An anodic oxidation dyeing intelligent monitoring method and system based on multi-dimensional data verification

Abstract

This invention discloses an intelligent monitoring method and system for anodizing dyeing based on multi-dimensional data verification. The method includes: acquiring snapshot data during anodizing dyeing and determining model prediction results based on the snapshot data; using an edge gateway to perform multi-dimensional data consistency verification between the model prediction results and the actual physical state, and determining the multi-dimensional data consistency verification result; automatically switching the interactive terminal's operating mode based on the multi-dimensional data consistency verification result and performing anomaly handling. By employing the technical solution of this invention, consistency verification between model prediction results and actual physical states is performed from multiple dimensions, solving the problem of inconsistencies between model prediction results and actual physical states caused by network latency, sudden changes in operating conditions, and equipment failures, thereby improving the accuracy of model prediction results and reducing the occurrence of anodizing dyeing quality accidents.

Description

Technical Field

[0001] This invention relates to the field of industrial production line monitoring technology, and in particular to an intelligent monitoring method and system for anodizing and dyeing based on multi-dimensional data verification. Background Technology

[0002] In existing anodizing dyeing processes in manufacturing, current dyeing techniques mainly rely on manual experience or fixed countdown timers. With the development of the Industrial Internet, some manufacturers are attempting to introduce machine learning models (such as tree models) to predict the optimal dyeing time.

[0003] Using machine learning models to predict dyeing time still presents several challenges. These include: complex industrial network environments; sensors (such as ammeters and level gauges) frequently experiencing drift, packet loss, or data delays; and the potential for severe distortion in predictions due to the direct use of unreliable data for AI inference. Existing systems often focus solely on the current step, neglecting context. For instance, if a workpiece was not properly cleaned in the previous tank (skipping the order) or if abnormal current results in insufficient oxide film thickness, simply adjusting the dyeing time is ineffective and may even lead to batch scrapping. Human-machine collaboration lacks a closed loop; the model provides a predicted time but doesn't guarantee whether the worker will execute it. Purely software-based alarms often remain only in IT personnel's computer logs, making it difficult for field operators in noisy, fast-paced workshop environments to receive timely alerts.

[0004] In existing technologies, model predictions stored in databases often fail to reflect the current physical production status due to network latency, sudden changes in operating conditions, or equipment malfunctions. Direct execution of these predictions can lead to serious quality issues. Therefore, improving the accuracy of model coloring duration predictions is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This invention provides an intelligent monitoring method and system for anodizing dyeing based on multidimensional data verification, which solves the problem that the model prediction results are inconsistent with the actual physical state due to network latency, sudden changes in operating conditions and equipment failures, thereby improving the accuracy of the model prediction results and reducing the occurrence of anodizing dyeing quality accidents.

[0006] According to one aspect of the present invention, an intelligent monitoring method for anodic oxidation staining based on multidimensional data verification is provided, the method comprising: Obtain snapshot data during anodic oxidation staining, and determine the model prediction results based on the snapshot data; An edge gateway is used to perform multi-dimensional data consistency verification between the model prediction results and the actual physical state, and the multi-dimensional data consistency verification result is determined. The interactive terminal's operating mode is automatically switched based on the multidimensional data consistency verification results, and anomaly handling is performed.

[0007] According to another aspect of the present invention, an intelligent monitoring system for anodizing staining based on multidimensional data verification is provided. The system is applied to an intelligent monitoring method for anodizing staining based on multidimensional data verification. The system includes a sensing module, a control module, an edge verification module, and an interactive terminal. The sensing module includes an anode conductive seat current monitoring unit and a bath environment monitoring group, which are used to acquire snapshot data during anodizing and dyeing. The control module includes a controller and an audible and visual warning unit; the controller is used to collect snapshot data acquired by the sensing module and map it to an internal register; the audible and visual warning unit is physically connected to the output port of the controller and is used to issue a warning when the multidimensional data consistency verification fails. The edge verification module includes a dual-port edge gateway and a verification engine; the dual-port edge gateway is used to read physical data from the controller and model prediction results stored in the database, respectively; the verification engine is used to perform multi-dimensional data consistency verification. The interactive terminal connects directly to the edge verification module via a protocol and displays the multi-dimensional data consistency verification results.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the intelligent monitoring method and system for anodizing staining based on multidimensional data verification according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the intelligent monitoring method and system for anodizing staining based on multidimensional data verification as described in any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the intelligent monitoring method and system for anodic oxidation dyeing based on multidimensional data verification as described in any embodiment of the present invention.

[0011] The technical solution of this invention, through an intelligent monitoring method and system for anodizing dyeing based on multi-dimensional data verification, acquires snapshot data during anodizing dyeing and determines the model prediction result based on the snapshot data; uses an edge gateway to perform multi-dimensional data consistency verification between the model prediction result and the actual physical state, and determines the multi-dimensional data consistency verification result; automatically switches the interactive terminal operating mode and performs anomaly handling based on the multi-dimensional data consistency verification result. By employing the technical solution of this invention, consistency verification between the model prediction result and the actual physical state is performed from multiple dimensions, solving the problem of inconsistency between the model prediction result and the actual physical state caused by network latency, sudden changes in operating conditions, and equipment failure, thereby improving the accuracy of the model prediction result and reducing the occurrence of anodizing dyeing quality accidents.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart of an intelligent monitoring method for anodizing staining based on multidimensional data verification, provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of an intelligent monitoring method for anodizing staining based on multidimensional data verification, provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of an anodizing dyeing intelligent monitoring system based on multidimensional data verification according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] The acquisition, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. It should be noted that the terms "first," "second," "target," and "original," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising," "etc.," and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] Example 1 Figure 1 This invention provides a flowchart of an intelligent monitoring method for anodizing staining based on multi-dimensional data verification, as described in Embodiment 1. This embodiment is applicable to situations requiring intelligent monitoring of anodizing staining from multiple dimensions. The method can be executed by an intelligent monitoring system for anodizing staining based on multi-dimensional data verification. This system can be implemented in hardware and / or software and can be configured in any electronic device with network communication capabilities. Figure 1 As shown, the method includes: S110. Obtain snapshot data during anodic oxidation staining, and determine the model prediction result based on the snapshot data.

[0018] Among them, anodizing dyeing can refer to a surface treatment technology that deposits dye in the pores of the porous alumina film formed by the anodizing process through physical adsorption or chemical reaction, so as to give the metal workpiece a specific color.

[0019] Snapshot data refers to real-time production data used by a preset model for inference calculations when the anodizing dyeing production line is in operation. It serves as the input basis for the model to generate prediction results. The snapshot data includes, but is not limited to, actual current, bath temperature, pH value, production line number, workpiece model, workpiece quantity, and timestamp. The preset model refers to a model used to predict the anodizing dyeing duration.

[0020] The model prediction result can refer to the model prediction result obtained by using snapshot data as input data and making predictions using a preset model; the model prediction result includes, but is not limited to, the model prediction duration, which refers to the anodic staining duration predicted by the model.

[0021] S120. Use an edge gateway to perform multi-dimensional data consistency verification between the model prediction results and the actual physical state, and determine the multi-dimensional data consistency verification result.

[0022] In this context, an edge gateway refers to a computing device deployed in an industrial site, physically close to the data source. In this embodiment of the invention, the edge gateway specifically refers to an industrial computer or embedded server that runs the core verification script of this invention, has dual network ports, and performs data cleaning and logical judgments.

[0023] The actual physical state refers to the physical state acquired in real time by sensors during anodizing dyeing. The actual physical state includes, but is not limited to, the actual process stage of anodizing dyeing, the actual dyeing time, and the actual current.

[0024] Multidimensional data consistency verification refers to the process of verifying the consistency between model predictions and actual physical states during anodizing dyeing from multiple dimensions. This multidimensional data consistency verification includes, but is not limited to, physical load consistency verification, aging consistency verification, process stage consistency verification, and dyeing duration consistency verification.

[0025] In this embodiment of the invention, an edge gateway is used to perform multi-dimensional data consistency verification between the actual physical state during anodizing and dyeing and the model prediction results, so as to determine the multi-dimensional data consistency verification result.

[0026] S130. Automatically switch the interactive terminal's operating mode based on the multi-dimensional data consistency verification result and perform exception handling.

[0027] Among them, the multidimensional data consistency verification result refers to the result of multidimensional data consistency verification of the model prediction result and the actual physical state; the multidimensional data consistency verification result includes, but is not limited to, physical load consistency verification result, time consistency verification result, process stage consistency verification result, and dyeing duration consistency verification result.

[0028] The interactive terminal refers to the large operating screen used at the on-site workstation in the intelligent monitoring system for anodizing and dyeing. It serves as the core human-machine interface connecting the artificial intelligence decision-making system and the on-site operator. The interactive terminal is used to display model prediction duration, current data, and anomaly warnings in real time.

[0029] Automatic switching of interactive terminal operating modes refers to the process of automatically switching the operating mode of the interactive terminal based on the results of multidimensional data consistency verification. For example, if all multidimensional data consistency verification results pass, the system automatically switches to the prediction mode using an artificial intelligence model; if any multidimensional data consistency verification result fails, the system automatically switches to the physical anomaly mode to display the standard staining duration.

[0030] Anomaly handling refers to a series of emergency response measures automatically triggered by the intelligent monitoring system for anodizing dyeing when multidimensional data consistency verification fails or sudden changes in operating conditions occur during production. These measures aim to ensure production continuity and prevent batch quality incidents. Anomaly handling includes, but is not limited to, suspending the dyeing process, automatically switching to standard dyeing duration, and extending verification waiting time.

[0031] This invention provides an intelligent monitoring method for anodizing dyeing based on multi-dimensional data verification. The method acquires snapshot data during anodizing dyeing and determines model prediction results based on this data. An edge gateway is used to perform multi-dimensional data consistency verification between the model prediction results and the actual physical state, determining the multi-dimensional data consistency verification result. Based on the multi-dimensional data consistency verification result, the method automatically switches the operating mode of the interactive terminal and performs anomaly handling. By employing the technical solution of this invention, consistency verification between model prediction results and actual physical states is performed from multiple dimensions, solving the problem of inconsistencies between model prediction results and actual physical states caused by network latency, sudden changes in operating conditions, and equipment failures. This improves the accuracy of model prediction results and reduces the occurrence of anodizing dyeing quality accidents.

[0032] Example 2 Figure 2 This is a flowchart of an intelligent monitoring method for anodic oxidation staining based on multidimensional data verification, provided in Embodiment 2 of the present invention. This embodiment further optimizes the aforementioned embodiments, and can be combined with various optional solutions from one or more of the above embodiments. For example... Figure 2 As shown, the method includes: S210. Obtain snapshot data during anodic oxidation staining, and determine the model prediction result based on the snapshot data.

[0033] Specifically, snapshot data of the anodizing dyeing production line during operation is obtained, and a prediction model is used based on the snapshot data to perform model prediction in order to determine the model prediction result.

[0034] As an optional but non-limiting implementation, the step of obtaining snapshot data during anodic oxidation staining and determining the model prediction results based on the snapshot data includes, but is not limited to, steps A1-A2: Step A1: Obtain snapshot data during anodizing and dyeing; wherein, the snapshot data includes actual current, bath temperature, pH value, production line number, workpiece model, workpiece quantity, and timestamp; Step A2: Input the snapshot data into the preset model to determine the model prediction result, and write the model prediction result and the snapshot data into the database; wherein, the preset model is used to predict the anodizing staining time.

[0035] Specifically, snapshot data of the anodizing dyeing production line during operation is obtained, and a preset model is used to infer the prediction result based on the snapshot data. The prediction result and the snapshot data are then written into a database for storage.

[0036] S220. Verify the consistency between the actual current and the theoretical current during anodizing and dyeing to determine the physical load consistency verification result.

[0037] In this embodiment of the invention, an edge gateway is introduced to use a monitoring script deployed on the edge gateway to poll the database at a preset frequency, thereby acting as a supervisor for artificial intelligence decision-making and verifying the consistency between the model prediction results and the actual physical state during anodizing and dyeing, thus achieving intelligent decision-making.

[0038] As an optional but non-limiting implementation, the process of verifying the consistency between the actual current and the theoretical current during anodizing and dyeing, and determining the physical load consistency verification result, includes, but is not limited to, steps B1-B3: Step B1: Obtain the actual current flowing through the hanger during anodizing and dyeing using a current sensor; Step B2: Determine the theoretical current based on the number of workpieces included in the snapshot data and the current coefficient corresponding to the anodizing production line; Step B3: Perform a consistency check between the actual current and the theoretical current to determine the physical load consistency check result.

[0039] The model predictions stored in the database are based on the input at that time, such as a full load of 180 workpieces. However, in actual execution, physical changes such as misalignment or poor contact of the fixtures may occur. If the dyeing time is still executed for 180 workpieces at this time, it will lead to color differences. Therefore, this embodiment of the invention proposes a physical load consistency verification method based on workpiece attribute snapshots.

[0040] Specifically, the most recent model prediction results are read from the database, and key fields are extracted, including but not limited to theoretical current and the number of workpieces. The theoretical current can be determined using the number of workpieces and the unit current coefficient corresponding to the anodizing production line. The number of workpieces refers to the total number of workpieces mounted on a single fixture, and the number of workpieces directly determines the magnitude of the theoretical current. The actual current of the conductive seat in the current slot is read using a high-precision Hall current sensor or OPC protocol. The actual current and theoretical current are then compared using a physical load consistency check to determine the result. Specifically, this can be expressed as: ; in, Indicates the actual current. Indicates the number of workpieces. This represents the unit current coefficient corresponding to the anodizing production line; This indicates the permissible physical fluctuation tolerance.

[0041] Optional, The preferred value is 15%; the actual current is dynamically compared with the theoretical current. When the deviation between the two is less than or equal to 15%, it indicates that the physical load consistency verification result is consistent; if the deviation is greater than 15%, it indicates that the physical load consistency verification result is inconsistent.

[0042] This invention verifies the consistency between theoretical current and actual current to prevent the originally correct model prediction result from becoming an erroneous instruction due to changes in the physical environment (such as component loss or loose connection). It achieves a safety interlock that allows the execution of model prediction results only when the physical state matches.

[0043] S230. Compare the time when the model prediction results are written with the data polling time of the edge gateway to determine the timeliness consistency verification result.

[0044] In industrial settings, network congestion or database lockouts can occur, sometimes causing the edge gateway to read outdated model predictions from "the previous shift" or "two hours ago." Therefore, it is necessary to verify the timeliness and consistency of the model prediction results.

[0045] As an optional but non-limiting implementation, comparing the model prediction result writing time with the edge gateway data polling time to determine the timeliness consistency verification result includes, but is not limited to, steps C1-C3: Step C1: Determine the time when the model prediction results are written to the database; Step C2: Use the edge gateway's verification engine to poll the database at a preset frequency to determine the current polling time; Step C3: Determine the lag time between the current polling time and the time when the model prediction result is written, and compare the lag time with the preset lag time threshold to determine the timeliness consistency verification result.

[0046] Specifically, the process includes: the model prediction result writing time when reading the model prediction result from the database and writing it back to the database; using the verification engine of the edge gateway to poll the database at a preset frequency to determine the current polling time; determining the lag time between the current polling time and the model prediction result writing time, and comparing the lag time with a preset lag time threshold to determine the timeliness consistency verification result.

[0047] Specifically, for example, if the preset lag time threshold is 10 minutes, if the lag time is greater than 10 minutes, it means that the model prediction results obtained from the database have become invalid and the timeliness consistency verification results are inconsistent; if the lag time is less than or equal to 10 minutes, it means that the model prediction results obtained from the database have not become invalid and the timeliness consistency verification results are consistent.

[0048] In this embodiment of the invention, the writing time of the model prediction result is compared with the data polling time of the edge gateway to determine the timeliness consistency verification result. This avoids the situation where network congestion or database lock-up in the industrial field leads to invalid model prediction results, thereby improving the timeliness of the data.

[0049] In one optional embodiment of the present invention, timeliness consistency verification can also be performed by checking the number of workpieces. For example, an industrial camera is installed above the anodizing dyeing tank, and the edge gateway calls a visual counting algorithm to directly count the number of workpieces on the hanger and compare it with the number of workpieces in the database to verify timeliness consistency. If the visual count does not match the workpiece count record in the database, it can also be determined that the model prediction result obtained from the database is invalid.

[0050] In one optional embodiment of the present invention, the edge gateway polls the database at a preset frequency; optionally, a database trigger or an interrupt signal from the controller can be used; for example, when a new model prediction result is inserted into the database or the controller detects a vehicle arrival signal, a verification request is actively sent to the edge verification module, thereby further reducing the system load.

[0051] S240. Perform consistency verification between the current process stage predicted by the model and the real-time process stage, and determine the consistency verification result of the process stage.

[0052] The database may contain multiple records for different processes. This can easily lead to a misalignment where the workpiece is still in the oxidation tank, while the interactive terminal's large screen displays the dyeing time. Therefore, it is necessary to verify the consistency of the model's prediction results across different processes.

[0053] As an optional but non-limiting implementation, the process of verifying the consistency between the current process stage during model prediction and the real-time process stage, and determining the consistency verification result, includes, but is not limited to, steps D1-D3: Step D1: Determine the current process stage when the model is making predictions, and write the current process stage into the database; Step D2: The physical position of the workpiece during anodizing and dyeing is collected in real time by a sensor, and the real-time process stage corresponding to the physical position is determined. Step D3: Perform a consistency check between the current process stage and the real-time process stage, and determine the consistency check result of the process stage.

[0054] The process involves reading the current status markers of the anodizing and dyeing fly rods from the database to determine the current process stage during model prediction; acquiring the physical position of the workpiece in real time using sensors to determine the real-time process stage; and performing a consistency check between the current process stage and the real-time process stage to determine the consistency check result. For example, if the physical position of the workpiece acquired by the sensors is a dyeing tank, and the current process stage predicted by the model is the dyeing process, then the consistency check result is determined to be consistent; if the physical position of the workpiece is a dyeing tank, but the current process stage is not the dyeing process, then the consistency check result is determined to be inconsistent.

[0055] In this embodiment of the invention, the current process stage during model prediction is checked for consistency with the real-time process stage to improve the accuracy of the process displayed in real time on the interactive terminal.

[0056] S250. Calculate the deviation rate between the actual staining time and the model prediction time to determine the consistency verification result of the staining time.

[0057] In this invention, after the preset model provides a prediction result, the model cannot determine whether the prediction result is used, resulting in a lack of closed-loop human-machine collaboration. Therefore, this embodiment calculates the deviation rate between the actual staining time and the model prediction time to determine the consistency verification result of the staining time, thereby determining whether the model prediction result is used and achieving a closed loop in human-machine collaboration.

[0058] As an optional but non-limiting implementation, the step of calculating the deviation rate between the actual staining duration and the model-predicted duration to determine the consistency verification result of the staining duration includes, but is not limited to, steps E1-E3: Step E1: Determine the actual staining time during anodic oxidation staining; Step E2: Compare the actual staining duration with the model prediction duration included in the model prediction results to determine the deviation rate; Step E3: Compare the deviation rate with the preset deviation rate threshold to determine the consistency verification result of the staining duration.

[0059] The process involves automatically collecting the actual dyeing time from the controller after the anodizing dyeing process is completed. This actual dyeing time is then written back to the model's predicted time field for comparison to determine the deviation rate. The deviation rate is then compared with a preset deviation rate threshold to determine the consistency verification result for the dyeing time. Optionally, taking a preset deviation rate threshold of 10% as an example, if the deviation rate is greater than 10%, the consistency verification result for the dyeing time is determined to be unsuccessful, indicating that the currently used dyeing time is not the model's predicted time; if the deviation rate is less than 10%, the consistency verification result for the dyeing time is determined to be successful, indicating that the currently used dyeing time is the model's predicted time.

[0060] In this embodiment of the invention, the actual staining time is compared with the model-predicted time to determine whether the currently used staining time is the model-predicted time, thereby improving the closed loop of human-machine collaboration.

[0061] S260. Automatically switch the interactive terminal's operating mode based on the multi-dimensional data consistency verification result and perform exception handling.

[0062] After undergoing four-dimensional data consistency verification, the interactive terminal operating model is automatically switched based on the data consistency verification results to handle anomalies.

[0063] As an optional but non-limiting implementation, the automatic switching of the interactive terminal's operating mode based on the multi-dimensional data consistency verification result and the handling of exceptions include, but are not limited to, steps F1-F2: Step F1: If at least one dimension of the multidimensional data consistency verification result fails, the interactive terminal operation mode is switched to physical anomaly mode, the reason for the anomaly is displayed through the interactive terminal, and the standard dyeing process time is automatically switched to be displayed. Step F2: If at least one dimension of the multidimensional data consistency verification result fails, the interactive terminal operation mode is switched to normal intelligent mode, and the model prediction duration is displayed through the interactive terminal.

[0064] When the data consistency verification results in all dimensions pass, it can be determined that the model prediction result of the preset model is consistent with the actual physical state at the current moment. Then, the running model of the interactive terminal will be automatically switched to normal intelligent mode to use the preset model for model prediction, and the model prediction duration will be displayed on the interactive terminal. At the same time, the background color of the interactive terminal will be adjusted to green.

[0065] If at least one dimension of the multidimensional data consistency verification result fails, it indicates that the model prediction result is inconsistent with the actual physical state, which may be due to inconsistent physical load consistency verification or inconsistent process stage consistency verification. In this case, the interactive terminal's running model will be automatically switched to physical anomaly mode, the specific anomaly reason will be displayed on the interactive terminal, the standard dyeing process time will be automatically switched to be displayed, and the background color of the interactive terminal will be adjusted to red.

[0066] In one optional embodiment of the present invention, when the edge gateway detects an interruption in the connection with the database, the edge gateway automatically takes over the display rights and displays a prompt message "Network offline, please operate manually" on the interactive terminal, and records local logs; it automatically uploads the logs after the network is restored.

[0067] In one optional embodiment of the present invention, anomaly handling can also be performed using a smart wearable device based on the multidimensional data consistency verification results. For example, if at least one dimension of the multidimensional data consistency verification results fails, the wristband worn by the technician can be made to vibrate to issue a warning; or a voice announcement can be made directly in the workshop broadcasting system using a speech synthesis module.

[0068] As an optional but non-limiting implementation, if at least one dimension of the multidimensional data consistency verification result fails, the interactive terminal's operating mode is switched to physical anomaly mode. The reason for the anomaly is displayed on the interactive terminal, and the standard dyeing process time is automatically switched to be displayed, including but not limited to steps G1-G4: Step G1: If the physical load consistency verification fails, it is determined that the current anodizing dyeing condition has changed, the model prediction result is invalid, and the interactive terminal automatically switches to display the standard dyeing process time and issues an abnormal current warning or part drop warning. Step G2: If the timeliness consistency check fails, it is determined that the model prediction results obtained by the edge gateway when polling the database have become invalid. The interactive terminal will automatically switch to display the standard dyeing process time and mark the invalid model prediction results. Step G3: If the process stage consistency check fails, it is determined that the current process stage of the current record in the database has expired, and the interactive terminal will automatically switch to display the standard dyeing process time and trigger an alarm. Step G4: If the consistency check of staining duration fails, it is determined that there is a deviation in the model's predicted duration. The interactive terminal triggers a model drift warning and writes the actual staining duration and deviation rate back to the database to optimize the preset model.

[0069] The system employs several mechanisms to handle data consistency checks. Specifically: If the physical load consistency check fails (e.g., the database indicates 180 parts, but the real-time current display only shows the level of 60 parts), the system determines "operating conditions have changed, prediction has failed." It immediately blocks the display of the database record and triggers a "current anomaly / part drop" alarm, forcing a manual confirmation process. If the timeliness consistency check fails, the system watermarks "data outdated" on the interactive terminal display and hides the prediction time to prevent workers from misusing historical data to operate the current workpiece. If the process stage consistency check fails, and the physical location is in the dyeing tank, but a database record is still in the degreasing stage, the system identifies this as "skipped production," triggering the highest level audible and visual alarm and recording the violation. If the dyeing duration consistency check fails (e.g., if the execution deviation rate of 10 consecutive batches on a production line is >10%), the system automatically generates a "model drift warning" and writes the actual dyeing duration and deviation rate back to the database, notifying the algorithm engineer to recalibrate the baseline parameters.

[0070] In one optional embodiment of the present invention, this solution is applicable to nickel / gold / silver electroplating production lines. The database stores preset plating thickness processes, and the film thickness standard is verified by real-time current and electroplating time.

[0071] In one optional embodiment of the present invention, this solution can be applied to electrophoresis of automotive parts, and by verifying the waveform matching degree of voltage and current, coating defects caused by poor insulation of the mounting bracket can be prevented.

[0072] In this embodiment of the invention, a multi-dimensional data consistency verification between the model prediction results and the actual physical state is performed through an edge gateway. A firewall is added to ensure that only model prediction results that conform to the actual physical state can guide production. No modification to the cloud-based intelligent model or rewriting of the controller's underlying logic is required; only bypass monitoring and interception through the edge gateway are needed. Implementation costs are low, and it is extremely easy to promote in older factories.

[0073] Example 3 Figure 3 This is a schematic diagram of the structure of an intelligent monitoring system for anodic oxidation staining based on multidimensional data verification, provided in Embodiment 3 of the present invention. The system is applied to the intelligent monitoring method for anodic oxidation staining based on multidimensional data verification described in any of the above embodiments. Figure 3As shown, the system includes a sensing module 310, a control module 320, an edge verification module 330, and an interactive terminal 340; wherein, The sensing module includes an anode conductive seat current monitoring unit and a bath environment monitoring group, which are used to acquire snapshot data during anodizing and dyeing. The control module includes a controller and an audible and visual warning unit; the controller is used to collect snapshot data acquired by the sensing module and map it to an internal register; the audible and visual warning unit is physically connected to the output port of the controller and is used to issue a warning when the multidimensional data consistency verification fails. The edge verification module includes a dual-port edge gateway and a verification engine; the dual-port edge gateway is used to read physical data from the controller and model prediction results stored in the database, respectively; the verification engine is used to perform multi-dimensional data consistency verification. The interactive terminal connects directly to the edge verification module via a protocol and displays the multi-dimensional data consistency verification results.

[0074] The sensing module includes an anode conductive base current monitoring unit and a bath environment monitoring group. The anode conductive base current monitoring unit refers to a high-precision Hall current sensor installed under each conductive copper base in the oxidation and dyeing tanks to collect the actual current flowing through the fixture. Optionally, the sensor outputs a 4-20mA analog signal, which is connected to the analog input module of the field controller. The sensor's sampling frequency is no less than 10Hz. The bath environment monitoring group includes a PT100 temperature sensor (monitoring bath temperature Tbath) and a pH meter (monitoring acidity / alkalinity), with data imported into the PLC in real time.

[0075] The control module includes a controller and an audible and visual alarm unit. The controller (Programmable Logic Controller, PLC) is responsible for collecting data from all the aforementioned sensors and mapping it to internal registers; the PLC acts as a "Single Source of Truth" at the OT (Operation Technology) end. The audible and visual alarm unit, physically connected to the PLC output port, is used to issue a flashing red light or a buzzer alarm when verification fails.

[0076] The edge verification module includes a dual-NIC edge gateway and a verification engine. The edge gateway uses an industrial-grade fanless PC deployed on the production line. It has two independent NICs: LAN1 (OT network), which connects to the PLC via Modbus TCP protocol to read millisecond-level physical data; and LAN2 (IT network), which connects to the enterprise database server via HTTPS / ODBC protocol to read model prediction results. The verification engine is a daemon running on the gateway, which is the core script of this invention; it does not rely on cloud commands and has local autonomous decision-making capabilities.

[0077] The interactive terminal can refer to a large visual screen at the workstation, deployed directly above the dyeing tank, and connected directly to the edge gateway via HDMI / DP. This screen does not display the original database records, but only the final operation instructions after multi-dimensional data consistency verification according to the embodiments of this invention.

[0078] The intelligent monitoring system for anodizing dyeing based on multidimensional data verification provided in the embodiments of the present invention can execute the intelligent monitoring method for anodizing dyeing based on multidimensional data verification provided in any of the embodiments of the present invention. It has the corresponding functions and beneficial effects of executing the intelligent monitoring method for anodizing dyeing based on multidimensional data verification. For detailed process, please refer to the relevant operations of the intelligent monitoring method for anodizing dyeing based on multidimensional data verification in the foregoing embodiments.

[0079] Example 4 Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0080] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0081] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0082] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the intelligent monitoring method and system for anodizing staining based on multi-dimensional data verification.

[0083] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0084] In some embodiments, the intelligent monitoring method and system for anodizing dyeing based on multidimensional data verification can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the intelligent monitoring method and system for anodizing dyeing based on multidimensional data verification described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the intelligent monitoring method and system for anodizing dyeing based on multidimensional data verification by any other suitable means (e.g., by means of firmware).

[0085] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0087] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0088] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0089] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0090] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0091] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0092] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A smart monitoring method for anodic oxidation staining based on multidimensional data verification, characterized in that, The method includes: Obtain snapshot data during anodic oxidation staining, and determine the model prediction results based on the snapshot data; An edge gateway is used to perform multi-dimensional data consistency verification between the model prediction results and the actual physical state, and the multi-dimensional data consistency verification result is determined. The interactive terminal's operating mode is automatically switched based on the multidimensional data consistency verification results, and anomaly handling is performed.

2. The method according to claim 1, characterized in that, The step of acquiring snapshot data during anodic oxidation staining and determining model prediction results based on the snapshot data includes: Acquire snapshot data during anodizing and dyeing; wherein, the snapshot data includes actual current, bath temperature, pH value, production line number, workpiece model, workpiece quantity, and timestamp; The snapshot data is input into a preset model to determine the model prediction result, and the model prediction result and the snapshot data are written into a database; wherein, the preset model is used to predict the duration of anodizing staining.

3. The method according to claim 1, characterized in that, The step of using an edge gateway to perform multi-dimensional data consistency verification between the model prediction results and the actual physical state, and determining the multi-dimensional data consistency verification result, includes: The consistency between the actual current and the theoretical current during anodizing dyeing is verified to determine the physical load consistency verification result. The time when the model prediction results are written is compared with the time when the edge gateway data is polled to determine the timeliness consistency verification result; The consistency verification between the current process stage when the model predicts and the real-time process stage is performed to determine the consistency verification result of the process stage. The deviation rate between the actual staining time and the model prediction time is calculated to determine the consistency verification result of the staining time.

4. The method according to claim 3, characterized in that, The process of verifying the consistency between the actual current and the theoretical current during anodizing and dyeing, and determining the physical load consistency verification result, includes: The actual current flowing through the hanger during anodizing dyeing is obtained using a current sensor; The theoretical current is determined based on the number of workpieces included in the snapshot data and the current coefficient corresponding to the anodizing production line; The consistency of the actual current and the theoretical current is verified to determine the physical load consistency verification result.

5. The method according to claim 3, characterized in that, The step of comparing the time when the model prediction results are written with the data polling time of the edge gateway to determine the timeliness consistency verification result includes: Determine the time when the model prediction results are written to the database; The verification engine of the edge gateway polls the database at a preset frequency to determine the current polling time; Determine the lag time between the current polling time and the time when the model prediction result is written, and compare the lag time with a preset lag time threshold to determine the timeliness consistency verification result.

6. The method according to claim 3, characterized in that, The process of verifying the consistency between the current process stage predicted by the model and the real-time process stage, and determining the consistency verification result of the process stage, includes: Determine the current process stage when the model makes predictions, and write the current process stage into the database; The physical position of the workpiece during anodizing and dyeing is collected in real time by sensors, and the real-time process stage corresponding to the physical position is determined. Perform a consistency check between the current process stage and the real-time process stage, and determine the consistency check result of the process stage.

7. The method according to claim 3, characterized in that, The step of calculating the deviation rate between the actual staining duration and the model-predicted duration to determine the consistency verification result of the staining duration includes: Determine the actual staining time during anodic oxidation staining; The actual staining time is compared with the model prediction time included in the model prediction results to determine the deviation rate; The deviation rate is compared with a preset deviation rate threshold to determine the consistency verification result of the staining duration.

8. The method according to claim 1, characterized in that, The automatic switching of the interactive terminal's operating mode based on the multidimensional data consistency verification result, and the handling of anomalies, include: If at least one dimension of the multidimensional data consistency verification result fails, the interactive terminal operation mode will be switched to physical anomaly mode, the reason for the anomaly will be displayed on the interactive terminal, and the standard dyeing process time will be automatically switched to be displayed. If no dimension fails the consistency check in the multidimensional data consistency check, the interactive terminal will be switched to normal intelligent mode, and the model prediction duration will be displayed on the interactive terminal.

9. The method according to any one of claims 1-8, characterized in that, If at least one dimension of the multidimensional data consistency verification result fails, the interactive terminal's operating mode will be switched to physical anomaly mode. The reason for the anomaly will be displayed on the interactive terminal, and the standard dyeing process time will be automatically switched to be displayed, including: If the physical load consistency verification fails, it is determined that the current anodizing dyeing condition has changed, the model prediction result is invalid, and the interactive terminal will automatically switch to display the standard dyeing process time and issue an abnormal current warning or part drop warning. If the timeliness consistency check fails, it is determined that the model prediction results obtained by the edge gateway when polling the database are invalid. The interactive terminal will automatically switch to display the standard dyeing process time and mark the invalid model prediction results. If the consistency check of the process stage fails, it is determined that the current process stage of the current record in the database has expired, and the interactive terminal will automatically switch to display the standard dyeing process time and trigger an alarm. If the consistency check of staining duration fails, it is determined that there is a deviation in the model's predicted duration. The interactive terminal triggers a model drift warning and writes the actual staining duration and deviation rate back to the database to optimize the preset model.

10. An intelligent monitoring system for anodizing staining based on multidimensional data verification, wherein the system is applied to the intelligent monitoring method for anodizing staining based on multidimensional data verification as described in claim 1, characterized in that, The system includes a sensing module, a control module, an edge verification module, and an interactive terminal; wherein, The sensing module includes an anode conductive seat current monitoring unit and a bath environment monitoring group, which are used to acquire snapshot data during anodizing and dyeing. The control module includes a controller and an audible and visual warning unit; the controller is used to collect snapshot data acquired by the sensing module and map it to an internal register; the audible and visual warning unit is physically connected to the output port of the controller and is used to issue a warning when the multidimensional data consistency verification fails. The edge verification module includes a dual-port edge gateway and a verification engine; the dual-port edge gateway is used to read physical data from the controller and model prediction results stored in the database, respectively; the verification engine is used to perform multi-dimensional data consistency verification. The interactive terminal connects directly to the edge verification module via a protocol and displays the multi-dimensional data consistency verification results.

Images