Display screen material identification and cutting parameter regulation and control system based on multi-source sensing fusion

Abstract

The invention provides a display screen material identification and cutting parameter regulation and control system based on multi-source sensing fusion, which relates to the technical field of display screen cutting and comprises a data input module, a data acquisition module, a calculation processing module and an execution control module, according to the method, the type of the display screen is input in advance, the corresponding cutting equipment and cutting parameters are called according to the type, and then the cutting parameters are finely adjusted according to the material difference of the display screen, so that the method is suitable for rapid parameter calling and rapid cutting of display screens made of different materials. According to the method, a database is constructed in advance, and cutting data of different display screen material types are collected to construct an identification model; the initial cutting parameters are adjusted by manually inputting the material type of a display screen; identifying the material to be cut; optimization is carried out on the basis of the initial cutting parameters to provide more accurate cutting parameter data, so that the cutting efficiency is improved, and the damage rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of display screen cutting, and more specifically, to a display screen material identification and cutting parameter regulation system based on multi-source sensing fusion. Background Art

[0002] A display screen is a display device commonly used as an interactive interface on various electronic devices. In the prior art, for display screens, such as in the production and manufacturing of liquid crystal displays and touch screens, in order to improve production efficiency, reduce manufacturing costs, and achieve large-scale mass production, multiple liquid crystal displays or touch screens are often fabricated on a larger piece of glass. After screen printing into a cell, there are multiple groups of liquid crystal display or touch screen units on the glass. These small units need to be separated before liquid crystal perfusion. The cutting process is to split the entire cell of glass into individual liquid crystal displays or touch screens. Currently, the relatively common cutting processes include dicing wheel cutting, laser cutting, and water jet cutting.

[0003] Generally, display screens are divided into two major categories: LCD and OLED. Traditional LCD uses glass as a substrate and needs to be paired with a backlight module, such as an LED backlight, a light guide plate, etc. to achieve the display function. At the same time, its structure also includes functional layers such as a liquid crystal layer, a color filter, and a polarizer. And OLED is divided into rigid OLED and flexible OLED. Rigid OLED is similar to LCD and both use glass material as a substrate; a transparent resin protective film needs to be covered on the surface, and its structure includes an organic light-emitting layer, an anode / cathode layer, and a packaging layer, etc. Flexible OLED usually uses polyimide (PI) film or flexible polymer as a substrate, and the packaging material is a flexible barrier film (such as an antistatic adhesive coating), supporting bending and folding functions.

[0004] Restricted by the different structures of liquid crystal display screens, different cutting processes need to be used for different types of liquid crystal display screens for processing; for example, LCD and rigid OLED: due to the brittle characteristics of the glass substrate, diamond dicing wheels are usually used for cutting, and precise cutting is achieved through mechanical stress. While for flexible OLED: since the plastic substrate cannot withstand the stress of mechanical cutting, laser cutting technology (such as CO 2 laser) is required to precisely peel off the support film or cut the substrate through thermal effects to avoid material deformation.

[0005] However, even for the same type of display screen, such as LCD or OLED, different structures of display screens are required due to their different application fields; different substrate thicknesses and the combination and composition of various functional films and the thickness components of ITO glue will affect the overall strength, resulting in the need to specifically adjust the cutting parameters (such as the pressure, angle, cutting speed, etc. of the cutting tool) to avoid the breakage of the glass substrate or the melting of the PI substrate. In the prior art, for newly developed display screens, it is usually necessary to test cut multiple times and adjust the cutting parameters multiple times to find the most suitable control parameters to reduce the scrap rate.

[0006] Therefore, a display screen material recognition and cutting parameter control system based on multi-source sensor fusion is needed to adaptively adjust the cutting parameters, improve the cutting effect, and reduce the scrap rate. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a display screen material recognition and cutting parameter control system based on multi-source sensor fusion.

[0008] According to one aspect of the present invention, a display screen material recognition and cutting parameter control system based on multi-source sensor fusion is provided, comprising: Data input module, data acquisition module, calculation processing module and execution control module; The data input module includes an interactive touch screen, through which the type of display screen to be cut is input to the execution control module; Data acquisition module, used for data acquisition of materials to be cut; The calculation processing module classifies the information collected by the data acquisition module, generates characteristic parameters for identifying the material type, and adjusts the cutting parameters according to the characteristic parameters; The execution control module calls the corresponding cutting equipment according to the cutting parameters and controls its operation, and saves the cutting data at the same time; By inputting the type of display screen in advance, calling the corresponding cutting equipment and cutting parameters according to the type, and then fine-tuning the cutting parameters according to the material difference of the display screen, it is possible to quickly call parameters and quickly cut display screens of different materials.

[0009] Preferably, the data acquisition module includes a hyperspectral imaging sensor, a laser confocal sensor, an acoustic wave surface sensor and a temperature sensor; The hyperspectral imaging sensor is used to detect the reflection spectrum of the display screen to be processed; The laser confocal sensor is used to detect the three-dimensional shape and thickness of the display screen to be processed; The acoustic wave surface sensor is used to detect the hardness and density of the display screen to be processed; The temperature sensor is used to detect the surface temperature data of the display screen to be processed; The data acquisition module further includes a communication port, and the data collected in real time is sent to the calculation and processing module through the communication port.

[0010] Preferably, the calculation and processing module preprocesses the collected original data and performs feature extraction; The steps of preprocessing include: data cleaning and normalization; data cleaning is used to remove noise; normalization is used to unify the dimensions of various types of data; For the reflection spectrum obtained by the hyperspectral imaging sensor, feature extraction is performed, and the characteristic peak position, slope, and polarized light transmittance of the reflection spectrum are analyzed to determine the material characteristics of the display screen to be measured: For the three-dimensional topography and thickness data obtained by the laser confocal sensor, feature extraction is performed to determine the interlayer thickness characteristics of the display screen to be measured; For the hardness and density data obtained by the surface acoustic wave sensor, feature extraction is performed to determine the auxiliary material characteristics of the display screen; For the temperature data obtained by the temperature sensor, feature extraction is performed to determine the real-time temperature of the display screen; The calculation and processing module performs spatio-temporal alignment on the extracted features.

[0011] Preferably, the calculation and processing module is built-in with a trained recognition model based on deep learning; after preprocessing the original data collected by the data acquisition module, the feature vector is sent as input to the recognition model; The appropriate cutting parameter data is output through the feature fusion and decision fusion steps of the recognition model.

[0012] Preferably, the recognition model adopts a convolutional neural network-random forest joint architecture; Deep learning is performed through the convolutional neural network model to process hyperspectral images and confocal topography maps; The acoustic wave data and temperature data are processed through the random forest model.

[0013] Preferably, the influence function of the feature parameters and the cutting parameters is determined by experiments, and a feature parameter-cutting parameter relationship library is established.

[0014] Preferably, decision fusion is performed on the results output by the recognition model; according to the confidence theory, the feature parameters output by the model are weighted and summed to output the final control parameter data.

[0015] The second aspect of the present invention provides a method for identifying the material of a display screen and dynamically regulating cutting parameters based on multi-source sensing fusion, which is applied to the above system, and includes the following specific steps: S1: Manually input the type and basic parameters of the display screen; S2: Collect data on the material to be cut; S3: Preprocess and extract features from the collected data; S4: Process the extracted features using an identification model and output cutting parameters; S5: Invoke the cutting device to process according to the output cutting parameters; S6: Detect the quality of the cut product and record it; Feed the cutting quality data back to the identification model to optimize the accuracy of the identification model.

[0016] Preferably, after manually inputting the display screen type, the identification model immediately invokes the corresponding cutting parameters; and based on the current cutting parameters and according to the output results, fine-tune the cutting parameters to output the final cutting parameters.

[0017] The third aspect of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the above-mentioned method for identifying the display screen material and dynamically regulating the cutting parameters based on multi-source sensing fusion.

[0018] Compared with the prior art, the present invention constructs a database in advance, collects cutting data of different display screen material types to construct an identification model; adjusts the initial cutting parameters by manually inputting the material type of the display screen; then identifies the material to be cut; and optimizes based on the initial cutting parameters to provide more accurate cutting parameter data, thereby improving the cutting efficiency and reducing the damage rate. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings: Figure 1 It is a system block diagram of a system for identifying the display screen material and regulating the cutting parameters based on multi-source sensing fusion according to an embodiment of the present invention.

[0020] Figure 2 It is a flowchart of a method for identifying the display screen material and regulating the cutting parameters based on multi-source sensing fusion according to an embodiment of the present invention.

[0021] Figure 3 It is a schematic structural diagram of a computer system of an electronic device according to an embodiment of the present invention. Detailed Embodiments

[0022] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein.

[0023] As mentioned in the above background art, in order to solve the problem that for the same type of display screen, such as LCD or OLED, due to different fields of actual application, display screens with different structures are required; since the thickness of different substrates, the combination methods, compositions of various functional films, and the thickness components of ITO glue will all affect the overall strength, resulting in the need to specifically adjust the cutting parameters (such as the pressure, angle, cutting speed, etc. of the cutting tool) to avoid the problem of glass substrate cracking or PI substrate melting, the following solutions are proposed: Embodiment 1 As Figure 1 described, a display screen material identification and cutting parameter regulation system based on multi-source sensing fusion is provided, including: a data input module, a data acquisition module, a calculation and processing module, and an execution control module; In this embodiment, the data input module includes an interactive touch screen, and the type of the display screen to be cut is input to the execution control module through the touch screen; by pre-inputting the type of the display screen, the relevant parameter data can be called; for example, if the input display screen type is LCD, a diamond knife wheel cutting device is preferentially called for cutting, and the standard LCD display screen cutting data in the cutting device database is called as the basic cutting parameters.

[0024] In this embodiment, the data acquisition module is used to acquire data of the material to be cut; the specific data acquisition module includes a hyperspectral imaging sensor, a laser confocal sensor, a surface acoustic wave sensor, and a temperature sensor; wherein the hyperspectral imaging sensor is used to detect the reflection spectrum of the display screen to be processed; the laser confocal sensor is used to detect the three-dimensional topography and thickness of the display screen to be processed; the surface acoustic wave sensor is used to detect the hardness and density of the display screen to be processed; the temperature sensor is used to detect the surface temperature data of the display screen to be processed; The data acquisition module further includes a communication port, and the data collected in real time is sent to the calculation and processing module through the communication port.

[0025] In this embodiment, the calculation and processing module classifies and processes the information collected by the data acquisition module, generates characteristic parameters for identifying the material type, and adjusts the cutting parameters according to the characteristic parameters; The calculation and processing module preprocesses the collected original data and performs feature extraction; The steps of preprocessing include: data cleaning and normalization; data cleaning is used to remove noise; normalization is used to unify the dimensions of various types of data; the calculation and processing module performs spatio-temporal alignment on the extracted features to improve the correlation between features.

[0026] Feature extraction is performed on the reflection spectrum obtained by the hyperspectral imaging sensor, and the characteristic peak position, slope, and polarization light transmittance of the reflection spectrum are analyzed to determine the material characteristics of the display screen to be measured. For example, whether the glass substrate is a soda-lime glass substrate or a borosilicate glass substrate without sodium. For the physical properties of different materials, a suitable cutting method and cutting parameters can be further selected; Feature extraction is performed on the three-dimensional topography and thickness data obtained by the laser confocal sensor to determine the interlayer thickness characteristics of the display screen to be measured; through the measured thickness data, the brittleness of the substrate can be analyzed to adaptively adjust the cutting angle and cutting direction of the cutting tool during cutting; Feature extraction is performed on the hardness and density data obtained by the surface acoustic wave sensor to assist in judging the material characteristics of the auxiliary material of the display screen to be cut, and further optimize the pressure during cutting to avoid brittle fracture of the substrate.

[0027] Feature extraction is performed on the temperature data obtained by the temperature sensor to determine the real-time temperature of the display screen; by controlling the power of the heat dissipation device and the power of the laser cutting device, the temperature on the surface of the display screen during cutting is dynamically adjusted to avoid damage to the display screen caused by high temperature.

[0028] The calculation and processing module has a pre-trained recognition model based on deep learning; after preprocessing the raw data collected by the data acquisition module, the calculation and processing module sends the feature vector as input to the recognition model; The appropriate cutting parameter data is output through the feature fusion and decision fusion steps of the recognition model. The recognition model adopts a convolutional neural network-random forest joint architecture; through the convolutional neural network model for deep learning, the hyperspectral image and the confocal topography map are processed. Based on the deep learning-based recognition model architecture, the hyperspectral image and the confocal topography map can be quickly processed to facilitate the rapid determination of the substrate material, three-dimensional topography, and thickness data of the display screen to be processed; Subsequently, the acoustic wave data and temperature data are processed by the random forest model to facilitate the rapid determination of the auxiliary material material and surface temperature data of the display screen to be processed.

[0029] Determine the influence function of characteristic parameters and cutting parameters through experiments, and establish a relationship library of characteristic parameters - cutting parameters; for example, the greater the thickness, the stronger the pressure-bearing capacity; the pressure applied during cutting can be increased. Then, perform decision fusion on the results output by the recognition model; perform weighted summation on the characteristic parameters output by the model according to the confidence theory to determine the final output control parameter data. In addition, constraint conditions can be set, and by establishing a cutting energy equation, with the lowest output energy as the optimization goal, the optimal control strategy can be output to reduce energy consumption; the cutting energy equation is as follows: In the formula, E is the total effective cutting energy, P(t) is the instantaneous laser power, v(t) is the cutting head movement speed; η is the material's laser energy absorption rate function; λ is the laser wavelength; T is the material surface temperature.

[0030] In this embodiment, the execution control module calls the corresponding cutting device according to the cutting parameters and controls its operation, and at the same time saves the cutting data; a corresponding database is established through the accumulation of data to optimize the accuracy of the recognition model and improve the accuracy of the output cutting parameters.

[0031] In the present invention, by pre-inputting the type of the display screen, the corresponding cutting device and cutting parameters are called according to the type, and then the cutting parameters are finely adjusted according to the material differences of the display screen to be applicable to different material display screens for rapid parameter calling and rapid cutting operations, forming cutting knife marks on the surface of the display screen, facilitating subsequent cleavage by a cleaving machine, and dividing the whole display screen into specified sizes, facilitating subsequent processing steps.

[0032] Embodiment 2 This embodiment takes an LCD display screen as an example to introduce the solution in Embodiment 1 in detail; Common LCD screens include a glass substrate, a liquid crystal layer, a polarizer, and a functional film layer; the glass substrate is divided into an upper substrate and a lower substrate; usually, a layer of indium tin oxide (ITO) conductive layer is plated on the lower substrate to form an electric field and control the arrangement of liquid crystal molecules; and the upper substrate is usually called a cover plate, and its surface is covered with a color filter for displaying colors and a black light-shielding adhesive for preventing light leakage; the cover plate is combined with the common electrode ITO layer; the liquid crystal layer is usually filled between the lower substrate and the cover plate; therefore, during the processing of the display screen, it is necessary to first clean the glass substrate and plate a layer of ITO conductive layer; after waiting for the steps of screen printing and cell formation, cutting is carried out to separate the units of multiple liquid crystal displays or touch screens on the glass before liquid crystal perfusion can be carried out; therefore, for LCD display screens, when performing cutting operations, it is necessary to first consider the thickness, composition of the glass substrate, and the thickness and physical properties of the ITO conductive layer.

[0033] Adjust the cutting parameters of the LCD display screen using the system in Embodiment 1; First, input the basic information of the LCD display screen through the interactive touch screen, i.e., the data input module, and divide the complete glass substrate into smaller display units according to actual processing needs; The cutting parameters call the standard cutting data of this type of LCD display screen in the database as the basic cutting parameters; For example, select a diamond knife wheel cutting machine for cutting, with a rotational speed of 9000 rpm and a feed speed of 0.3 m / s. Then use the data acquisition module to collect data on the material to be cut; The specific data acquisition module includes a hyperspectral imaging sensor, a laser confocal sensor, a surface acoustic wave sensor, and a temperature sensor; Among them, the hyperspectral imaging sensor is used to detect the reflection spectrum of the display screen to be processed; The laser confocal sensor is used to detect the three-dimensional topography and thickness of the display screen to be processed; The surface acoustic wave sensor is used to detect the hardness and density of the display screen to be processed; The temperature sensor is used to detect the surface temperature data of the display screen to be processed; The calculation and processing module classifies and processes the information collected by the data acquisition module, generates characteristic parameters for identifying the material type, and adjusts the cutting parameters according to the characteristic parameters; The calculation and processing module preprocesses the collected original data and performs feature extraction; The steps of preprocessing include: data cleaning and normalization; Data cleaning is used to remove noise; Normalization is used to unify the dimensions of various types of data; The calculation and processing module performs spatio-temporal alignment on the extracted features to improve the correlation between features.

[0034] For the reflection spectrum obtained by the hyperspectral imaging sensor, feature extraction is performed, and the characteristic peak position, slope, and polarized light transmittance of the reflection spectrum are analyzed to determine the material characteristics of the display screen to be measured; For the three-dimensional topography and thickness data obtained by the laser confocal sensor, feature extraction is performed to determine the interlayer thickness characteristics of the display screen to be measured; Through the measured thickness data, the brittleness of the substrate can be analyzed to adaptively adjust the cutting angle and cutting direction of the cutting tool during cutting; For the hardness and density data obtained by the surface acoustic wave sensor, feature extraction is performed to assist in judging the material characteristics of the auxiliary materials of the display screen to be cut, and further optimize the pressure during cutting to avoid substrate cracking. For the temperature data obtained by the temperature sensor, feature extraction is performed to determine the real-time temperature of the display screen.

[0035] The calculation and processing module has a pre-trained deep learning-based recognition model built in; After the calculation and processing module preprocesses the original data collected by the data acquisition module, the feature vector is sent as input to the recognition model; Output the cutting parameter data adapted through the feature fusion and decision fusion steps of the recognition model. The recognition model adopts a combined architecture of convolutional neural network - random forest; perform deep learning through the convolutional neural network model to process hyperspectral images and confocal topography maps. Based on the deep learning-based recognition model architecture, hyperspectral images and confocal topography maps can be processed quickly to facilitate the rapid determination of the substrate material, three-dimensional topography, and thickness data of the display screen to be processed; After that, process the acoustic wave data and temperature data through the random forest model to facilitate the rapid determination of the auxiliary material material and surface temperature data of the display screen to be processed. Then perform decision fusion on the results output by the recognition model; perform weighted summation on the feature parameters output by the model according to the confidence theory to determine the final output control parameter data. For example, the hyperspectral image and confocal topography map data have higher accuracy, while the acoustic wave data and temperature data are more affected by the external environment. Therefore, set the initial weight a of the convolutional neural network model to 0.6, and the weight b of the random forest model to 0.4; through actual testing of a large amount of data, adaptively adjust the weights a and b according to the accuracy of the measured data and the predicted data, but still need to satisfy a + b = 1.

[0036] In this embodiment, assume that the following results are identified according to the recognition model: the glass substrate to be measured is a soda-lime glass substrate; the thickness is 0.5 mm, the ITO film layer is 0.1 mm, and the current surface temperature of the glass substrate is 20 degrees Celsius; compared with the manually input data, the thickness of the glass substrate increases by 0.1 mm. Based on the previous basic cutting parameters, adjust the cutting parameters; Here, due to the increase in the thickness of the glass substrate, and according to the established relationship library of feature parameters - cutting parameters, it can be known that the pressure resistance increases with the increase in thickness. Therefore, adjust the rotation speed in the cutting parameters to 10,000 rpm.

[0037] After that, the execution control module calls the corresponding cutting device according to the cutting parameters and controls its operation, and at the same time saves the cutting data; establish a corresponding database through the accumulation of data to optimize the accuracy of the recognition model and improve the accuracy of the output cutting parameters. When the feature parameters similar to the display screen structure material are detected again, preferentially use the cutting parameters of this time as the output to control the cutting device for cutting.

[0038] When the recognition result output by the recognition model of the calculation module deviates greatly from the manually input result; a warning prompt will be given through the interactive display touch screen to avoid waste of raw materials caused by misoperation.

[0039] For example, the material of the manually input glass substrate is soda-lime glass, with a thickness of 0.4 mm and an ITO film layer of 0.1 mm. In this embodiment, it is assumed that the following results are recognized according to the recognition model: the glass substrate to be measured is identified as non-sodium borosilicate glass; the thickness is 0.3 mm, the ITO film layer is 0.1 mm, and the current surface temperature of the glass substrate is 10 degrees Celsius. Compared with the manually input data, there are obvious and significant differences. Due to the high brittleness of soda-lime glass, a cutter head with higher precision and faster rotation speed needs to be used to reduce chipping. Since non-sodium borosilicate glass has higher hardness, wear-resistant tools need to be used to reduce the wear of the cutting equipment. For ultra-thin LCD substrates with a thickness less than 0.35 mm, due to their high brittleness, diamond blade cutting equipment is not suitable. Therefore, a warning is given through an interactive display touch screen. Assuming that there is an error in the manually input data here, the process is repeated after the manual data is corrected. At this time, a laser cutting equipment is preferably used for cutting, and the cutting power is adjusted within the range of 20 - 200 w according to the type of glass, and the cutting speed is less than 0.6 m / min. The laser cutting equipment is sensitive to temperature, so the surface temperature of the initial glass substrate needs to be combined to adjust the laser cutting power to avoid deformation and failure of the glass substrate caused by thermal effects.

[0040] In the present invention, by pre-inputting the type of the display screen, the corresponding cutting equipment and cutting parameters are called according to the type, and then the cutting parameters are finely adjusted according to the material differences of the display screen to enable rapid parameter calling for different material display screens and rapid cutting operations, forming cutting marks on the surface of the display screen to facilitate subsequent breaking by a splitting machine, dividing the whole display screen into specified sizes for subsequent processing steps.

[0041] Embodiment 3 As Figure 2 shown, the present invention provides a method for identifying the material of a display screen and dynamically regulating cutting parameters based on multi-source sensing fusion, which is applied to the system in Embodiment 1 and includes the following specific steps: S1: Manually input the type and basic parameters of the display screen; S2: Collect data on the material to be cut; S3: Preprocess and extract features from the collected data; S4: Use the recognition model to process the extracted features and output cutting parameters; S5: Call the cutting equipment to process according to the output cutting parameters; S6: Detect and record the quality of the cut product; feedback the cutting quality data to the recognition model to optimize the accuracy of the recognition model.

[0042] Preferably, after manually inputting the display screen type, the recognition model immediately calls the corresponding cutting parameters; and based on the output result, fine-tunes the cutting parameters on the basis of the current cutting parameters to output the final cutting parameters.

[0043] Embodiment 4 Figure 3 FIG. shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present invention.

[0044] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present invention.

[0045] The computer system in this embodiment includes a central processing unit 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory 402 or the program loaded from the storage section 408 into the random access memory 403, such as executing the system and method for identifying display screen materials and regulating cutting parameters based on multi-source sensing fusion described in the above embodiments. In the random access memory 403, various programs and data required for system operation are also stored. The central processing unit 401, the read-only memory 402, and the random access memory 403 are connected to each other via a bus 404. The input / output interface 405 is also connected to the bus 404.

[0046] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A driver 410 is also connected to the input / output interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the driver 410 as needed so that a computer program read from it can be installed into the storage section 408 as needed.

[0047] In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit 401, various functions defined in the system of the present invention are executed.

[0048] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0049] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes may occur in a different order than that marked in the accompanying drawings. For example, two consecutive boxes shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, as well as the combination of boxes in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0050] The units involved in the embodiments of the present invention can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the units themselves in some cases.

[0051] According to one aspect of the present invention, there is provided a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various alternative implementation manners.

[0052] As another aspect, the present invention further provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by an electronic device, the electronic device implements the system and method for identifying the display screen material and regulating the cutting parameters based on multi-source sensing fusion described in the above embodiments.

[0053] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present invention, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0054] From the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0055] Here, those skilled in the art can understand that the specific operations of each step in the above method for identifying the display screen material and dynamically adjusting the cutting parameters based on multi-source sensing fusion have been introduced in detail in the description of the Figure 1 system for identifying the display screen material and adjusting the cutting parameters based on multi-source sensing fusion, and therefore, the repeated description thereof will be omitted.

[0056] In summary, the system for identifying the display screen material and adjusting the cutting parameters based on multi-source sensing fusion according to the embodiments of the present invention is clarified, which first inputs the cutting parameters in advance and then identifies the material to be cut; and optimizes based on the initial cutting parameters to improve the cutting efficiency and reduce the damage rate.

Claims

1. A display screen material recognition and cutting parameter control system based on multi-source sensor fusion, characterized in that: include: Data input module, data acquisition module, calculation processing module and execution control module; The data input module includes an interactive touch screen, through which the type of display screen to be cut is input to the execution control module; Data acquisition module, used for data acquisition of materials to be cut; The calculation processing module classifies the information collected by the data acquisition module, generates characteristic parameters for identifying the material type, and adjusts the cutting parameters according to the characteristic parameters; The execution control module calls the corresponding cutting equipment according to the cutting parameters and controls its operation, and saves the cutting data at the same time; By inputting the type of display screen in advance, calling the corresponding cutting equipment and cutting parameters according to the type, and then fine-tuning the cutting parameters according to the material difference of the display screen, it is possible to quickly call parameters and quickly cut display screens of different materials.

2. The display screen material identification and cutting parameter control system based on multi-source sensor fusion according to claim 1 is characterized in that: The data acquisition module includes a hyperspectral imaging sensor, a laser confocal sensor, an acoustic wave surface sensor, and a temperature sensor; The hyperspectral imaging sensor is used to detect the reflection spectrum of the display screen to be processed; The laser confocal sensor is used to detect the three-dimensional shape and thickness of the display screen to be processed; The acoustic wave surface sensor is used to detect the hardness and density of the display screen to be processed; The temperature sensor is used to detect the surface temperature data of the display screen to be processed; The data acquisition module also includes a communication port, through which the real-time collected data is sent to the calculation processing module.

3. The display screen material identification and cutting parameter control system based on multi-source sensor fusion according to claim 2 is characterized in that: The computing and processing module pre-processes the collected raw data and performs feature extraction; The preprocessing steps include: data cleaning and normalization; data cleaning is used to remove noise; normalization is used to unify the dimensions of various types of data; The reflection spectrum obtained by the hyperspectral imaging sensor is extracted to analyze the characteristic peak position, slope and polarized light transmittance of the reflection spectrum to determine the material characteristics of the display screen to be tested: Perform feature extraction on the three-dimensional topography and thickness data obtained by the laser confocal sensor to determine the interlayer thickness characteristics of the display screen to be tested; Perform feature extraction on the hardness and density data obtained by the acoustic wave surface sensor to determine the material characteristics of the auxiliary materials of the display screen; Perform feature extraction on the temperature data obtained by the temperature sensor to determine the real-time temperature of the display screen; The computing and processing module performs spatiotemporal alignment on the extracted features.

4. The display screen material identification and cutting parameter control system based on multi-source sensor fusion according to claim 1 is characterized in that: The computational processing module has a built-in trained recognition model based on deep learning; after the computational processing module pre-processes the raw data collected by the data acquisition module, it sends the feature vector as input to the recognition model; The adaptive cutting parameter data is output through the feature fusion and decision fusion steps of the recognition model.

5. The display screen material identification and cutting parameter control system based on multi-source sensor fusion according to claim 4 is characterized in that: The recognition model uses a convolutional neural network-random forest joint architecture; Processing hyperspectral images and confocal topography images through deep learning using convolutional neural network models; The acoustic wave data and temperature data are processed by the random forest model.

6. The display screen material identification and cutting parameter control system based on multi-source sensor fusion according to claim 4 or 5, characterized in that: The influence functions of characteristic parameters and cutting parameters are determined by experiments, and a characteristic parameter-cutting parameter relationship library is established.

7. The display screen material identification and cutting parameter control system based on multi-source sensor fusion according to claim 6 is characterized in that: Perform decision fusion on the results output by the recognition model; perform weighted summation on the characteristic parameters output by the model according to the confidence theory, and output the final control parameter data.

8. A method for display screen material identification and cutting parameter dynamic control based on multi-source sensor fusion, applied to the system according to any one of claims 1 to 7, characterized in that: The specific steps include: S1: Manually input the type and basic parameters of the display screen; S2: Collect data of the material to be cut; S3: preprocessing and feature extraction of collected data; S4: Use the recognition model to process the extracted features and output cutting parameters; S5: calling the cutting device to process according to the output cutting parameters; S6: Detect the quality of the cut product and record it; feed the cutting quality data back to the recognition model to optimize the accuracy of the recognition model.

9. The method for display screen material identification and cutting parameter dynamic control based on multi-source sensor fusion according to claim 8 is characterized in that: After manually inputting the display screen type, the recognition model calls the corresponding cutting parameters; and based on the current cutting parameters, the cutting parameters are fine-tuned according to the output results to output the final cutting parameters.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for display screen material identification and cutting parameter dynamic control based on multi-source sensor fusion as described in any one of claims 1 to 7 are implemented.

Images