System for real-time monitoring of oxidation treatment of aluminum decorative strip and adaptive adjustment of technological parameters

Abstract

The invention relates to the technical field of aluminum decorative strip oxidation treatment, and discloses an aluminum decorative strip oxidation treatment real-time monitoring and process parameter self-adaptive adjustment system which comprises a process data acquisition module, a parameter optimization module, a surface monitoring module, a parameter matching module, a process adjustment module and a parameter self-learning module. The process data acquisition module acquires data in real time and generates a related characteristic value and parameter adjustment set; the parameter optimization module is used for generating personalized process parameters and control strategies; the surface monitoring module obtains and screens abnormal surface data; the parameter matching module matches the data to generate a matching degree, and selects a target parameter; the process adjustment module drives the correction parameters; and the parameter self-learning module updates the process database according to the feedback data. The system realizes oxidation treatment real-time monitoring and process parameter self-adaptive adjustment, improves product quality and production efficiency, and is suitable for oxidation treatment of aluminum decorative strips.

Description

Technical Field

[0001] The present invention relates to the technical field of oxidation treatment of aluminum decorative strips, and in particular to a system for real-time monitoring and adaptive adjustment of process parameters of oxidation treatment of aluminum decorative strips. Background Art

[0002] Oxidation is a key process in the manufacturing of aluminum trim strips. Its goal is to form a uniform, dense, and high-performance oxide film on the surface of the aluminum trim strips, thereby improving the strips' corrosion resistance, wear resistance, and decorative properties. However, traditional oxidation treatment processes for aluminum trim strips have numerous challenges, making them difficult to meet the high-quality, high-efficiency, and high-stability requirements of modern industrial production.

[0003] In terms of process parameter control, traditional oxidation processes typically use fixed process parameters. However, in actual production, oxidation tank process parameters (such as current density, oxidizing solution concentration, and temperature) can fluctuate due to a variety of factors, including changes in equipment operating conditions, raw material differences, and production batches. Fixed process parameters cannot be adjusted to these real-time changes, resulting in inconsistent oxide film quality across batches and even within the same batch of aluminum trim. For example, unstable current density can lead to uneven oxide film growth rates, affecting film thickness and uniformity. Fluctuations in oxidizing solution concentration can affect the oxidation reaction; excessively high or low concentrations can lead to oxide film quality defects, such as loose film layers and uneven color. Temperature fluctuations can affect reaction kinetics, further impacting the performance and appearance of the oxide film.

[0004] Traditional methods for surface quality monitoring often rely on manual inspection. This approach is not only inefficient but also susceptible to human influence, making it difficult to accurately monitor the surface quality of aluminum trim during oxidation. Manual inspection cannot promptly detect anomalies during the oxidation process, such as color differences, spots, and scratches on the oxide film surface. This prevents timely adjustment of process parameters, resulting in a large number of substandard products, increased production costs, and reduced production efficiency.

[0005] Furthermore, traditional aluminum trim oxidation processes lack adaptive adjustment capabilities. When process parameter fluctuations or surface quality anomalies occur during production, the appropriate adjustment parameters cannot be quickly and accurately determined. Operators must rely on their experience to make trial adjustments, which is not only time-consuming and labor-intensive, but also difficult to guarantee effective results. Differences in operator experience and skill levels result in poor consistency and stability in process adjustments, further impacting the quality and efficiency of the aluminum trim oxidation process.

[0006] With the development of industrial automation and intelligentization, higher requirements are being placed on the oxidation treatment process for aluminum trim strips. There is an urgent need for a system that can monitor the process parameters and surface quality during the oxidation process in real time and automatically adjust the process parameters based on real-time data. This is to achieve precise control of the oxidation treatment of aluminum trim strips, improve the stability and consistency of product quality, reduce production costs, and improve production efficiency. Existing aluminum trim strip oxidation treatment technologies have obvious deficiencies in real-time monitoring and adaptive adjustment, and cannot meet the needs of modern industrial production. Therefore, the development of a new system for real-time monitoring and adaptive adjustment of process parameters for aluminum trim strip oxidation treatment is of great practical significance. Summary of the Invention

[0007] The purpose of the present invention is to provide a system for real-time monitoring and adaptive adjustment of process parameters of aluminum trim oxidation treatment to solve the problems raised in the above background technology.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment, the system comprising:

[0009] The process data acquisition module is used to collect the process parameter data and surface condition data of the aluminum trim oxidation tank in real time through the industrial Internet of Things terminal equipment, analyze and process the data to generate the characteristic values ​​of the oxide film growth rate and the dynamic parameter characteristic values ​​of the tank liquid, and generate the dynamic adjustment set of process parameters based on the initial process parameter set stored in the process database;

[0010] The parameter optimization module processes the personalized process parameters of the current batch of aluminum trim strips based on the characteristic values ​​of the oxide film growth rate and generates a dynamic oxidation control strategy;

[0011] The surface monitoring module is used to obtain real-time surface quality data of the aluminum trim during the oxidation process through a multispectral sensor, filter out abnormal surface data that meets the dynamic adjustment range, and send it to the parameter matching module;

[0012] The parameter matching module is used to perform multi-dimensional matching between abnormal surface data and each parameter item in the process parameter dynamic adjustment set, generate the matching degree between real-time data and each process parameter item, and select the process parameter corresponding to the highest matching degree as the target adjustment parameter;

[0013] The process adjustment module is used to receive the target adjustment parameters and call the parameter adjustment protocol preset in the process database to drive the oxidation tank to perform process parameter correction operations.

[0014] Preferably, the process parameter data of the aluminum trim oxidation tank is collected in real time through the industrial Internet of Things terminal device, and the specific process is:

[0015] Identify the unique identification code of the oxidation tank equipment. If it is a newly connected equipment, collect basic process parameters including initial current density, oxidation solution concentration baseline value and temperature control range, establish process characteristic nodes based on the initial data, perform parameter calibration, and generate characteristic values ​​of oxide film growth rate;

[0016] If it is a historically connected device, the historical process data set and surface quality change curve of the device are extracted. The historical process data set includes current fluctuation extremes, concentration deviation records, and temperature control delay duration, and is marked as the initial parameter set for the current process analysis.

[0017] Preferably, generating a dynamic adjustment set of process parameters based on an initial process parameter set stored in a process database specifically includes:

[0018] Extracting an initial standard set and a dynamic correction coefficient set of each process parameter from a process database, wherein the initial standard set includes: a current density safety range, a concentration fluctuation tolerance range, and a temperature adjustment reference value;

[0019] The dynamic correction coefficient set includes a current density compensation coefficient, a concentration gradient adjustment coefficient and a temperature response weight parameter;

[0020] Based on the real-time bath liquid dynamic parameter characteristic values, the initial standard set of each process parameter is dynamically adjusted, and the adjusted parameter set is recorded as the process parameter dynamic adjustment set;

[0021] The process parameter dynamic adjustment set includes the current dynamic range, concentration adaptability threshold and temperature optimization control value of each parameter item.

[0022] Preferably, the processing based on the characteristic value of the oxide film growth rate to obtain the personalized process parameters of the current batch of aluminum trim strips and generate a dynamic oxidation control strategy specifically includes:

[0023] According to the characteristic value of the oxide film growth rate, pattern matching is performed with the preset oxidation process characteristic library to determine the priority sequence of process parameter adjustment;

[0024] An adaptive control strategy including parameter triggering conditions, adjustment step rules and fault handling mechanism is generated based on the adjustment priority sequence.

[0025] Preferably, the acquiring of real-time surface quality data of the aluminum trim strip during oxidation by a multispectral sensor specifically includes:

[0026] Monitor the real-time spectral data stream of the oxide film formation process, including film thickness variation, surface uniformity index and color difference fluctuation value;

[0027] When the real-time spectral data stream exceeds the preset qualified process range, the abnormal flag is activated and the surface data of the abnormal period is extracted as effective monitoring data.

[0028] Preferably, the matching degree between the generated real-time data and each process parameter item specifically includes:

[0029] Analyze the thickness deviation, uniformity gradient, and color difference fluctuation amplitude in abnormal surface data, and perform difference calculations with the current dynamic range, concentration adaptability threshold, and temperature optimization control value of each process parameter;

[0030] Based on the difference calculation results, a matching index between real-time data and each process parameter item is generated.

[0031] Preferably, the process parameters corresponding to the highest matching degree are selected as target adjustment parameters, specifically including:

[0032] Establish a matching ranking list of each process parameter item, and select the parameter item with the highest matching degree in the list;

[0033] If the first matching degree is lower than the preset adjustment trigger threshold, the backup parameter set is called and the matching degree is recalculated.

[0034] Preferably, the matching index between the real-time data and each process parameter item is generated based on the difference calculation result, and the specific processing process is as follows:

[0035] A multi-dimensional matching algorithm is used to normalize the current difference, concentration gradient and temperature deviation to generate a process parameter matching value ranging from 0 to 100.

[0036] The closer the matching value is to 100, the stronger the adaptability of real-time data and process parameters is.

[0037] Preferably, the system further includes a parameter self-learning module, specifically including:

[0038] Record the oxide film quality feedback data after each process adjustment, including actual film thickness uniformity, surface gloss change and color difference control effect;

[0039] The feedback data is reversely verified with the dynamic adjustment set of process parameters to generate parameter correction factors and update the dynamic correction coefficient set to the process database.

[0040] Preferably, the generating parameter correction factor specifically includes:

[0041] Based on the degree of deviation between the feedback data and the expected process target, the current compensation factor, concentration adjustment factor and temperature optimization weight are calculated;

[0042] The exponentially weighted average algorithm is used to dynamically smooth the historical correction factors to generate a new set of dynamic correction coefficients.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] In terms of real-time monitoring capabilities, the process data acquisition module can collect the process parameter data and surface status data of the aluminum trim oxidation tank in real time through the industrial Internet of Things terminal equipment. For newly connected equipment, basic process parameters such as initial current density and oxidation liquid concentration baseline value can be collected to establish process feature nodes and perform parameter calibration; for historically connected equipment, historical process data sets and surface quality change curves are extracted to provide rich and accurate data support for subsequent process analysis and adjustments. The surface monitoring module uses a multi-spectral sensor to obtain real-time spectral data streams during the oxidation process of aluminum trim, including film thickness change values, surface uniformity indicators, and color difference fluctuation values. It can promptly detect abnormal surface quality during the oxidation process, realize dynamic and real-time monitoring of the oxidation process, and change the lag and inaccuracy of traditional manual detection.

[0045] In terms of adaptive adjustment of process parameters, the system can automatically generate dynamic adjustment sets of process parameters and personalized process parameters based on real-time monitored data. The process data acquisition module dynamically adjusts the initial standard set of each process parameter based on the initial process parameter set stored in the process database, combined with the real-time bath liquid dynamic parameter characteristic values, to generate a dynamic adjustment set of process parameters, including current dynamic range, concentration adaptability threshold, and temperature optimization control value. The parameter optimization module performs pattern matching based on the oxide film growth rate characteristic value and the preset oxidation process characteristic library to determine the process parameter adjustment priority sequence and generate an adaptive control strategy that includes parameter trigger conditions, adjustment step rules, and fault handling mechanisms, thus realizing personalized process parameter settings for the current batch of aluminum trim strips. When the surface monitoring module detects abnormal surface data, the parameter matching module matches the abnormal surface data with each parameter item in the dynamic adjustment set of process parameters through a multi-dimensional matching algorithm, generates a matching index between the real-time data and each process parameter item, and selects the process parameter corresponding to the highest matching degree as the target adjustment parameter. The process adjustment module receives the target adjustment parameter and drives the oxidation tank to perform process parameter correction operations, realizing rapid and precise adjustment of process parameters, improving the efficiency and accuracy of process adjustment, and avoiding the blindness and uncertainty of traditional adjustment relying on manual experience.

[0046] In terms of system self-learning and optimization, the parameter self-learning module records feedback data on oxide film quality after each process adjustment, including actual film thickness uniformity, surface gloss changes, and color difference control effects. This feedback data is then reverse-verified against the dynamic process parameter adjustment set to generate parameter correction factors. This historical correction factors are dynamically smoothed using an exponentially weighted average algorithm, and the dynamic correction coefficient set in the process database is updated. This allows the system to continuously accumulate experience and automatically optimize process parameters based on actual production conditions, improving the system's adaptability and stability. As production progresses, the system's control effectiveness will continue to improve, further ensuring the stability and consistency of the oxidation treatment quality of aluminum trim strips.

[0047] Through the synergistic effect of the above aspects, the system realizes the automation and intelligent control of the oxidation treatment process of aluminum trim strips, significantly improves product quality, reduces the unqualified rate, reduces the cost of manual inspection and process adjustment, and improves production efficiency. It has good economic and social benefits and provides new directions and ideas for the development of oxidation treatment technology for aluminum trim strips. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a working principle diagram of the system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to the present invention;

[0049] Figure 2 This is the working principle diagram of the process data acquisition module;

[0050] Figure 3 Schematic diagram generated for dynamic adjustment of process parameters. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0052] See also Figure 1-Figure 3 The present invention relates to a system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment, which includes:

[0053] Process data acquisition module, parameter optimization module, surface monitoring module, parameter matching module and process adjustment module.

[0054] The process data acquisition module performs the following operations through the industrial Internet of Things terminal device: real-time collection of process parameter data (such as current density, oxidation liquid concentration, temperature, etc.) and surface state data of the aluminum trim oxidation tank, analysis and processing of the collected data, and generation of characteristic values ​​of the oxide film growth rate and characteristic values ​​of the tank liquid dynamic parameters (such as concentration change gradient, temperature response delay, etc.); at the same time, based on the initial process parameter set stored in the process database (including basic parameters such as the current density safety range and the concentration fluctuation tolerance range), combined with real-time data, a dynamic adjustment set of process parameters is generated (including adjustable parameter items such as the current dynamic range and the concentration adaptability threshold).

[0055] The parameter optimization module matches the characteristic value of the oxide film growth rate with the preset oxidation process feature library to determine the priority sequence of process parameter adjustment (for example, current density adjustment takes precedence over temperature adjustment). It then generates a dynamic oxidation control strategy that includes parameter trigger conditions (for example, current adjustment is triggered when the film thickness growth rate is lower than the threshold), adjustment step rules (for example, increasing current density in stages), and fault handling mechanisms (for example, out-of-range alarm shutdown), and accordingly obtains the personalized process parameters for the current batch of aluminum trim strips.

[0056] The surface monitoring module continuously obtains real-time spectral data streams during the oxidation process of aluminum trim strips through multi-spectral sensors, including real-time surface quality data such as film thickness change values, surface uniformity indicators, and color difference fluctuation values. When the real-time spectral data stream is detected to exceed the preset qualified process range, the abnormality mark is activated and the surface data of the abnormal period (such as thickness deviation, uniformity mutation value, etc.) is extracted as effective monitoring data. The abnormal surface data that meets the dynamic adjustment range is screened out and sent to the parameter matching module.

[0057] The parameter matching module receives abnormal surface data, analyzes characteristic parameters such as thickness deviation, uniformity change gradient and color difference fluctuation amplitude, and calculates the difference with the current dynamic range, concentration adaptability threshold and temperature optimization control value in the dynamic adjustment set of process parameters. A multi-dimensional matching algorithm is used to standardize the current difference, concentration gradient and temperature deviation to generate a process parameter matching value in the range of 0-100 (the closer the matching value is to 100, the stronger the adaptability). A matching ranking list of each process parameter item is established, and the parameter item corresponding to the first matching degree in the list is selected as the target adjustment parameter. If the first matching degree is lower than the preset adjustment trigger threshold (such as lower than 60), the backup parameter set is called and the matching degree calculation is re-performed.

[0058] The process adjustment module receives the target adjustment parameters, calls the parameter adjustment protocol preset in the process database (such as current adjustment step rules, concentration addition ratio rules, etc.), drives the oxidation tank to perform process parameter correction operations (such as automatically adjusting the power supply output current, starting the liquid replenishment pump to add concentrate, etc.), and realizes real-time correction of process parameters.

[0059] The present invention will be further described below in conjunction with Examples 1 to 5:

[0060] Example 1

[0061] The system's process data collection module implements a differentiated data collection process based on the connected oxidation tank equipment. For newly connected equipment, the system first identifies the device using its unique identification code, which can be obtained through the device nameplate, the device ID field specified in the Industrial Internet of Things protocol, or the electronic tag built into the sensor module. After identifying the newly connected device, the system initiates the initial data collection process, collecting basic process parameters, including initial current density, baseline oxidizing solution concentration, and temperature control range. The initial current density collection range is predefined within a safe range based on the oxidation process type and the aluminum trim material. For example, for conventional aluminum alloy trim, the initial current density can be collected within a range of 1.5-2.5 A / dm², determined by industry standard process parameters stored in the process database. The baseline oxidizing solution concentration is collected based on the oxidizing solution type. For example, for sulfuric acid anodizing, the baseline concentration is collected within a range of 180-200 g / L, which meets the typical concentration requirements for sulfuric acid anodizing. The temperature control range is set based on the thermodynamic characteristics of the oxidation reaction and is typically collected within a range of 20-30°C to ensure stable oxide film growth.

[0062] Based on the basic process parameter data collected for the first time, the system establishes a process feature node. The process of establishing a process feature node includes associating and mapping parameters such as the initial current density, concentration baseline value, and temperature control range with the oxide film growth rate. For example, the coordinate parameters of the first process feature node are established by the measured value of the film thickness growth rate at an initial current density of 1.5A / dm², a concentration of 180g / L, and a temperature of 20°C. Parameter calibration is then performed, and the calibration process is achieved by comparing the deviation between the theoretical calculated value and the measured value. The theoretical calculated value is derived based on Faraday's law and the oxide film growth model. For example, the theoretical film thickness is calculated based on the current density and time, and compared with the measured film thickness. If the deviation exceeds a preset threshold (such as ±5%), the initial parameters are corrected. The correction method includes linear interpolation adjustment or proportional coefficient correction, and finally the oxide film growth rate characteristic value is generated. This characteristic value includes parameters such as the film thickness growth per unit time and the growth rate fluctuation coefficient.

[0063] For historically connected equipment, the system searches the process database through the equipment's unique identification code to extract the equipment's historical process data set and surface quality change curve. The historical process data set contains historical parameters such as current fluctuation extremes, concentration deviation records, and temperature control delay time. The current fluctuation extremes record the highest and lowest current density values ​​of the equipment during the previous oxidation process. For example, the historical current fluctuation extremes of a certain device are 1.2-2.8A / dm², reflecting the current stability of the device in different batches of production; the concentration deviation record stores the amplitude and duration of the oxidation solution concentration deviation from the baseline value. For example, a concentration deviation of +15g / L lasted for 30 minutes, reflecting the fluctuation of concentration control; the temperature control delay time refers to the time interval from the system receiving the temperature adjustment command to the actual temperature reaching the target value. For example, the temperature control delay time of a certain device is 15 minutes, reflecting the response characteristics of the equipment temperature control system.

[0064] The surface quality change curve is generated from surface monitoring data from historical production processes and includes trends in film thickness uniformity over time, surface gloss fluctuation curves, and color difference evolution trajectories. For example, during the oxidation process of a batch of aluminum trim strips, the standard deviation of film thickness uniformity gradually increased from 2μm to 5μm within 0-30 minutes, and then decreased to 3μm after adjusting the current density, forming a specific fluctuation curve; surface gloss increased rapidly in the early stages of oxidation, reaching a peak and then stabilizing, reflecting the staged characteristics of oxide film formation; the color difference fluctuation curve records the degree of color deviation from the standard value during the oxidation process, such as the process in which the ΔE value in the CIELab color space gradually increases from 1.0 to 2.5, and then decreases to 1.5 through process adjustments.

[0065] The system marks the extracted historical process data sets and surface quality change curves as the initial parameter set for the current process analysis. This initial parameter set serves as a baseline reference for the current batch production and is used for trend analysis and deviation comparison when dynamically adjusting process parameters. For example, in the current batch production, if the real-time monitored current density fluctuations approach historical fluctuation extremes, the system can trigger an early warning mechanism or adjust the dynamic correction factor to avoid exceeding the safety range. If the surface quality change curve shows that the current film thickness uniformity change trend is similar to that of a historical batch, the system can directly call the process parameter adjustment strategy for that batch to improve adjustment efficiency.

[0066] During data collection, IIoT terminal devices acquire multi-dimensional data through a sensor network. Current density data is collected in real time using a Hall effect current sensor installed in the oxidation tank power circuit, with an accuracy of ±1%. Oxidation solution concentration data is measured using an online concentration meter, such as a conductivity sensor or refractometer, which converts the solution's conductivity or refractive index to a concentration value with a resolution of 0.1 g / L. Temperature data is collected using a Pt100 temperature sensor placed in the oxidation tank solution, with an accuracy of ±0.5°C. Surface condition data is acquired using image acquisition devices or spectral sensors, such as using a linear array CCD camera to capture images of the aluminum trim surface, or using a multispectral sensor to collect reflectance spectral data for subsequent analysis of oxide film growth rate and surface quality.

[0067] In terms of data transmission, IIoT terminal devices transmit collected real-time data to the processing unit of the process data acquisition module via wired networks (such as Ethernet) or wireless networks (such as Wi-Fi and 5G). The processing unit utilizes an edge computing architecture to preprocess the raw data, including denoising filtering, data normalization, and feature extraction. Denoising filtering uses median filtering or Kalman filtering algorithms to remove random noise, ensuring data reliability. Data normalization converts parameters of different dimensions into a uniform range of values ​​for subsequent analysis. Feature extraction extracts characteristic values ​​of the oxide film growth rate and the dynamic parameters of the bath solution from the raw data. For example, differential calculations are used to determine the concentration gradient, and delay estimation algorithms are used to determine the temperature response delay.

[0068] The process data acquisition module also features data storage and query capabilities, storing collected historical data and generated characteristic values ​​in a process database to form equipment archives and process history records. This stored data can be used for subsequent process optimization, equipment performance evaluation, and fault tracing. For example, by analyzing a certain equipment's historical process data set, it is possible to identify patterns in which temperature control delay increases with equipment age, enabling the development of targeted maintenance plans. By comparing surface quality curves across batches, it is possible to optimize the initial set of process parameters and improve process stability.

[0069] Example 2:

[0070] When the system's process data acquisition module generates a dynamic adjustment set of process parameters, it extracts the initial standard set and dynamic correction coefficient set from the process database and adjusts the parameters based on the real-time bath liquid dynamic parameter characteristic values. The following describes this process in detail with reference to specific scenarios:

[0071] For example, a sulfuric acid anodizing process is used in an aluminum trim oxidation tank. The initial standard set stored in the process database includes a current density safety range of 1.0-3.0 A / dm², a concentration fluctuation tolerance of ±10 g / L (based on a baseline of 200 g / L), and a temperature control baseline of 25°C. The dynamic correction coefficient set includes a current density compensation factor of ±0.1 A / dm² / μm (indicating an adjustment of 0.1 A / dm² for every 1 μm deviation from the target film thickness growth rate), a concentration gradient adjustment factor of ±5 g / L / ‰ (adjusting the concentration threshold by 5 g / L for every detected concentration change rate exceeding 1‰ / min), and a temperature response weight parameter of 0.8-1.2 (used to adjust the weight of the temperature's influence on the film thickness growth rate).

[0072] During a production batch, the following dynamic bath parameter characteristics were collected by online sensors: the measured oxidizing solution concentration was 185g / L and continuously decreasing at a rate of 2‰ / min; the measured temperature was 28°C, fluctuating within ±1.5°C; and the current film thickness growth rate was 0.18μm / min, which was 0.2μm / min below the preset target. Based on this real-time data, the system initiated a dynamic adjustment process:

[0073] First, consider the concentration parameters. The initial concentration baseline value is 200 g / L. The measured value of 185 g / L deviates from the baseline by 15 g / L, exceeding the initial tolerance range of ±10 g / L. Furthermore, the concentration rate of change is -2‰ / min (a negative sign indicates a decrease), exceeding the trigger threshold of 1‰ / min. Based on the concentration gradient adjustment coefficient of ±5 g / L / ‰ in the dynamic correction coefficient set, the concentration adaptation threshold adjustment is calculated as: 2‰ / min × 5 g / L / ‰ = 10 g / L. Therefore, the lower limit of the concentration after dynamic adjustment is adjusted from the initial 190 g / L (200 - 10) to 180 g / L (200 - 10 - 10), while the upper limit remains unchanged at 210 g / L, resulting in a new concentration adaptation threshold of 180-210 g / L.

[0074] Next, the current density parameters were adjusted. Since the film thickness growth rate was lower than the target value of 0.02μm / min, the current density compensation factor of ±0.1A / dm² / μm was used to calculate the current density compensation: -0.02μm / min × 0.1A / dm² / μm = -0.002A / dm² (the negative sign indicates that the current density needs to be reduced to slow the growth rate). However, this needs to be considered in light of the current density safety range: the initial safety range is 1.0-3.0A / dm². The current density is currently measured at 2.5A / dm², so after adjustment, it is 2.5-0.002 = 2.498A / dm², which is still within the safety range. Therefore, the current dynamic range maintains its initial lower limit of 1.0A / dm², while the upper limit is adjusted to 2.5A / dm² (based on the current measured value and the compensation amount to avoid over-adjustment), resulting in a new current dynamic range of 1.0-2.5A / dm².

[0075] In terms of temperature parameter adjustment, the measured temperature is 28°C, which is higher than the reference value of 25°C, and the fluctuation range exceeds the initial allowable range (usually the default fluctuation range is ±1°C). The temperature response weight parameter is used to adjust the weight of the influence of temperature on the film thickness growth rate. The current measured temperature is too high, and the system automatically increases the temperature response weight from the default value of 1.0 to 1.1 to enhance the regulatory effect of temperature on the growth rate. Based on the temperature adjustment reference value of 25°C and the real-time temperature of 28°C, the calculated temperature optimization control value is 25°C + (28°C - 25°C) × 1.1 = 28.3°C, but it needs to be limited to the temperature range allowed by the process (such as 20-30°C). Therefore, the final temperature optimization control value is set to 28°C, and the temperature control priority is raised to second in the current adjustment sequence (second only to concentration adjustment).

[0076] During these adjustments, the system needs to verify the relevance of each parameter adjustment. For example, a decrease in concentration may reduce solution conductivity, and a simultaneous decrease in current density may further affect film thickness uniformity. Therefore, when generating a dynamic process parameter adjustment set, the system uses parameter association models stored in the process database (such as the concentration and current density synergy curve) to ensure that the adjusted parameter combination (concentration 180-210g / L, current 1.0-2.5A / dm², temperature 28°C) has a successful case in historical process data to avoid parameter conflicts.

[0077] In another scenario, if the oxidation tank liquid experiences an increase in impurity ion concentration (e.g., copper ion content) due to prolonged use, real-time monitoring reveals abnormalities in the dynamic parameter characteristics of the tank liquid: the concentration change rate fluctuates dramatically (±3‰ / min), and the temperature control delay increases from the historical average of 10 minutes to 15 minutes. In this case, the system automatically calls a backup coefficient set from the dynamic correction coefficient set: the concentration gradient adjustment coefficient is temporarily adjusted from ±5g / L / ‰ to ±8g / L / ‰ to account for the rapid concentration fluctuations; the lower limit of the temperature response weight parameter is reduced from 0.8 to 0.6 to reduce the sensitivity of temperature adjustments and avoid over-adjustments caused by temperature control delays. After these adjustments, the concentration adaptability threshold range is expanded to 175-225g / L (200±25g / L), the current dynamic range remains unchanged at 1.0-3.0A / dm² (because the impact of impurities is primarily concentration-dependent), and the optimized temperature control value is set to 25°C±2°C (increasing the fluctuation tolerance range).

[0078] To ensure real-time parameter adjustments, the system collects and analyzes data once per second through the edge computing units of industrial IoT terminal devices, ensuring that the dynamic adjustment set is updated every five minutes. For example, if the concentration change rate slows from -2‰ / min to -1‰ / min within 10 minutes, the system automatically adjusts the lower limit of the concentration adaptability threshold from 180g / L to 185g / L during the second update, gradually converging to near the initial baseline value, demonstrating the gradual nature of adaptive adjustments.

[0079] After the dynamic adjustment set of process parameters is generated, the system synchronizes it to the parameter optimization module and the parameter matching module. Based on the current dynamic range and concentration adaptability threshold in the set, and combined with the material characteristics of the current batch of aluminum trim strips (such as the low oxidation difficulty of 6063 aluminum alloy), the parameter optimization module further refines the personalized parameters: the initial current density value is set to 2.0A / dm² (in the middle of the dynamic range), and the concentration control target value is set to 195g / L (close to the baseline value and leaving room for decrease). The parameter matching module uses this set as a matching benchmark. When the subsequent surface monitoring module detects a decrease in film thickness uniformity, it can quickly match the current dynamic range and temperature optimization control value in the set to determine the adjustment direction.

[0080] Throughout the entire generation process, the process database serves as a core support, storing over 1,000 historical process parameter combinations and their corresponding surface quality data, forming an empirical knowledge base for parameter adjustments. For example, when the system detects a simultaneous decrease in concentration and increase in temperature, it can retrieve historical adjustment examples from the database under similar conditions (e.g., adjusting the lower concentration limit to 180g / L and the upper temperature limit to 28°C in a particular batch resulted in improved film thickness uniformity). The parameter adjustment range from that case can be directly used as a reference, shortening calculation time and improving adjustment accuracy.

[0081] Example 3:

[0082] The parameter optimization module generates a dynamic oxidation control strategy based on the oxide film growth rate characteristic value, which requires a combination of process feature library matching and parameter priority logic. The specific implementation method is detailed below:

[0083] For example, let's assume a batch of aluminum trim strips is made of AA6061 aluminum alloy. The oxidation process goal is to produce an anodic oxide film with a thickness of 20μm. A pre-set oxidation process feature library stores film growth rate models for different current density, concentration, and temperature combinations. This process feature library is constructed based on historical process data. For example, it includes typical parameter combinations such as Condition A (current density 2.0A / dm², concentration 200g / L, temperature 25°C, film growth rate 0.2μm / min) and Condition B (current density 2.5A / dm², concentration 190g / L, temperature 28°C, film growth rate 0.25μm / min), along with their corresponding growth rate characteristic values.

[0084] In real-time processing, the process data acquisition module generated an oxide film growth rate characteristic value of 0.16μm / min (measured value), which is lower than the target value of 0.2μm / min. The parameter optimization module first matches this characteristic value with the model in the process feature library and uses the Euclidean distance algorithm to calculate the difference between the measured value and each operating condition. The formula is:

[0085]

[0086] in, is the difference, is the measured growth rate (unit: μm / min), The process feature library The growth rate of the group condition, is the measured concentration (unit: g / L), is the concentration corresponding to the working condition, is the measured temperature (unit: °C), is the temperature of the corresponding working condition, and is the weight coefficient of concentration and temperature (default , , showing that concentration has a more significant effect on growth rate).

[0087] Through calculation, the difference between the measured value and working condition A , the difference from working condition B Condition A was determined to be the most suitable mode. Based on the parameter deviations in Condition A (the measured current density was 1.8A / dm², lower than the 2.0A / dm² in Condition A), the priority order for process parameter adjustments was determined to be: current density adjustment > concentration adjustment > temperature adjustment. This priority is based on oxidation process principles: current density directly affects the electrochemical reaction rate and is the most direct factor controlling film thickness growth; concentration fluctuations affect solution conductivity, which is secondary; and temperature primarily affects the reaction activation energy and has the lowest adjustment priority.

[0088] Based on the priority sequence, the system generates a dynamic oxidation control strategy. First, the parameter trigger condition is set: when the growth rate is lower than 0.18μm / min for 10 consecutive minutes, the current density adjustment is triggered. The adjustment step rules are divided into three stages: in the first stage, the current density is increased from 1.8A / dm² to 2.0A / dm² and monitored continuously for 15 minutes; if the growth rate does not meet the standard (still <0.2μm / min), the concentration is increased from 195g / L to 200g / L in the second stage, while maintaining the current density at 2.0A / dm², and monitoring is continued for another 15 minutes; if it still does not meet the standard, the temperature is increased from 23℃ to 25℃ in the third stage, forming a combined adjustment.

[0089] The fault handling mechanism includes: if the growth rate is still lower than 0.15μm / min after three adjustments, it is judged as an abnormal operating condition, triggering an alarm and automatically suspending the oxidation tank operation. At the same time, a fault log is generated (recording current parameters, adjustment history and abnormal characteristics) for manual investigation. In addition, in the personalized parameter processing of AA6061 material, the system retrieves the historical correction coefficient of the material in the process database (such as the current density sensitivity coefficient + 0.1A / dm²·μm - ¹), reducing the current density adjustment step from the default 0.2A / dm² to 0.1A / dm² to avoid excessive current surges due to differences in material conductivity.

[0090] In another application scenario, if the measured oxide film growth rate is 0.25μm / min (0.2μm / min higher than the target), the system matches the process feature library and finds that it matches the operating condition B (high current density, low concentration, high temperature) mode. In this case, the adjustment priority sequence is: current density reduction > temperature reduction > concentration increase. The trigger condition is set as the growth rate > 0.23μm / min for 5 consecutive minutes. The adjustment steps are as follows: first, reduce the current density from 2.8A / dm² to 2.5A / dm², and simultaneously reduce the temperature from 28°C to 25°C to achieve a coordinated adjustment. If the growth rate does not return to the target range after 30 minutes, then increase the concentration from 185g / L to 195g / L, indirectly reducing the effective current density by increasing the solution resistance.

[0091] The parameter optimization module also needs to deal with multi-parameter coupling effects. For example, when the current density increases, the heat released by the oxidation reaction may cause the temperature to passively increase. The system foresees this coupling relationship through historical data in the process database. While adjusting the current density, the temperature control target value is lowered by 1°C in advance to offset the effect of the reaction heat release and maintain temperature stability. In addition, in view of the surface pretreatment differences of different batches of aluminum trim strips (such as the degree of mechanical polishing affecting the film formation rate), the system automatically adjusts the matching weight of the process feature library through the input pretreatment process code (such as P01 for rough polishing and P02 for fine polishing): the film formation rate of fine polished workpieces is usually 10% faster than that of rough polishing. Therefore, the tolerance for growth rate deviation is expanded to ±0.02μm / min during matching to avoid misadjustment due to pretreatment differences.

[0092] After the dynamic oxidation control strategy is generated, the system converts it into an executable parameter instruction sequence, such as:

[0093] Current density adjustment command: +0.2A / dm² (relative to the current value), execution time t=0min;

[0094] Concentration monitoring instruction: detect the concentration value every 5 minutes, if it is less than 190g / L, trigger the rehydration pump;

[0095] Temperature adjustment instruction: If the current density is ≥2.0A / dm² after 30 minutes, the cooling system will be started to control the temperature at 24±1℃.

[0096] These instructions are transmitted to the oxidation tank's control system via an industrial bus (such as PROFINET), enabling automatic parameter adjustment. Furthermore, the strategy's time parameters (such as monitoring intervals and adjustment delays) are set based on the device's response characteristics. For example, if the oxidation tank's current adjustment response time is 2 minutes, the interval between two adjustments should be at least 5 minutes to ensure the full effect of the previous adjustment.

[0097] The process feature library is updated throughout the entire process. After each completed batch, the system stores the actual process parameters (such as a final current density of 2.2 A / dm², a concentration of 198 g / L, and a temperature of 25°C) and the corresponding growth rate (0.21 μm / min) in the process feature library, expanding the model's coverage. New parameter combinations (such as a current density of 3.0 A / dm² and a concentration of 210 g / L) are automatically marked as "pending verification conditions." Surface quality data collected under these conditions will be prioritized in subsequent production runs, gradually improving model accuracy.

[0098] Example 4:

[0099] The surface monitoring module uses a multispectral sensor to obtain real-time surface quality data during the oxidation process of aluminum trim strips. This is illustrated using the oxidation production of AA6063 aluminum alloy trim strips as an example. The system utilizes a multispectral sensor based on visible-near infrared spectroscopy, integrated with a 400-1000nm spectral acquisition unit. Installed 20cm above the oxidation tank outlet, the sensor dynamically scans the surface of the aluminum trim strips on the conveyor belt at a vertical viewing angle, acquiring 10 sets of spectral data per second and simultaneously recording the acquisition timestamp.

[0100] During the initial stages of oxide film formation (0-15 minutes), the sensor continuously monitors the spectral data stream and analyzes key parameters. The film thickness change is calculated using a spectral reflectance model. For example, when an oxide film begins to form on the surface of an aluminum substrate, the reflectance at a wavelength of 450nm gradually decreases from 85% of aluminum. Based on the mapping relationship between the Fresnel reflection formula and film thickness, the real-time film thickness can be calculated. Assuming that the spectral data at a certain moment shows a reflectance of 72% at 450nm, corresponding to a film thickness of 2.3μm, the thickness change is +0.2μm compared to the previous moment (2.1μm). The surface uniformity index is obtained by calculating the spectral difference coefficient of different pixels within the same scan line. For example, the surface of the decorative strip is divided into 10 detection areas, 50 spectral samples are extracted from each area, and the standard deviation of the spectral mean of each area is calculated. If the standard deviation of a certain area is 8%, the uniformity index is 8%. The color difference fluctuation value is calculated using the CIELab color space. Taking the L*=85, a*=0, b*=5 of the aluminum material before oxidation as the benchmark value, when the real-time spectrum data is converted to L*=83, a*=+1.2, b*=6.5, the color difference ΔE=√[(83-85)²+(1.2-0)²+(6.5-5)²]≈2.5.

[0101] When a batch of aluminum trim strips was oxidized for 20 minutes, the sensor detected the following anomalies: the film thickness change value dropped sharply from 0.15μm / min to 0.08μm / min within 18-20 minutes, the surface uniformity index increased sharply from 5% to 12%, and the color difference fluctuation value ΔE increased from 1.8 to 3.0. These parameters exceeded the preset qualified process range (thickness change rate ≥ 0.1μm / min and ≤ 0.2μm / min, uniformity ≤ 8%, ΔE ≤ 2.5). The system immediately activated the anomaly flag and extracted the surface data from the abnormal period (18-22 minutes) as valid monitoring data. Specifically, it included:

[0102] Continuous spectrum sampling points: one set of spectrum data every 10 seconds, a total of 24 sets, including reflectance at each wavelength, calculated film thickness, real-time uniformity value and color difference ΔE value;

[0103] Corresponding process parameter timestamps: for example, at 18:05, current density 2.2A / dm², concentration 195g / L, and temperature 26°C; at 18:10, current density 2.3A / dm², concentration 193g / L, and temperature 27°C;

[0104] Surface image features: Pseudo-color images reconstructed from spectral data show a band-like area of ​​low reflectivity in the middle of the trim, presumably due to uneven oxide film thickness.

[0105] During the abnormal surface data screening process, the system first eliminates accidental fluctuations caused by conveyor belt vibration (for example, data with a vibration amplitude greater than 0.5mm is automatically marked as invalid). It also avoids false alarms by setting a time window (for example, an abnormality is triggered only when three consecutive samples exceed the threshold). In this example, the thickness change rate is less than 0.1μm / min for four consecutive samples, and the uniformity exceeds 10% twice in a row, meeting the abnormality trigger conditions. Therefore, the data is confirmed to be valid and sent to the parameter matching module.

[0106] The multispectral sensor's calibration mechanism ensures data reliability. Before daily startup, the system automatically performs white plate calibration (100% reflectance) and dark current calibration (detecting noise by blocking the light source). After calibration, the spectral acquisition error remains within ±2%. During production, a standard oxide film sample (10μm thickness, 3% uniformity, ΔE = 1.0) is inserted hourly for real-time verification. If the measured value deviates from the standard by more than 5%, a drift correction algorithm is automatically activated, adjusting the spectrum-parameter conversion model through polynomial fitting.

[0107] Monitoring priorities are dynamically adjusted at different process stages. During the initial oxidation phase (0-10 minutes), the system focuses on monitoring whether the film thickness growth rate reaches the theoretical value (e.g., 0.15-0.2μm / min). If it falls below the lower limit, current density adjustment is triggered in advance. During the mid- to late-stage oxidation phase (10-30 minutes), uniformity and color difference become the primary monitoring indicators. For example, when the film thickness approaches the target value of 20μm, uniformity must be controlled to ≤6% and ΔE ≤2.0. Otherwise, concentration or temperature adjustments are made to improve surface quality.

[0108] For aluminum trim strips with complex geometries (such as those with grooves or curved surfaces), the multispectral sensor utilizes a two-dimensional scanning mechanism to monitor surfaces with varying curvatures. For example, the spectral acquisition angle in the trim strip groove area is adjusted to 45° to avoid interference from direct light reflections. A curvature compensation factor is also added to the algorithm (for example, when the groove depth is greater than 2mm, the calculated film thickness is multiplied by a correction factor of 1.1) to ensure data consistency across different regions.

[0109] In terms of data transmission, real-time spectral data streams are transmitted via Gigabit Ethernet to the edge computing server. The server's onboard FPGA chip performs real-time analysis of the spectral data, with a latency of less than 500ms from raw spectral data to the generation of parameters such as thickness, uniformity, and color difference. When abnormal data is triggered, the edge computing server simultaneously sends an early warning signal to the parameter matching module, initiating multi-threaded processing: while continuing to collect real-time data, the abnormal period data is packaged and stored on a solid-state drive for subsequent retrospective analysis.

[0110] The surface monitoring module's historical data storage strategy utilizes a tiered storage strategy: real-time data is retained for the last 24 hours for real-time analysis; daily data is compressed and stored on a disk array for a three-month retention period; and key abnormal data (such as uniformity > 15% or ΔE > 3.0) is automatically backed up to a cloud server for long-term storage. Historical data queries can be used to analyze trends in the impact of different process parameter combinations on surface quality. For example, when temperature > 28°C and concentration < 190g / L, the probability of uniformity exceeding the standard increases by 40%, providing data support for process optimization.

[0111] Example 5:

[0112] The system's parameter self-learning module records quality feedback data after process adjustments and reversely optimizes the process parameter set to achieve system adaptive evolution. The following details the working mechanism of this module in conjunction with the specific implementation process:

[0113] Assume that during the oxidation process of a batch of aluminum trim strips, the process adjustment module adjusts the current density from 2.0A / dm² to 2.2A / dm² based on the parameter matching results to increase the film thickness growth rate. After the adjustment is completed, the parameter self-learning module starts the data recording process and collects the following oxide film quality feedback data:

[0114] Actual film thickness uniformity: The full surface was scanned by a multispectral sensor, and the calculated film thickness standard deviation σ was 4.2μm (5.0μm before adjustment);

[0115] Surface gloss change: Using a 60° gloss meter to test, the average gloss value increased from 85GU to 92GU;

[0116] Color difference control effect: In the CIELab color space, the final color difference ΔE value dropped from 2.8 to 2.3, close to the target value of 2.0.

[0117] These feedback data were reverse-verified with the initial parameters in the process parameter dynamic adjustment set (current dynamic range 1.8-2.5A / dm², concentration adaptability threshold 190-210g / L). The verification process included:

[0118] Parameter correlation analysis: Confirmed the correlation between current density adjustment and improved film thickness uniformity. Through historical data comparison, it was found that when the current density is in the range of 2.1-2.3A / dm², the uniformity standard deviation decreases by an average of 15%-20%. This adjustment is in line with this trend;

[0119] Target deviation calculation: The target value for film thickness uniformity is σ≤4.0μm. The measured value of 4.2μm still deviates from the target by 0.2μm. The color difference target value ΔE≤2.0, and the measured value deviates by 0.3μm, indicating that the adjustment effect has not fully met the standard and a correction factor needs to be generated.

[0120] Based on the deviation between the feedback data and the expected target, the system calculates parameter correction factors. For current density, since uniformity improved but fell short of the target, the current compensation factor is calculated as: (target σ - measured σ) × 0.1A / dm² / μm = (4.0-4.2) × 0.1 = -0.02A / dm² (a negative sign indicates a slight reduction in current density is needed to further optimize uniformity). For color difference, concentration adjustment has a more significant impact on color difference, so the concentration adjustment factor is calculated as: (measured ΔE - target ΔE) × 5g / L / ΔE = (2.3-2.0) × 5 = +1.5g / L (a positive sign indicates a need to increase concentration to reduce color difference). Regarding temperature optimization weighting, the temperature was maintained at 25°C in this adjustment. Since gloss improvement is not directly related to temperature, the weight parameter remains at its default value of 1.0.

[0121] The generation of correction factors requires smoothing of historical data. The system retrieves the correction factors for the previous three similar process adjustments: the first current compensation factor was -0.05A / dm², and the concentration adjustment factor was +2.0g / L; the second was -0.03A / dm² and +1.0g / L; and the third was -0.04A / dm² and +1.5g / L. Using an exponentially weighted average algorithm, the latest correction factors (-0.02A / dm², +1.5g / L) are dynamically smoothed with the historical values. The most recent correction factor is given a 40% weight, and the previous two correction factors are given 30% and 20% weights respectively. The new current density compensation coefficient is calculated as: (-0.02×40%)+(-0.04×30%)+(-0.03×20%)=-0.03A / dm² / μm

[0122] The concentration gradient adjustment coefficient is: (+1.5×40%)+(+1.5×30%)+(+1.0×20%)=+1.35g / L / ΔE

[0123] The newly generated set of dynamic correction coefficients is updated to the process database, replacing the original coefficients (original current compensation coefficient -0.01A / dm² / μm, concentration adjustment coefficient +1.0g / L / ΔE). In subsequent batches of production, when similar operating conditions recur (e.g., film thickness growth rate meets the target but uniformity is insufficient), the system will prioritize the updated coefficients for parameter adjustment. For example, the current density adjustment step size is adjusted from 0.2A / dm² to 0.17A / dm² (0.03A / dm² / μm x 0.6μm film thickness deviation) to more accurately approach the target value.

[0124] In another application scenario, due to the increase in service life of a certain oxidation tank equipment, the temperature control delay time increased from the historical average of 10 minutes to 15 minutes, resulting in multiple process adjustment delays. The parameter self-learning module records the temperature response feedback data of the equipment: under the same temperature adjustment command, the actual temperature takes 5 minutes longer to reach the target value than the preset value in the process database, and the fluctuation amplitude of the film thickness growth rate increases by 0.03μm / min within 30 minutes after the adjustment. Based on this, the system generates a temperature response weight correction factor: the temperature response weight parameter is increased from the default value of 1.0 to 1.2 to enhance the lead time of temperature adjustment. For example, when the temperature needs to be increased from 23°C to 25°C, the system issues a command 5 minutes in advance and increases the adjustment range from 2°C to 2.4°C (2°C × 1.2) to offset the delay effect.

[0125] The parameter self-learning module collects feedback data across the entire process chain. For pretreatment (e.g., insufficient alkaline etching time leading to poor oxide film adhesion), the system uses sensors embedded in the pretreatment equipment to collect data such as alkaline etching solution concentration, temperature, and treatment time. This data is then correlated with post-oxidation film adhesion test results (e.g., cross-hatch ratings) to generate synergistic correction factors for pretreatment parameters and the oxidation process. For example, if a 2°C decrease in alkaline etching solution temperature results in a 10% decrease in oxide film adhesion, the system will automatically increase the lower current density limit by 0.1A / dm² when adjusting oxidation process parameters to compensate for the pretreatment discrepancy.

[0126] Data security mechanisms ensure the reliability of the learning process. All feedback data is de-identified, removing sensitive information such as the device's unique identifier before storage. Correction factor updates are subject to dual verification: first, the system automatically verifies the fit against historical data (R² value > 0.8), and second, process engineers manually review and adjust the logic to avoid learning errors caused by abnormal data. For example, if a sensor failure caused a sudden change in gloss data, the system automatically verified the R² value to be only 0.4. The correction factor was not adopted, and a sensor failure alarm was triggered.

[0127] The parameter self-learning module is designed to be time-efficient: after every five production batches, global coefficient optimization is automatically initiated, integrating all feedback data to retrain the dynamic correction coefficient set. This training process utilizes the random forest algorithm, a machine learning algorithm, to extract features from over 1,000 sets of historical data, identifying key influencing factors (such as current density, which has a 45% influence on uniformity, and concentration, which has a 30% influence on color difference). The correction priority of each parameter is then adjusted accordingly. For example, after global optimization, the adjustment accuracy of the current density compensation coefficient has increased from ±0.01A / dm² / μm to ±0.005A / dm² / μm, and the response speed of the concentration adjustment coefficient has increased by 20%.

[0128] In cross-device learning scenarios, when a new device is connected to the system, the parameter self-learning module automatically retrieves historical correction factors from similar devices (such as the same model oxidation tank) as initial values, accelerating process commissioning for the new device. For example, the dynamic correction coefficient set for device A (model OX-200) includes a current density compensation coefficient of -0.03A / dm² / μm and a concentration adjustment coefficient of +1.5g / L / ΔE. When device B (of the same model) is connected, the system directly copies this coefficient set to device B's process database and marks it as "pending verification." During the first 10 production batches of device B, the coefficients are gradually localized and corrected using actual feedback data, ultimately forming coefficients uniquely suited for device B.

[0129] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0130] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment, characterized in that: include: The process data acquisition module is used to collect the process parameter data and surface condition data of the aluminum trim oxidation tank in real time through the industrial Internet of Things terminal equipment, analyze and process the data to generate the characteristic values ​​of the oxide film growth rate and the dynamic parameter characteristic values ​​of the tank liquid, and generate the dynamic adjustment set of process parameters based on the initial process parameter set stored in the process database; The parameter optimization module processes the personalized process parameters of the current batch of aluminum trim strips based on the characteristic values ​​of the oxide film growth rate and generates a dynamic oxidation control strategy; The surface monitoring module is used to obtain real-time surface quality data of the aluminum trim during the oxidation process through a multispectral sensor, filter out abnormal surface data that meets the dynamic adjustment range, and send it to the parameter matching module; The parameter matching module is used to perform multi-dimensional matching between abnormal surface data and each parameter item in the process parameter dynamic adjustment set, generate the matching degree between real-time data and each process parameter item, and select the process parameter corresponding to the highest matching degree as the target adjustment parameter; The process adjustment module is used to receive the target adjustment parameters and call the parameter adjustment protocol preset in the process database to drive the oxidation tank to perform process parameter correction operations.

2. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 1, characterized in that: The process of collecting the process parameter data of the aluminum trim oxidation tank in real time through the industrial Internet of Things terminal device is as follows: Identify the unique identification code of the oxidation tank equipment. If it is a newly connected equipment, collect basic process parameters including initial current density, oxidation solution concentration baseline value and temperature control range, establish process characteristic nodes based on the initial data, perform parameter calibration, and generate characteristic values ​​of oxide film growth rate; If it is a historically connected device, the historical process data set and surface quality change curve of the device are extracted. The historical process data set includes current fluctuation extremes, concentration deviation records, and temperature control delay duration, and is marked as the initial parameter set for the current process analysis.

3. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 1, characterized in that: The generating of the dynamic adjustment set of process parameters based on the initial process parameter set stored in the process database specifically includes: Extracting an initial standard set and a dynamic correction coefficient set of each process parameter from a process database, wherein the initial standard set includes: a current density safety range, a concentration fluctuation tolerance range, and a temperature adjustment reference value; The dynamic correction coefficient set includes a current density compensation coefficient, a concentration gradient adjustment coefficient and a temperature response weight parameter; Based on the real-time bath liquid dynamic parameter characteristic values, the initial standard set of each process parameter is dynamically adjusted, and the adjusted parameter set is recorded as the process parameter dynamic adjustment set; The process parameter dynamic adjustment set includes the current dynamic range, concentration adaptability threshold and temperature optimization control value of each parameter item.

4. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 3, characterized in that: The method of obtaining personalized process parameters of the current batch of aluminum trim strips based on the characteristic value of the oxide film growth rate and generating a dynamic oxidation control strategy specifically includes: According to the characteristic value of the oxide film growth rate, pattern matching is performed with the preset oxidation process characteristic library to determine the priority sequence of process parameter adjustment; An adaptive control strategy including parameter triggering conditions, adjustment step rules and fault handling mechanism is generated based on the adjustment priority sequence.

5. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 4, characterized in that: The real-time surface quality data of the aluminum trim strip during oxidation is obtained by using a multispectral sensor, specifically including: Monitor the real-time spectral data stream of the oxide film formation process, including film thickness variation, surface uniformity index and color difference fluctuation value; When the real-time spectral data stream exceeds the preset qualified process range, the abnormal flag is activated and the surface data of the abnormal period is extracted as effective monitoring data.

6. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 4, characterized in that: The matching degree between the generated real-time data and each process parameter item specifically includes: Analyze the thickness deviation, uniformity gradient, and color difference fluctuation amplitude in abnormal surface data, and perform difference calculations with the current dynamic range, concentration adaptability threshold, and temperature optimization control value of each process parameter; Based on the difference calculation results, a matching index between real-time data and each process parameter item is generated.

7. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 3, characterized in that: The process parameters corresponding to the highest matching degree are selected as target adjustment parameters, specifically including: Establish a matching ranking list of each process parameter item, and select the parameter item with the highest matching degree in the list; If the first matching degree is lower than the preset adjustment trigger threshold, the backup parameter set is called and the matching degree is recalculated.

8. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 6, characterized in that: The matching index between the real-time data and each process parameter item is generated based on the difference calculation result. The specific processing process is as follows: A multi-dimensional matching algorithm is used to normalize the current difference, concentration gradient and temperature deviation to generate a process parameter matching value ranging from 0 to 100. The closer the matching value is to 100, the stronger the adaptability of real-time data and process parameters is.

9. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 1, characterized in that: It also includes parameter self-learning modules, including: Record the oxide film quality feedback data after each process adjustment, including actual film thickness uniformity, surface gloss change and color difference control effect; The feedback data is reversely verified with the dynamic adjustment set of process parameters to generate parameter correction factors and update the dynamic correction coefficient set to the process database.

10. The system for real-time monitoring and process parameter adaptive adjustment of aluminum trim oxidation treatment according to claim 9, characterized in that: The generation parameter correction factor specifically includes: Based on the degree of deviation between the feedback data and the expected process target, the current compensation factor, concentration adjustment factor and temperature optimization weight are calculated; The exponentially weighted average algorithm is used to dynamically smooth the historical correction factors to generate a new set of dynamic correction coefficients.

Images