Intelligent material carrying and sorting system for TFT displayer production

Abstract

The invention provides an intelligent material carrying and sorting system for TFT display production, and relates to the technical field of material carrying and sorting, and the system comprises a position identification module which is used for obtaining the position information of a material and updating the position and state of the material in real time to obtain the real-time position information of the material; the feature extraction module is used for acquiring multi-modal information of the material and performing feature extraction on the multi-modal information to obtain features of the material, and the multi-modal information comprises color, texture and shape information; and the carrying module is used for adjusting a carrying strategy in real time by adopting a self-adaptive control algorithm according to the characteristics and the real-time position information of the materials and carrying the materials. According to the intelligent material carrying and sorting system for TFT displayer production, the defects in the prior art can be effectively overcome, the production efficiency and the product quality are improved, and the labor cost and the safety risk are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of material handling and sorting, and in particular to an intelligent material handling and sorting system for TFT display production. Background Art

[0002] TFT (Thin Film Transistor) display production is a highly automated and sophisticated process involving multiple links, including material handling, processing, testing, sorting, etc. As consumers' demand for large-size, high-definition displays increases, the scale of TFT display production continues to expand, and the requirements for production efficiency and precision are also getting higher and higher. Therefore, the application of intelligent material handling and sorting systems in TFT display production has become particularly important; in the existing technology, the handling and sorting systems are designed and manufactured according to specific materials and handling requirements. Therefore, when the material type or handling requirements change, the system's adaptability is limited and may require corresponding modifications or upgrades. Summary of the invention

[0003] The present invention provides an intelligent material handling and sorting system for TFT display production, which can effectively solve the deficiencies of the prior art, improve production efficiency and product quality, and reduce labor costs and safety risks.

[0004] The present invention provides an intelligent material handling and sorting system for TFT display production, comprising: The location identification module is used to obtain the location information of the material and update the location and status of the material in real time to obtain the real-time location information of the material; A feature extraction module is used to obtain multimodal information of the material and perform feature extraction on the multimodal information to obtain the characteristics of the material, wherein the multimodal information includes color, texture, and shape information; The handling module is used to adjust the handling strategy and carry out the handling in real time using an adaptive control algorithm based on the characteristics and real-time location information of the material; Sorting module, used to determine the category of materials and sort them according to fuzzy logic algorithm; The control module is used to obtain feedback information during the handling and sorting process in real time, and use a closed-loop control system to adjust and optimize the handling module and sorting module in real time; The location identification module comprises: The state prediction module is used to predict the state of the material according to the location information and speed information of the material to obtain the state prediction information of the material; The state correction module is used to obtain the actual measurement value of the material and correct the state prediction information of the material to obtain the corrected state information.

[0005] Furthermore, the state of the material is predicted based on the position information and speed information of the material to obtain the state prediction information of the material, including: use The formula predicts the material status, where: Indicated in Moment based on The state prediction value of the moment information, is the state transition matrix, indicating the system state changes from Time has come The transfer relationship of time, Indicated in The estimated value of the state based on all available information at the moment, is the control input matrix, is the control input vector.

[0006] Furthermore, the actual measurement value of the material is obtained, and the state prediction information of the material is corrected to obtain the corrected state information, including: use Get the actual measurement value of the material, where Indicated in The estimated value of the state based on the measured value at each moment, State prediction value, is the Kalman gain matrix, is The vector of measurements obtained at time , is the measurement matrix; Use the material status prediction information and the corrected status information as the initial value for the next iteration and repeat the above steps.

[0007] Furthermore, the feature extraction module includes: Information fusion module, used to obtain the color, texture, and shape information of the material and fuse them to obtain multimodal information; A spatial feature extraction module is used to extract features from the multimodal information using a convolutional layer of a convolutional neural network model to obtain spatial features; The dimension reduction module is used to reduce the dimension of spatial features through the pooling layer according to the spatial features, and convert them into feature vectors, that is, the features of the material, through the fully connected layer.

[0008] Furthermore, the transport module includes: A first preprocessing module is used to perform preprocessing according to the characteristics of the material and the real-time location information of the material to obtain preprocessed information; A first calculation processing module is used to calculate using an adaptive control algorithm according to the preprocessed information and preset transportation targets and constraints to obtain a transportation strategy; A first execution module, used for receiving a handling strategy from an adaptive control algorithm and executing a handling action; The first monitoring module is used for monitoring the force change in the handling process in real time during the handling process to obtain force feedback information; A first adjustment module is used to adjust the handling strategy in real time according to the force feedback information; The judgment module is used to judge whether the material is transported to the target location according to the real-time location of the material after the transport module transports the material to the target location.

[0009] Furthermore, the sorting module comprises: The second preprocessing module is used to perform preprocessing according to the characteristics of the material to obtain the characteristics after preprocessing; The second calculation processing module is used to determine the fuzzy logic rules, fuzzy sets and membership functions according to the preprocessed features to obtain a fuzzy logic model; The reasoning module is used to perform reasoning using fuzzy logic rules according to the preprocessed features and the fuzzy logic model to obtain the reasoning result; According to the inference results, calculate the degree of membership of the material to each category; According to the degree of membership and the preset threshold, the material category is determined to obtain the judgment result; The second execution module is used for sorting the materials according to the judgment result.

[0010] Furthermore, the control module includes: The comparison module is used to compare the feedback information during the handling and sorting process with the preset target to obtain the comparison result; The error analysis module is used to analyze the sources of errors in the handling and sorting process according to the comparison results to obtain error analysis results; An optimization module is used to optimize the closed-loop control system according to the error analysis results to obtain the adjusted handling strategy and fuzzy logic model parameters; The second adjustment module adjusts the operation status of the transport module and the sorting module in real time according to the adjusted control and handling strategy and fuzzy logic model parameters; The second monitoring module continues to monitor the handling and sorting feedback data of the equipment in real time during the adjustment process; Continuously fine-tune control strategies based on feedback data.

[0011] The intelligent material handling and sorting system for TFT display production provided by the present invention can realize efficient and accurate material handling and sorting by integrating advanced sensing and positioning technology, motion control technology and collaborative robot technology, thereby significantly improving production efficiency and precision; the intelligent material handling and sorting system can replace manual labor to complete heavy and monotonous handling work, reducing manpower requirements and labor intensity, thereby reducing labor costs; the present invention adopts a modular and configurable design, which can be flexibly adjusted according to different material types and handling requirements, thereby improving the adaptability and scalability of the system; through precise positioning and motion control technology, the present invention can avoid accidents and injuries that may occur in manual handling, thereby improving the safety and reliability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 is a schematic diagram of an intelligent material handling and sorting system for TFT display production provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] like Figure 1 As shown, the intelligent material handling and sorting system for TFT display production provided by the embodiment of the present invention mainly includes: Material identification module, used to identify and locate materials and to track and extract features of materials in real time; The handling module is used to adjust the handling strategy and carry out the handling in real time using an adaptive control algorithm based on the characteristics and real-time location information of the material; Sorting module, used to determine the category of materials and sort them according to fuzzy logic algorithm; The control module is used to obtain real-time feedback information during the handling and sorting process, and adopts a closed-loop control system to adjust and optimize the handling module and sorting module in real time.

[0016] In the embodiment of the present invention, an efficient and accurate material handling process is achieved by integrating a material identification module, a handling module and a sorting module; the material identification module uses advanced sensor technology (such as visual sensors, RFID technology, etc.) to quickly and accurately identify materials, determine their types, specifications and real-time locations, ensure the accuracy of subsequent handling and sorting operations, and reduce production delays or material losses caused by recognition errors. By tracking materials in real time, the system can dynamically grasp the flow of materials on the production line and respond to production changes in a timely manner. The feature extraction function enables the system to have an in-depth understanding of the physical properties (such as size, shape, weight, etc.) and status (such as whether it is damaged, contaminated, etc.) of the materials, providing key information for subsequent handling and sorting; the handling module adopts an adaptive control algorithm to dynamically adjust the handling strategy (such as handling path, speed, strength) according to the characteristics and real-time location information of the materials. etc.), which not only improves the handling efficiency, but also ensures the safety and stability of materials during the handling process; because the system can perceive the changes in material status and production environment in real time, the handling module can quickly adjust the handling strategy to deal with emergencies (such as material position offset, production line congestion, etc.), thereby maintaining the continuity and stability of the production line; the sorting module uses fuzzy logic algorithms to make intelligent judgments on the categories of materials, which can handle the uncertainty and ambiguity of material characteristics and improve the accuracy of sorting. Even if there are slight differences or changes in material characteristics, the system can accurately identify and sort them to the correct location; based on accurate classification judgments, the sorting module can quickly sort materials to the designated storage area or the next process point on the production line, reducing sorting time and improving the overall efficiency of the production line. Accurate sorting also ensures the smooth progress of subsequent processes and reduces production confusion and cost waste caused by sorting errors.

[0017] like Figure 1 As shown, the material identification module includes: The location identification module is used to obtain the location information of the material and use the Kalman filter real-time tracking algorithm to update the location and status of the material in real time to obtain the real-time location information of the material; The feature extraction module is used to obtain the multimodal information of the material and use the convolutional neural network deep learning algorithm to extract features from the multimodal information to obtain the characteristics of the material. The multimodal information includes color, texture, and shape information.

[0018] In an embodiment of the present invention, the location information of the material is obtained, and the location and status of the material are updated in real time using a Kalman filter real-time tracking algorithm. The location information of the material on the production line can be obtained in real time and accurately, and the location and status of the material are predicted and updated through the Kalman filter algorithm, thereby reducing handling and sorting errors caused by uncertain material position or state changes, and improving the response speed and accuracy of the system; the multimodal information of the material is obtained, and the multimodal information is extracted using a convolutional neural network deep learning algorithm; the multimodal information of the material, such as color, texture, and shape, can be fully obtained, and the convolutional neural network deep learning algorithm is used to perform deep mining and feature extraction on this information, which can more accurately understand the physical properties and category attributes of the material, and provide rich feature information for subsequent handling and sorting operations.

[0019] like Figure 1 As shown, the location identification module includes: The state prediction module is used to use the material location information and speed information The material status is predicted by the formula to obtain the material status prediction information, where: Indicated in Moment based on The state prediction value of the moment information, is the state transition matrix, indicating the system state changes from Time has come The transfer relationship of time, Indicated in The estimated value of the state based on all available information at the moment, is the control input matrix, is the control input vector; Status correction module, use The actual measured value of the material is obtained, and the state prediction information of the material is corrected to obtain the corrected state information, where: Indicated in The estimated value of the state based on the measured value at each moment, State prediction value, is the Kalman gain matrix, is The vector of measurements obtained at time , is the measurement matrix; Use the material status prediction information and the corrected status information as the initial value for the next iteration and repeat the above steps.

[0020] In an embodiment of the present invention, a formula is used to predict the state of the material based on the position information and speed information of the material. The system can accurately predict the state of the material (such as position, speed, etc.) at a future moment by utilizing the position information and speed information of the material in combination with the state transfer matrix and the control input matrix. The system can make decisions in advance and optimize the transportation and sorting paths. Since the state prediction is based on real-time data, the system can quickly respond to changes in the production line, such as changes in the flow speed of the material, congestion of the production line, etc., so as to adjust the transportation and sorting strategies in time. Through accurate state prediction, the system can reduce the time wasted waiting for the material to arrive at the specified position or speed adjustment, thereby improving the overall production efficiency. The actual measurement value of the material is obtained and the state prediction information of the material is corrected. Due to the influence of various factors (such as sensor noise, inaccurate system modeling, etc.), there may be certain errors in the state prediction. By obtaining the actual measurement value of the material and using the Kalman gain matrix to correct the predicted value, the system can significantly reduce this error and improve the state The accuracy of the estimation and correction process makes the system more robust to external interference and uncertainty factors, and can maintain a high state estimation accuracy even in a complex and changeable production environment. Each correction is based on the latest measurement value, so the system can update the material status information in real time, provide accurate data support for subsequent handling and sorting operations, and use the material status prediction information and the corrected status information as the initial value of the next iteration, and repeat the above steps; through continuous iteration of the state prediction and correction process, the system can continuously optimize the material state estimation, so that the prediction results are closer and closer to the actual value, and improve the automation level and production efficiency of the production line; in the iterative process, the system can gradually learn the operating rules of the production line and the flow characteristics of the material, so as to adaptively adjust the parameters of the state prediction and correction, and improve the intelligence level of the system; because the system can update and correct the material status information in real time, it can ensure that the handling and sorting operations on the production line are always based on accurate data, so as to maintain the stable operation and high-quality output of the production line.

[0021] like Figure 1 As shown, the feature extraction module includes: Information fusion module, used to obtain the color, texture, and shape information of the material and fuse them to obtain multimodal information; A spatial feature extraction module is used to extract features from the multimodal information using a convolutional layer of a convolutional neural network model to obtain spatial features; The dimension reduction module is used to reduce the dimension of spatial features through the pooling layer according to the spatial features, and convert them into feature vectors, that is, the features of the material, through the fully connected layer.

[0022] In an embodiment of the present invention, the color, texture, and shape information of the material are obtained and fused to obtain multimodal information. The system can simultaneously obtain the color, texture, and shape information of the material. These information together constitute a comprehensive perception of the material. The acquisition method of multimodal information is richer and more accurate than that of a single modality, which is helpful for subsequent feature extraction and classification. By fusing these different modal information, the system can form a comprehensive description of the material, which not only improves the utilization rate of the information, but also provides a richer data basis for subsequent feature extraction; based on the multimodal information, the convolutional layer of the convolutional neural network model is used to extract features of the multimodal information to obtain spatial features. The convolutional neural network model can deeply mine the spatial features in the multimodal information through its convolutional layer. These features include edges, corners, texture patterns, etc. of the material; convolution Neural networks have the ability to learn automatically and can automatically adjust the parameters of the convolution kernel through training to extract the spatial features that are most conducive to material classification. According to the spatial features, the dimension of the spatial features is reduced through the pooling layer and converted into a feature vector, i.e., the feature of the material, through the fully connected layer. The pooling layer reduces the dimension of the spatial features through downsampling operations, which helps to reduce the amount of calculation and improve the efficiency of feature extraction. The pooling operation can also retain important feature information and remove redundancy and noise. The fully connected layer converts the pooled spatial features into a feature vector, which is a compact representation of the material features, making subsequent tasks such as classification and clustering easier and more efficient. The feature vector extracted by the convolutional neural network deep learning algorithm has a high generalization ability and can accurately identify and classify materials under different lighting conditions, changes in viewing angles, etc.

[0023] like Figure 1 As shown, the transport module includes: A first preprocessing module is used to perform preprocessing according to the characteristics of the material and the real-time location information of the material to obtain preprocessed information; A first calculation processing module is used to calculate using an adaptive control algorithm according to the preprocessed information and preset transportation targets and constraints to obtain a transportation strategy; A first execution module, used for receiving a handling strategy from an adaptive control algorithm and executing a handling action; The first monitoring module is used for monitoring the force change in the handling process in real time during the handling process to obtain force feedback information; A first adjustment module is used to adjust the handling strategy in real time according to the force feedback information; The judgment module is used to judge whether the material is transported to the target location according to the real-time location of the material after the transport module transports the material to the target location.

[0024] In an embodiment of the present invention, preprocessing is performed based on the characteristics of the material and the real-time location information of the material to obtain preprocessed information. The system first integrates multiple characteristics of the material (such as shape, size, weight, etc.) and real-time location information to provide a comprehensive and accurate data basis for subsequent decision-making. The preprocessing process may include data cleaning, format conversion, normalization and other operations to ensure the accuracy and consistency of the data and improve the processing efficiency of the subsequent algorithm; based on the preprocessed information and the preset handling goals and constraints, an adaptive control algorithm is used to perform calculations to obtain a handling strategy. The adaptive control algorithm can intelligently calculate the optimal handling strategy based on the characteristics of the material, the real-time location, and the handling goals and constraints (such as handling paths, time limits, safety requirements, etc.). The algorithm is adaptive and can dynamically adjust the handling strategy according to the actual situation of the production line (such as changes in material flow, fluctuations in equipment status, etc.) to ensure the efficiency and stability of the handling process; the handling module receives the handling strategy from the adaptive control algorithm and executes the handling action. The handling module accurately controls the actuators such as the robotic arm and the conveyor belt according to the handling strategy output by the algorithm to achieve accurate material handling. The handling module can Receive and respond to the output of the algorithm in real time to ensure that the handling process is synchronized with the decision of the algorithm; during the handling process, the handling module monitors the force changes in the handling process in real time to obtain force feedback information. By real-time monitoring of the force changes in the handling process, the system can promptly detect and handle possible abnormal situations (such as material slipping, collision, etc.) to ensure the safety of the handling process. The force feedback information can also be used to fine-tune the force and speed in the handling process to improve the accuracy and stability of the handling; according to the force feedback information, the handling strategy is adjusted in real time. The system can adjust the handling strategy in real time according to the force feedback information to cope with the uncertainty and changes in the handling process, which improves the flexibility and adaptability of the handling process. By continuously adjusting the strategy according to the feedback information, the system can gradually learn a more optimized handling method and achieve continuous improvement; according to the real-time position of the material, the handling module will carry the material to the target position and make a handling completion judgment. The system confirms whether the material has been accurately carried to the target position by detecting the real-time position of the material. After the handling is completed, the system can automatically trigger the subsequent production process (such as sorting, processing, etc.) to ensure the continuity and efficiency of the entire production line.

[0025] like Figure 1 As shown, the sorting module includes: The second preprocessing module is used to perform preprocessing according to the characteristics of the material to obtain the characteristics after preprocessing; The second calculation processing module is used to determine the fuzzy logic rules, fuzzy sets and membership functions according to the preprocessed features to obtain a fuzzy logic model; The reasoning module is used to perform reasoning using fuzzy logic rules according to the preprocessed features and the fuzzy logic model to obtain the reasoning result; According to the inference results, calculate the degree of membership of the material to each category; According to the degree of membership and the preset threshold, the material category is determined to obtain the judgment result; The second execution module is used for sorting the materials according to the judgment result.

[0026] In an embodiment of the present invention, preprocessing is performed according to the characteristics of the material to obtain preprocessed characteristics. By preprocessing the original characteristics of the material, such as denoising, normalization, feature selection, etc., more representative characteristics can be extracted to improve the accuracy of subsequent fuzzy logic judgments. The preprocessing process may reduce the number or dimensions of features, thereby reducing computational complexity and improving the operating efficiency of the algorithm; according to the preprocessed characteristics, fuzzy logic rules, fuzzy sets and membership functions are determined to obtain a fuzzy logic model; according to the characteristics of the material and sorting requirements, a fuzzy logic model is customized to be constructed, including defining fuzzy sets, establishing membership functions and formulating fuzzy logic rules, which provide a basis for subsequent fuzzy reasoning. The fuzzy logic model can handle uncertainty and ambiguity, adapt to the diversity and variability of material characteristics, and improve the flexibility and robustness of classification; according to the preprocessed characteristics and the fuzzy logic model, fuzzy logic rules are used to perform reasoning to obtain reasoning results. Based on the fuzzy logic rules, the system can perform fuzzy reasoning on the characteristics of the material and deduce that the material may belong to The degree or possibility of each category, the reasoning process comprehensively considers multiple characteristics of the material and their relationship with each other, and improves the comprehensiveness and accuracy of the classification decision; according to the reasoning result, the membership degree of the material belonging to each category is calculated. By calculating the membership degree, the result of fuzzy reasoning is quantified into a specific value, which is convenient for comparison and decision-making. The membership degree provides the clarity of the material belonging to each category, and provides a basis for subsequent judgment of the material category according to the threshold; according to the membership degree and the preset threshold, the category of the material is judged to obtain the judgment result. By comparing the membership degree and the preset threshold, the system can clearly judge the category to which the material belongs, and provide accurate instructions for the sorting operation. The threshold can be flexibly adjusted according to the actual sorting needs and changes in material characteristics, so as to improve the accuracy and adaptability of the classification; according to the judgment result, the sorting module sorts the material. According to the judgment result, the sorting module accurately sorts the material into the corresponding category, which improves the accuracy and efficiency of sorting. The entire sorting process is automatically completed by the system, which reduces manual intervention and improves the automation level of the production line.

[0027] like Figure 1 As shown, the control module includes: The comparison module is used to compare the feedback information during the handling and sorting process with the preset target to obtain the comparison result; The error analysis module is used to analyze the sources of errors in the handling and sorting process according to the comparison results to obtain error analysis results; An optimization module is used to optimize the closed-loop control system according to the error analysis results to obtain the adjusted handling strategy and fuzzy logic model parameters; The second adjustment module adjusts the operation status of the transport module and the sorting module in real time according to the adjusted control and handling strategy and fuzzy logic model parameters; The second monitoring module continues to monitor the handling and sorting feedback data of the equipment in real time during the adjustment process; Continuously fine-tune control strategies based on feedback data.

[0028] In an embodiment of the present invention, feedback information in the handling and sorting process is compared with a preset target to obtain a comparison result. By comparing the real-time feedback information with the preset target, the actual performance of the handling and sorting process, including accuracy, efficiency, stability, etc., can be accurately evaluated. The comparison result can quickly reveal the deviation between the actual operation and the expected target, providing a basis for subsequent error analysis; according to the comparison result, the source of the error in the handling and sorting process is analyzed to obtain an error analysis result. Through in-depth analysis of the error, the specific source of the error in the handling and sorting process can be traced back, such as equipment calibration problems, improper algorithm parameters, environmental interference, etc. The error analysis result indicates the direction and focus of optimization, and provides a basis for subsequent control strategy adjustment; according to the error analysis result, the closed-loop control system is optimized to obtain the adjusted handling strategy and fuzzy logic model parameters. Based on the error analysis result, the parameters of the handling strategy and fuzzy logic model are adjusted in a targeted manner to improve the system. Accuracy and robustness, it can make adaptive adjustments according to changes in actual conditions to ensure that the system always remains in the best state; according to the adjusted handling strategy and fuzzy logic model parameters, the handling module and sorting module adjust the operating status in real time, the handling module and sorting module can quickly respond to the adjustment of the control strategy, and realize real-time update of the operating status. The handling and sorting processes are more coordinated under the adjusted strategy, which improves the overall production efficiency and accuracy; during the adjustment process, continue to monitor the handling and sorting feedback data of the equipment in real time. By continuously monitoring the feedback data, the actual operation of the handling and sorting process can be grasped in real time to ensure the effectiveness of the adjustment. Long-term data accumulation provides rich data support for subsequent error analysis and strategy optimization; according to the feedback data, continuously fine-tune the control strategy, and based on the real-time feedback data, continuously fine-tune the control strategy to ensure that the system always remains in the best state. This continuous fine-tuning process is a process of continuous learning and improvement, which can continuously improve the performance and stability of the system.

[0029] Figure 2 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0030] like Figure 2 As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communications interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the intelligent material handling and sorting system for TFT display production.

[0031] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0032] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the intelligent material handling and sorting system for TFT display production provided by the above methods.

[0033] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the intelligent material handling and sorting system for TFT display production provided by the above-mentioned methods.

[0034] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0035] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0036] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent material handling and sorting system for TFT display production, characterized in that: include: The location identification module is used to obtain the location information of the material and update the location and status of the material in real time to obtain the real-time location information of the material; A feature extraction module is used to obtain multimodal information of the material and perform feature extraction on the multimodal information to obtain the characteristics of the material, wherein the multimodal information includes color, texture, and shape information; The handling module is used to adjust the handling strategy and carry out the handling in real time using an adaptive control algorithm based on the characteristics and real-time location information of the material; Sorting module, used to determine the category of materials and sort them according to fuzzy logic algorithm; The control module is used to obtain feedback information during the handling and sorting process in real time, and use a closed-loop control system to adjust and optimize the handling module and sorting module in real time; The location identification module comprises: The state prediction module is used to predict the state of the material according to the location information and speed information of the material to obtain the state prediction information of the material; The state correction module is used to obtain the actual measurement value of the material and correct the state prediction information of the material to obtain the corrected state information.

2. The intelligent material handling and sorting system for TFT display production according to claim 1, characterized in that: According to the material's location information and speed information, the material's state is predicted to obtain the material's state prediction information, including: use The formula predicts the material status, where: Indicated in Moment based on The state prediction value of the moment information, is the state transition matrix, indicating the system state changes from Time has come The transfer relationship of time, Indicated in The estimated value of the state based on all available information at the moment, is the control input matrix, is the control input vector.

3. The intelligent material handling and sorting system for TFT display production according to claim 2, characterized in that: The actual measured value of the material is obtained, and the material status prediction information is corrected to obtain the corrected status information, including: use Get the actual measurement value of the material, where Indicated in The estimated value of the state based on the measured value at each moment, State prediction value, is the Kalman gain matrix, is The vector of measurements obtained at time , is the measurement matrix; Use the material status prediction information and the corrected status information as the initial value for the next iteration and repeat the above steps.

4. The intelligent material handling and sorting system for TFT display production according to claim 1, characterized in that: The feature extraction module comprises: Information fusion module, used to obtain the color, texture, and shape information of the material and fuse them to obtain multimodal information; A spatial feature extraction module is used to extract features from the multimodal information using a convolutional layer of a convolutional neural network model to obtain spatial features; The dimension reduction module is used to reduce the dimension of spatial features through the pooling layer according to the spatial features, and convert them into feature vectors, that is, the features of the material, through the fully connected layer.

5. The intelligent material handling and sorting system for TFT display production according to claim 1, characterized in that: The transport module comprises: A first preprocessing module is used to perform preprocessing according to the characteristics of the material and the real-time location information of the material to obtain preprocessed information; A first calculation processing module is used to calculate using an adaptive control algorithm according to the preprocessed information and preset transportation targets and constraints to obtain a transportation strategy; A first execution module, used for receiving a handling strategy from an adaptive control algorithm and executing a handling action; The first monitoring module is used for monitoring the force change in the handling process in real time during the handling process to obtain force feedback information; A first adjustment module is used to adjust the handling strategy in real time according to the force feedback information; The judgment module is used to judge whether the material is transported to the target location according to the real-time location of the material after the transport module transports the material to the target location.

6. The intelligent material handling and sorting system for TFT display production according to claim 1, characterized in that: The sorting module comprises: The second preprocessing module is used to perform preprocessing according to the characteristics of the material to obtain the characteristics after preprocessing; The second calculation processing module is used to determine the fuzzy logic rules, fuzzy sets and membership functions according to the preprocessed features to obtain a fuzzy logic model; The reasoning module is used to perform reasoning using fuzzy logic rules according to the preprocessed features and the fuzzy logic model to obtain the reasoning result; According to the inference results, calculate the degree of membership of the material to each category; According to the degree of membership and the preset threshold, the material category is determined to obtain the judgment result; The second execution module is used for sorting the materials according to the judgment result.

7. The intelligent material handling and sorting system for TFT display production according to claim 1, characterized in that: The control module comprises: The comparison module is used to compare the feedback information during the handling and sorting process with the preset target to obtain the comparison result; The error analysis module is used to analyze the sources of errors in the handling and sorting process according to the comparison results to obtain error analysis results; An optimization module is used to optimize the closed-loop control system according to the error analysis results to obtain the adjusted handling strategy and fuzzy logic model parameters; The second adjustment module adjusts the operation status of the transport module and the sorting module in real time according to the adjusted control and handling strategy and fuzzy logic model parameters; The second monitoring module continues to monitor the handling and sorting feedback data of the equipment in real time during the adjustment process; Continuously fine-tune control strategies based on feedback data.

Images