An intelligent monitoring and management system and method for a precise assembly process of an optoelectronic module

Abstract

This application provides an intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules, comprising: processing the uneven distribution in high-frequency operations using data analysis methods based on the real-time dynamic information flow to determine the deviation index of the current assembly state; extracting historical dynamic information flow from the interruption protection data packet and restoring the continuous sequence of operations before the abnormal interruption using data reconstruction methods to obtain the restored assembly state; obtaining the matching degree between the subsequent real-time dynamic information flow and the interruption protection data packet for the restored assembly state, and determining whether it is necessary to adjust the position deviation to maintain the continuity of operation; if the matching degree is lower than a preset threshold, fusing the restored assembly state and the newly added dynamic information flow using data integration methods to determine an optimized assembly parameter sequence; generating control commands based on the optimized assembly parameter sequence and transmitting them to the assembly equipment to obtain a continuously executed precision assembly process.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to an intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules. Background Technology

[0002] In modern manufacturing, the precision assembly of optoelectronic modules is a crucial area, directly impacting the performance and reliability of products in industries such as communications, medical, and industrial automation. The assembly process involves numerous high-precision operations; even the slightest deviation can lead to product malfunction. Therefore, real-time monitoring and management of the assembly process are paramount. With the widespread adoption of intelligent technologies, improving assembly efficiency and quality through intelligent systems has become a core requirement for industry development.

[0003] However, current methods for monitoring and managing optoelectronic module assembly have significant shortcomings when dealing with complex environments. Many systems struggle to adapt to the large amounts of dynamic information generated during assembly, particularly in data processing and storage, often failing to balance the demands for real-time performance and long-term preservation. This not only leads to the loss of critical information during high-frequency operations but also makes subsequent analysis and problem tracing difficult, impacting overall production efficiency and product quality stability.

[0004] A deeper technical challenge lies in effectively managing the diverse information flows generated during the assembly process. Assembly involves a wide variety of data, such as positional deviations, temperature changes, and image recordings. The distribution of this data in time and space is extremely uneven, making it difficult for the system to balance rapid response with comprehensive storage. Furthermore, this unevenness means that the system cannot properly preserve its current state in the face of sudden interruptions, leading to the risk of data loss or operational failure.

[0005] Therefore, in the intelligent monitoring and management of precision assembly of optoelectronic modules, a key issue urgently needs to be addressed: how to build a data management mechanism that can quickly respond to real-time needs, properly preserve historical information, and ensure operational continuity after abnormal interruptions. This problem is particularly prominent in actual business operations. For example, during lens assembly, if the system loses the current positional deviation data due to an unexpected interruption, it cannot accurately restore the previous assembly state after restarting, seriously affecting production progress and product quality.

[0006] A thorough analysis of this issue reveals that resolving the contradiction between efficiency and sustainability in data management is a crucial breakthrough for improving the intelligence level of optoelectronic module assembly and an urgent need to drive technological progress in the industry. Summary of the Invention

[0007] This invention provides an intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules, mainly including: By deploying a sensor network in the precision assembly environment of optoelectronic modules, diverse data such as position deviation, temperature change and image recording are collected from the assembly process to obtain a real-time dynamic information stream; Based on the real-time dynamic information flow, data analysis methods are used to process the uneven distribution in high-frequency operations and determine the deviation index of the current assembly state. If the deviation index exceeds the preset threshold, the caching mechanism is triggered to write the deviation index of the current assembly state and related dynamic information stream into the temporary storage area to obtain the interruption protection data packet. Historical dynamic information streams are extracted from the interruption protection data packets, and the continuous sequence of operations before the abnormal interruption is restored using a data reconstruction method to obtain the restored assembly state. For the restored assembly state, the matching degree between the subsequent real-time dynamic information stream and the interruption protection data packet is obtained to determine whether the position deviation needs to be adjusted to maintain operation continuity. If the matching degree is lower than the preset threshold, the restored assembly state and the newly added dynamic information flow are fused by the data integration method to determine the optimized assembly parameter sequence. Based on the optimized assembly parameter sequence, control commands are generated and transmitted to the assembly equipment to obtain a continuously executed precision assembly process.

[0008] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This invention discloses an intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules. It proposes an intelligent solution to address complex problems in the precision assembly of optoelectronic modules, such as positional deviations, temperature changes, and operational interruptions caused by uneven distribution of high-frequency operations. This invention deploys a sensor network to collect diverse data in real time, forming a dynamic information flow. Data analysis methods are used to accurately determine assembly state deviation indicators. Once a threshold is exceeded, a caching mechanism is triggered to generate an interruption protection data packet. Subsequently, a data reconstruction method is used to restore the continuous sequence of operations before the abnormal interruption, ensuring the continuity of the assembly state. Simultaneously, this invention combines matching degree judgment and data integration methods to optimize the assembly parameter sequence and generate control commands that are transmitted to the equipment, ultimately achieving continuous execution of the precision assembly process. The core innovation of this invention lies in its data-driven intelligent monitoring and dynamic adjustment, which significantly improves assembly accuracy and stability, ensuring the high efficiency and reliability of optoelectronic module production. Attached Figure Description

[0009] Figure 1 This is a flowchart of an intelligent monitoring and management system and method for the precision assembly process of an optoelectronic module according to the present invention.

[0010] Figure 2This is a schematic diagram of an intelligent monitoring and management system and method for the precision assembly process of an optoelectronic module according to the present invention.

[0011] Figure 3 This is another schematic diagram of an intelligent monitoring and management system and method for the precision assembly process of an optoelectronic module according to the present invention. Detailed Implementation

[0012] To further understand the content of this invention, a detailed description of the invention is provided in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0013] like Figures 1-3 This embodiment of an intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules may specifically include: S101. By deploying a sensor network in the precision assembly environment of optoelectronic modules, diverse data such as position deviation, temperature change and image recording are collected from the assembly process to obtain a real-time dynamic information stream.

[0014] Multidimensional data is acquired from the precision assembly environment of optoelectronic modules using a sensor network. Real-time acquisition of positional deviations, temperature changes, and image recordings generates an initial data stream. Based on this initial data stream, a pre-established classification model is used for preliminary screening of positional deviations and temperature changes. If a positional deviation exceeds a preset threshold, it is marked as an abnormal data point, and the range of abnormal data is determined. For the abnormal data range, visual information for the corresponding time period is extracted from the image recordings to obtain image segments related to the positional deviation and determine whether there is a significant assembly deviation. Based on the image segment judgment results, if a significant assembly deviation is found, detailed comparison of the image segments is performed, and edge detection methods are used to extract the contour features of the deviation area to obtain the distribution information of the deviation area. By combining the distribution information of the deviation area with temperature change data, the influence of temperature on positional deviation is analyzed to determine the correlation between temperature change and deviation distribution. The correlation analysis results are obtained, and for temperature change data with high correlation, environmental monitoring records during the assembly process are traced to determine whether there are any abnormal environmental factors. Based on the judgment results of the environmental monitoring records, a targeted data adjustment strategy is generated, resulting in an optimized assembly process monitoring scheme.

[0015] In the precision assembly environment of optoelectronic modules, sensor networks continuously collect multidimensional data streams.

[0016] For example, position sensors provide micron-level precision feedback on the module's installation coordinates, temperature sensors monitor localized temperature rise on the assembly table, and industrial cameras record visual images of the assembly process frame by frame. These initial data streams are transmitted to the central processing unit in real time. In one possible implementation, the system employs a pre-trained random forest classification model to initially filter the positional deviation and temperature data.

[0017] Specifically, the preset threshold for positional deviation is ±15 micrometers. When the real-time acquired X-axis deviation reaches 20 micrometers, the data point is marked as abnormal, and an abnormal data range is defined by extending a time window forward and backward by 0.5 seconds from this point. For this abnormal range, the system automatically indexes the corresponding time segment from the massive image records.

[0018] For example, at time T, an image fragment shows a visible gap at the expected fit between the module edge and the reference fixture. Through manual verification or a pre-set image comparison algorithm, a significant assembly deviation is identified at this point. Subsequently, this portion of the image undergoes detailed analysis. The Canny edge detection method is used to extract the difference region between the module contour and the reference contour, thereby obtaining the specific shape and pixel distribution information of the deviation region.

[0019] For example, the analysis revealed that the deviation mainly manifested as an arc-shaped gap band approximately 5 pixels long and of uneven width. Next, the system correlated and analyzed the temperature change data with the deviation distribution information.

[0020] Understandably, during the abnormal time period, the temperature sensor recorded a local temperature fluctuation at the assembly point ranging from 22.5 degrees Celsius to 24.8 degrees Celsius. Calculations revealed a high degree of synchronization between the area change in the deviation region and the temperature fluctuation curve, with a Pearson correlation coefficient of 0.87. Based on this, it was determined that the temperature increase was the primary factor contributing to the increased positional deviation. Following this high correlation conclusion, the system traced environmental monitoring records from the same time period to check for other abnormal factors besides temperature.

[0021] For example, humidity records were stable and vibration spectra were normal, but a brief abrupt change in the airflow direction at the air conditioner vent was observed, which may have led to localized uneven thermal fields. Based on the above analysis chain, the system generates targeted data adjustment strategies.

[0022] In one embodiment, the optimization scheme includes: First, setting stricter warning thresholds for temperature parameters in the monitoring system, for example, triggering an alarm when the rate of change exceeds 0.5 degrees Celsius per minute. Second, adjusting the image acquisition triggering logic so that when the correlation between temperature and position deviation exceeds 0.8, the image sampling frequency of the corresponding workstation is automatically increased. Finally, adding prompts to the assembly process guidance so that when the system alarms, the operator should check the local heat dissipation and airflow conditions. These strategies together constitute the optimized assembly process monitoring scheme, the beneficial effect of which is to achieve a closed loop from data anomaly perception and multi-source information correlation to root cause tracing and strategy generation, thereby improving the initiative and accuracy of quality control in the precision assembly process.

[0023] S102. Based on the real-time dynamic information flow, data analysis methods are used to process the uneven distribution in high-frequency operations and determine the deviation index of the current assembly state.

[0024] By acquiring high-frequency operation data records from information flow through real-time dynamic monitoring, the fluctuation range of operation frequency is determined. Based on the fluctuation range of operation frequency, data analysis methods are used to decompose the uneven distribution phenomenon and obtain specific patterns of uneven distribution. For specific patterns of uneven distribution, information processing technology is used to analyze the assembly status layer by layer to identify anomalies in the status assessment. If the anomalies in the status assessment exceed a preset threshold, deviation identification technology is used to quantify the degree of deviation and determine the distribution range of the deviation degree. Based on the distribution range of the deviation degree, time series data from dynamic monitoring is acquired to determine the stability performance of the assembly status in different time periods. Based on the analysis results of stability performance, combined with data analysis methods, the adjustment strategy for high-frequency operations is optimized to obtain the final deviation control scheme.

[0025] In the field of precision assembly of optoelectronic modules, real-time dynamic monitoring systems continuously capture data records of operators performing high-frequency actions such as screw fastening, lens focusing, or fiber end face cleaning.

[0026] For example, the system records the timestamps of operational events at a frequency of tens of times per second using sensors installed on tools or workbenches. By statistically analyzing several hours of data within a production batch, the normal fluctuation range of this operational frequency can be determined. For instance, an average of 12 latching operations per minute has a normal fluctuation range of 10 to 14 times per minute. When the monitored frequency is consistently below 10 times or above 14 times, it indicates an uneven distribution of production rhythm. To address this uneven distribution, in-depth data analysis methods are needed.

[0027] Specifically, time series analysis can be used to identify specific patterns of uneven distribution, such as periodic fluctuations, sudden stagnation, or upward trends.

[0028] In one possible implementation, analysis revealed a regular decrease in operation frequency during specific periods each afternoon, possibly due to a slowdown caused by personnel fatigue or changes in ambient light. Another pattern might manifest as a sudden drop in frequency after a material batch change, suggesting potential problems with material compatibility or preparation. Based on the identified patterns, information processing techniques are used to analyze the assembly status layer by layer.

[0029] For example, during periods of periodic slowdown, the system correlates and analyzes vibration monitoring data from assembly stations with preliminary light transmission test results from modules. Through layer-by-layer comparison, it determines if there are any anomalies in the status assessment, such as whether the dispersion of light transmission power is increasing synchronously. If this dispersion exceeds a preset threshold, a deviation identification process is triggered. Next, deviation identification technology quantifies the degree of deviation.

[0030] Understandably, the system will calculate the magnitude and duration of the optical power deviation from the standard value, and based on historical experience data, classify the degree of deviation into different distribution ranges such as slight, moderate, and severe.

[0031] For example, power fluctuations within ±5% of the standard value are considered normal, ±5% to ±10% are considered a warning range, and deviations exceeding ±10% are considered severe deviations. Based on the determined deviation range, the system will retrospectively acquire dynamic monitoring time-series data for the corresponding time period, such as operating frequency, fixture pressure, and ambient temperature and humidity. By comprehensively analyzing this data, the stability of the assembly status at different time periods can be determined.

[0032] For example, analysis might reveal that during periods when the operating frequency enters the warning range, the ambient temperature also fluctuates by more than ±2 degrees Celsius, and the assembly stability of the modules significantly decreases. Ultimately, based on the analysis results of the aforementioned stability performance, and combined with data analysis methods, the adjustment strategy for high-frequency operations is optimized. One embodiment is that, for the slowdown in pace and quality fluctuations caused by fatigue in the afternoon, the system can generate a deviation control scheme, suggesting the introduction of short, mandatory breaks during this period, or automatically adjusting the auxiliary parameters of the assembly equipment to compensate for the natural decline in operator precision. Another solution is to optimize the pre-inspection process and operational prompts before material loading to address anomalies caused by material changes. These adjustments aim to fundamentally mitigate abnormal fluctuations in operating frequency, thereby stabilizing the assembly process and improving product consistency and yield.

[0033] S103. If the deviation index exceeds the preset threshold, the caching mechanism is triggered to write the deviation index of the current assembly state and the related dynamic information flow into the temporary storage area to obtain the interruption protection data packet.

[0034] If the deviation index exceeds a preset threshold, the monitoring system captures detailed data of the current assembly status and performs preliminary processing based on the dynamic information flow to obtain an initial status dataset. Based on this initial status dataset, a caching mechanism is used to process the processed deviation index and dynamic information in layers, writing them to a temporary storage area to determine the cached data packets. Using these cached data packets, data integrity is verified for interruption protection requirements. If the verification result indicates missing data, supplementary information is retrieved from the assembly status to obtain a complete protection dataset. Based on the complete protection dataset, the flow pattern of dynamic information is analyzed. If abnormal fluctuations occur during the flow, a backup storage path is triggered to ensure the stability of data writing, determining a stable storage result. Using the stable storage result, data is distributed for status monitoring requirements, storing data packets in designated storage units and recording the trigger time to obtain a distribution completion identifier. Based on the distribution completion identifier, interruption protection logs are generated, and combined with the information flow trajectory data, a traceable data link is formed to determine the final protection data packet. Using the final protection data packet, the trigger conditions of the caching mechanism are periodically updated. If a new abnormal deviation index is detected, the data writing process is restarted to obtain an updated storage status.

[0035] For example, in the field of assembly status monitoring, when deviation indicators exceed preset thresholds, the monitoring system can capture detailed data and perform preliminary processing. Suppose that on an automotive parts assembly line, the system detects that the installation angle deviation of a key component reaches 5 degrees, while the preset threshold is 3 degrees. The monitoring system will immediately record various parameters of the current assembly status, such as installation angle, pressure value, and time point, forming an initial status dataset. The purpose of this process is to provide a reliable data foundation for subsequent analysis and ensure the traceability of deviation issues.

[0036] For example, when using a caching mechanism to perform layered data processing based on the initial state dataset, deviation indicators and dynamic information flows can be written to a temporary storage area in chronological order and according to importance. Assume the system stores the installation angle deviation data and corresponding operation time points as a 2MB data packet with high priority to ensure fast retrieval in subsequent processing. This layered processing method helps improve data retrieval efficiency, especially in high-frequency operation environments, avoiding data corruption or loss.

[0037] For example, when performing data integrity checks to address interruption protection requirements, if the system finds that some time point records are missing from the data packet, it will retrieve the supplementary information from the assembly status. Suppose that in the assembly line scenario described above, pressure value data for a certain time period is missing; the system will re-collect data for that time period using backup sensors to form a complete protection dataset. This approach ensures data integrity and provides comprehensive support for subsequent analysis.

[0038] For example, when analyzing the dynamic flow of information, if abnormal fluctuations are detected during the flow, such as a sudden drop in data transmission rate to 50% of its normal value, the system will trigger a backup storage path to write the data to the backup storage unit, ensuring the stability of the data write. This mechanism is particularly important in high-frequency operation scenarios, as it can effectively prevent data loss due to network fluctuations.

[0039] For example, when distributing data for status monitoring needs, the system stores the data packets in a designated storage unit and records the time of the trigger condition. Suppose that in an assembly line, a batch of data packets is distributed to a long-term storage unit, and the trigger time is recorded as 14:30, forming a distribution completion marker. This method facilitates subsequent data retrieval and problem tracing.

[0040] For example, when generating interruption protection logs, the system combines information flow trajectory data to form a traceable data link. Suppose the log shows that a data packet passed through three nodes during transmission, the system will record the processing time and status of each node in detail, forming the final protected data packet. This link recording helps to quickly locate the root cause of the problem.

[0041] For example, when the cache mechanism is periodically updated, if a new abnormal deviation indicator is detected, such as an increase in the installation angle deviation to 6 degrees, the system will restart the data writing process and update the storage status. This dynamic adjustment mechanism can adapt to real-time changes on the assembly line, ensuring the flexibility and reliability of data management.

[0042] S104. Extract the historical dynamic information stream from the interruption protection data packet, and use the data reconstruction method to restore the continuous sequence of operations before the abnormal interruption, so as to obtain the restored assembly state.

[0043] The historical flow and dynamic information in the protection package are obtained. A reconstruction method is used to perform sequence chain analysis on the historical flow. If a continuous break exists in the sequence chain, it is determined to be the position before the interruption. The operation sequence at the break is supplemented based on the dynamic information. The supplemented operation sequence is integrated to generate a restored state sequence. The final assembly state value is calculated based on the restored state sequence.

[0044] For example, when analyzing historical and dynamic information within a protective package, one can begin by ensuring the completeness of the data. Historical information typically records a series of operational trajectories during the assembly process, while dynamic information reflects real-time state changes. Suppose that in an assembly scenario, the historical information contains key operational records of a device over the past 24 hours, such as the start time and type of assembly actions, while the dynamic information includes the current operating parameters of the device, such as real-time data on speed and pressure. Extracting this data can lay the foundation for subsequent sequence chain analysis.

[0045] For example, when using the reconstruction method to perform sequence chain analysis on historical data, the core lies in clarifying the temporal order and logical relationships of operations. Suppose the historical data records 10 consecutive operations in a certain assembly process, but the timestamp of the 5th operation is missing, causing a break in the sequence chain. In this case, the break point can be determined as the critical point before the interruption. The principle of the reconstruction method is to infer the missing content by analyzing the logical relationships between preceding and following operations. For example, based on the end time of the previous operation and the start time of the next operation, the approximate time range of the missing operation can be estimated. This method helps to quickly locate the problem point and provides a basis for subsequent supplementation.

[0046] For example, to supplement the operation sequence at the break point in the sequence chain, real-time data from dynamic information can be used for assistance. Suppose the dynamic information shows that the equipment's operating speed suddenly decreased during the break period. Combining this with the types of operations before and after in the historical stream, it can be inferred that the missing operation might be equipment adjustment or a pause. By supplementing this inferred operation sequence into the sequence chain, a more complete operation sequence can be formed. This supplementation method can effectively restore the actual situation during the assembly process and ensure the continuity of the data chain.

[0047] For example, when integrating the supplemented operation sequence and generating the recovery state sequence, the focus is on verifying the rationality of the supplementary content. Assuming the supplemented operation sequence indicates that the device completed an adjustment within a certain time period, the recovery state sequence needs to reflect the impact of this adjustment on subsequent operations, such as whether the device's operating parameters have returned to normal after the adjustment. By integrating all operation sequences to form a complete recovery state sequence, reliable data support can be provided for subsequent state value calculations.

[0048] For example, when calculating the final assembly state value based on the recovery state sequence, the final state can be determined by analyzing the impact of each operation in the sequence on the assembly result. Assuming the recovery state sequence shows that a device operates stably after adjustment, and subsequent operations all meet expectations, then the final assembly state value can reflect a high stability index, such as 90% completion. This calculation method can intuitively reflect the overall effect of the assembly process, providing a reference for subsequent optimization. Such analysis and calculation processes not only help identify potential problems but also provide data support for improving the assembly process.

[0049] For example, from another perspective, the generation of the recovery state sequence can also be calibrated by incorporating long-term trends in historical data. Suppose the historical data shows that a device experienced brief interruptions in several similar operations in the past, but ultimately recovered. Then, when generating the recovery state sequence, this trend can be referenced to reduce excessive focus on individual interruptions, thereby improving the accuracy of the state values. This multi-faceted analysis approach can verify the rationality of the data from different dimensions, ensuring the reliability of the final results.

[0050] For example, in practical applications, the above method can be extended to more complex assembly scenarios. Suppose an assembly process involves the collaborative work of multiple devices; analysis of historical flow and dynamic information can help identify collaboration problems between devices, such as whether an interruption of a device affects the overall process. Through targeted supplementation and recovery state sequence generation, a basis for optimizing the entire process can be provided. This extended application further demonstrates the method's adaptability to multiple scenarios and helps improve overall assembly efficiency.

[0051] S105. For the restored assembly state, obtain the matching degree between the subsequent real-time dynamic information stream and the interruption protection data packet, and determine whether it is necessary to adjust the position deviation to maintain operation continuity.

[0052] The system acquires restored assembly status data and continuously tracks the status using a pre-established monitoring module to obtain real-time changes in the assembly status. Based on these real-time changes, it acquires subsequent real-time dynamic information streams and uses streaming processing technology to analyze the information flow and determine its correlation with the assembly status. From the correlation analysis of the information flow, it extracts data packets related to interruption protection. If the data packet body is inconsistent with the preset protection standard, a comparison algorithm is used to determine the degree of matching. Based on the degree of matching, it analyzes whether there is a significant shift in positional deviation. If the positional deviation exceeds a preset threshold, a dynamic adjustment mechanism is triggered to obtain adjusted positional data. Based on the adjusted positional data, it monitors the stability of operational continuity by updating the real-time dynamic information stream to determine whether operational continuity is disturbed. Based on the operational continuity determination result and the feedback data from status monitoring, it verifies the accuracy of information matching and determines the final system operating status.

[0053] For example, when acquiring restored assembly status data, a pre-set monitoring module can continuously track the status. Assuming an industrial assembly scenario, the monitoring module collects assembly status data every 5 seconds, recording the position and angle information of key components. This real-time tracking helps the system quickly identify status changes; for instance, when a component moves from position A to position B, the system immediately updates the data stream to ensure the accuracy of subsequent analysis.

[0054] For example, when acquiring dynamic information streams based on real-time changes in assembly status, streaming processing techniques can be used to analyze the information flow. Assuming the information stream contains data on the speed and direction of component movement, the system will parse this information line by line, determining its relevance to the assembly status. For instance, if a component's movement speed suddenly increases, the system will analyze whether this is related to the current assembly task, thus avoiding interference from irrelevant data.

[0055] For example, when extracting data packets related to interruption protection, a comparison algorithm can be used to determine their degree of matching with preset protection standards. Assuming the data packet contains operation logs from before the interruption, the system will compare them one by one with standard logs. If the matching degree is only 70%, further analysis will be conducted to determine if there are potential risks. This approach helps to detect problems promptly and ensure the security of system operation.

[0056] For example, when analyzing whether a positional deviation is significant, a threshold can be set, such as triggering a dynamic adjustment mechanism if the deviation exceeds 2 millimeters. Suppose the actual position of a component deviates from the target position by 3 millimeters, the system will automatically activate the adjustment mechanism and generate new position data. This mechanism can effectively reduce the impact of deviations and improve assembly accuracy.

[0057] For example, when monitoring the stability of operational continuity based on adjusted location data, real-time updates of the dynamic information stream can be used to determine if interference has occurred. Assuming the information stream indicates that operational continuity has returned to normal after the adjustment, the system will record this status to ensure that subsequent operations are not interrupted by interference. This monitoring method helps maintain system stability.

[0058] For example, when verifying the accuracy of information matching by combining status monitoring feedback data, the final system operating status can be determined through multi-dimensional data comparison. Assuming the feedback data indicates that the information matching accuracy reaches 95%, the system will confirm that the current operating status is good and continue to execute the task. This verification method can improve the reliability of the system and ensure accurate judgment of the operating status. Through the above analysis and examples, we can see the specific implementation methods of each technical topic in practical applications. Whether it's status monitoring, streaming processing, deviation adjustment, or continuous monitoring, all are closely related to the business areas of assembly status recovery and interruption protection. These methods are not only logically rigorous but also effectively improve the stability and accuracy of the system in actual operation, providing reliable support for industrial assembly scenarios.

[0059] S106. If the matching degree is lower than a preset threshold, the restored assembly state and the newly added dynamic information flow are fused by a data integration method to determine an optimized assembly parameter sequence.

[0060] Acquire the recovered assembly status data and newly added dynamic information flow data. Process the assembly status data and dynamic information flow data using a preset fusion method. If the integration degree after fusion is higher than a preset value, extract dynamic quantity features. Adjust the sequence values ​​of the parameter column based on the dynamic quantity features and optimization criteria. Analyze the mapping relationship between the sequence values ​​and the assembly status using a linear regression model. Determine the optimal assembly parameter sequence that satisfies the mapping relationship.

[0061] In one possible implementation, when acquiring restored assembly status data and newly added dynamic information flow data, the restored position coordinates and velocity parameters can be collected from sensors on the assembly line. For example, the restored status data includes the coordinates of the component position at x=10, y=5, while the newly added dynamic information flow data covers real-time velocity changes such as a flow value of 2 m / s. This acquisition method ensures the timeliness of the data and is beneficial to the accuracy of subsequent processing.

[0062] In one possible implementation, a pre-defined fusion method is used to process these data. For example, a weighted average algorithm is used to fuse the coordinates of the assembly status data with the velocity of the dynamic information flow to calculate a comprehensive vector. If the fused integration degree is calculated to be 0.85, which is higher than the preset value of 0.7, it indicates strong data consistency and is beneficial to improving the system's response speed to assembly changes.

[0063] For example, when extracting dynamic features, velocity fluctuation features can be extracted from the fused data, such as feature values ​​in the range of 3-5 m / s. This helps to identify potential interruption risks and provides a basis for optimization.

[0064] In one possible implementation, the sequence values ​​of the parameter column are adjusted according to the dynamic characteristics and optimization objectives. For example, if the optimization objective is to minimize positional deviation, and the characteristics show large fluctuations, the sequence values ​​are adjusted from the initial [1,2,3] to [1.2,2.5,3.1]. This adjustment helps maintain the continuity of assembly and avoids operational interruptions.

[0065] For example, when using a linear regression model to analyze the mapping relationship between sequence values ​​and assembly status, the adjusted sequence values ​​are input, and the model fits a relationship such as a positive correlation between the degree of status improvement and the sequence. The analysis process shows that when the sequence value increases to 3.1, the stability of mapping to the assembly status improves by 20%, which is helpful in predicting potential deviations.

[0066] In one possible implementation, the optimal sequence of assembly parameters that satisfies the mapping relationship is determined, for example by iteratively selecting the sequence [1.2,2.5,3.1] as the optimal value, ensuring that the assembly position deviation is less than 0.5, which is beneficial to the stability and efficiency of the overall operation.

[0067] S107. Based on the optimized assembly parameter sequence, control commands are generated and transmitted to the assembly equipment to obtain a continuously executed precision assembly process.

[0068] The assembly process acquires pre-established assembly parameter sequence data. By parsing key fields, it determines the execution order and parameter configuration of each step in the assembly process. For the parsed parameter configuration, an instruction generation module converts the parameter sequence into specific control instructions, obtaining operation codes recognizable by the equipment. The generated operation codes are sent to the assembly equipment via a transmission module, completing the instruction issuance and equipment reception confirmation. When the equipment receives the control instructions, a continuous execution mechanism is triggered, driving the assembly equipment to complete each step sequentially according to the instructions, obtaining real-time execution status feedback. Based on the execution status feedback, it is determined whether there are deviations or anomalies. If the feedback data exceeds a preset threshold range, a correction mechanism is initiated to adjust the generation logic of subsequent instructions, determining an optimized execution path. Using the optimized execution path, the assembly equipment's operation instructions are updated, driving the equipment to achieve precise assembly according to the adjusted process, obtaining the final assembly result. Based on the final assembly result, execution efficiency data is recorded and stored in a preset database for reference in subsequent process optimization, completing the closed-loop processing of the entire assembly process.

[0069] For example, in the precision assembly scenario of a smartphone camera module, the system first acquires pre-established assembly parameter sequence data.

[0070] Specifically, the sequence data contains key fields for lens capture, adhesive dispensing, and bonding. By analyzing these fields, it can be determined that the execution order is adhesive dispensing first, followed by bonding, and parameters such as adhesive dispensing pressure of 2.5 MPa and bonding depth of 0.15 mm can be extracted.

[0071] It should be noted that this precise analysis ensures the accuracy of the baseline data for subsequent operations, preventing damage to precision modules due to incorrect parameters and laying a data foundation for the entire automated process.

[0072] For example, the instruction generation module converts the parsed parameter configuration into operation code that the device can recognize.

[0073] Specifically, the 2.5 MPa dispensing pressure is converted into low-level electrical signal commands that control the opening angle and timing of the dispensing valve. These operation codes are then sent to the robotic arm and dispensing machine via a transmission module, and the equipment returns an acknowledgment signal upon receiving the commands.

[0074] It should be noted that this process achieves a seamless connection between digital parameters and physical actions, significantly improving the real-time nature of command issuance and the accuracy of device response.

[0075] For example, after receiving an instruction, the device triggers a continuous execution mechanism, and the robotic arm performs grasping and dispensing operations in sequence, and provides real-time feedback on the execution status.

[0076] Specifically, if the actual dispensing pressure reported by the sensor reaches 2.8 MPa, exceeding the preset threshold range of 2.4 to 2.6 MPa, the system immediately activates a correction mechanism. At this time, the system adjusts the generation logic of subsequent instructions and fine-tunes the closing time of the dispensing valve to determine the optimized execution path.

[0077] It should be noted that this dynamic correction mechanism can effectively prevent the generation of defective products such as glue overflow or insufficient glue, and significantly improve the assembly yield.

[0078] For example, through the optimized execution path, the system updates the operation instructions of the assembly equipment, driving the robotic arm to complete the final precision bonding of the camera module according to the adjusted process.

[0079] Specifically, after assembly is completed, the system will record the execution efficiency data such as the time consumed per unit and the number of abnormal corrections during the assembly, and store it in the preset production database.

[0080] It should be noted that this historical data provides a reliable reference for subsequent optimization of dispensing pressure benchmarks and robotic arm motion trajectories, thereby completely opening up a closed-loop process for the entire assembly process and achieving continuous iterative improvement in production efficiency and process precision.

[0081] If the technical solution of this application involves the collection, storage, use, processing, transmission, provision, disclosure, or deletion of personal information, the products using this technical solution have clearly and understandably informed the users of the personal information processing rules before processing personal information, and have obtained the individuals' voluntary consent in accordance with the law. If the technical solution of this application involves sensitive personal information (such as biometrics, religious beliefs, specific identities, medical and health information, financial accounts, and location tracking), the products using this solution have obtained the individuals' separate consent before processing sensitive personal information, and have also met the requirement of "express consent," ensuring that individuals make authorization decisions voluntarily based on full knowledge.

[0082] Specific implementation methods include, but are not limited to, the following: setting up clear and prominent signs at personal information collection devices such as cameras and sensors to inform relevant personnel that they have entered the scope of personal information collection and that their personal information will be collected and processed. If an individual voluntarily enters the collection scope after being informed, it is deemed that they have agreed to the collection of their personal information; or using obvious icons, text descriptions, or other means on the terminal device or system interface for personal information processing to inform them of the rules for personal information processing, and obtaining the individual's explicit authorization through interactive methods such as pop-up prompts, check confirmation boxes, or asking the individual to upload their personal information themselves.

[0083] The aforementioned personal information processing rules should include, but are not limited to, the name and contact information of the personal information processor, the specific purpose of personal information processing, the processing method, the types of personal information processed, the retention period, and the methods and procedures for individuals to exercise their relevant rights.

[0084] It should be noted that the above examples are merely some specific embodiments of the present invention. Obviously, the present invention is not limited to the above embodiments and many variations are possible. All variations that can be directly derived or conceived by those skilled in the art from the content disclosed in this invention should be considered within the scope of protection of this invention.

Claims

1. An intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules, characterized in that, The method includes: By deploying a sensor network in the precision assembly environment of optoelectronic modules, diverse data such as position deviation, temperature change and image recording are collected from the assembly process to obtain a real-time dynamic information stream; Based on the real-time dynamic information flow, data analysis methods are used to process the uneven distribution in high-frequency operations and determine the deviation index of the current assembly state. If the deviation index exceeds the preset threshold, the caching mechanism is triggered to write the deviation index of the current assembly state and related dynamic information stream into the temporary storage area to obtain the interruption protection data packet. Historical dynamic information streams are extracted from the interruption protection data packets, and the continuous sequence of operations before the abnormal interruption is restored using a data reconstruction method to obtain the restored assembly state. For the restored assembly state, the matching degree between the subsequent real-time dynamic information stream and the interruption protection data packet is obtained to determine whether the position deviation needs to be adjusted to maintain operation continuity. If the matching degree is lower than the preset threshold, the restored assembly state and the newly added dynamic information flow are fused by the data integration method to determine the optimized assembly parameter sequence. Based on the optimized assembly parameter sequence, control commands are generated and transmitted to the assembly equipment to obtain a continuously executed precision assembly process.

2. The intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules according to claim 1, characterized in that, The sensor network deployed in the precision assembly environment of the optoelectronic module collects diverse data such as position deviation, temperature change, and image recording during the assembly process to obtain a real-time dynamic information stream, including: Multidimensional data is acquired from the precision assembly environment of optoelectronic modules through a sensor network. Real-time acquisition is performed on position deviation, temperature change and image recording to obtain an initial data stream. Based on the initial data stream, a pre-established classification model is used to initially screen for position deviations and temperature changes. If the position deviation exceeds the preset threshold, it is marked as an abnormal data point, and the range of abnormal data is determined. For the range of abnormal data, visual information for the corresponding time period is extracted from the image records, and image segments related to the positional deviation are obtained to determine whether there is an obvious assembly deviation. Based on the judgment results of the image segments, if there are obvious assembly deviations, the image segments are compared in detail, and the edge detection method is used to extract the contour features of the deviation area to obtain the distribution information of the deviation area. By combining the distribution information of the deviation area with temperature change data, we can analyze the degree of influence of temperature on the position deviation and determine the correlation between temperature change and deviation distribution. Obtain the correlation analysis results, and for temperature change data with high correlation, trace the environmental monitoring records during the assembly process to determine whether there are any abnormal environmental factors. Based on the judgment results of environmental monitoring records, targeted data adjustment strategies are generated to obtain an optimized assembly process monitoring scheme.

3. The intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules according to claim 1, characterized in that, The step of processing uneven distribution in high-frequency operations using data analysis methods based on the real-time dynamic information flow to determine the deviation index of the current assembly state includes: By monitoring in real time, data records of high-frequency operations are obtained from the information flow to determine the fluctuation range of the operation frequency; Based on the fluctuation range of the operating frequency, data analysis methods are used to decompose the uneven distribution phenomenon and obtain the specific pattern of uneven distribution. For specific patterns of uneven distribution, information processing technology is used to analyze the assembly status layer by layer to identify anomalies in the status assessment. If the outliers in the status assessment exceed the preset threshold, the degree of deviation is quantified by deviation identification technology to determine the distribution range of the degree of deviation. Based on the distribution range of the degree of deviation, time series data in dynamic monitoring are obtained to determine the stability of the assembly status in different time periods. By analyzing the stability performance and combining it with data analysis methods, the adjustment strategy for high-frequency operations is optimized to obtain the final deviation control scheme.

4. The intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules according to claim 1, characterized in that, If the deviation index exceeds a preset threshold, a caching mechanism is triggered to write the deviation index of the current assembly state and related dynamic information stream into a temporary storage area, resulting in an interruption protection data packet, including: If the deviation index exceeds the preset threshold, the monitoring system will capture detailed data of the current assembly status and combine it with the dynamic information flow for preliminary processing to obtain the initial status dataset. Based on the initial state dataset, a caching mechanism is used to perform hierarchical processing on the sorted deviation indicators and dynamic information, and write them into a temporary storage area to determine the cached data packets. Using the cached data packets, perform data integrity verification for interruption protection requirements. If the verification result shows that data is missing, retrieve supplementary information from the assembly state to obtain a complete protection dataset. Based on the complete protection dataset, analyze the flow pattern of dynamic information. If abnormal fluctuations occur during the flow, trigger the backup storage path to ensure the stability of data writing and determine the stable storage result. By stabilizing the storage results, data is distributed to meet the needs of status monitoring. Data packets are stored in designated storage units, and the time points of triggering conditions are recorded to obtain the distribution completion identifier. Based on the distribution completion identifier, an interruption protection log record is generated. Combined with the information flow trajectory data, a traceable data link is formed to determine the final protection data packet. By using the final protection data packet, the triggering conditions of the caching mechanism are updated periodically. If a new abnormal deviation indicator is detected, the data writing process is restarted to obtain the updated storage state.

5. The intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules according to claim 1, characterized in that, The step of extracting historical dynamic information streams from the interruption protection data packet, using a data reconstruction method to restore the continuous sequence of operations before the abnormal interruption, and obtaining the restored assembly state includes: Obtain historical and dynamic information from the protection package; The reconstruction method was used to perform sequence chain analysis on historical flows; If there is a continuous break in the sequence chain, it is determined to be the position before the interruption; The operation sequence at the fracture point is supplemented based on the dynamic information; The integrated and supplemented operation sequence is used to generate a recovery state sequence; The final assembly state value is calculated based on the recovery state sequence.

6. The intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules according to claim 1, characterized in that, The step of obtaining the matching degree between the subsequent real-time dynamic information stream and the interruption protection data packet for the restored assembly state, and determining whether the positional deviation needs to be adjusted to maintain operational continuity, includes: The assembly status data after recovery is obtained, and the status is continuously tracked through a pre-established monitoring module to obtain the real-time changes in the assembly status. To detect real-time changes in the assembly status, the system acquires subsequent real-time dynamic information streams and uses streaming processing technology to analyze the information flow direction, determining the correlation between the information flow direction and the assembly status. From the correlation analysis of information flow, extract the data packet body related to interruption protection. If the data packet body is inconsistent with the preset protection standard, the degree of matching is judged by the comparison algorithm. Based on the degree of matching, analyze whether there is a significant shift in positional deviation. If the positional deviation exceeds a preset threshold, a dynamic adjustment mechanism is triggered to obtain the adjusted positional data. Based on the adjusted location data, monitor the stability of operational continuity and determine whether operational continuity is disturbed by updating the real-time dynamic information flow; Based on the judgment results of continuous operation and combined with the feedback data of status monitoring, the accuracy of information matching is verified to determine the final system operating status.

7. The intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules according to claim 1, characterized in that, If the matching degree is lower than a preset threshold, the restored assembly state and the newly added dynamic information flow are fused using a data integration method to determine an optimized assembly parameter sequence, including: Acquire the restored assembly status data and the newly added dynamic information flow data; A pre-defined fusion method is used to process assembly status data and dynamic information flow data; If the integration degree after fusion processing is higher than the preset value, then dynamic quantity features are extracted; Adjust the sequence values ​​of the parameter column based on the dynamic characteristics and optimization criteria; A linear regression model was used to analyze the mapping relationship between sequence values ​​and assembly state; Determine the optimal sequence of assembly parameters that satisfies the mapping relationship.

8. The intelligent monitoring and management system and method for the precision assembly process of optoelectronic modules according to claim 1, characterized in that, The step of generating control commands based on the optimized assembly parameter sequence and transmitting them to the assembly equipment to obtain a continuously executed precision assembly process includes: Obtain pre-established assembly parameter sequence data, and determine the execution order and parameter configuration of each step in the assembly process by parsing the key fields; For the parsed parameter configuration, an instruction generation module is used to convert the parameter sequence into specific control instructions, resulting in operation codes that can be recognized by the device. The generated operation code is sent to the assembly equipment through the transmission process module, completing the issuance of instructions and the receipt confirmation by the equipment. When the equipment receives a control command, it triggers a continuous execution mechanism, which drives the assembly equipment to complete each step of the operation in sequence according to the command content, and obtains real-time execution status feedback. Based on the execution status feedback, determine whether there are any deviations or anomalies. If the feedback data exceeds the preset threshold range, activate the correction mechanism, adjust the generation logic of subsequent instructions, and determine the optimized execution path. By optimizing the execution path, the operation instructions of the assembly equipment are updated, driving the equipment to perform precision assembly according to the adjusted process, and obtaining the final assembly result; Based on the final assembly result, the execution efficiency data is recorded and stored in a preset database for reference in subsequent process optimization, thus completing the closed-loop processing of the entire assembly process.

Images