A control system and method for a highly adaptable industrial liquid crystal display driver board.

Abstract

The present invention relates to the field of industrial display control technology, and specifically discloses a control system and method for a high-adaptability industrial liquid crystal display driver board. By constructing a hierarchical adaptive control architecture of a hardware interface recognition layer, a drive strategy adaptation layer, and a dynamic optimization execution layer, the interface information and key parameters of the liquid crystal screen are automatically detected and analyzed in the initialization stage, and a preset drive algorithm library is called to generate an initialization drive configuration sequence. During the operation stage, by continuously monitoring the display content characteristics and the board operation environment status, key parameters such as the refresh rate and the backlight drive current are dynamically adjusted, and control instructions are executed collaboratively through the drive strategy adaptation layer and the hardware interface recognition layer to achieve adaptive driving of various liquid crystal screens. The present invention can solve the problems of poor compatibility, parameter固化, and insufficient adaptability to complex industrial environments of existing driver boards, improve the compatibility and deployment efficiency of driver boards, optimize the display quality, reliability, and energy efficiency performance, provide high adaptability, and reduce the maintenance cost. It should be noted that the "固化" in the original text may be a misspelling. If it is "固化" meaning "fixed", the translation is adjusted as above. If it has a different correct form, the translation needs to be further adjusted according to the correct word.

Description

Technical Field

[0001] This invention relates to the field of industrial display control technology, and in particular to a control system and method for a highly adaptable industrial liquid crystal display driver board. Background Technology

[0002] With the rapid development of industrial automation, intelligent manufacturing and other fields, LCD display devices are being used more and more widely in industrial scenarios, and they need to be compatible with different brands and models of LCD screens to meet diverse display needs.

[0003] Existing industrial LCD display driver boards primarily rely on hardware jumper configurations, manual firmware burning, or fixed parameter driving modes. To drive a specific LCD screen, technicians must manually consult screen parameter manuals, adjust hardware interfaces, or burn corresponding drivers. This not only increases the complexity of engineering deployment and labor costs but also makes the display prone to abnormalities due to human error. Furthermore, the display parameters of existing driver boards are mostly fixed settings, unable to be dynamically adjusted according to the characteristics of the actual display content. For example, maintaining a high refresh rate for static interfaces leads to energy waste, while insufficient response speed causes blurry images for high-speed dynamic videos. They also lack adaptability to complex operating conditions in industrial environments such as electromagnetic interference, temperature fluctuations, and power supply voltage fluctuations, easily resulting in signal distortion, display instability, or even hardware damage in high-temperature or strong interference environments.

[0004] Therefore, there is an urgent need for a control system and method for highly adaptable industrial liquid crystal display driver boards to solve the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide a control method for a highly adaptable industrial liquid crystal display driver board, comprising the following steps: On the processor built into the driver board, a layered adaptive control architecture including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer is constructed. During the system initialization phase, the hardware interface identification layer automatically detects and parses the interface information of the connected LCD screen, identifies key screen parameters, and based on the identification results, the driver strategy adaptation layer calls the preset driver algorithm library for matching and optimization to generate the corresponding screen initialization driver configuration sequence. The driver is loaded according to the screen initialization driver configuration sequence, and during the running phase, the display content characteristics and the board running environment status are continuously monitored through the dynamic optimization execution layer to obtain real-time monitoring data; Based on the real-time monitoring data, a lightweight machine learning algorithm deployed in the dynamic optimization execution layer is used to dynamically calculate and adjust the driving parameters output to the LCD screen. The final control command is generated based on the dynamically adjusted driving parameters, and the LCD screen is driven to display the image, so as to achieve adaptive driving of various LCD screens and optimization of display quality in complex industrial environments.

[0006] Furthermore, the present invention also discloses a control system for a highly adaptable industrial liquid crystal display driver board, comprising: The building module is used to build a layered adaptive control architecture, including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer, on the processor built into the driver board. The matching optimization module is used to automatically detect and parse the interface information of the connected LCD screen through the hardware interface identification layer during the system initialization phase, identify key screen parameters, and, based on the identification results, call the preset driver algorithm library by the driver strategy adaptation layer to perform matching and optimization, and generate the corresponding screen initialization driver configuration sequence. The acquisition module is used to complete driver loading according to the screen initialization driver configuration sequence, and during the running phase, continuously monitor the display content characteristics and board running environment status through the dynamic optimization execution layer to acquire real-time monitoring data; The adjustment module is used to dynamically calculate and adjust the driving parameters output to the LCD screen based on the real-time monitoring data and using a lightweight machine learning algorithm deployed in the dynamic optimization execution layer. The control module is used to generate final control commands based on dynamically adjusted driving parameters and drive the LCD screen to display, so as to achieve adaptive driving of various LCD screens and optimization of display quality in complex industrial environments.

[0007] Furthermore, the matching optimization module includes: The acquisition unit is used to acquire the extended display identification data of the connected LCD screen or its response characteristics to the standard timing probe signal through the hardware interface identification layer. The extraction unit is used to parse the extended display recognition data or response features and extract the original parameter information of the LCD screen; The calculation unit is used to calculate and determine the set of key driving parameters for driving the LCD screen based on the original parameter information and the hardware support capabilities of the driver board. The matching unit is used to perform feature matching in the driving algorithm library of the driving strategy adaptation layer according to the set of key driving parameters, so as to obtain the most matching set of calibration driving parameters as the basic template. The generation unit is used to generate a screen initialization driver configuration sequence containing initialization configuration values, timing and correction data based on the basic template and the key driver parameter set through parameter fine-tuning and interpolation calculation.

[0008] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described control method for a highly adaptable industrial liquid crystal display driver board.

[0009] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the control method for a highly adaptable industrial liquid crystal display driver board described above.

[0010] The beneficial effects of this application are as follows: Firstly, this invention addresses the problem of poor hardware compatibility of existing driver boards by automatically detecting and parsing the EDID information or simulated timing characteristics of the LCD screen through the hardware interface identification layer in the hierarchical adaptive control architecture. Combined with the feature matching mechanism of the driver algorithm library, it achieves fully automatic adaptation to LCD screens of different interface types and specifications without the need to replace the driver board or manually configure parameters. This significantly improves the compatibility of the driver board with various LCD screens and reduces the maintenance costs of equipment replacement and upgrades.

[0011] Secondly, this invention solves the problem of the need for a lot of manual configuration and debugging in the prior art. Through automatic parameter identification in the initialization stage, generation of driver configuration sequence and dynamic optimization in the running stage, it completely replaces the cumbersome process of relying on hardware jumpers and manual firmware burning, reduces human error, shortens the engineering deployment cycle, reduces the dependence on the professional level of technical personnel, and improves deployment efficiency.

[0012] Thirdly, this invention addresses the deficiency of fixed display parameters that cannot be dynamically optimized. By continuously monitoring the characteristics of the displayed content and the environmental state through a dynamic optimization execution layer, it uses a lightweight machine learning algorithm to dynamically adjust key parameters such as refresh rate and backlight drive current. This achieves targeted optimizations for energy saving in static interfaces, smooth dynamic videos, and clear high-contrast charts, thereby reducing system energy consumption while ensuring display quality.

[0013] Fourth, this invention can address the problem of insufficient adaptability to complex industrial environments. By collecting environmental data such as temperature and electromagnetic interference intensity in real time through onboard sensor groups, it adaptively adjusts parameters such as signal pre-emphasis intensity, synchronization signal timing margin, and power supply voltage, thereby enhancing the anti-interference capability and operational stability of the driver board under complex working conditions such as high temperature, strong interference, and voltage fluctuations. This avoids problems such as signal distortion and display abnormalities, and extends the service life of the driver board and LCD screen. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of a method flow proposed in an embodiment of this application.

[0015] Figure 2This is a schematic diagram of the system structure proposed in an embodiment of the present invention.

[0016] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] like Figure 1 As shown, this application provides a control method for a highly adaptable industrial liquid crystal display driver board, including the following steps: S1. On the processor built into the driver board, a layered adaptive control architecture including a hardware interface identification layer, a driver strategy adaptation layer and a dynamic optimization execution layer is constructed. S2, During the system initialization phase, the hardware interface identification layer automatically detects and parses the interface information of the connected LCD screen, identifies key screen parameters, and based on the identification results, the driver strategy adaptation layer calls the preset driver algorithm library for matching and optimization to generate the corresponding screen initialization driver configuration sequence. S3, complete driver loading according to the screen initialization driver configuration sequence, and during the running phase, continuously monitor the display content characteristics and board running environment status through the dynamic optimization execution layer to obtain real-time monitoring data; S4. Based on the real-time monitoring data, a lightweight machine learning algorithm deployed in the dynamic optimization execution layer is used to dynamically calculate and adjust the driving parameters output to the LCD screen. S5 generates the final control command based on the dynamically adjusted driving parameters and drives the LCD screen to display, so as to achieve adaptive driving of various LCD screens and optimization of display quality in complex industrial environments.

[0019] As described in steps S1-S5 above, this application constructs a hierarchical adaptive control architecture, combining automatic parameter identification and drive matching in the initialization phase, real-time status monitoring in the operation phase, and dynamic parameter adjustment driven by a lightweight machine learning algorithm, to achieve fully automatic software adaptation for various LCD screens. At the same time, it optimizes the display quality, reliability, and energy efficiency in complex industrial environments, achieving the goal of high adaptability and low maintenance cost for industrial LCD display drivers.

[0020] The core problem facing existing industrial LCD driver boards is the significant differences in key parameters such as interface type, resolution, and timing requirements among different brands and models of LCD screens. Traditional driving methods rely on hardware jumpers, manual firmware burning, and cumbersome debugging, resulting in poor hardware compatibility, difficult engineering deployment, and fixed display parameter settings. These methods cannot dynamically optimize based on the characteristics of different display content, such as static images and dynamic videos, or environmental changes common in industrial scenarios, such as temperature fluctuations and electromagnetic interference, thus affecting display quality and system stability. Therefore, there is an urgent need to establish a fully automated adaptation mechanism from hardware recognition to dynamic optimization, which can solve the compatibility problem of multiple LCD screens and improve adaptability in complex environments.

[0021] Traditional solutions rely on manual intervention to identify and configure LCD screen parameters, resulting in low efficiency and a high risk of errors. Display parameters lack dynamic adjustment capabilities, making it difficult to balance display performance and energy consumption when faced with different content. Furthermore, in industrial environments with electromagnetic interference or temperature variations, parameter optimization fails to ensure display stability. This invention proposes a layered adaptive control architecture and a fully automated strategy. A hardware interface identification layer enables automatic parameter detection, a driver strategy adaptation layer ensures precise driver matching, and a dynamic optimization execution layer adjusts parameters based on real-time data, forming a closed-loop control system. This completely eliminates reliance on manual operation and enables dynamic adaptation of display strategies.

[0022] The core logic of this solution is to construct a layered adaptive control architecture as functional support, focusing on full-process automated adaptation and dynamic optimization. It specifically addresses the problems of poor hardware compatibility, the need for manual configuration and debugging, fixed display parameters, and insufficient adaptability to complex industrial environments in existing driver boards. The principle is to first build a layered architecture on the driver board's built-in processor, including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer, laying the foundation for collaborative work among various stages. Then, during system initialization, the hardware interface identification layer automatically detects and parses the interface information of the connected LCD screen and identifies key parameters. The driver strategy adaptation layer calls a pre-built driver algorithm library to complete matching and optimization, generating an adapted screen initialization driver configuration sequence, achieving driver loading preparation without manual intervention. Subsequently... During operation, the dynamic optimization execution layer continuously collects display content features and board operating environment status data, which are then used as input for a lightweight machine learning algorithm. The algorithm dynamically calculates and adjusts key driving parameters such as the LCD screen's refresh rate and backlight drive current. Finally, based on the adjusted parameters, it generates final control commands to drive the LCD screen display. The entire process forms a closed-loop control system encompassing architecture support, automatic initialization adaptation, dynamic optimization during operation, and command execution. By replacing traditional manual operation with intelligent adaptation of software algorithms, the system improves the compatibility and deployment efficiency of the driver board for various LCD screens. Furthermore, through scene perception and dynamic parameter adjustment, it enhances display quality, reliability, and energy efficiency in complex industrial environments, ultimately achieving the goal of highly adaptable and low-maintenance industrial LCD display drivers.

[0023] In one embodiment, the steps of constructing a hierarchical adaptive control architecture including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer include: S11, obtain the physical interface type and communication protocol type of the connected LCD screen, logically partition the display driver system according to the interface and protocol type, divide the LCD screens using the same or compatible interfaces and protocols into the same hardware adaptation area, and configure a hardware interface identification node for each hardware adaptation area. The hardware interface identification node is responsible for the initial signal detection and parsing of all LCD screens in the area. S12, configure a driver strategy adaptation node for each hardware interface identification node, obtain the data processing capability and storage space of each driver strategy adaptation node, and comprehensively determine the cycle of the driver strategy adaptation node generating control instructions based on the data processing capability, the amount of screen parameter data to be processed, the amount of driver algorithm data to be called from the storage space, and the read and write performance of the storage space. S13, Configure a dynamic optimization execution node at the main control terminal of the driver board system, obtain the monitoring data acquisition frequency and instruction issuance delay of the main control terminal for all hardware adaptation areas, and determine the cycle for the dynamic optimization execution node to make optimization decisions based on the acquisition frequency and instruction issuance delay; S14, configure a low-level signal control module for the physical communication channel within each hardware interface identification node, obtain the clock signal accuracy and level stability parameters of each low-level signal control module, and determine the step size of the low-level signal control module to adjust the drive signal waveform based on the clock period corresponding to the clock signal accuracy and the signal stability establishment time reflected by the level stability parameters. S15. Based on the dynamic optimization execution node, multiple driving strategy adaptation nodes, and multiple underlying signal control modules, a hierarchical adaptive control architecture is constructed in which the hardware interface identification layer, driving strategy adaptation layer, and dynamic optimization execution layer work together. This forms a positive control flow from bottom-level signal acquisition and mid-level strategy matching to top-level dynamic optimization, as well as a reverse optimization flow from top-level optimization decision feedback to bottom-level signal adjustment.

[0024] As described in steps S11-S15 above, by dividing the hardware adaptation area according to the interface and protocol type, configuring the corresponding functional nodes and modules, dynamically determining the instruction generation cycle, optimization decision cycle and signal adjustment step size, a hierarchical adaptive control architecture is constructed in which the hardware interface identification layer, the driver strategy adaptation layer and the dynamic optimization execution layer work together, forming a positive control flow and a reverse optimization flow, providing efficient and stable architectural support for subsequent automatic recognition of LCD screens, driver matching and dynamic parameter optimization.

[0025] In industrial settings, LCD screens exhibit diverse physical interface types and communication protocols. Different types of LCDs differ in signal transmission rules and data formats. Without proper partitioning and functional division of the display driver system, initial signal detection and parsing can become chaotic, reducing recognition efficiency and accuracy. Furthermore, the data processing capabilities, storage space, and read / write performance of driver strategy adaptation nodes vary. The amount of screen parameter data to be processed and the amount of driver algorithm data to be invoked also vary depending on the LCD model. A fixed instruction generation cycle cannot adapt to the processing needs of different scenarios, potentially leading to data backlog or resource waste. The optimization decision cycle of the dynamic optimization execution node must match the monitoring data acquisition frequency and instruction issuance delay; otherwise, optimization decisions may be delayed or too frequent, affecting the dynamic optimization effect. The clock signal accuracy and level stability of the underlying signal control module directly determine the adjustment accuracy of the driver signal waveform. A fixed adjustment step size cannot adapt to the different signal stabilization time requirements, resulting in insufficient signal transmission stability. Therefore, a reasonable architecture design and parameter configuration are needed to solve the collaborative work problems caused by hardware differences and scenario changes, ensuring efficient connection between functions at each layer.

[0026] Traditional solutions fail to logically partition the interface and protocol types, relying on a single identification node to handle signal detection and parsing for all types of LCD screens. This results in low identification efficiency and a high susceptibility to errors. Furthermore, the instruction generation cycle of the drive strategy adaptation node, the optimization decision cycle of the dynamic optimization execution node, and the adjustment step size of the underlying signal control module are all fixed values, unable to dynamically adjust according to hardware performance and actual data volume, leading to poor adaptability. The lack of a clear forward control flow and reverse optimization flow design also hinders seamless collaboration between functional modules, impacting overall control efficiency. This invention specifically proposes a solution that partitions the interface and protocol, configures dedicated functional nodes and modules, and dynamically calculates key cycles and step sizes. This achieves precise adaptation and efficient collaboration among the various parts of the architecture, overcoming the rigidity and poor adaptability of traditional architecture designs.

[0027] The system obtains the physical interface type and communication protocol type of the connected LCD screens. Based on these types, the display driver system is logically partitioned, grouping LCD screens using the same or compatible interfaces and protocols into the same hardware adaptation area. A hardware interface identification node is configured for each hardware adaptation area, responsible for the initial signal detection and parsing of all LCD screens within that area. The physical interface type and communication protocol type are obtained through the interface detection circuitry built into the driver board. For example, if some LCD screens use HDMI interfaces and protocols, while others use LVDS interfaces and protocols, they are divided into two independent hardware adaptation areas. Configuring a dedicated hardware interface identification node for each area ensures that each node handles only specific signal detection and parsing tasks, avoiding interference between different signal types and improving recognition accuracy and efficiency. For instance, the identification node in the HDMI interface hardware adaptation area only detects and parses HDMI protocol signal transmission rules, without handling LVDS protocol signals, reducing node processing load and increasing recognition speed.

[0028] A driver policy adaptation node is configured for each hardware interface identification node. The data processing capability and storage space of each driver policy adaptation node are obtained. Based on the data processing capability, the amount of screen parameter data to be processed, the amount of driver algorithm data to be called from the storage space, and the read / write performance of the storage space, the cycle for generating control instructions for that driver policy adaptation node is comprehensively determined. The data processing capability of the driver policy adaptation node is obtained through its onboard processor parameters; the storage space and read / write performance are obtained through the hardware parameters of the storage module; the amount of screen parameter data to be processed is determined by the detection results of the hardware interface identification node; and the amount of driver algorithm data to be called is determined by the preset parameters of the driver algorithm library. For example, if a driver policy adaptation node has a data processing capability of 80MB / s, a screen parameter data to be processed of 0.8MB, a driver algorithm data to be called of 0.2MB, and a storage space read / write performance of 100MB / s, its instruction generation cycle is calculated to be 12.5ms. This ensures that the node has sufficient time to complete data processing and instruction generation while avoiding response lag due to an excessively long cycle.

[0029] A dynamic optimization execution node is configured at the system control terminal of the driver board. This node acquires the monitoring data acquisition frequency and command issuance delay for all hardware adaptation areas from the system control terminal. Based on these parameters, the optimization decision-making cycle of the dynamic optimization execution node is determined. The monitoring data acquisition frequency is determined by the operating parameters of the sensor group and content analysis module in the dynamic optimization execution layer. The command issuance delay is obtained through testing the communication module of the driver board. For example, if the monitoring data acquisition frequency for all hardware adaptation areas from the system control terminal is 40Hz and the command issuance delay is 4ms, the optimization decision-making cycle is determined to be 25ms. This ensures that the optimization decision-making can respond promptly to changes in the monitoring data without wasting system resources due to excessively frequent decision-making.

[0030] A low-level signal control module is configured for the physical communication channel within each hardware interface identification node. The clock signal accuracy and level stability parameters of each low-level signal control module are obtained. Based on the clock period corresponding to the clock signal accuracy and the signal settling time reflected by the level stability parameters, the step size for adjusting the drive signal waveform of that low-level signal control module is determined. The clock signal accuracy and level stability parameters of the low-level signal control module are obtained from the module's hardware specifications. The clock period is calculated from the clock signal accuracy, and the signal settling time is obtained through actual testing. For example, if the clock period corresponding to the clock signal accuracy of a certain low-level signal control module is 0.4ns, and the signal settling time reflected by the level stability parameters is 0.8ns, the step size for adjusting the drive signal waveform is determined to be 0.08ns. This ensures that the signal waveform adjustment accurately matches the signal settling time requirement, improving the stability and reliability of signal transmission.

[0031] Based on dynamic optimization execution nodes, multiple drive strategy adaptation nodes, and multiple underlying signal control modules, a hierarchical adaptive control architecture is constructed, in which the hardware interface identification layer, drive strategy adaptation layer, and dynamic optimization execution layer work collaboratively. This forms a forward control flow from bottom-level signal acquisition and mid-level strategy matching to top-level dynamic optimization, and a reverse optimization flow from top-level optimization decision feedback to bottom-level signal adjustment. The hardware interface identification layer completes signal acquisition and preliminary processing through various hardware interface identification nodes and underlying signal control modules, transmitting the results to the drive strategy adaptation layer. The drive strategy adaptation layer completes drive algorithm matching and control command generation through various drive strategy adaptation nodes, then transmits the results to the dynamic optimization execution layer. The dynamic optimization execution layer completes optimization decisions through dynamic optimization execution nodes, forming a forward control flow. Simultaneously, the dynamic optimization execution nodes feed back the optimization decision results to the drive strategy adaptation layer and the hardware interface identification layer. The drive strategy adaptation layer adjusts the control commands, and the hardware interface identification layer adjusts the signal detection and parsing methods and drive signal waveforms, forming a reverse optimization flow. This bidirectional data flow design ensures efficient collaboration among all layers of the architecture, enabling seamless integration from bottom-level signal processing to top-level optimization decisions, and improving the adaptability and response speed of the entire driver board control method.

[0032] In one embodiment, the step of generating the corresponding screen initialization driver configuration sequence includes: S21, through the hardware interface identification layer, send an extended display identification data request command to the connected LCD screen, or apply a set of standard timing analog detection signals to obtain the EDID data packet returned by the LCD screen or the response characteristic waveform of the analog detection signal; S22, parse the EDID data packet or analyze the response feature waveform to extract the original parameter information. The original parameter information includes at least screen manufacturer information, a list of supported resolutions, horizontal / vertical scan frequency range, pixel clock range, synchronization signal polarity, and recommended color depth. S23. Based on the original parameter information and the hardware support capabilities of the driver board, calculate and determine the final set of key driver parameters. The set of key driver parameters includes the target resolution, pixel clock, total horizontal pixels, total vertical rows, horizontal synchronization pulse width, vertical synchronization pulse width, horizontal leading and trailing edges, vertical leading and trailing edges, and interface data bit width. Among them, the target resolution is selected from the set of resolutions extracted from the original parameter information and supported by the driver board, under the constraint that it does not exceed the maximum pixel clock capability of the driver board and that each timing parameter is within the allowable range of the hardware timing generator, and the resolution with the largest area is selected. S24, based on the set of key driving parameters, feature matching is performed in the driving algorithm library of the driving strategy adaptation layer; the driving algorithm library pre-stores calibration driving parameter sets, gamma correction curves, overdrive voltage meters and power timing requirements for various LCD screen models; the matching process includes: firstly performing precise model matching, and if it fails, matching is performed based on the similarity between the set of key driving parameters and each calibration parameter set, and the calibration parameter set with the highest similarity is selected as the basic template; S25, based on the matched basic template, and combined with the key driver parameter set, perform parameter fine-tuning and interpolation calculations to generate a complete screen initialization driver configuration sequence including initialization register configuration values, power-on timing, gamma correction table and overdrive lookup table.

[0033] As described in steps S21-S25 above, the hardware interface identification layer automatically detects and parses the LCD screen interface information and extracts the original parameters. Combined with the hardware support capabilities of the driver board, the key driver parameter set is determined. Then, the driver strategy adaptation layer calls the driver algorithm library to perform feature matching and parameter fine-tuning, generating a complete screen initialization driver configuration sequence. This achieves fully automatic adaptation between the driver board and various LCD screens, providing accurate and compatible parameter support for subsequent driver loading.

[0034] Different brands and models of LCD screens exhibit significant differences in core parameters such as interface protocols, resolution, and timing requirements. These parameters directly determine the form and transmission rules of the drive signals. If these parameters cannot be accurately obtained and a suitable driver configuration cannot be generated, the driver board will be unable to drive the LCD screen properly, or problems such as blurry display, screen flickering, or even hardware damage may occur. Furthermore, the hardware support capabilities of the driver board have an upper limit; its maximum pixel clock speed, timing generator operating range, and other hardware specifications limit the range of configurable drive parameters. If the parameters exceed the hardware limit, it will cause abnormal operation of the drive system. Therefore, it is necessary to solve the parameter compatibility problem between the LCD screen and the driver board through systematic parameter detection, filtering, matching, and optimization to ensure the effectiveness and stability of driver initialization.

[0035] Traditional solutions rely on manually consulting LCD screen parameter manuals and configuring driver parameters via hardware jumpers or manual firmware flashing. This is inefficient and prone to human error, leading to incorrect parameter configurations. Furthermore, the lack of an automatic parameter detection mechanism makes it incompatible with different LCD screen models, resulting in poor versatility. Blindly applying parameters without considering the hardware support capabilities of the driver board can cause them to exceed the hardware's capacity, leading to system failures. This invention proposes a comprehensive solution that automatically detects and parses parameters, selects parameters based on hardware capabilities, and performs algorithm library matching and fine-tuning. This automates parameter acquisition, filtering, and matching, overcoming the problems of manual operation, poor versatility, and insufficient compatibility inherent in traditional methods.

[0036] The hardware interface identification layer sends an Extended Display Identification Data Request (EDID) command to the connected LCD screen, or applies a set of standard timing analog probe signals, to obtain the EDID data packet returned by the LCD screen or the response characteristic waveform of the analog probe signals. The EDID data request command follows the VESA standard's communication protocol for EDID data and is sent to the LCD screen's control chip via the driver board's interface communication circuit. The standard timing analog probe signals are pre-set signals conforming to the general display interface timing specifications; for example, the horizontal synchronization signal period is set to 12 microseconds, and the vertical synchronization signal period is set to 16 milliseconds. The signal amplitude conforms to the LCD screen's interface voltage standard and is generated and applied by the driver board's signal generation module. When the LCD screen supports the EDID data protocol, it returns an EDID data packet containing its own parameter information, which is transmitted to the hardware interface identification layer via the interface receiving circuit. LCD screens that do not support this protocol will generate a specific response waveform to the analog probe signals. The period, amplitude, phase, and other characteristics of the response waveform are related to the LCD screen's scanning frequency, synchronization polarity, and other parameters. The response characteristic waveform is obtained through the signal acquisition module, providing a data basis for subsequent parameter extraction.

[0037] The EDID data packet is parsed or the response characteristic waveform is analyzed to extract raw parameter information. This raw parameter information includes at least screen manufacturer information, a list of supported resolutions, horizontal scan frequency range, vertical scan frequency range, pixel clock range, sync signal polarity, and recommended color depth. The EDID data packet is parsed according to the format specified by the VESA standard. For example, the screen manufacturer's identification code is extracted from specific byte segments of the data packet; the list of supported resolutions is extracted from the resolution description field; and the horizontal and vertical scan frequency ranges and pixel clock ranges are extracted from the timing parameter field. The response characteristic waveform is processed using dedicated waveform analysis algorithms. For example, the horizontal scan frequency range is calculated by measuring the period of the horizontal sync signal, the vertical scan frequency range is calculated by measuring the period of the vertical sync signal, the sync signal polarity is determined by judging the duration of the high and low levels of the sync signal, and the recommended color depth is inferred from the amplitude changes of the waveform. This ensures the comprehensiveness and accuracy of the extracted raw parameter information, providing a basis for determining subsequent key driving parameters.

[0038] Based on the original parameter information and the hardware support capabilities of the driver board, the final set of key driver parameters is calculated and determined. This set includes the target resolution, pixel clock, total horizontal pixels, total vertical rows, horizontal sync pulse width, vertical sync pulse width, horizontal leading and trailing edges, vertical leading and trailing edges, and interface data bit width. The target resolution is selected from the set of resolutions supported by the driver board, extracted from the original parameter information, and chosen based on the constraint that it does not exceed the driver board's maximum pixel clock capability and that all timing parameters are within the allowable range of the hardware timing generator. The driver board's hardware support capabilities are obtained by reading its hardware configuration file. This file stores key hardware indicators such as the maximum pixel clock, the allowable range of total horizontal pixels by the hardware timing generator, and the allowable range of total vertical rows. For example, the driver board's maximum pixel clock is 135 MHz, the allowable range of total horizontal pixels by the hardware timing generator is 1200 to 2200, and the allowable range of total vertical rows is 600 to 1200. When selecting the target resolution, firstly, the resolutions supported by the driver board are filtered from the list of supported resolutions in the original parameter information. Then, the pixel clock corresponding to each filtered resolution is verified to ensure that it does not exceed the driver board's maximum pixel clock, and that timing parameters such as the total number of horizontal pixels and the total number of vertical rows are within the allowable range of the hardware timing generator. Finally, the resolution that meets the constraints and has the largest area is selected. For example, if the original parameter information supports resolutions including 1920×1080 and 1600×900, both of which are supported by the driver board and meet the timing requirements, and 1920×1080 has a larger area, it is determined as the target resolution. The pixel clock is calculated based on the target resolution and the scanning frequency. For example, when the target resolution is 1920×1080 and the vertical scanning frequency is 60 Hz, the pixel clock is calculated as 1920×1080×60×1.05=131.22 MHz. Timing parameters such as total horizontal pixels, total vertical rows, and horizontal sync pulse width are calculated and determined based on the target resolution and display industry standard timing specifications. The interface data bit width is determined based on the LCD screen's interface type and the color depth in the original parameters. For example, when the color depth is 24 bits, the interface data bit width is set to 24 bits to ensure that the set of key driving parameters meets both the LCD screen requirements and the driver board hardware capabilities.

[0039] Based on the key driving parameter set, feature matching is performed in the driving algorithm library of the driving strategy adaptation layer. The driving algorithm library pre-stores calibration driving parameter sets, gamma correction curves, overdrive voltage meters, and power timing requirements for various LCD screen models. The matching process includes: first, performing precise model matching; if that fails, matching is performed based on the similarity between the key driving parameter set and each calibration parameter set, selecting the calibration parameter set with the highest similarity as the base template. The driving algorithm library is stored in the non-volatile memory of the driving board. The calibration driving parameter sets in the library have the same parameter types as the key driving parameter sets, both containing core parameters such as resolution, pixel clock, and timing parameters. During precise model matching, the screen manufacturer information in the key driving parameter set and the model information extracted from the original parameters are compared with the LCD screen models corresponding to the calibration driving parameter sets in the driving algorithm library. If a completely matching model is found, the calibration parameter set corresponding to that model is directly called. If no matching model is found, the similarity between the key driving parameter set and each calibration parameter set is calculated. The similarity is obtained by calculating the weighted sum of the deviation rates of each corresponding parameter. The smaller the deviation rate and the larger the weight, the higher the similarity. The formula for calculating the similarity is: ; Among them, the This indicates the similarity between the key driving parameter set and the calibration parameter set. This represents the actual value of the i-th key driving parameter, which comes from the set of key driving parameters mentioned above. This represents the calibration value of the i-th key driving parameter, which comes from a pre-set set of calibration driving parameters in the driving algorithm library. The value represents the weight of the i-th key parameter, ranging from 0.1 to 0.3. Core parameters (such as pixel clock and target resolution) have higher weights, and their values ​​are calibrated through offline matching tests. n represents the number of key parameters involved in the matching, such as target resolution, pixel clock, synchronization pulse width, and other core parameters. The number is fixed at 8 to 10. For example, the deviation rate weight between the target resolution and the resolution of the calibration parameter set is 0.3, the pixel clock deviation rate weight is 0.2, and the sum of the timing parameter deviation rate weights is 0.5. If the similarity of a certain calibration parameter set is calculated to be 92%, which is the highest among all calibration parameter sets, then this calibration parameter set is selected as the basic template to ensure that the calibration parameters that best fit the current LCD screen are matched.

[0040] Based on the matched base template, parameter fine-tuning and interpolation calculations are performed using a set of key driving parameters to generate a complete screen initialization driver configuration sequence, including initialization register configuration values, power-on timing, gamma correction table, and overdrive lookup table. During parameter fine-tuning, slight adjustments are made to timing parameters and voltage parameters to address differences between the calibration driver parameter set in the base template and the key driving parameter set. For example, if the horizontal sync pulse width of the base template is 100 pixel clock cycles, while the calculated horizontal sync pulse width in the key driving parameter set is 105 pixel clock cycles, then this parameter in the base template is adjusted to 105 pixel clock cycles. Interpolation calculations are mainly applied to the gamma correction curve and the overdrive voltage table. For example, if the gamma correction curve of the base template corresponds to a color depth of 24 bits and a gamma value of 2.2, while the recommended gamma value in the key driving parameter set is 2.0, then the voltage values ​​corresponding to each gray level in the gamma correction curve are adjusted using a linear interpolation algorithm. The overdrive voltage table supplements the overdrive voltage corresponding to different gray level transitions based on the pixel clock and target resolution in the key driving parameter set through interpolation calculations. The initialization register configuration value is generated based on the adjusted driver parameters, corresponding to the register addresses and configuration values ​​of functional modules such as the timing generator and interface controller in the driver board. The power-on sequence is determined based on the power requirements of the LCD screen and the characteristics of the power management module of the driver board. For example, the 3.3V logic power supply is started first, and the 12V backlight power supply is started after a 10-millisecond delay. The gamma correction table and overdrive lookup table are generated based on the results of fine-tuning and interpolation. Finally, they are integrated into a complete screen initialization driver configuration sequence to ensure that the sequence can accurately drive the current LCD screen to complete the initialization.

[0041] In one embodiment, the step of acquiring real-time monitoring data includes: S31, the screen initialization driver configuration sequence is loaded into the corresponding functional module of the driver board, and the power timing control, register configuration, gamma table and overdrive table writing operations are executed in sequence to complete the driver initialization of the LCD screen and start screen output. S32, during the operation phase, the content analysis module in the dynamic optimization execution layer performs real-time analysis on the input video frame data, extracts and quantifies the display content feature vector; the display content feature vector includes at least: scene type identifier, average screen brightness, brightness change gradient, color saturation distribution, and refresh requirement identifier for a specific area. S33, at the same time, the board's operating environment status data is acquired through the onboard sensor group, and an environmental status vector is constructed; the environmental status vector includes at least: the core temperature of the drive board, the ambient temperature, the power input voltage fluctuation value, and the noise interference intensity index obtained through the onboard electromagnetic field sensor or signal integrity monitoring circuit; S34, the display content feature vector and the environment state vector are timestamped and fused to form a multi-dimensional real-time monitoring data stream; and the real-time monitoring data stream is preprocessed by sliding window averaging and outlier filtering to generate a standardized input feature set for use by lightweight machine learning algorithms.

[0042] As described in steps S31-S34 above, the LCD screen driver initialization is completed by loading the screen initialization driver configuration sequence. During the operation phase, the display content characteristics and the board operating environment status are monitored synchronously. The collected data is timestamped, fused, and preprocessed to generate a standardized input feature set, which provides accurate and reliable data support for the subsequent lightweight machine learning algorithm to dynamically adjust the driver parameters.

[0043] During the operation of industrial LCD displays, the displayed content exhibits different characteristics depending on the application scenario. Different types of display content, such as static interfaces, high-speed dynamic videos, and high-contrast charts, have different requirements for drive parameters. For example, dynamic videos require higher refresh rates to ensure smooth playback, while static interfaces can reduce refresh rates to save energy. Simultaneously, the complexity of the industrial environment leads to significant fluctuations in the operating environment of the circuit boards. Increased core temperature of the drive board can affect the performance of electronic components, electromagnetic interference can cause signal transmission distortion, and fluctuations in power input voltage can affect the stability of the drive signal. These environmental factors directly impact display quality and system operational safety. Without real-time data acquisition, drive parameters lack a basis for adjustment, remaining at fixed settings and unable to adapt to changes in display content and environmental conditions, ultimately resulting in poor display performance or decreased system stability. Therefore, comprehensive and real-time monitoring and data processing are necessary to provide objective evidence for the dynamic optimization of drive parameters.

[0044] Traditional solutions rely solely on fixed driving parameters, neglecting to monitor display content characteristics and failing to adjust strategies for different display scenarios. Environmental monitoring is limited, typically focusing only on temperature while ignoring crucial factors like electromagnetic interference and voltage fluctuations. Furthermore, the collected data lacks effective fusion and preprocessing, resulting in insufficient accuracy and consistency, making it unsuitable for direct algorithm computation. This invention specifically proposes a solution that simultaneously monitors display content and environmental conditions, integrates multi-dimensional data, and employs sliding window averaging and outlier filtering. This achieves comprehensive data acquisition and precise data processing, overcoming the shortcomings of traditional methods such as insufficient data support and poor adaptability.

[0045] The screen initialization driver configuration sequence is loaded into the corresponding functional modules of the driver board. Power timing control, register configuration, and writing operations for the gamma table and overdrive table are executed sequentially to complete the driver initialization of the LCD screen and initiate screen output. The corresponding functional modules of the driver board include a power management module, a timing generator, a register group, a gamma correction module, and an overdrive control module. The hardware parameters of these modules are predefined through the driver board's hardware configuration file. During loading, the power management module executes control according to the power-on sequence in the initialization driver configuration sequence. For example, it first starts the 3.3V logic power supply, then delays for 10 milliseconds before starting the 12V backlight power supply to ensure stable power switching. The register group receives the initialization register configuration values ​​from the configuration sequence and writes key parameters such as target resolution, pixel clock, and synchronization signal polarity. The gamma correction module writes the corresponding gamma correction table to calibrate color reproduction accuracy, and the overdrive control module writes the overdrive lookup table to improve pixel response speed. After each operation is completed, the timing generator generates a drive signal according to the configured timing parameters, initiating LCD screen output and providing a basis for subsequent status monitoring.

[0046] During the runtime phase, the content analysis module in the dynamic optimization execution layer performs real-time analysis on the input video frame data, extracting and quantifying the display content feature vector. The display content feature vector includes at least a scene type identifier, average screen brightness, brightness variation gradient, color saturation distribution, and refresh requirement identifier for specific areas. The content analysis module consists of an image processor and dedicated algorithm circuitry. The input video frame data comes from the video input interface of the driver board, and the data format is RGB888. The scene type identifier is determined by analyzing the pixel change rate between video frames. When the pixel change rate is less than 5%, it is considered a static interface, and the scene type identifier is set to 0. When the pixel change rate is greater than 30%, it is considered high-speed dynamic video, and the scene type identifier is set to 1. Values ​​between these values ​​are considered high-contrast graphics, and the scene type identifier is set to 2. The average screen brightness is obtained by calculating the average brightness of the RGB components of all pixels within a single frame. For example, if the total pixel brightness of a single frame is 15,360,000 nits and the total number of pixels is 1,024,000, then the average screen brightness is 15 nits. The brightness gradient is obtained by calculating the absolute value of the average brightness difference between two adjacent frames. For example, if the average brightness of the previous frame is 15 nits and the average brightness of the current frame is 18 nits, then the brightness gradient is 3 nits / frame. Color saturation distribution is obtained by statistically analyzing the saturation values ​​of the RGB components of each pixel within a single frame, dividing it into high, medium, and low intervals, and calculating the pixel percentage in each interval. For example, high saturation pixels account for 30%, medium saturation pixels account for 50%, and low saturation pixels account for 20%. The refresh requirement flag for a specific region is obtained by analyzing the pixel change frequency of local regions within a frame. When the pixel change frequency of a local region is higher than 50Hz, the refresh requirement flag for that region is set to 1; otherwise, it is set to 0, ensuring that subsequent parameter adjustments can specifically meet the high-frequency refresh requirements of local areas.

[0047] Simultaneously, the onboard sensor array acquires environmental status data of the board and constructs an environmental state vector. This environmental state vector includes at least the core temperature of the driver board, ambient temperature, power input voltage fluctuation, and noise interference intensity obtained through the onboard electromagnetic field sensor or signal integrity monitoring circuit. The onboard sensor array includes a temperature sensor, a voltage sensor, an electromagnetic field sensor, and a signal integrity monitoring circuit. The temperature sensor is installed near the core chip of the driver board, acquiring the core temperature of the driver board with a measurement range of -40℃ to 125℃ and an accuracy of ±0.5℃. Ambient temperature is collected by a temperature sensor installed on the board's casing, with the same measurement range and accuracy as the core temperature sensor. A voltage sensor is connected in series in the power input circuit to collect the power input voltage in real time. By calculating the difference between the maximum and minimum voltage values ​​within a 100-millisecond interval, the power input voltage fluctuation value is obtained. The measurement range is 0V to 24V, with an accuracy of ±0.01V. An electromagnetic field sensor is installed near the board's signal transmission lines to collect the surrounding electromagnetic field strength. The signal integrity monitoring circuit analyzes the eye diagram parameters of the transmitted signal and combines the data from both to obtain a noise interference intensity index, ranging from 0 to 100, with higher values ​​indicating more severe interference. The data acquisition frequency of all sensors and monitoring circuits is set to 100Hz to ensure real-time data transmission.

[0048] The display content feature vector and environmental state vector are timestamped and fused to form a multi-dimensional real-time monitoring data stream. The real-time monitoring data stream is preprocessed with sliding window averaging and outlier filtering to generate a standardized input feature set for lightweight machine learning algorithms. Timestamp alignment is achieved through the driver board's system clock, adding a unified timestamp to the display content feature vector and the concurrently collected environmental state vector for each frame, ensuring data consistency in the time dimension. For example, display content features within the same 10-millisecond time window are correlated with environmental state data. Data fusion is achieved through vector concatenation, where the display content feature vector and environmental state vector are concatenated in a fixed order to form a nine-dimensional real-time monitoring data stream containing scene type identifiers, average screen brightness, brightness change gradient, color saturation distribution, refresh requirement identifiers for specific areas, driver board core temperature, ambient temperature, power input voltage fluctuation values, and noise interference intensity indicators. The sliding window averaging uses a data window of size 5 to calculate the arithmetic mean of 5 consecutive data points in the real-time monitoring data stream, smoothing out data fluctuations. For example, averaging 5 consecutive core temperature data points of 60℃, 61℃, 60℃, 62℃, and 61℃ yields a processed value of 60.8℃. Outlier filtering employs the 3σ criterion, calculating the mean and standard deviation of each data dimension. Data exceeding the mean ± 3 times the standard deviation is identified as outliers and replaced with the mean of that dimension. For instance, the mean of the power input voltage fluctuation is 0.2V, and the standard deviation is 0.1V. A data point with 0.8V exceeds the mean ± 3 times the standard deviation (0.2V ± 0.3V) and is therefore identified as an outlier, replaced with 0.2V. After preprocessing, the min-max normalization method is used to map the data to the interval between 0 and 1, generating a standardized input feature set to ensure a consistent data format and meet the input requirements of lightweight machine learning algorithms.

[0049] In one embodiment, the step of dynamically calculating and adjusting the driving parameters output to the LCD screen includes: S41, the standardized input feature set is input into the lightweight machine learning algorithm model, the model being a small neural network or decision tree ensemble model trained offline, and its output being a series of driving parameter adjustment factor vectors; S42, apply the driving parameter adjustment factor vector to a set of basic driving parameters. The basic driving parameter set is derived from the currently used screen initialization driving configuration sequence or the parameters after the last optimization. By calculating the adjustment factor with the adjustment sensitivity coefficient and basic value corresponding to each parameter, the dynamically adjusted target driving parameter set is obtained. S43, the target driving parameter set includes at least: LCD screen refresh rate, backlight driving current or pulse width modulation duty cycle, pixel data pre-emphasis intensity, synchronization signal timing margin, and analog power supply voltage fine-tuning value; the adjustment sensitivity coefficient is used to map the normalized adjustment factor to the actual physical adjustment range of each parameter. S44. Based on the target driving parameter set, generate corresponding intermediate layer control instructions. These instructions describe the target values ​​or relative changes that each driving parameter needs to achieve and pass them to the driving strategy adaptation layer and hardware interface identification layer.

[0050] As described in steps S41-S44 above, by inputting the standardized input feature set into the lightweight machine learning algorithm model trained offline, a driving parameter adjustment factor vector is generated. This vector is applied to the basic driving parameter set and combined with the adjustment sensitivity coefficient to calculate the target driving parameter set. Finally, intermediate layer control instructions are generated and transmitted to the corresponding level, thereby realizing the dynamic and precise adjustment of driving parameters. This allows the driving strategy to adapt to changes in the display content features and the board's operating environment in real time.

[0051] During the operation of industrial LCD displays, the characteristics of the displayed content and the operating environment of the circuit boards are constantly changing. Static interfaces and high-speed dynamic videos have different requirements for refresh rate and color saturation. High-temperature and strong electromagnetic interference environments have different requirements for power supply voltage and signal drive strength. Fixed drive parameters cannot simultaneously address display quality, energy consumption, and system stability in different scenarios. For example, a high refresh rate in a static interface can lead to unnecessary energy waste; an unadjusted analog power supply voltage in a high-temperature environment may cause increased circuit board heating; and insufficient pre-emphasis intensity in a strong interference environment can cause signal distortion. Therefore, it is necessary to dynamically adjust drive parameters based on real-time monitoring data to accurately match the drive strategy with the current scenario and solve display and operational problems in different scenarios.

[0052] Traditional solutions often employ fixed driving parameters, failing to adapt to dynamic changes in displayed content and environmental conditions. Parameter adjustments based solely on simple threshold judgments suffer from low precision and poor adaptability, lacking intelligent computing mechanisms based on multi-dimensional monitoring data, making precise parameter optimization difficult. This invention specifically proposes a dynamic parameter calculation scheme based on lightweight machine learning algorithms. By combining the collaborative calculation of basic parameters, adjustment factors, and sensitivity coefficients, it achieves refined and scenario-specific adjustments of driving parameters, overcoming the rigidity, low precision, and insufficient adaptability of traditional methods.

[0053] The standardized input feature set is fed into a lightweight machine learning algorithm model, which is a small neural network or decision tree ensemble model trained offline. Its output is a series of driving parameter adjustment factor vectors. The standardized input feature set is nine-dimensional data preprocessed by timestamp alignment, data fusion, sliding window averaging, and outlier filtering. It includes scene type identifiers, average screen brightness, brightness variation gradient, color saturation distribution, refresh requirement identifiers for specific areas, driver board core temperature, ambient temperature, power input voltage fluctuation, and noise interference intensity. The small neural network uses a two-layer hidden layer structure with 16 neurons in each layer. The ReLU activation function is used. The input layer receives the nine-dimensional standardized features, and the output layer outputs a five-dimensional driving parameter adjustment factor vector, corresponding to the adjustment ratios of LCD screen refresh rate, backlight drive current or pulse width modulation duty cycle, pixel data pre-emphasis intensity, synchronization signal timing margin, and analog power supply voltage fine-tuning. The decision tree ensemble model consists of three decision trees with a depth not exceeding 5. A voting mechanism is used to output the final five-dimensional adjustment factor vector, avoiding the overfitting problem of a single decision tree. During offline training, 1000 sets of display content features and environmental state data commonly found in industrial scenarios are used as the training set. Each set of data is labeled with the corresponding optimal driving parameters. The model parameters are optimized through gradient descent algorithm to ensure that the model can accurately output the appropriate adjustment factor vector based on the input features. The numerical range of the adjustment factor vector is normalized to 0 to 1. For example, when the interface is static (scene type identifier 0) and the core temperature of the driver board is 50℃, the output refresh rate adjustment factor is 0.3 and the backlight driving current adjustment factor is 0.2.

[0054] The driving parameter adjustment factor vector is applied to a set of basic driving parameters, which are derived from the currently used screen initialization driving configuration sequence or the parameters from the last optimization. The dynamically adjusted target driving parameter set is obtained by calculating the adjustment factor along with the corresponding adjustment sensitivity coefficients and base values ​​for each parameter. The selection of the basic driving parameter set follows the latest effective principle. If the system has just completed initialization and has not undergone parameter optimization, the parameters from the screen initialization driving configuration sequence are used, such as an initial refresh rate of 60Hz, backlight driving current of 100mA, pixel data pre-emphasis intensity of 0.5V, synchronization signal timing margin of 5ns, and analog power supply voltage of 3.3V. If at least one parameter optimization has been performed, the target driving parameter set from the last optimization is used as the basic parameters. The sensitivity adjustment coefficient is a dimensionless coefficient preset based on the driver board hardware specifications and LCD screen characteristics. It maps the normalized adjustment factor to the actual physical adjustment range of each parameter. For example, the refresh rate adjustment sensitivity coefficient is 10Hz / unit factor, the backlight drive current adjustment sensitivity coefficient is 20mA / unit factor, the pixel data pre-emphasis intensity adjustment sensitivity coefficient is 0.3V / unit factor, the synchronization signal timing margin adjustment sensitivity coefficient is 2ns / unit factor, and the analog power supply voltage fine-tuning value adjustment sensitivity coefficient is 0.1V / unit factor. Parameter calculation uses a linear superposition method: target parameter value = base parameter value + adjustment factor × sensitivity adjustment coefficient. For example, with a base refresh rate of 60Hz, an adjustment factor of 0.3, and a sensitivity coefficient of 10Hz / unit factor, the calculated target refresh rate is 60 + 0.3 × 10 = 63Hz. With a base simulated power supply voltage of 3.3V, an adjustment factor of 0.5, and a sensitivity coefficient of 0.1V / unit factor, the target simulated power supply voltage is calculated to be 3.3 + 0.5 × 0.1 = 3.35V. This ensures that the adjusted parameters are suitable for the current scenario without exceeding the operating range of the hardware and the LCD screen.

[0055] The target driving parameter set includes at least the LCD screen refresh rate, backlight drive current or pulse width modulation duty cycle, pixel data pre-emphasis intensity, synchronization signal timing margin, and analog power supply voltage fine-tuning value. The LCD screen refresh rate adjustment needs to match the characteristics of the displayed content. For example, for a static interface with scene type identifier 0, an adjustment factor of 0.2 and a base refresh rate of 60Hz, the calculated target refresh rate is 60 + 0.2 × 10 = 62Hz. If the adjustment factor is 0.1, the target refresh rate is 60 + 0.1 × 10 = 61Hz, achieving energy saving by reducing the refresh rate. For high-speed dynamic video with scene type identifier 1, an adjustment factor of 0.8 results in a target refresh rate of 60 + 0.8 × 10 = 68Hz, where increasing the refresh rate ensures smooth video playback. The backlight drive current or pulse width modulation duty cycle is adjusted based on the average screen brightness. When the average screen brightness is 10 nits, the adjustment factor is 0.6, the base current is 100mA, and the target current = 100 + 0.6 × 20 = 112mA, enhancing brightness. When the average screen brightness is 20 nits, the adjustment factor is 0.1, and the target current = 100 + 0.1 × 20 = 102mA, avoiding excessive brightness that is glaring. The pixel data pre-emphasis intensity is adjusted according to the noise interference intensity index. When the noise interference intensity index is 80, the adjustment factor is 0.9, the base intensity is 0.5V, and the target intensity = 0.5 + 0.9 × 0.3 = 0.77V, enhancing signal driving capability to resist interference. When the noise interference intensity index is 30, the adjustment factor is 0.2, and the target intensity = 0.5 + 0.2 × 0.3 = 0.56V, avoiding excessive pre-emphasis that could cause signal distortion. The timing margin of the synchronization signal is adjusted based on the fluctuation of the power input voltage. When the fluctuation is 0.3V, the adjustment factor is 0.7, the base margin is 5ns, and the target margin is 5 + 0.7 × 2 = 6.4ns, improving timing fault tolerance. When the fluctuation is 0.1V, the adjustment factor is 0.3, and the target margin is 5 + 0.3 × 2 = 5.6ns, avoiding excessive margin from affecting display efficiency. The analog power supply voltage is fine-tuned in conjunction with the core temperature of the driver board. When the core temperature is 65℃, the adjustment factor is 0.4, the base voltage is 3.3V, and the target voltage is 3.3 + 0.4 × 0.1 = 3.34V, fine-tuning the voltage to reduce heat generation; when the core temperature is 45℃, the adjustment factor is 0.1, and the target voltage is 3.3 + 0.1 × 0.1 = 3.31V, maintaining voltage stability.

[0056] Based on the target driver parameter set, corresponding intermediate layer control instructions are generated. These instructions describe the target value or relative change amount that each driver parameter needs to achieve, and are then passed to the driver strategy adaptation layer and hardware interface identification layer. The intermediate layer control instructions use a standardized data format, containing three core fields: parameter type identifier, target value, and relative change amount. For example, the instruction for the LCD screen refresh rate is: Parameter Type: Refresh Rate, Target Value: 62Hz, Relative Change Amount: +2Hz; the instruction for pixel data pre-emphasis intensity is: Parameter Type: Pre-emphasis Intensity, Target Value: 0.77V, Relative Change Amount: +0.27V. The instructions are transmitted through a high-speed serial communication bus inside the driver board. The transmission rate of the communication bus is 1Gbps, ensuring the real-time performance and accuracy of instruction transmission. This provides a clear and standardized data foundation for the subsequent low-level command conversion of the driver strategy adaptation layer, ensuring the smooth progress of the parameter adjustment process.

[0057] In one embodiment, the step of generating a final control command based on dynamically adjusted driving parameters and driving the LCD screen to display the image includes: S51, the driving strategy adaptation layer receives intermediate layer control instructions from the dynamic optimization execution layer, translates and decomposes them into executable low-level register configuration commands or analog control signal parameters for specific hardware functional modules; S52, the hardware interface identification layer, in collaboration with the underlying signal control module, executes the underlying register configuration command or adjusts the analog control signal parameters. Specific operations include: adjusting the frequency division ratio of the timing generator to change the refresh rate, modifying the pulse width modulation register of the backlight controller to adjust the brightness, updating the transmitter equalizer settings to change the pre-emphasis, and fine-tuning the voltage supplied to the LCD screen through the programmable power management chip. S53, after adjusting the driving parameters, the dynamic optimization execution layer collects a new round of display content features and environmental status data, and verifies the effect by combining the preset image quality evaluation index and system stability index. S54. If the effect verification meets the preset optimization target threshold, the current target driving parameter set is updated to a new basic driving parameter set for the next round of optimization. If it does not meet the threshold, the iterative correction process of the control command is triggered. The lightweight machine learning algorithm model is fine-tuned according to the verification result and the target deviation, and the parameter dynamic calculation and adjustment steps are re-executed until the display effect and system stability reach a balance.

[0058] As described in steps S51-S54 above, the intermediate layer control instructions are translated and decomposed by the drive strategy adaptation layer, and the hardware interface identification layer coordinates with the underlying signal control module to perform parameter adjustments. Combined with the closed-loop verification and iterative correction mechanism for display effect and system stability, the dynamically adjusted drive parameters are converted into control signals that the LCD screen can execute, realizing full-process closed-loop control of adaptive drive, and ensuring that display quality and system stability are balanced in complex industrial environments.

[0059] Intermediate-layer control instructions only describe the target values ​​or relative changes of drive parameters. These are high-level logic instructions and cannot be directly recognized and executed by hardware functional modules such as the timing generator and backlight controller on the driver board. Hardware functional modules only respond to low-level register configuration commands or analog control signal parameters in a specific format. The lack of instruction translation and decomposition steps prevents parameter adjustments from being effectively implemented. Furthermore, after driver parameter adjustments, inconsistencies with actual requirements may arise due to individual hardware differences and dynamic environmental changes. Without effect verification, this could lead to display blurring, signal distortion, or even hardware damage. Industrial environments have stringent requirements for display continuity and stability. Closed-loop verification is essential to promptly identify parameter deviations and iteratively correct them to ensure effective adjustments and avoid impacting user experience due to improper parameters.

[0060] Traditional solutions directly send high-level parameter commands to the hardware module, lacking a translation and decomposition process. This results in the hardware being unable to recognize and execute the commands, and there is no effect verification process after parameter adjustments, making it impossible to determine whether the adjustments have met the standards. Furthermore, the absence of an iterative correction mechanism means that parameter deviations cannot be corrected in a timely manner, making it difficult to adapt to the dynamic changes in complex industrial environments. This invention specifically proposes a closed-loop solution encompassing command translation and decomposition, hardware collaborative execution, effect verification, and iterative correction. This ensures that commands are executable, adjustments are effective, and the system is stable, overcoming the problems of command incompatibility, blind adjustments, and insufficient stability inherent in traditional methods.

[0061] The driver strategy adaptation layer receives intermediate layer control instructions from the dynamic optimization execution layer, translates and decomposes them into executable low-level register configuration commands or analog control signal parameters for specific hardware functional modules. The intermediate layer control instructions include target values ​​or relative changes for LCD screen refresh rate, backlight drive current, pixel data pre-emphasis intensity, synchronization signal timing margin, and analog power supply voltage fine-tuning values, such as "target refresh rate 62Hz" or "relative change in analog power supply voltage +0.05V". The driver strategy adaptation layer has a built-in instruction mapping library for hardware functional modules, storing the register addresses, command formats, and parameter ranges corresponding to modules such as timing generators, backlight controllers, transmitter equalizers, and programmable power management chips. During translation and decomposition, the corresponding hardware module is matched according to the parameter type in the instruction, and the target value or relative change is converted into a format that the module can recognize. For example, the refresh rate of 62Hz is converted into the frequency division ratio register configuration value of the timing generator, and the analog power supply voltage change of +0.05V is converted into the voltage adjustment parameter of the programmable power management chip. This ensures that the communication protocol and data format of the underlying command and the hardware module are fully matched, providing an operable instruction basis for subsequent execution steps.

[0062] The hardware interface identification layer, in collaboration with the underlying signal control module, executes underlying register configuration commands or adjusts analog control signal parameters. Specifically, it adjusts the division ratio of the timing generator to change the refresh rate. The division ratio of the timing generator is inversely proportional to the output frequency. After calculating the received division ratio configuration value, it outputs a drive signal for the corresponding frequency, precisely adjusting the refresh rate from 60Hz to 62Hz. The brightness is adjusted by modifying the pulse width modulation register of the backlight controller. The configuration value of the pulse width modulation register is linearly related to the backlight drive current. When the configuration value is adjusted from a specific value to a higher value, the backlight drive current increases from 100mA to 105mA, and the brightness of the LCD screen is enhanced accordingly. The equalizer settings at the transmitting end are updated to change the pre-emphasis intensity. The equalizer setting parameters directly determine the pre-emphasis voltage amplitude. The parameter is adjusted from 0.5V to 0.6V to enhance the driving capability of high-frequency signals and resist electromagnetic interference. The voltage supplied to the LCD screen is fine-tuned through the programmable power management chip. Based on the voltage adjustment parameters, the analog power supply voltage is fine-tuned from 3.3V to 3.35V to adapt to the signal transmission requirements in high-temperature environments. All hardware modules work together to ensure that the adjustment of drive parameters is accurate.

[0063] After adjusting the drive parameters, a new round of display content features and environmental state data is collected again through dynamic optimization of the execution layer. The results are then verified by combining preset image quality evaluation indicators and system stability indicators. The data collection process is consistent with steps S32 and S33. The content analysis module extracts new scene type identifiers, average screen brightness, brightness change gradients, and other feature vectors. The onboard sensor group acquires new environmental state vectors such as the core temperature of the drive board, ambient temperature, and noise interference intensity. Preset image quality evaluation indicators include image sharpness, color reproduction, and brightness uniformity. System stability indicators include signal transmission error rate and hardware module operating temperature range. For example, image sharpness is calculated using an edge sharpness algorithm with a preset threshold of 0.8, and the preset threshold for signal transmission error rate is... The hardware module's operating temperature is preset to a threshold of 70℃. By comparing newly collected data with preset indicators, it is determined whether the parameter adjustments have achieved the optimization goal, providing a basis for whether further corrections are needed.

[0064] If the effect verification meets the preset optimization target threshold, the current target driving parameter set is updated to the new basic driving parameter set for the next optimization cycle. If it does not meet the target threshold, the iterative correction process of the control command is triggered. The optimization target threshold is calibrated through offline experiments and must simultaneously meet the following conditions: image clarity ≥ 0.8 and signal transmission bit error rate ≤ 0.8. Conditions such as hardware temperature ≤70℃ are met. When these conditions are met, parameters such as 62Hz refresh rate, 105mA backlight drive current, 0.6V pre-emphasis intensity, and 3.35V analog power supply voltage are updated to a new set of basic drive parameters. When these conditions are not met, the lightweight machine learning algorithm model is fine-tuned based on the verification results and the deviation from the target. For example, if the image clarity is 0.75, which is lower than the threshold of 0.8 and the deviation is 0.05, the weight coefficients corresponding to the brightness change gradient in the model are adjusted to enhance the influence of this feature on the refresh rate and backlight current. The parameter dynamic calculation and adjustment steps are then re-executed until the display effect and system stability reach a balance, forming a closed-loop control to ensure that parameter adjustments continuously adapt to dynamically changing scenarios and environments.

[0065] like Figure 2 As shown, the present invention also discloses a control system for a highly adaptable industrial liquid crystal display driver board, comprising: Module 1 is used to build a hierarchical adaptive control architecture, including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer, on the processor built into the driver board. The matching optimization module 2 is used to automatically detect and parse the interface information of the connected LCD screen through the hardware interface identification layer during the system initialization phase, identify key screen parameters, and, based on the identification results, call the preset driver algorithm library by the driver strategy adaptation layer to perform matching and optimization, and generate the corresponding screen initialization driver configuration sequence. The acquisition module 3 is used to complete driver loading according to the screen initialization driver configuration sequence, and during the running phase, continuously monitor the display content characteristics and the board running environment status through the dynamic optimization execution layer to obtain real-time monitoring data; Adjustment module 4 is used to dynamically calculate and adjust the driving parameters output to the LCD screen based on the real-time monitoring data and using a lightweight machine learning algorithm deployed in the dynamic optimization execution layer. The control module 5 is used to generate final control commands based on dynamically adjusted driving parameters and drive the LCD screen to display, so as to achieve adaptive driving of various LCD screens and optimization of display quality in complex industrial environments.

[0066] In one embodiment, the matching optimization module includes: The acquisition unit is used to acquire the extended display identification data of the connected LCD screen or its response characteristics to the standard timing probe signal through the hardware interface identification layer. The extraction unit is used to parse the extended display recognition data or response features and extract the original parameter information of the LCD screen; The calculation unit is used to calculate and determine the set of key driving parameters for driving the LCD screen based on the original parameter information and the hardware support capabilities of the driver board. The matching unit is used to perform feature matching in the driving algorithm library of the driving strategy adaptation layer according to the set of key driving parameters, so as to obtain the most matching set of calibration driving parameters as the basic template. The generation unit is used to generate a screen initialization driver configuration sequence containing initialization configuration values, timing and correction data based on the basic template and the key driver parameter set through parameter fine-tuning and interpolation calculation.

[0067] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described control method for a highly adaptable industrial liquid crystal display driver board.

[0068] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the control method for a highly adaptable industrial liquid crystal display driver board described above.

[0069] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in this application and in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0070] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0071] The above description is merely a preferred embodiment of the present invention and does not limit the scope of this application. Any equivalent results or equivalent process transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of protection of this application.

Claims

1. A control method for a highly adaptable industrial liquid crystal display driver board, characterized in that, Includes the following steps: On the processor built into the driver board, a layered adaptive control architecture including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer is constructed. During the system initialization phase, the hardware interface identification layer automatically detects and parses the interface information of the connected LCD screen, identifies key screen parameters, and based on the identification results, the driver strategy adaptation layer calls the preset driver algorithm library for matching and optimization to generate the corresponding screen initialization driver configuration sequence. The driver is loaded according to the screen initialization driver configuration sequence, and during the running phase, the display content characteristics and the board running environment status are continuously monitored through the dynamic optimization execution layer to obtain real-time monitoring data; Based on the real-time monitoring data, a lightweight machine learning algorithm deployed in the dynamic optimization execution layer is used to dynamically calculate and adjust the driving parameters output to the LCD screen. The final control command is generated based on the dynamically adjusted driving parameters, and the LCD screen is driven to display the image, so as to achieve adaptive driving of various LCD screens and optimization of display quality in complex industrial environments.

2. The control method for the highly adaptable industrial liquid crystal display driver board according to claim 1, characterized in that, The steps for constructing a hierarchical adaptive control architecture, including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer, include: Based on the physical interface type and communication protocol type of the connected LCD screen, the display driver system is logically partitioned to divide into multiple hardware adaptation areas, and a hardware interface identification node is configured for each hardware adaptation area. Configure a driver policy adaptation node for each hardware interface identification node, and determine its control instruction generation cycle based on the data processing capability and the amount of data to be processed of the driver policy adaptation node; A dynamic optimization execution node is configured at the main control terminal of the driver board system. The optimization decision cycle of the dynamic optimization execution node is determined based on the monitoring data acquisition frequency and instruction issuance delay of the main control terminal. Configure a low-level signal control module for the physical communication channel within each hardware interface identification node, and determine the adjustment step size of its drive signal waveform based on the clock signal accuracy and level stability parameters of the low-level signal control module; Based on the dynamic optimization execution node, multiple driving strategy adaptation nodes, and multiple underlying signal control modules, the hierarchical adaptive control architecture is constructed, forming a forward control flow and a reverse optimization flow.

3. The control method for the highly adaptable industrial liquid crystal display driver board according to claim 1, characterized in that, The step of generating the corresponding screen initialization driver configuration sequence includes: The extended display identification data of the connected LCD screen or its response characteristics to the standard timing detection signal are obtained through the hardware interface identification layer. The extended display recognition data or response features are analyzed to extract the original parameter information of the LCD screen; Based on the original parameter information and the hardware support capabilities of the driver board, the set of key driving parameters used to drive the LCD screen is calculated and determined. Based on the set of key driving parameters, feature matching is performed in the driving algorithm library of the driving strategy adaptation layer to obtain the most matching set of calibration driving parameters as the basic template. Based on the basic template and the set of key driving parameters, a screen initialization driver configuration sequence containing initialization configuration values, timing and correction data is generated through parameter fine-tuning and interpolation calculation.

4. The control method for the highly adaptable industrial liquid crystal display driver board according to claim 1, characterized in that, The steps for acquiring real-time monitoring data include: Load the screen initialization driver configuration sequence to complete the driver initialization of the LCD screen and start screen output; During the runtime phase, the content analysis module in the dynamic optimization execution layer performs real-time analysis on the input video frame data, extracts and quantifies the display content feature vector; The board's operating environment status data is acquired through the onboard sensor array, and an environment status vector is constructed. The display content feature vector and the environment state vector are timestamped and fused to obtain real-time monitoring data. The fused real-time monitoring data is then preprocessed to generate a standardized input feature set.

5. The control method for the highly adaptable industrial liquid crystal display driver board according to claim 4, characterized in that, The steps of dynamically calculating and adjusting the driving parameters output to the LCD screen include: The standardized input feature set is input into the lightweight machine learning algorithm model to obtain the driving parameter adjustment factor vector; The driving parameter adjustment factor vector is applied to a set of basic driving parameters. Based on the adjustment factor, the adjustment sensitivity coefficients corresponding to each parameter, and the basic parameter values, the dynamically adjusted target driving parameter set is calculated. Based on the target driving parameter set, intermediate layer control instructions describing the target value or change of each driving parameter are generated and transmitted to the driving strategy adaptation layer and hardware interface identification layer.

6. The control method for the highly adaptable industrial liquid crystal display driver board according to claim 1, characterized in that, The step of generating the final control command based on the dynamically adjusted driving parameters and driving the LCD screen to display the data includes: The driving strategy adaptation layer translates and decomposes the received intermediate layer control instructions into executable low-level control commands for specific hardware functional modules. The hardware interface identification layer, in collaboration with the underlying signal control module, executes the underlying control commands to adjust the timing, backlight, signal, and voltage parameters of the driver board. After the execution parameters are adjusted, a new round of display content features and environmental status data are collected through the dynamic optimization execution layer, and the effect is verified in combination with preset evaluation indicators. Based on the results of the effect verification, a decision is made on whether to update the basic driver parameter set. If the optimization goal is not met, an iterative correction process for the control instructions is triggered until the display effect and system stability reach a balance.

7. A control system for a highly adaptable industrial liquid crystal display driver board, characterized in that, include: The building module is used to build a layered adaptive control architecture, including a hardware interface identification layer, a driver strategy adaptation layer, and a dynamic optimization execution layer, on the processor built into the driver board. The matching optimization module is used to automatically detect and parse the interface information of the connected LCD screen through the hardware interface identification layer during the system initialization phase, identify key screen parameters, and, based on the identification results, call the preset driver algorithm library by the driver strategy adaptation layer to perform matching and optimization, and generate the corresponding screen initialization driver configuration sequence. The acquisition module is used to complete driver loading according to the screen initialization driver configuration sequence, and during the running phase, continuously monitor the display content characteristics and board running environment status through the dynamic optimization execution layer to acquire real-time monitoring data; The adjustment module is used to dynamically calculate and adjust the driving parameters output to the LCD screen based on the real-time monitoring data and using a lightweight machine learning algorithm deployed in the dynamic optimization execution layer. The control module is used to generate final control commands based on dynamically adjusted driving parameters and drive the LCD screen to display, so as to achieve adaptive driving of various LCD screens and optimization of display quality in complex industrial environments.

8. The control system of the highly adaptable industrial liquid crystal display driver board according to claim 7, characterized in that, The matching optimization module includes: The acquisition unit is used to acquire the extended display identification data of the connected LCD screen or its response characteristics to the standard timing probe signal through the hardware interface identification layer. The extraction unit is used to parse the extended display recognition data or response features and extract the original parameter information of the LCD screen; The calculation unit is used to calculate and determine the set of key driving parameters for driving the LCD screen based on the original parameter information and the hardware support capabilities of the driver board. The matching unit is used to perform feature matching in the driving algorithm library of the driving strategy adaptation layer according to the set of key driving parameters, so as to obtain the most matching set of calibration driving parameters as the basic template. The generation unit is used to generate a screen initialization driver configuration sequence containing initialization configuration values, timing and correction data based on the basic template and the key driver parameter set through parameter fine-tuning and interpolation calculation.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images