination process is automatically completed, and the frequency state of the equipment is monitored in real time. The frequency drift detection results are summarized to form the equipment frequency drift state data, including the drift amplitude, duration, and abnormal alarm identifier, which are used as important basis for equipment operation state evaluation and subsequent maintenance decision.

[0052] Estimating the failure of pearlescent material mixing according to the running frequency drift condition of the production equipment; In the embodiment of the present application, the failure of pearlescent material mixing is estimated according to the running frequency drift condition of the production equipment. Mixing failure refers to the abnormal particle size distribution and color difference fluctuation caused by uneven mixing of raw materials. By synchronously comparing the frequency drift data with the particle size distribution data collected by the particle size sensor, the coupling relationship between frequency abnormality and particle size abnormality is analyzed. The particle size abnormality determination standard is that the D50 particle size changes by more than 10%, and the particle size distribution width (D90-D10) changes by more than 15%. Based on the coupling analysis results, the mixing failure rate percentage is calculated.

[0053] Estimating the particle size deviation degree of pearlescent material based on the failure of pearlescent material mixing; In the embodiment of the present application, the particle size deviation degree of pearlescent material is estimated based on the failure of pearlescent material mixing. The particle size of the sample is detected by a laser particle size analyzer to quantify the particle size deviation rate. This operation is performed at key processes on the production line (after stirring is completed, before packaging), and the D10, D50, and D90 indicators are measured to calculate the deviation proportion of the average particle size relative to the standard value. If the particle size deviation exceeds 5%, it is recorded as an abnormal deviation. The particle size deviation data is used as input for color difference fluctuation evaluation.

[0054] Determining the color difference fluctuation condition of the finished pearlescent material according to the particle size deviation degree of the pearlescent material; In the embodiments of the present application, the color difference fluctuation of the finished pearl material is determined according to the degree of particle size deviation of the pearl material, the color difference of the finished pearl material sample is measured by using a high-precision spectrophotometer, the measurement process is carried out in a constant temperature and humidity environment, the temperature is controlled at 23±1°C, and the humidity is controlled at 50±5%RH, so as to ensure the stability and repeatability of the measurement data. The spectrophotometer converts the spectral data into internationally recognized CIELAB color space parameters, including brightness value L*, red-green coordinate a and yellow-blue coordinate b, by measuring the reflectance spectrum of the sample. The color space can objectively reflect the difference in color perception of the human eye. Each finished sample is measured at multiple points to obtain uniformity data and reduce the influence of local color difference on overall judgment. The measured L*, a* and b* values are compared with the pre-determined standard sample color value, the color difference value ΔE is calculated, the CIEDE2000 standard is used in the calculation formula, and the accuracy and scientificity of the color difference evaluation are ensured. By comparing the color difference data of the finished products of the continuous batches, the change trend of the color difference with the degree of particle size deviation is analyzed, when ΔE exceeds 2, it is determined that the color difference fluctuation is abnormal, which indicates that the color of the finished product changes obviously and affects the visual consistency. The color difference data and the particle size deviation data are combined, and the correlation between them is established by statistical analysis method, which reflects the influence of particle size change on the appearance stability of the finished product. The color difference fluctuation analysis result output is an important basis for evaluating the dynamic stability of the finished product, which supports quality control and production process adjustment.

[0055] The finished pearl material dynamic stability is monitored based on the color difference fluctuation of the finished pearl material and the degree of particle size deviation of the pearl material.

[0056] In the embodiment of the present application, based on the color difference fluctuation and particle size deviation of the finished pearlescent material, the dynamic stability of the finished pearlescent material is monitored, the finished product sample is periodically measured by a high-precision color difference instrument, color difference data is obtained, the instrument ensures the accuracy and repeatability of the color difference measurement through a standardized light source and an optical sensor; at the same time, the particle size distribution of the finished pearlescent material is continuously detected by a laser particle size analyzer, detailed data of the particle size deviation is obtained, and the timeliness and accuracy of the particle size data are ensured. The color difference data and the particle size data are synchronously processed in time sequence, the dynamic change trend of the two types of data is evaluated by time series analysis method, a fixed length time window is set by sliding window technology, the data is intercepted and the standard deviation of the particle size and the standard deviation of the color difference in the window are calculated, and these standard deviations are used as stability indicators to reflect the fluctuation amplitude of the particle size distribution and the color uniformity of the finished product. By continuously calculating the stability indicators in the sliding window, a change curve of the dynamic stability is formed, which can effectively capture the stable state and abnormal fluctuation of the finished product at different time nodes. The above analysis results are arranged into a dynamic stability evaluation report, which describes the particle size and color difference fluctuation characteristics of the finished product in the sampling period, including fluctuation amplitude, trend change and abnormal point identification, and the report data is stored in a structured manner for subsequent calling. The report serves as an important input data for the subsequent packaging and transportation simulation and quality safety detection, provides a basis for accurately simulating the performance change of the material in the packaging and transportation process, supports dynamic early warning and adjustment of quality safety risks, ensures the accuracy and reliability of the data used in the optimization process of the pearlescent material production process, and realizes closed-loop management of the whole process quality control.

[0057] Preferably, step S3 comprises the following steps: Step S31: simulating the packaging and transportation of the pearlescent material based on the dynamic stability of the finished pearlescent material, and obtaining the simulation data of the packaging and transportation of the pearlescent material; In the embodiment of the present application, the whole process data of the pearlescent material production is collected, including the finished product particle size distribution, color difference fluctuation, packaging material performance parameters, packaging sealing state and other key indicators. The finite element analysis (FEA) technology is used to simulate the mechanical properties of the packaging structure, simulate the vibration, impact and pressure distribution in the transportation process. The vibration data is collected from the acceleration sensor in the transportation environment, combined with the vibration curve of the historical logistics path, and the actual transportation vibration load is input into the packaging structure model. The packaging material performance parameters include elastic modulus, yield strength and fatigue resistance, which are obtained based on the laboratory test data. Through numerical simulation, the dynamic response of the packaging structure under stress in the transportation process is obtained, the stress distribution and deformation of the packaging damage critical point are calculated, and the packaging simulation data is output, including the stress field, deformation field and damage probability of the packaging structure. The simulation data serves as the basis for subsequent damage prediction.

[0058] Step S32: According to the pearl material packaging transportation simulation data, the pearl material packaging structure damage prediction is carried out, and the pearl material packaging structure damage data is obtained. In the embodiment of the application, the stress and deformation data obtained in the packaging transportation simulation are combined with the material fatigue life curve to evaluate the fatigue life. The fatigue damage of the packaging material is quantified by using the Miner linear cumulative damage theory, and the fatigue damage ratio corresponding to the cumulative stress cycle number and stress amplitude is calculated. The threshold of the fatigue damage ratio (such as 0.7) is set to determine the critical state of the packaging structure damage. At the same time, based on the local stress concentration area in the simulation data, the crack propagation rate is calculated by using the stress intensity factor (K) in fracture mechanics to predict the time and position of crack occurrence. The damage prediction result is output in the form of packaging structure damage probability, damage position and time node, forming the packaging structure damage data. The data provides a direct basis for subsequent quality deterioration trend monitoring.

[0059] Step S33: Based on the pearl material packaging structure damage data, the pearl material product dynamic stability is monitored to obtain the pearl material product quality deterioration trend. In the embodiment of the application, the influence of packaging damage on the physical environment of the finished product is analyzed by correlating the packaging damage position with the finished product storage position. Combined with the packaging damage part leakage rate data, the change of the humidity and oxygen content in the finished product is measured, and the data is collected in real time by using the humidity sensor and oxygen sensor. According to the packaging damage leakage rate and the internal environment change trend of the finished product, the chemical reaction rate and physical change rate of the material in the finished product are calculated, and a finished product quality deterioration rate model is established. The model is based on the Arrhenius equation and the material stability test data, and quantitatively describes the quality deterioration process of the material affected by the packaging damage. The output pearl material product quality deterioration trend data is expressed as a change curve of the quality deterioration index with time, reflecting the trend of the decrease of the stability of the finished product.

[0060] Step S34: Based on the pearl material product quality deterioration trend, the pearl material quality safety data is detected.

[0061] In the embodiment of the application, the quality deterioration trend data is compared with the quality safety standard, including the material color difference threshold, particle size change threshold and harmful substance release limit. A multi-index fusion algorithm is used to comprehensively calculate the quality deterioration index, packaging damage probability and internal environment parameters of the finished product to form a comprehensive quality safety score. Whether the finished product meets the quality safety requirements is determined by the quality safety score, and the pearl material quality safety data is output. The data is used as a core index of quality control to guide the production process optimization and logistics management, and to ensure the quality and safety of the finished product. The data between the steps is closed-loop transmitted, the packaging transportation simulation data provides input for the damage prediction, the damage data guides the quality deterioration trend monitoring, the quality safety data is formed, and the dynamic monitoring chain is completed.

[0062] Especially important is that step S32 includes the following steps: Step S321: detecting the pearl material storage environment data according to the pearl material packaging transportation simulation data; In the embodiment of the present application, in the pearl material packaging transportation simulation process, by constructing a data simulation system containing transportation period, transportation route, temperature and humidity change, illumination condition, vibration frequency and acceleration and other variables, the environmental parameters exposed to the pearl material in the whole packaging transportation chain are restored. The time node in the transportation simulation data is corresponded with the geographical position, combined with the real-time collected environmental monitoring data (including GPS positioning data, environmental sensor data), the temperature, humidity, air pressure, concentration of volatile substances in the air and other key environmental indicators of the environment where the pearl material is located in different stages of simulation are extracted. A multi-channel data acquisition module with GPRS communication function is used to automatically record these parameters, and the accuracy is ensured through calibrated sensors (SHT31 is selected for temperature and humidity module, and MG811 is selected for gas sensing module). The pearl material storage environment data is formed through structured processing, the data format is unified as JSON structure, and the content includes time stamp, geographical position, temperature value (unit: °C), relative humidity value (unit: %RH), air pressure value (unit: hPa) and the like, which is used as the basic input data for subsequent ultraviolet irradiation intensity analysis and packaging damage prediction.

[0063] Step S322: detecting the storage environment ultraviolet irradiation intensity data based on the pearl material storage environment data; In the embodiment of the present application, according to the pearl material storage environment data formed in step S321, the ultraviolet irradiation intensity of the storage area is further associated and detected. The specific operation includes using the latitude and longitude information of the corresponding place in the simulated transportation path to call the ultraviolet irradiation recorder (such as UV-B recorder MS-212W) to obtain the measured or historical data, and combining the time point and weather condition to perform data matching processing. In the area not covered by the sensor, the weather type and cloud cover level in the environmental data are used as auxiliary variables, and the irradiation intensity conversion formula is used to map the weather and time information into the estimated value of the ultraviolet irradiation intensity. All data uses W / m² as the unit, and is arranged in time sequence according to one data point per hour. In addition, the UV irradiation intensity is integrated to form the cumulative irradiation total amount (unit: J / cm²) of each stage, which is used to reflect the degree of influence of the packaging material on light aging. The storage environment ultraviolet irradiation intensity data is output in time sequence structure and stored in a unified database as an important input for subsequent coupling load calculation.

[0064] Step S323: determining the pearl material transportation collision intensity data based on the pearl material packaging transportation simulation data; In the embodiment of the present application, according to the simulation data of the pearl material packaging and transportation, the collision information is collected at each transportation stage (such as loading, driving and unloading). The collision intensity data is collected by installing a three-axis acceleration sensor (model ADXL357) and a high-frequency sampling vibration recorder (sampling rate of 1 kHz) on the transportation carrier. The data acquisition device sets a threshold alarm mechanism, and any axis acceleration exceeding ±10g will trigger a record mark, forming a high-intensity collision event log. All collision data is calculated by vector synthesis, and the RMS acceleration formula is used to analyze the continuous impact, and the vibration duration, frequency and directionality are weighted, and the pearl material transportation collision intensity data is output. The data is stored in an event sequence structure, including collision time, impact strength (unit: g), impact direction and duration (unit: ms), which is used to evaluate the physical load during transportation.

[0065] Step S324: determining the coupling load intensity data of the pearl material packaging according to the pearl material transportation collision intensity data and the storage environment ultraviolet irradiation intensity data; In the embodiment of the present application, the ultraviolet irradiation intensity data output in step S322 is fused and analyzed with the transportation collision intensity data obtained in step S323 to construct a pearl material packaging coupling load intensity calculation model. The coupling logic is based on the stress-strain behavior of the packaging material, and the ultraviolet irradiation is used as the material aging factor and the collision intensity is used as the physical damage factor. According to the weighted scoring mechanism, the ultraviolet irradiation and the impact acceleration are respectively given a reduction coefficient (the intensity reduction caused by aging is set to 0.2% / MJ·m², and the impact cumulative intensity weighting coefficient is 0.5 points / g·time), and the comprehensive load intensity value output data is the pearl material packaging coupling load intensity data, which is used to represent the integrity level of the packaging system after the simulation process, and is used as the direct input basis for the packaging structure damage prediction.

[0066] Step S325: performing pearl material packaging structure damage prediction according to the pearl material packaging coupling load intensity data to obtain pearl material packaging structure damage data.

[0067] In the embodiment of the present application, according to the packaging coupling load strength data output in step S324, the packaging material fatigue strength critical threshold and the fracture life curve obtained by actual test are referred to for judgment. The breaking point load and the endurance life parameters of the packaging material (such as polyethylene film, multi-layer carton, etc.) under different UV irradiation and impact stress conditions are determined by artificial fatigue test. When the coupling load strength is lower than the critical value of the material tolerance (set as less than 30% of the remaining endurance), it is predicted to be a high risk of damage. The historical data is combined to statistically analyze the damage probability, and the pearl material packaging structure damage data is output, including the damage position risk level (high, medium, low), the predicted damage period, the packaging level (outer box, inner film) and the damage mode (tearing, compression deformation, etc.). The data is directly used as the key input for subsequent finished product dynamic stability analysis and quality risk assessment.

[0068] Preferably, step S33 comprises the following steps: Step S331: estimating the sealing performance degradation of the pearl material packaging structure based on the pearl material packaging structure damage data; In the embodiment of the present application, the pearl material packaging structure damage data is obtained, which includes crack size, crack position and fatigue damage degree of the packaging structure. The pressure decay test and helium leakage test are performed on the packaging sample by using the air tightness detection instrument, the internal air pressure change rate or the helium leakage rate is measured, and the sealing performance degradation of the packaging structure is calculated in combination with the packaging structure damage data. The numerical interpolation and regression analysis method is adopted to establish a corresponding relationship model between the crack size and the sealing performance degradation percentage, so as to realize the quantitative estimation from the damage data to the sealing performance change. The sealing performance degradation value of the pearl material packaging structure is output as the basic input for subsequent moisture absorption probability calculation.

[0069] Step S332: calculating the pearl material moisture absorption probability of the pearl material finished product dynamic stability based on the sealing performance degradation of the pearl material packaging structure, to obtain the pearl material moisture absorption probability data; In the embodiment of the present application, based on the sealing performance degradation value and the external environment humidity data, the diffusion transmission theory is applied to calculate the permeation rate of water vapor through the damaged packaging structure. The internal humidity rise amount per unit time is estimated by using the Darcy's law combined with the packaging damage area. The moisture absorption probability is calculated in combination with the weighted threshold of the humidity sensitivity of the finished product. The sealing performance and environmental data of multiple batches of packaging samples are analyzed by using the probability statistical method, to obtain the moisture absorption probability distribution in a statistical sense. The pearl material moisture absorption probability data is output to clearly indicate the probability of the finished product exposed to the moisture absorption risk.

[0070] Step S333: determining the oxidation decomposition trend of the surface coating layer based on the pearl material moisture absorption probability data; In the embodiment of the present application, the moisture probability data is combined with the hydrolysis and oxidation reaction kinetics parameters of the surface coating material of the finished product. The moisture effect curve on the oxidation rate of the coating layer obtained in the accelerated aging test is used to deduce the oxidation decomposition rate under the current moisture probability condition. By continuously monitoring the thickness change and chemical composition change of the coating layer, the decomposition state of the coating layer is analyzed using Fourier transform infrared spectroscopy (FTIR) and scanning electron microscopy (SEM), and the oxidation decomposition trend curve of the coating layer is calculated by combining the oxidation rate model. The oxidation decomposition trend data is output, which provides key parameters for subsequent deterioration trend monitoring.

[0071] Step S334: Calculate the bacterial infection probability based on the pearl material packaging structure damage data and the pearl material moisture probability data to obtain pearl material bacterial infection probability data; In the embodiment of the present application, the environmental exposure and internal humidity rise caused by packaging damage are combined to infer the bacterial invasion and reproduction conditions. According to the packaging damage area and the moisture probability, a bacterial invasion rate model is established, and the Monod equation is used to describe the dependence of bacterial growth rate on humidity and temperature based on the bacterial growth kinetics model. The bacterial infection probability is calculated by using the finished product storage environment monitoring data (temperature, humidity) and the packaging damage parameters. The bacterial number is detected by real-time or periodic sampling culture to verify the model output result, and the pearl material bacterial infection probability data is output to represent the microbial risk level of the finished product.

[0072] Step S335: Perform acid-base change trend analysis according to the pearl material bacterial infection probability data to obtain pearl material acid-base change trend data; In the embodiments of the present application, the correlation between the probability of bacterial infection and the change of the internal environment pH of the finished product is established. A high-sensitivity electrochemical pH sensor is arranged inside the pearl material finished product to collect the pH value change curve inside the finished product in real time. The sensor can detect the slight pH fluctuation caused by the acidic or alkaline metabolites produced in the bacterial metabolic process. These data are continuously recorded by the data acquisition system to form complete time series pH change data. At the same time, the degree of bacterial infection is determined according to the microbial detection data on the surface and inside of the finished product, including indicators such as bacterial species, quantity and growth rate. Based on the collected pH time series data and the degree of bacterial infection, a kinetic model of the accumulation of acidic and alkaline substances produced by bacterial metabolism is established. The model mathematically describes the generation rate, diffusion and interaction of bacterial metabolites with the internal environment of the finished product, simulates the accumulation process of acidic and alkaline substances under different levels of bacterial infection. Linear regression, nonlinear curve fitting or machine learning methods are used to analyze the pH change trend over time, determine the quantitative relationship between the acid-base change and the process of bacterial infection, and identify the dynamic characteristics of the acid-base change such as the change rate, peak value and stable interval. The output acid-base change trend data not only reflects the influence of bacterial infection on the internal environment of the finished product, but also provides accurate environmental parameter support for the subsequent estimation of the degree of irritant growth, ensuring that the comprehensive evaluation of the safety and stability of the material has a scientific data basis, and further guiding the optimization of production process and the formulation of quality control measures.

[0073] Step S336: estimating the degree of irritant growth of the pearl material based on the acid-base change trend data of the pearl material; In the embodiment of the present application, the pH value data at different time nodes is collected by continuously monitoring the acid-base change of the finished product of the pearlescent material according to the acid-base change trend and the stimulation reaction threshold of the material, and a complete acid-base change curve is formed. Combined with the cytotoxicity experimental data, the cytotoxicity reaction of the material to skin cells and related environmental microorganisms under different acid-base environments is determined through in vitro cell culture experiments, and the key indicators such as cell survival rate, cell apoptosis rate and inflammatory factor release are obtained, and the stimulation threshold and reaction intensity of the material in different pH value ranges are determined. Using the quantitative structure-activity relationship (QSAR) method, the acid-base value and the stimulation index are mathematically modeled to construct the functional mapping relationship between acid-base and stimulation, the specific process includes selecting an appropriate mathematical model (such as polynomial regression, support vector machine or neural network, etc.), inputting the acid-base change data and corresponding cytotoxicity indicators of multiple batches of samples, and obtaining the prediction formula of the acid-base to the stimulation index after model training and verification. Based on the model, the subsequent collected acid-base change trend data is predicted and calculated to generate a stimulation growth curve of the pearlescent material, which dynamically reflects the stimulation change trend of the finished product in the production and storage process. The stimulation growth degree data provides a quantitative basis for the safety evaluation of the finished product, helps to early warn potential skin or environmental stimulation risks, and guides production adjustment and quality control measures.

[0074] Step S337: Monitoring the deterioration trend of the finished product of the pearlescent material according to the stimulation growth degree of the pearlescent material and the oxidation decomposition trend of the surface coating layer, and obtaining the deterioration trend of the finished product of the pearlescent material.

[0075] In the embodiment of the present application, the stimulation growth degree data and the oxidation decomposition trend data are analyzed by multi-index fusion, and the two indexes are integrated by weighted average method or principal component analysis method to form a comprehensive deterioration index. By establishing the corresponding relationship between the deterioration index and the actual quality index (such as color difference, particle size change), a dynamic deterioration trend curve is formed. The deterioration trend data of the finished product of the pearlescent material is output, which provides a basis for quality safety control and subsequent production improvement. The data of each step above is linked, forming a complete monitoring link from packaging damage to finished product deterioration, ensuring accurate data transmission and rigorous logic.

[0076] Especially important is that step S34 includes the following steps: Step S341: Estimating the color difference fluctuation enhancement condition of the finished product of the pearlescent material according to the deterioration trend of the finished product of the pearlescent material; In the embodiment of the present application, after collecting the deterioration trend data of the finished pearl material, the environmental factors closely related to the deterioration process, such as humidity fluctuation, oxidation degree, acid-base change, etc. are classified and arranged, and combined with environmental accelerated aging simulation experiment, the color difference change process of the material under different environmental conditions is observed. High-resolution spectrophotometer is used to measure the color difference of multiple batches of finished products in a controlled constant temperature and humidity environment, and the illumination conditions are kept constant during the measurement process to eliminate the interference of environmental light source. The color values of each batch at different time points are recorded as time series data, and by comparing the initial color state with the change trend after multiple periods, the trend of color difference value with time is observed. When the accelerated growth of color difference change is detected, the color difference change amplitude, the fluctuation stage identification, and the structured data file containing the batch number, the measurement time, the color difference change amplitude, and the fluctuation stage identification are output as the input basis for subsequent evaluation of the color performance stability of the pearl material.

[0077] Step S342: determining the color rendering ability attenuation of the pearl material based on the color difference fluctuation enhancement condition of the pearl material; In the embodiment of the present application, the color difference fluctuation enhancement condition data obtained in the previous step is used as the basis for judgment, and the reflectivity of the pearl material under specific light source irradiation conditions is analyzed. By using a spectral color measurement device under standard lighting conditions (such as D65 daylight lamp), multi-band spectral reflectance data of the sample is collected, and the intensity change of the main reflection peak and the continuity and smoothness change of the reflection spectrum are monitored. If the reflection ability of the main peak is significantly weakened or the reflection spectrum shows abnormal phenomena such as deformation, gap, etc., it is determined that the material has attenuated in color rendering ability. At the same time, combined with artificial visual comparison experiment, the sample and standard color card are compared in different viewing angles and backgrounds, and the difference in visual perception is verified. The output content includes: reflection spectrum change information, color rendering ability attenuation degree classification, detection batch identification, and related color difference historical data traceability path, forming a data set of the color rendering ability attenuation of the pearl material.

[0078] Step S343: estimating the color deviation condition of the pearl material according to the color rendering ability attenuation of the pearl material; In the embodiment of the present application, based on the confirmed color presentation capability attenuation data, the color deviation of the pearlescent material under the natural visual identification system is further analyzed. A high-definition industrial camera is used to collect images of multiple samples in a standardized photographic environment, and a constant light source device is used to uniformly irradiate the samples to ensure the consistency and comparability of the image data. After collecting the images, an image analysis device is used to separate the main color area, the edge area and the background transition area in the image, and calculate the color deviation degree of each area in the visual channel. If the color presentation difference between the main color area and the edge area exceeds the acceptable threshold, the batch of samples is marked as color deviation abnormality. The color deviation condition data content includes visual deviation level, deviation positioning area, color tendency change direction (such as cold, warm, red, etc.), and is one-to-one corresponding with the color attenuation data of the previous link, which is used to judge the continuity and trend of the color system deviation.

[0079] Step S344: detecting the optical performance instability condition of the pearlescent material according to the color deviation condition of the pearlescent material; In the embodiment of the present application, after obtaining the color deviation condition, it is further analyzed whether the optical structure of the pearlescent material is systematically unstable. Representative samples are selected, and a laser particle size analysis device is used to measure the particle size distribution characteristics, and the concentration and dispersion of the particle size are observed. If the sample shows abnormal increase of particle size or bimodal distribution, it means that the particle structure is imbalanced, which will have adverse effects on the processes of light reflection, refraction and scattering. At the same time, a special glossiness measuring device is used to measure the gloss of the material surface, and the fluctuation of the gloss value with the storage period or environmental stress is tracked. The abnormal particle size data, abnormal gloss value and color deviation information are compared and analyzed, and when the three have relevance and show abnormalities at the same time, it is determined that the material has entered the optical performance instability state. The output data includes instability batch number, abnormal particle size interval, gloss decline degree, deviation correlation item and other detailed records.

[0080] Step S345: estimating the material dispersion performance attenuation condition according to the finished product deterioration trend of the pearlescent material; In the embodiment of the present application, the core index data affecting the dispersion performance of the pearlescent material is collected around the metamorphic trend of the material in the finished product stage. It includes monitoring the viscosity change of the material dispersion liquid, observing the particle agglomeration behavior, and measuring the surface state change. Through dynamic light scattering test on the dispersion liquid sample under constant speed stirring condition, the particle size distribution change data is obtained, and whether the particle agglomeration or stratification phenomenon occurs is judged. At the same time, the flowability parameters of the material under standard shear rate are measured by using a rotational viscometer, and the relationship between the parameters and the material metamorphic index is analyzed. For example, under high temperature and high humidity conditions, if the viscosity continues to rise and the particle distribution shows stratification trend, it is considered as a significant feature of the attenuation of dispersion performance. The structural dispersion performance attenuation data containing particle distribution offset information, flowability attenuation data, and metamorphic influence factor tracking chain are generated to comprehensively judge the stability state of the material.

[0081] Step S346: detecting the quality safety data of the pearlescent material based on the dispersion performance attenuation of the material and the optical performance instability state of the pearlescent material.

[0082] In the embodiment of the present application, on the basis of the obtained dispersion performance attenuation data and optical performance instability state, the quality safety state of the pearlescent material is comprehensively evaluated. The two data sets are time-synchronized, and the key abnormal indexes such as particle size fluctuation range, gloss change trend, dispersion uniformity grade, etc. are extracted. Data tags are established for each batch of samples. By setting a critical threshold system of multiple indexes, samples exceeding the range are classified and identified, for example, as “potential quality risk” or “high instability risk”. A unified quality risk grade division table is established, and quality safety data reports are generated based on parameters such as time, batch, and production line number. The content covers the trigger factor, associated index, detection time period, and environmental state of each abnormal event. This data serves as a core component of the material production quality safety database, providing direct data support and evaluation basis for the traceability system and production process optimization module.

[0083] Preferably, step S4 comprises the following steps: Step S41: performing data fusion processing on the quality safety data of the pearlescent material and the finished product dynamic stability of the pearlescent material to obtain material production process fluctuation characteristic data; In the embodiment of the present application, the two types of data are time and space aligned to ensure the consistency of the time stamp of data acquisition and the matching of the sampling granularity. Data preprocessing techniques such as normalization processing are used to convert quality safety indicators (such as deterioration trend, bacterial infection probability, acid-base change, etc.) and dynamic stability property parameters (such as particle size deviation degree, color difference fluctuation amplitude, etc.) into a unified numerical interval to eliminate dimensional differences. Then, using a weighted fusion algorithm, the weights of quality safety data and dynamic stability property data are set to a fixed proportion based on historical production experience and statistical analysis to ensure reasonable allocation of the contribution of the two. Through multivariate statistical analysis method, key fluctuation characteristics are extracted, time series analysis technology is used for abnormal fluctuation detection of the fused data, and material production process fluctuation characteristic data are obtained. The data reflects the combined fluctuation state of quality and stability in the production process of the pearl material, and provides an accurate basis for subsequent full-process tracing.

[0084] Step S42: performing pearl material production full-process tracing processing based on the material production process fluctuation characteristic data to obtain pearl material production full-process tracing data; In the embodiment of the present application, the material production process fluctuation characteristic data obtained in step S41 is used to carry out pearl material production full-process tracing processing. The tracing processing constructs a multi-dimensional tracing model based on time series and production nodes, which covers the complete production chain from raw material entering the factory, workshop processing, equipment running state to finished product packaging and transportation. Combined with production log data, equipment monitoring data and quality detection data, multi-source data correlation analysis is carried out, and different production stage data are linked into a chain using a unique identifier. Data mapping and indexing technology is applied to realize the construction of the tracing path, and the abnormal points identified in the fluctuation characteristic data are traced back to the specific process and equipment running state, and the pearl material production full-process tracing data is generated. The data records the parameter changes and quality safety state of each production link in detail, and forms a comprehensive production quality traceability information.

[0085] Step S43: evaluating pearl material production process defect data based on the pearl material production full-process tracing data; In the embodiment of the present application, based on the pearl material production full-process tracing data, production process defect evaluation is carried out. The evaluation compares the historical data template of the normal production process with the parameters in the current tracing data, and uses statistical control chart method to identify the deviation and abnormal section in the process. The evaluation focuses on covering raw material property change, equipment running anomaly, process parameter fluctuation, etc., and quantitatively describes the type, degree and influence of defects in combination with the deviation amplitude of quality safety indicators. The defect data is output in a structured data form, including defect category code, defect time sequence position, associated equipment and process node, etc. The defect data provides clear positioning basis for risk points and bottlenecks in the production process.

[0086] Step S44: based on the pearl material production process defect data, the pearl material production process data is processed for production process optimization to obtain pearl material production process optimization data.

[0087] In the embodiment of the application, the pearl material production process defect data obtained in step S43 is used to carry out production process optimization processing on the pearl material production process data. The optimization processing identifies the main influencing factors and their action paths based on the defect data, and uses causal relationship analysis technology to determine the influence weight of each defect parameter on the production quality. Then, by formulating targeted process parameter adjustment strategies and equipment maintenance schemes, the key process parameters such as raw material ratio, processing temperature, stirring speed, etc. are adjusted, and the equipment operation mode is optimized to reduce load fluctuation and coupling degradation. The optimization process uses a closed-loop control system to monitor the implementation effect of the optimization measures in real time, dynamically adjusts the optimization strategy combined with online quality detection data, and ensures that the optimization measures are effectively implemented to generate pearl material production process optimization data. The data contains the optimized process parameter set, equipment operation state improvement scheme and quality improvement prediction index, which serves as an important basis for subsequent production management and quality control.

[0088] The application also provides a data fusion system for pearl material production quality safety traceability, which is used to execute the data fusion method for pearl material production quality safety traceability as described above. The data fusion system for pearl material production quality safety traceability comprises: A raw material initial property determination module is used to acquire pearl material production process data, collect pearl material production workshop data based on the pearl material production process data, and determine pearl raw material initial property data based on the pearl material production workshop data and the pearl material production process data. A finished product dynamic stability property monitoring module is used to determine the material production equipment dynamic fatigue growth trend based on the pearl material production workshop data, determine the material production equipment coupling degradation condition based on the pearl raw material initial property data and the material production equipment dynamic fatigue growth trend, and monitor the pearl material finished product dynamic stability property based on the material production equipment coupling degradation condition. A pearl material quality safety detection module is used to simulate pearl material packaging and transportation based on the pearl material finished product dynamic stability property, obtain pearl material packaging and transportation simulation data, monitor the pearl material finished product deterioration trend based on the pearl material packaging and transportation simulation data, and detect pearl material quality safety data based on the pearl material finished product deterioration trend. A production process optimization processing module is used to evaluate pearl material production process defect data based on the pearl material quality safety data and the pearl material finished product dynamic stability property, and perform production process optimization processing on the pearl material production process data based on the pearl material production process defect data to obtain pearl material production process optimization data.

[0089] The foregoing is considered as illustrative only of the principles of the application. Numerous modifications and changes will readily occur to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the scope of the application is indicated by the appended claims rather than by the foregoing description, and all changes that come within the meaning and range of equivalents are intended to be embraced therein.

Claims

1. A data fusion method for quality safety traceability of production of a pearlescent material, characterized in that, The method comprises the following steps: Step S1: obtaining the whole-process data of the production of the pearlescent material; collecting the data of the production workshop of the pearlescent material based on the whole-process data of the production of the pearlescent material; and determining the initial property data of the raw material of the pearlescent material based on the data of the production workshop of the pearlescent material and the whole-process data of the production of the pearlescent material; Step S2: determining the dynamic fatigue growth trend of the material production equipment according to the data of the production workshop of the pearlescent material; determining the coupled degradation condition of the material production equipment according to the initial property data of the raw material of the pearlescent material and the dynamic fatigue growth trend of the material production equipment; monitoring the dynamic stable property of the finished product of the pearlescent material based on the coupled degradation condition of the material production equipment; Step S3: simulating the packaging and transportation of the finished product of the pearlescent material based on the whole-process data of the production of the pearlescent material to obtain the simulation data of the packaging and transportation of the finished product of the pearlescent material; and monitoring the deterioration trend of the finished product of the pearlescent material according to the simulation data of the packaging and transportation of the finished product of the pearlescent material; detecting the quality and safety data of the pearlescent material based on the deterioration trend of the finished product of the pearlescent material; Step S4: evaluating the defect data of the production process of the pearlescent material based on the quality and safety data of the pearlescent material and the dynamic stable property of the finished product of the pearlescent material; optimizing the production process based on the defect data of the production process of the pearlescent material to obtain the optimized data of the production process of the pearlescent material.

2. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 1, characterized in that, Step S1 comprises the following steps: Step S11: obtaining the whole-process data of the production of the pearlescent material; Step S12: collecting the data of the raw material of the pearlescent material based on the whole-process data of the production of the pearlescent material; Step S13: collecting the data of the production workshop of the pearlescent material based on the whole-process data of the production of the pearlescent material; Step S14: determining the initial property data of the raw material of the pearlescent material based on the data of the production workshop of the pearlescent material and the data of the raw material of the pearlescent material.

3. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 2, characterized in that, Step S14 comprises the following steps: Step S141: detecting the impurity content of the raw material of the pearlescent material to obtain the impurity content data of the raw material of the pearlescent material; Step S142: determining the heavy metal content data of the raw material of the pearlescent material according to the impurity content data of the raw material of the pearlescent material; Step S143: detecting the catalytic oxidation of the raw material of the pearlescent material according to the heavy metal content data of the raw material of the pearlescent material to obtain the catalytic oxidation condition of the raw material of the pearlescent material; Step S144: detecting the surface charge variation trend of the raw material of the pearlescent material; Step S145: measuring the temperature variation trend of the production workshop of the pearlescent material based on the data of the production workshop of the pearlescent material; Step S146: when the temperature variation trend of the production workshop of the pearlescent material exceeds ±3.2°C, determining the decrease of the electrostatic repulsion of the raw material particles according to the surface charge variation trend of the raw material of the pearlescent material; Step S147: estimating the spontaneous agglomeration condition of the raw material of the pearlescent material according to the decrease of the electrostatic repulsion of the raw material particles; Step S148: determining the initial property data of the raw material of the pearlescent material based on the spontaneous agglomeration condition of the raw material of the pearlescent material and the catalytic oxidation condition of the raw material of the pearlescent material.

4. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 1, characterized in that, In Step S2, the dynamic fatigue growth trend of the material production equipment is determined according to the data of the production workshop of the pearlescent material, which comprises the following steps: determining the structural complexity of the production workshop of the pearlescent material according to the data of the production workshop of the pearlescent material; According to the data extraction of the pearl material production workshop, the operation log of the pearl material production workshop is obtained; The time sequence analysis is performed on the operation log of the pearl material production workshop, and the time sequence data of the pearl material production workshop is obtained; Based on the time sequence data of the pearl material production workshop, the change data of the material production demand of the workshop is obtained; Based on the change data of the material production demand of the workshop, the production operation intensity fluctuation diagram of the workshop is drawn, and the operation intensity rising slope value of the workshop is calculated according to the operation intensity fluctuation diagram of the workshop; Based on the time sequence data of the pearl material production workshop, the operation state correlation analysis between the devices is performed, and the cooperative operation data of the devices in the workshop are obtained; Based on the cooperative operation data of the devices in the workshop, the coupling interference risk data between the devices is determined; When the operation intensity rising slope value of the workshop exceeds 0.87, and the coupling interference risk data between the devices is determined, the dynamic fatigue growth trend of the material production equipment is determined.

5. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 3, characterized in that, In step S2, the coupling degradation status of the material production equipment is determined according to the initial property data of the pearl raw material and the dynamic fatigue growth trend of the material production equipment, including: According to the initial property data of the pearl raw material, the initial water content of the raw material is measured; According to the initial property data of the pearl raw material, the particle size distribution status of the pearl raw material is determined; Based on the particle size distribution status of the pearl raw material and the initial water content of the raw material, the processing viscosity growth trend of the raw material is predicted; Based on the processing viscosity growth trend of the raw material, the stirring resistance rising trend of the material stirring equipment is estimated; According to the initial property data of the pearl raw material, the dynamic fluctuation of the pearl raw material rest angle is estimated; According to the dynamic fluctuation of the pearl raw material rest angle and the stirring resistance rising trend of the material stirring equipment, the abnormal situation of the shear stress of the equipment is detected; Based on the abnormal situation of the shear stress of the equipment and the dynamic fatigue growth trend of the material production equipment, the torque jitter growth trend of the equipment is estimated; According to the torque jitter growth trend, the coupling degradation status of the material production equipment is determined.

6. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 4, characterized in that, In step S2, the dynamic stability of the finished pearl material is monitored based on the coupling degradation status of the material production equipment, including: Based on the coupling degradation status of the material production equipment, the imbalance situation of the coordination degree of the material production equipment is detected; According to the imbalance situation of the coordination degree of the material production equipment, the abnormal accumulation situation of the load of the material production equipment is estimated; Based on the abnormal accumulation situation of the load of the production equipment, the running frequency drift situation of the production equipment is detected; According to the running frequency drift situation of the production equipment, the mixing failure situation of the pearl material is estimated; Based on the mixing failure situation of the pearl material, the particle size deviation degree of the pearl material is estimated; According to the particle size deviation degree of the pearl material, the color difference fluctuation situation of the finished pearl material is determined; Based on the color difference fluctuation situation of the finished pearl material and the particle size deviation degree of the pearl material, the dynamic stability of the finished pearl material is monitored.

7. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Based on the data of the whole process of the pearl material production, the dynamic stability of the finished pearl material is simulated for the packaging and transportation of the pearl material, and the packaging and transportation simulation data of the pearl material is obtained; Step S32: According to the packaging and transportation simulation data of the pearl material, the damage prediction of the packaging structure of the pearl material is performed, and the packaging structure damage data of the pearl material is obtained; Step S33: Based on the pearl material packaging structure damage data, the dynamic stability of the finished product of the pearl material is monitored for the deterioration trend of the finished product of the pearl material, and the deterioration trend of the finished product of the pearl material is obtained. Step S34: Based on the deterioration trend of the finished product of the pearl material, the quality and safety data of the pearl material are detected.

8. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 7, characterized in that, Step S33 includes the following steps: Step S331: Estimate the sealing decline of the material packaging structure based on the pearl material packaging structure damage data; Step S332: Calculate the moisture probability of the pearl material based on the sealing decline of the material packaging structure, and obtain the moisture probability data of the pearl material; Step S333: Determine the oxidation decomposition trend of the surface coating layer based on the moisture probability data of the pearl material; Step S334: Calculate the bacterial infection probability based on the pearl material packaging structure damage data and the moisture probability data of the pearl material, and obtain the bacterial infection probability data of the pearl material; Step S335: Analyze the acid-base change trend based on the bacterial infection probability data of the pearl material, and obtain the acid-base change trend data of the pearl material; Step S336: Estimate the degree of irritant growth of the pearl material based on the acid-base change trend data of the pearl material; Step S337: Monitor the deterioration trend of the finished product of the pearl material according to the degree of irritant growth of the pearl material and the oxidation decomposition trend of the surface coating layer, and obtain the deterioration trend of the finished product of the pearl material.

9. The data fusion method for quality safety traceability of pearl-oriented material production according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Perform data fusion processing on the quality and safety data of the pearl material and the dynamic stability of the finished product of the pearl material, and obtain material production process fluctuation characteristic data; Step S42: Based on the material production process fluctuation characteristic data, perform pearl material production full-process tracking processing, and obtain pearl material production full-process tracking data; Step S43: Based on the pearl material production full-process tracking data, evaluate the pearl material production process defect data; Step S44: Based on the pearl material production process defect data, perform production process optimization processing on the pearl material production whole process data, and obtain pearl material production process optimization data.

10. A data fusion system for quality safety traceability of production of a nacreous material, characterized in that, The data fusion system for tracing the quality and safety of pearl material production as claimed in claim 1 includes: Raw material initial property determination module, for acquiring pearl material production whole process data; collecting pearl material production workshop data based on pearl material production whole process data; determining pearl raw material initial property data based on pearl material production workshop data and pearl material production whole process data; Finished product dynamic stability monitoring module, for determining material production equipment dynamic fatigue growth trend according to pearl material production workshop data; determining material production equipment coupling degradation condition according to pearl material initial property data and material production equipment dynamic fatigue growth trend; monitoring the dynamic stability of the finished product of the pearl material based on the coupling degradation condition of the material production equipment; The pearl material quality safety detection module is used for simulating the packaging and transportation of the pearl material based on the whole process data of the pearl material production, obtaining the pearl material packaging and transportation simulation data, monitoring the deterioration trend of the pearl material product according to the pearl material packaging and transportation simulation data, and detecting the pearl material quality safety data based on the deterioration trend of the pearl material product. The production process optimization processing module is used for evaluating the pearl material production process defect data based on the pearl material quality safety data and the dynamic stability property of the pearl material product, performing the production process optimization processing on the whole process data of the pearl material based on the pearl material production process defect data, and obtaining the pearl material production process optimization data.

Images