A discharging screening and guiding system for LCD display

Abstract

The application discloses a discharging screening and guiding system of an LCD display screen and relates to the technical field of LCD liquid crystal display screens. A data acquisition module is used to acquire multi-modal parameters, an adaptive detection module is used to comprehensively analyze the screen through pre-classification, feature extraction and defect detection, an adaptive screening module is used to set a threshold according to the screen type and to weight the defect result, and a discharging guiding module is used to generate different signals according to the result, so that qualified products are discharged, unqualified products are repaired and cost evaluated, and then, it is determined whether the unqualified products are to be reworked or scrapped. The application solves the problem that the existing discharging screening and guiding system of an LCD display screen does not consider the differences in structure and performance of different types of screens, so that the detailed defects cannot be effectively identified. The application realizes comprehensive and accurate detection and reasonable discharging guiding of the LCD display screen.

Description

Technical Field

[0001] This invention relates to the field of LCD liquid crystal display technology, and more specifically to an output screening and guidance system for LCD displays. Background Technology

[0002] The production of LCD displays involves multiple sophisticated processes, including thin-film deposition, photolithography, and encapsulation. Improper operation in any single process can introduce different types of defects, leading to quality issues such as uneven display quality, bright spots, dark spots, color shift, and light leakage, making the displays unable to meet factory standards. Therefore, providing material screening guidance at the final stage of the production line helps to identify quality defects in LCD displays and reject unqualified displays.

[0003] Different types of LCD displays vary significantly in structure, pixel density, and display quality. High-resolution displays (such as 4K or higher resolution displays) have a higher number of pixels per inch and a lower tolerance for spatial defects. However, current technologies often use a uniform standard to guide the screening of different types of LCD displays, failing to consider the differences in structural and performance requirements between different screen types. This results in the inability to effectively identify detailed defects in LCD displays, affecting the display effect and quality, and may even lead to substandard products entering the market.

[0004] Therefore, an output screening guidance system for LCD displays is needed to solve the above problems. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention discloses a material screening and guidance system for LCD displays. Through the collaborative work of multiple modules, it achieves comprehensive and accurate detection and reasonable material discharge guidance for LCD displays.

[0006] The present invention adopts the following technical solution:

[0007] An LCD display screen discharge screening guidance system includes:

[0008] The data acquisition module is used to collect multimodal parameters of the display screen to be discharged;

[0009] The adaptive detection module includes a pre-classification unit, a feature extraction unit, and a defect detection unit. The pre-classification unit is used to identify the screen type of the display screen to be unloaded. The feature extraction unit is used to extract the spatial features, temporal features, and physical features of the display screen to be unloaded. The defect detection unit is used to perform spatial defect detection, temporal defect detection, and physical defect detection on the display screen to be unloaded.

[0010] The adaptive screening module sets the judgment threshold for defects in the display screen to be shipped based on the screen type, and performs adaptive weighting processing on the detection results of different defects according to the degree of impact of different defects on the quality of the display screen to be shipped. When the weighted score of all defect detection results is lower than the judgment threshold, it is judged as a qualified product; otherwise, it is judged as an unqualified product.

[0011] The material discharge guidance module generates a factory path guidance signal when the display screen determines that the material to be discharged is a qualified product. When the display screen determines that the material to be discharged is a non-qualified product, the repair cost of the non-qualified product is evaluated. If the repair cost is lower than the scrap loss, it is determined to be a rework product and a rework path guidance signal is generated. Otherwise, it is determined to be a scrap product and a scrap disposal guidance signal is generated.

[0012] Furthermore, the data acquisition module acquires the specifications of the display screen to be unloaded by scanning, and dynamically adjusts the flexible sensor array based on the acquired specifications to acquire multimodal parameters of the display screen to be unloaded. The specifications include the size, resolution, brightness and contrast of the display screen, and the multimodal parameters include visual images, electrical parameters, optical parameters and physical parameters. The flexible sensor array dynamically adjusts the arrangement of the sensors in the array, the sampling frequency and the measurement range through a microcontroller.

[0013] Furthermore, the pre-classification unit spatiotemporally aligns the collected visual images, electrical parameters, optical parameters, and physical parameters according to timestamps and spatial locations, and uses a multimodal fusion analysis model to analyze the collected multimodal parameters to identify the screen type of the display screen to be unloaded. The feature extraction unit adaptively adjusts the extraction degree of spatial features, temporal features, and physical features based on the screen type, and uses edge node distributed extraction to extract the spatial features, temporal features, and physical features of the display screen to be unloaded. The defect detection unit uses a self-supervised learning framework to perform spatial defect detection, temporal defect detection, and physical defect detection.

[0014] Furthermore, the multimodal fusion analysis model uses a multi-branch neural network to extract feature vectors corresponding to different modal parameters and inputs them into a classifier to identify the screen types corresponding to different modal feature vectors. Then, an attention mechanism is used to perform weighted fusion on the identified screen types to obtain the screen type of the display screen to be output. The screen types include at least organic light-emitting diode screens, curved screens, and liquid crystal displays.

[0015] Furthermore, the feature extraction unit employs a gating mechanism to control the activation ratio of the spatial feature channel, temporal feature channel, and physical feature channel. When extracting spatial features, the edge nodes use image segmentation and principal component analysis to extract the pixel arrangement, brightness distribution, and color distribution features of the visual image, and use edge detection to identify the edge and contour features of the display screen to be unloaded. When extracting temporal features, the edge nodes extract the response time and harmonic dynamic features of the display screen by performing time-frequency transformation on the current and voltage signals, and obtain dynamic contrast and afterimage features through the brightness change curve. When extracting physical features, the edge nodes establish a temperature gradient field feature model through thermal imaging, and obtain the curvature of the display screen to be unloaded by measuring the radius of curvature and curvature angle.

[0016] Furthermore, the self-supervised learning framework employs parallel computing for spatial defect detection, temporal defect detection, and physical defect detection. In spatial defect detection, a U-Net segmentation network is used to annotate defect regions at the pixel level and output the defect area ratio. In temporal defect detection, an LSTM time series prediction model is used to obtain the comparison deviation between the predicted response curve and the actual measured value. In physical defect detection, stress distribution is simulated based on finite element analysis, and the potential cracking risk rate is calculated based on measured vibration data.

[0017] Furthermore, the adaptive screening module stores the feature information of all known defects by constructing a dynamic defect library, and sets defect judgment thresholds for different types of screens according to the quality requirements for different screen types and known defect data. It also uses an improved hierarchical analysis method to adaptively weight the detection results of different defects. The improved hierarchical analysis method transforms subjective experience weight allocation judgment into objective quantitative weight allocation through fuzzy mathematics and dynamic feedback mechanism.

[0018] Furthermore, the working method of the improved analytic hierarchy process includes the following steps:

[0019] S1. Construct a three-layer indicator system, which includes a target layer, a criterion layer, and a solution layer. The target layer is the overall quality of the display screen, the criterion layer includes spatial defects, temporal defects, and physical defects, and the solution layer is the degree of impact of different defects on the quality of the output display screen.

[0020] S2. Triangular fuzzy numbers are used to quantify the indicators of the criterion layer and the scheme layer, and dynamic confidence intervals are constructed for different screen types, different production batches and different quality requirements.

[0021] S3. Based on the triangular fuzzy number and dynamic confidence interval obtained by quantization, a fuzzy judgment matrix is ​​constructed, and the weight is calculated by the extended analysis method, which comprehensively analyzes the influence weight of different indicators.

[0022] S4. The dynamic defect library updates the defect feature vector in real time. When a defect type update is detected, a weight redistribution is triggered.

[0023] Furthermore, the material discharge guidance module uses a multi-point operation control model to generate factory exit path guidance signals, rework path guidance signals, and scrap disposal guidance signals respectively. The multi-point operation control model uses a distributed operation node structure to independently control and make decisions on the factory exit decision node, rework decision node, and scrap disposal decision node. The factory exit decision node determines the optimal factory exit path for qualified products based on a preset factory layout and shipping process information database, and generates a factory exit path guidance signal according to coding rules. The rework decision node determines the optimal rework path for qualified products based on a preset factory layout and rework process information database, and generates a rework path guidance signal according to coding rules. The scrap disposal decision node determines the optimal rework path for reworked products based on defects in the reworked products and the workload at the rework location, and generates a rework path guidance signal according to coding rules. The scrap disposal decision node determines the optimal scrap disposal path for scrapped products based on a scrap disposal information database and scrap disposal area, and generates a scrap disposal guidance signal according to coding rules.

[0024] Furthermore, during the execution of the material screening guidelines, full-chain quality traceability is achieved by embedding blockchain hash values, and SPC control charts are used to display the distribution and frequency of detected defects in real time.

[0025] The beneficial effects of this invention are as follows:

[0026] 1. This invention acquires multimodal parameters, including visual images, electrical parameters, optical parameters and physical parameters, through a data acquisition module. This enables comprehensive acquisition of information about the display screen to be unloaded, greatly improving the accuracy of defect detection and reducing missed detections and false judgments.

[0027] 2. This invention first employs a pre-classification unit to identify screen types, enabling subsequent feature extraction and defect detection to be performed according to the characteristics of different screen types. This avoids potential misjudgments caused by standardized testing and significantly improves the accuracy of defect detection for different types of LCD displays. Then, the feature extraction unit extracts features from three dimensions: spatial, temporal, and physical. The defect detection unit also performs multi-dimensional detection accordingly, comprehensively identifying various potential defects in the display screen and further enhancing detection accuracy.

[0028] 3. This invention sets defect judgment thresholds based on screen type, fully considering the differences in defect tolerance among different screen types, making the screening results more consistent with reality. Furthermore, it adaptively weights the results according to the degree of impact of different defects on display quality, enabling a more scientific assessment of the overall display quality and avoiding the excessive influence of a single defect on the screening results, thus improving the rationality of the screening process.

[0029] 4. This invention generates corresponding path guidance signals based on the judgment results of the display screen. For qualified products, it directly guides them to leave the factory. For unqualified products, it conducts a repair cost assessment before deciding whether to rework or scrap them. This makes the entire material output process clearer and more efficient. By assessing the repair cost of unqualified products and prioritizing rework, it can reduce production costs and improve resource utilization while ensuring product quality. Attached Figure Description

[0030] Figure 1 This is a schematic diagram of the overall system architecture of the present invention;

[0031] Figure 2 This is a schematic diagram of the overall system flow of the present invention;

[0032] Figure 3 This is a flowchart illustrating the improved analytic hierarchy process in this invention. Detailed Implementation

[0033] The following will refer to the appendices in the embodiments of the present invention. Figure 1 To be continued Figure 3 The technical solutions in the embodiments of the present invention are clearly and completely described herein. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0034] This invention discloses a material screening and guidance system for LCD displays. This system achieves automated quality control throughout the entire LCD display material output process through four core modules: multimodal data acquisition, adaptive detection, dynamic screening, and intelligent guidance. The modules work collaboratively to ensure efficient and accurate screening of qualified products, reworked products, and scrapped products, as shown in the attached diagram. Figure 1 As shown, the system includes:

[0035] The data acquisition module is used to collect visual images, electrical parameters, optical parameters, and physical parameters of the display screen to be unloaded. It acquires images of the screen surface using a high-resolution industrial camera, supports multi-angle shooting, and measures voltage, current, response time, etc. using a multimeter or dedicated testing equipment. It uses a spectrum analyzer to detect brightness, contrast, color temperature, color gamut coverage, etc., and uses sensors to measure dimensions, thickness, weight, surface flatness, etc., and structures multimodal datasets for subsequent module processing.

[0036] The adaptive detection module is used for detailed detection and analysis of the display screen. This module is divided into three sub-units. The pre-classification unit identifies the type of display screen in advance based on the collected multimodal parameters. This step can quickly distinguish the different types of display screens, such as LED and OLED, providing a basis for subsequent detection.

[0037] The feature extraction unit extracts spatial features (such as scratches and cracks on the screen surface), temporal features (such as display stability and response time), and physical features (such as strength and weight) from multimodal parameters. These features are crucial for determining whether the screen is qualified. The defect detection unit performs defect detection based on the extracted features, which is divided into three categories: spatial defect detection: checking for visible defects on the screen surface, such as scratches, bubbles, and color differences; temporal defect detection: checking the display effect of the screen to see if there are problems such as color difference and uneven brightness; and physical defect detection: detecting whether the physical performance of the screen meets the standards, such as non-compliant size or abnormal weight.

[0038] The adaptive screening module sets appropriate defect judgment thresholds based on the screen type of the display. Different types of displays have different tolerances for defects, therefore, personalized judgment criteria need to be set. Among all defect detection results, each defect result is weighted according to its impact on the display quality. Each defect has a different weight; serious defects have a greater impact, while minor defects have a smaller weight. Finally, the quality of the display is comprehensively judged by the weighted score. When the weighted score is lower than the set judgment threshold, the display is judged as a qualified product; otherwise, it is judged as a defective product.

[0039] The material discharge guidance module generates corresponding guidance signals based on the judgment results of the adaptive screening module: Qualified Products: When a display screen is judged to be a qualified product, a factory exit path guidance signal is generated, guiding the display screen into the normal factory exit process. Unqualified Products: When a display screen is judged to be an unqualified product, the system will perform a repair cost assessment. If the repair cost is lower than the scrap loss, it is judged as a reworkable product, and a rework path guidance signal is generated; otherwise, it is judged as a scrapped product, and a scrap disposal guidance signal is generated.

[0040] The connection between the output of the data acquisition module and the input of the adaptive detection module; the connection between the output of the adaptive detection module and the input of the adaptive screening module; and the connection between the output of the adaptive screening module and the input of the discharge guidance module.

[0041] As attached Figure 2 As shown, the overall system process includes the following steps:

[0042] Step 1: Multimodal sensors synchronously acquire screen parameters;

[0043] Step 2: Adaptive detection of the display screen to be unloaded. The pre-classification unit identifies the screen type, the feature extraction unit extracts spatial, temporal, and physical features, and the defect detection unit performs multi-dimensional defect identification.

[0044] Step 3: Adaptive screening of the material to be discharged display screen is achieved through dynamic threshold determination and weighted scoring;

[0045] Step 4: Generate outgoing, rework, or scrap path signals based on the quality results to guide material output.

[0046] The data acquisition module obtains the specifications of the display screen to be unloaded through scanning and dynamically adjusts the configuration of the flexible sensor array based on these specifications. Specifically, this includes the following steps:

[0047] First, the module scans and acquires the key specifications of the display screen, including: the screen's physical dimensions, such as length and width; the number of pixels, typically expressed in horizontal and vertical pixels (resolution); the light intensity emitted by the display screen (brightness); and the brightness difference between the brightest and darkest areas of the display (contrast ratio). Based on the acquired specifications, the flexible sensor array dynamically adjusts its configuration, including: adjusting the sensor layout according to the size and resolution of the display screen to adapt to displays of different sizes and resolutions; adjusting the frequency of sensor data acquisition according to the display screen's operating characteristics (e.g., image refresh rate or the speed of change of displayed content) to capture accurate multimodal data; and adjusting the sensor's measurement range according to parameters such as brightness and contrast of the display screen to ensure accurate capture of relevant data.

[0048] Flexible sensor arrays are used not only to acquire traditional visual images but also to handle several other parameters, including: capturing images of the display screen through visual sensors (such as cameras or image sensors); electrical characteristics of the display screen such as current and voltage; optical characteristics of the display screen such as brightness, spectral distribution, and reflectivity; and environmental factors such as temperature, humidity, and pressure that may affect the display screen's performance. The microcontroller is responsible for real-time control and adjustment of the sensor array's operating mode, ensuring that the array's behavior is dynamically adjusted according to the display screen's specifications, thereby achieving efficient and accurate data acquisition.

[0049] In summary, by automatically adjusting the configuration of the flexible sensor array, the data acquisition module can flexibly collect various multimodal data related to the performance of different displays according to their specifications, so as to facilitate further analysis or application.

[0050] The pre-classification unit first aligns the data from different modalities (visual images, electrical parameters, optical parameters, and physical parameters) spatiotemporally using timestamps and spatial locations. This ensures that data collected by different sensors correspond at the same time and spatial location, improving the accuracy of the analysis. A multimodal fusion model is used to analyze various types of data, identifying the screen type of the display to be output by fusing features from different modalities. Multimodal fusion effectively integrates different types of signals and information, thereby improving classification accuracy. The multimodal fusion analysis model uses a multi-branch neural network, with each branch processing input data from different modalities (e.g., visual images, electrical signals). Each branch extracts feature vectors from different modalities, which are then identified by a classifier. Finally, these identification results are weighted and fused using an attention mechanism to output the final screen type. This method can identify different types of displays, including OLED screens, curved screens, and LCD screens.

[0051] The feature extraction unit adaptively adjusts its extraction strategies for spatial, temporal, and physical features based on the screen type. This helps extract more effective and relevant features across different display types. Edge nodes are used in a distributed computing approach to extract the spatial, temporal, and physical features of the display screen separately. Edge computing helps reduce the burden on the central processing unit and improves processing efficiency.

[0052] Spatial feature extraction: Pixel arrangement, brightness distribution, and color distribution features in the visual image are extracted through image segmentation and principal component analysis (PCA). Edge detection algorithms are used to identify the edges and contour features of the display screen. These features are crucial for subsequent defect detection and screen recognition.

[0053] Timing feature extraction: By performing time-frequency transformation on current and voltage signals, the screen's response time and harmonic dynamic features are extracted. Dynamic contrast and afterimage features are obtained through brightness variation curves.

[0054] Physical feature extraction: A temperature gradient field is established using thermal imaging technology to further extract the temperature distribution characteristics of the display screen. Furthermore, measuring the radius of curvature and angle of curvature can help assess the shape deformation of the display screen, especially for curved screens.

[0055] A self-supervised learning framework is used to detect spatial, temporal, and physical defects through parallel computing.

[0056] Spatial defect detection: Using the U-Net segmentation network for pixel-level annotation, it can accurately identify defect areas on the display screen and output the defect area percentage.

[0057] Timing defect detection: An LSTM (Long Short-Term Memory) time series prediction model is used to compare the deviation between the predicted response curve and the actual measured value to identify timing problems on the screen.

[0058] Physical defect detection: Based on finite element analysis (FEA) to simulate stress distribution and calculate potential cracking risk based on vibration data.

[0059] The adaptive detection module combines multimodal data analysis, deep learning, edge computing, and self-supervised learning to perform efficient defect detection across various display types. It can not only accurately identify screen types but also efficiently detect spatial, temporal, and physical defects, thereby improving the quality control level of displays.

[0060] The adaptive screening module stores feature information of all known defects by establishing a dynamic defect inventory. It then combines this information with the quality requirements of different screen types and known defect data to set defect judgment thresholds for different screen types. The dynamic defect inventory stores feature information on all known defects, including their type, location, size, shape, brightness, and color. This data is compiled based on historical inspection results or pre-collected quality data, providing a foundation for subsequent defect judgment. Defect judgment thresholds are dynamically set according to the different quality requirements of different screen types (such as LED screens and OLED screens). For example, some screen types may have a higher tolerance for a small range of defects, while others may have a lower tolerance. By analyzing historical defect data and the quality standards of different screen types, adaptive defect detection standards can be set for different types of screens.

[0061] The improved Analytic Hierarchy Process (AHP) performs multi-dimensional, hierarchical weighted analysis on defect detection results to obtain a final importance score for each defect detection result. This method assigns different weights to different types of defects to more accurately determine their impact on screen quality. "Improved" refers to the optimization of the traditional AHP method, particularly in the weight allocation and judgment matrix processing, employing more scientific and efficient strategies. Traditional AHP methods may rely too heavily on human experience, while the improved AHP method combines fuzzy mathematics and dynamic feedback mechanisms, resulting in more objective and accurate weight allocation.

[0062] Fuzzy mathematics is an effective method for handling uncertainty and ambiguity. In this system, fuzzy mathematics is used to quantify subjective experience, helping to solve the judgment ambiguity problems that may occur in traditional methods. Through fuzzy mathematics, subjective judgments can be transformed into clearer quantitative data, avoiding human bias. The dynamic feedback mechanism enables the system to adaptively adjust judgment criteria and weights based on changes in actual detection results. As detection data accumulates, the system can continuously optimize its weight allocation and defect threshold settings through feedback, improving overall detection accuracy and reliability.

[0063] Using the methods described above, the system can weight the detection results of different types of defects, assigning different weights to the impact of each defect based on its importance and the requirements of the screen type. This adaptive weighting process can more accurately identify which defects have a greater impact on screen quality, thereby improving screening efficiency and accuracy.

[0064] In summary, this adaptive screening module, by combining dynamic defect inventory, improved hierarchical analysis, fuzzy mathematics, and dynamic feedback mechanisms, can provide more accurate defect judgment criteria for different types of screens, and optimize defect detection results through adaptive weighting, thereby improving overall detection accuracy and screen quality control.

[0065] The improved analytic hierarchy process (AHP) combines fuzzy mathematics with a dynamic feedback mechanism to achieve a reasonable allocation of defect judgment weights, as shown in the attached figure. Figure 3 As shown, its workflow includes the following steps:

[0066] S1: Constructing a three-tiered indicator system

[0067] Target layer: This layer mainly focuses on the overall quality of the display screen, with the goal of evaluating the overall quality level of the display screen.

[0068] Criteria Layer: Includes three main defect types: Spatial Defects: Physical problems on the surface or structure of the display screen, such as dead pixels and bright pixels. Timing Defects: Timing synchronization problems that may occur during display screen operation, usually involving refresh rate, etc. Physical Defects: Hardware damage, manufacturing defects, etc. of the display screen.

[0069] Solution Layer: This layer assesses the impact of different defects on display quality. The severity of each defect affects the final quality evaluation.

[0070] S2: Quantization is performed using triangular fuzzy numbers.

[0071] Triangular fuzzy numbers are used to quantify indicators at the criterion and scheme layers. They can express the fuzziness and uncertainty of various indicators; for example, the impact of a defect on screen quality is not simply quantified, but could be described as "minor impact," "moderate impact," or "serious impact."

[0072] Dynamic confidence intervals are established for each indicator based on different screen types, production batches, and quality requirements. This helps to adjust judgment criteria in real time and improves adaptability.

[0073] S3: Construct the fuzzy judgment matrix and calculate the weights.

[0074] The fuzzy judgment matrix is ​​constructed by combining quantized triangular fuzzy numbers and dynamic confidence intervals to express the relationships and relative importance of various indicators.

[0075] The extended analysis method further calculates the weights of the fuzzy judgment matrix, comprehensively analyzing the influence weights of different indicators. By calculating the relative importance of each indicator, the degree of influence of each defect type on the overall quality of the display screen is determined.

[0076] S4: Real-time updates and weight redistribution of the dynamic defect library

[0077] The known defect feature vectors are updated in real time, and the defect database is updated when a new defect type is detected.

[0078] Once a new defect type is detected, the system automatically recalculates the defect weighting, thereby adjusting the results of the display quality assessment. This ensures that the system always makes judgments based on the latest defect data.

[0079] Through the above steps, the improved analytic hierarchy process (AHP), combined with fuzzy mathematics and a dynamic feedback mechanism, enables the defect detection process to adaptively adjust weights, objectively quantifying the impact of different defects on screen quality. This method not only improves the accuracy of defect detection but also updates and optimizes evaluation standards in real time according to changes in production conditions, enhancing the quality control level in the display production process. The material output guidance module uses a multi-point computational control model to generate outgoing path guidance signals, rework path guidance signals, and scrap processing guidance signals respectively. Its core function is to control different decision nodes through distributed computation to generate outgoing, rework, and scrap processing path guidance signals respectively. It can make optimal decisions for different product states (such as qualified products, reworked products, or scrapped products) and generate corresponding path guidance signals.

[0080] The multi-point operation control model adopts a distributed operation node structure, using multiple independent control nodes to manage different decisions. Each decision node corresponds to a different task: the outgoing decision node is responsible for determining the path of qualified products; the rework decision node is responsible for determining the path of reworked products; and the scrap decision node is responsible for determining the path of scrapped products.

[0081] The outgoing decision node uses factory layout information and a shipping process information database to determine the optimal outgoing route for qualified products and generates path guidance signals according to specific coding rules to ensure that qualified products can be successfully shipped. The rework decision node, based on the rework process information database and factory layout information, determines the optimal rework route for reworked products and generates corresponding rework path guidance signals. This ensures the efficiency and accuracy of the rework process. The scrap decision node, based on the defect data of reworked products and the workload at the rework location, determines whether rework is necessary and, if necessary, determines the disposal route for scrapped products using a scrap disposal information database. The generated scrap path guidance signals help products enter the scrap disposal process.

[0082] All decision-making nodes (shipment, rework, scrap) generate guidance signals according to coding rules. These signals help factory operators and automation systems understand the product's status during the production process and guide it onto the appropriate path, reducing errors and waste.

[0083] In summary, this system can effectively guide products along different paths during the production process, ensuring both efficient and precise material flow on the production line. This multi-point computational control model can significantly improve the intelligence level of production management and optimize the overall efficiency of the factory.

[0084] In the process of implementing the outgoing material screening guidelines, the combination of embedding blockchain hash values ​​and using SPC control charts can significantly improve the accuracy of product quality traceability and the visualization of process control.

[0085] Blockchain provides a secure and tamper-proof record system through its distributed ledger technology. By embedding blockchain hash values ​​in the material screening guidelines, end-to-end quality traceability of products can be achieved, ensuring that every stage from production and testing to shipment is recorded and cannot be tampered with. Whenever a product passes through a quality inspection stage, the system generates a hash value, recording the product's inspection data (such as defect type, inspector, timestamp, etc.). The hash value serves as a unique identifier for this data and is stored on the blockchain. Once data is embedded in the blockchain, it can never be modified or deleted. Even if problems arise later, it is possible to accurately trace back to each inspection stage and its specific data. Through blockchain technology, users or managers can query the production and inspection process of each product in real time to understand its quality status, thereby providing transparent quality information to consumers or regulatory authorities.

[0086] SPC (Statistical Process Control) helps companies identify potential quality fluctuations and ensure product stability by monitoring and analyzing process data in real time. SPC control charts display the distribution and frequency of defects in real time, allowing inspection personnel to observe the status of quality control during production. When product quality deviates from its target, the control chart quickly reflects this, alerting inspection personnel to take corrective action. SPC control charts can help analyze the frequency and distribution patterns of defects. For example, by displaying defect types in different time periods and production batches, it can analyze defect trends and potential causes, enabling targeted improvement measures. When the control chart shows anomalies (e.g., data points exceeding control limits), the system automatically issues an alarm, prompting relevant personnel to make adjustments or stop production for inspection to prevent non-conforming products from being released.

[0087] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, any equivalent modifications or substitutions made by those skilled in the art to the relevant technical features will fall within the scope of protection of the present invention.

Claims

1. A material sorting and guidance system for LCD displays, characterized in that, The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device.

2. The LCD display screen outfeed screening and indexing system of claim 1, wherein, The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to a display screen quality adaptive screening method and device. The application relates to 3. The LCD display screen outfeed screening and indexing system of claim 1, wherein, The pre-classification unit performs space-time alignment on the collected visual images, electrical parameters, optical parameters and physical parameters according to timestamps and spatial positions, and analyzes the collected multi-modal parameters by using a multi-modal fusion analysis model to identify the screen type of the display screen to be discharged, the feature extraction unit adaptively adjusts the extraction degree of spatial features, time sequence features and physical features based on the screen type, and uses edge node distributed extraction to extract the spatial features, time sequence features and physical features of the display screen to be discharged, and the defect detection unit uses a self-supervised learning framework to perform spatial defect detection, time sequence defect detection and physical defect detection.

4. The LCD display screen outfeed screening and indexing system of claim 3, wherein, The multi-modal fusion analysis model uses a multi-branch neural network to extract feature vectors corresponding to different modal parameters, and inputs them into a classifier to identify the screen type corresponding to different modal feature vectors, and then uses an attention mechanism to weight and fuse the identified screen types to obtain the screen type of the display screen to be discharged, which at least includes an organic light-emitting diode screen, a curved screen and a liquid crystal display screen.

5. The LCD display screen outfeed screening and indexing system of claim 3, wherein, The feature extraction unit uses a gating mechanism to control the activation proportion of the spatial feature channel, the time sequence feature channel and the physical feature channel, when extracting spatial features, the edge node extracts the pixel arrangement, brightness distribution and color distribution features of the visual image by using image segmentation and principal component analysis, and uses edge detection to identify the edge and contour features of the display screen to be discharged, when extracting time sequence features, the edge node extracts the response time and harmonic dynamic features of the display screen to be discharged by performing time-frequency transformation on the current voltage signal, and obtains the dynamic contrast and residual image features by the brightness change curve, when extracting physical features, the edge node establishes a temperature gradient field feature model by thermal imaging, and obtains the curvature of the display screen to be discharged by measuring the curvature radius and curvature angle.

6. The LCD display screen outfeed screening and indexing system of claim 3, wherein, The self-supervised learning framework uses parallel computing to perform spatial defect detection, time sequence defect detection and physical defect detection, when performing spatial defect detection, a U-Net segmentation network is used to label the defect area at the pixel level and output the defect area ratio, when performing time sequence defect detection, an LSTM time series prediction model is used to obtain the comparison deviation between the predicted response curve and the actual measured value, and when performing physical defect detection, the stress distribution is simulated based on finite element analysis, and the potential cracking risk rate is calculated according to the measured vibration data.

7. The LCD display screen outfeed screening and indexing system of claim 1, wherein, The discharge guidance module generates factory path guidance signals, rework path guidance signals and scrap processing guidance signals respectively by using a multi-point operation control model, the multi-point operation control model uses a distributed operation node structure to independently control and decide factory decision nodes, rework decision nodes and scrap decision nodes, the factory decision nodes judge the optimal factory path of qualified products based on the preset factory layout and delivery process information base, and generate factory path guidance signals according to coding rules, the rework decision nodes judge the optimal rework path of qualified products based on the preset factory layout and rework process information base, and generate rework path guidance signals according to coding rules, the scrap decision nodes judge the optimal rework path of rework products based on the defects of the rework products and the work load of the rework site, and generate rework path guidance signals according to coding rules, and the scrap decision nodes judge the optimal scrap path of scrap products based on the scrap processing information base and the scrap processing area, and generate scrap processing guidance signals according to coding rules.

8. The LCD display screen outfeed screening and indexing system of claim 1, wherein, In the process of executing the discharge screening guidance, the blockchain hash value is embedded to realize full-link quality traceability, and the SPC control chart is used to display the detection defect distribution and frequency in real time.

Images