An intelligent control system for a flat material device

Abstract

The present invention relates to the technical field of control systems for flattening devices, and discloses an intelligent control system for a flattening device, which includes modules such as material identification, parameter processing, and grade division. The material identification module divides the flattening and to-be-processed areas, and the parameter processing module controls the start of the flattening operation. The status monitoring module collects basic material morphological data and the real-time motion trajectory of the device, and the storage unit stores historical characteristic data, distribution difference characteristics, and fluctuation data. The grade division module determines the material characteristic level and flatness level, and the strategy generation module generates a dynamic adjustment strategy based on this and the distance between the operation starting points. The difference determination module identifies the adjustment area, and the distribution detection module determines whether the trajectory deviates and triggers correction. The system also realizes surface data analysis and visualization through the surface analysis module and the operation terminal, thereby improving the intelligence, accuracy, and efficiency of the flattening operation, and is suitable for industrial material leveling scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of control systems for flat material devices, and in particular to an intelligent control system for flat material devices. Background Art

[0002] In industrial production, material stacking is a common process, such as the stacking of goods in warehousing and logistics and the accumulation of raw materials in chemical production. The flatness of material stacking directly impacts the efficiency and quality of subsequent production processes. For example, during material transportation, uneven stacking can cause material scattering, increasing transportation risks and costs. During processing, insufficient material flatness can affect the positioning accuracy of processing equipment, leading to increased machining errors and even damage. Traditional material leveling operations rely primarily on manual operation or simple mechanical control, which presents numerous drawbacks.

[0003] Manual material leveling is labor-intensive, inefficient, and significantly affected by the operator's experience and skill level, making it difficult to ensure consistent material quality. For example, in large-scale warehouses, manually leveling large quantities of material requires significant time and manpower, and is prone to omissions and uneven leveling. Simple mechanically controlled material leveling devices typically employ fixed operating strategies and are unable to dynamically adjust to the actual conditions of the material stack. The physical properties of different materials (such as moisture, thickness, and particle size) vary significantly, and the stacking state of the same material in different areas may also vary. Traditional mechanical control cannot perceive these changes in real time, resulting in poor material leveling results.

[0004] The advancement of industrial automation and intelligentization has placed higher demands on the intelligent control of material leveling devices. While some existing technologies incorporate sensors for status monitoring, most are only capable of collecting a single parameter, such as material thickness or moisture, and are unable to comprehensively assess the material stack by integrating multi-dimensional data. Furthermore, existing control systems lack effective utilization of historical data, making it impossible to predict potential problems in the current material leveling operation based on the material's historical characteristics. This results in a lack of scientific and targeted approach to material leveling strategies.

[0005] Furthermore, existing technologies face the challenge of adjusting the flattening device's trajectory in real time to accommodate material distribution variations during operation. Conventional systems struggle to accurately determine whether the flattening device has entered an area requiring adjustment, and they are unable to dynamically adjust its trajectory based on material distribution variations. This can easily cause the flattening device to deviate from its optimal path during operation, impacting flattening efficiency and quality. For example, if a material stack contains areas of high humidity or thickness, conventional systems may be unable to adjust their intensity and trajectory in a timely manner, resulting in incomplete flattening of that area. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent control system for a flat material device to solve the problems raised in the above background technology.

[0007] To achieve the above-mentioned object, the present invention provides the following technical solution: an intelligent control system for a flat material device, the system comprising:

[0008] Material identification module, parameter processing module, grade classification module, storage unit, strategy generation module, status monitoring module, distribution detection module and difference determination module;

[0009] The material identification module is used to divide the flattened area and the area to be processed of the material stack; the parameter processing module is used to control the flattening device to start the flattening operation after receiving the instruction; when performing the initial flattening operation, the state monitoring module is used to collect the basic morphological data of the material stack and transmit it to the grade classification module; the storage unit is used to store the historical characteristic data of the material stack and transmit it to the grade classification module; the grade classification module is used to determine the characteristic grade and flatness grade of the material stack, generate the historical characteristic grade and the flatness grade and transmit them to the strategy generation module; the strategy generation module is used to generate the dynamic adjustment strategy of the flattening device during operation according to the flatness grade and the historical characteristic grade, and transmit the dynamic adjustment strategy to the parameter processing module;

[0010] When the flattening device performs the flattening operation according to the dynamic adjustment strategy, the status monitoring module is also used to collect the real-time motion trajectory of the flattening device and transmit it to the difference judgment module; the storage unit is also used to store the distribution difference characteristics in the material stack and the fluctuation data corresponding to the distribution difference characteristics and transmit them to the difference judgment module; the difference judgment module is used to determine whether the flattening device enters the adjustment area. If a trajectory correction signal is generated, the real-time motion trajectory of the flattening device in the adjustment area is transmitted to the distribution detection module; the distribution detection module is used to determine whether the flattening device deviates from the reference path during the operation in the adjustment area based on the real-time motion trajectory. If deviated, a motion trajectory correction instruction is sent to the parameter processing module.

[0011] Preferably, the system also includes a surface analysis module and an operation terminal. The status monitoring module is also used to collect real-time surface data of the material stack and transmit it to the surface analysis module. The surface analysis module is used to analyze the real-time surface data of the material stack in real time. If the analysis generates a defect signal or a deformation signal, the coordinate mark and the corresponding real-time surface data are transmitted to the operation terminal. The operation terminal is used for visualization of the real-time surface data of the material stack.

[0012] Preferably, the basic morphological data includes a thickness deviation value and a humidity fluctuation value of the material stack;

[0013] The historical characteristic data is the number of historical thickness fluctuations of the material stack and the adjustment time corresponding to each fluctuation.

[0014] Preferably, the determination process of the level classification module is as follows:

[0015] Obtain the historical thickness fluctuation times of each material stack, then obtain the adjustment time corresponding to each fluctuation of each material stack, and accumulate the adjustment time corresponding to each fluctuation to calculate the average adjustment time of each material stack;

[0016] Calculate the characteristic coefficient of each material stack based on the number of historical thickness fluctuations and the average adjustment time;

[0017] Compare the characteristic coefficient with the preset characteristic threshold to determine whether the historical characteristic level of the material stack is a primary characteristic, a secondary characteristic, or a tertiary characteristic;

[0018] Synchronously obtain the thickness deviation and humidity fluctuation values of each material stack, and calculate the flatness coefficient of each material stack;

[0019] The flatness coefficient is compared with a preset flatness threshold to determine whether the flatness level of the material stack is level one, level two, or level three.

[0020] Preferably, the complexity corresponding to the third-level features is higher than that of the second-level features, and the complexity corresponding to the second-level features is higher than that of the first-level features;

[0021] The finishing requirements for level 3 flatness are higher than those for level 2 flatness, and the finishing requirements for level 2 flatness are higher than those for level 1 flatness.

[0022] Preferably, the working process of the strategy generation module is as follows:

[0023] The flatness level of the material stack is used as the first priority factor, the historical characteristic level of the material stack is used as the second priority factor, and the distance between the current position of the flattening device and the operation starting point of the material stack is used as the third priority factor.

[0024] The flattening device starts working from the current operation starting point. If there are multiple material stacks with the same flatness level near the starting point, the material stack with a higher historical feature level will be processed first.

[0025] If the flatness level and historical characteristic level of the material stack are the same, the material stack closest to the operation starting point is selected for processing;

[0026] When the flat material device reaches the dividing point:

[0027] If the dividing point is connected to only a single material stack, the flattening device will directly process the material stack;

[0028] If the demarcation point connects two or more material stacks, the material stack with the higher flatness grade will be processed first; if the flatness grades of multiple material stacks connected by the demarcation point are the same, the material stack with the higher historical characteristic grade will be processed first; if the flatness grades and historical characteristic grades of the material stacks connected by the demarcation point are the same, a material stack will be randomly selected for processing;

[0029] If the dividing point is not connected to other material stacks and there are unprocessed areas, the nearest unprocessed area will be processed first; when the flattening device reaches any dividing point, if other areas have been processed, it will return to the initial position and stop;

[0030] Generate dynamic adjustment strategies for flat material device operation according to the above rules;

[0031] When the flattening device operates according to the dynamic adjustment strategy, it performs operations with different working intensities in areas corresponding to different flatness levels or third-level features.

[0032] Preferably, the fluctuation data are the core coordinate points of the distribution difference characteristics, the reference fluctuation amplitude and the attenuation change rate.

[0033] Preferably, the determination process of the difference determination module is specifically as follows:

[0034] Calculate the displacement difference between the real-time motion trajectory of the flattening device and the core coordinate point of the distribution difference feature;

[0035] Obtain the fluctuation data corresponding to the distribution difference characteristics in the material stack, extract the core coordinate point, the baseline fluctuation amplitude and the attenuation change rate, and calculate the adjustment radius of the distribution difference characteristics by dividing the baseline fluctuation amplitude by the attenuation change rate;

[0036] With the core coordinate point as the center point and the adjustment radius as the coverage range, an adjustment area with distribution difference characteristics is constructed;

[0037] When the displacement difference is greater than the adjustment radius, the flattening device performs operations outside the adjustment area and maintains the current operating state;

[0038] When the displacement difference is less than or equal to the adjustment radius, the flattening device enters the adjustment area to perform operations and generates a trajectory correction signal.

[0039] Preferably, the judgment process of the distribution detection module is specifically as follows:

[0040] Set the standard pressure range and allowable deviation threshold for the flat material device operation;

[0041] If the pressure sensor feedback value is within the allowable deviation threshold and the flat material device travel speed is within the standard pressure range, the current operating parameters are maintained;

[0042] If the pressure sensor feedback value exceeds the allowable deviation threshold or the flat material device travel speed deviates from the standard pressure range, a motion trajectory correction instruction is generated.

[0043] Preferably, the analysis process of the surface analysis module is as follows:

[0044] Capture 3D point cloud data of material stacks;

[0045] The point cloud data is converted into a two-dimensional projection image. Median filtering is used to eliminate noise. The filtering threshold is set according to the height difference between the material surface morphology and the background to extract the effective surface area of the material stack. Morphological closing operations are applied to fill small holes and retain the complete surface contour features. Hough transform is used to detect straight line edges, match the geometric structure features of the material stack, and filter out non-structural interference areas.

[0046] Synchronously acquire infrared thermal imaging data of material stacks, set the temperature gradient range to identify abnormal heating areas, use pseudo-color enhancement technology to enhance the display of temperature differences, and combine edge detection algorithms to extract temperature mutation boundaries and identify abnormal internal structures of materials;

[0047] If the 3D point cloud data and infrared thermal imaging data show abnormalities at the same time, a defect signal is generated and the corresponding coordinates are marked;

[0048] If both data are normal, maintain normal operation process;

[0049] If any of the data is abnormal, a deformation signal is generated and the corresponding coordinates are marked.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The intelligent control system for the flattening device provided by the present invention significantly improves the intelligence level and operation quality of the flattening operation through the collaborative work of multiple modules. The material identification module can accurately divide the flattening area and the area to be processed, so that the flattening device can carry out operations in a targeted manner, avoiding the inefficiency caused by traditional blind operations, and reducing unnecessary energy consumption and time waste. The cooperation between the parameter processing module and the status monitoring module realizes the dynamic monitoring and data collection of the flattening operation. The status monitoring module can not only collect basic morphological data, but also obtain real-time motion trajectory and other information, providing rich data support for the precise control of the system.

[0052] The grading module analyzes historical feature data and real-time data to scientifically determine the characteristic and flatness levels of material stacks. This grading mechanism enables the system to develop differentiated flattening strategies based on the material's complexity and finishing requirements. For example, for stacks of materials with third-level features and third-level flatness, the system can use more intensive operating parameters to ensure flattening results; whereas for materials with first-level features and first-level flatness, the system can appropriately reduce operating parameters to improve efficiency while ensuring quality.

[0053] The strategy generation module generates dynamic adjustment strategies based on flatness level, historical feature level, and distance between operation starting points as priority factors, enabling the flattening device to rationally plan the operation sequence and path in complex material stacking scenarios. When multiple material stacks are present, the system prioritizes areas with high flatness levels, high historical feature levels, or close proximity, ensuring the scientific and orderly nature of the flattening operation. Furthermore, the establishment of demarcation point processing rules effectively resolves the operational decision-making difficulties faced by traditional devices when connecting multiple areas, avoiding operational conflicts and omissions, and further improving flattening efficiency.

[0054] The presence of a difference determination module and a distribution detection module enables real-time monitoring and correction of the flattening device's trajectory. By calculating displacement differences and constructing adjustment zones, the system accurately determines whether the flattening device has entered an area requiring adjustment and dynamically corrects its trajectory based on the distribution difference characteristics. If the pressure sensor feedback value or travel speed is abnormal, the distribution detection module promptly issues correction instructions, ensuring that the flattening device remains on the reference path. This avoids uneven flattening caused by trajectory deviation and improves the accuracy and stability of the flattening operation.

[0055] The combination of the surface analysis module and the operator terminal provides powerful support for surface condition monitoring of material stacks. Through comprehensive analysis of 3D point cloud data and infrared thermal imaging data, the system can promptly detect surface defects and internal structural anomalies. Visualizing these findings through the operator terminal allows operators to understand material status in real time, enabling them to take targeted measures and prevent quality issues. This real-time monitoring and feedback mechanism further enhances the reliability and safety of flattening operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a working principle diagram of the intelligent control system of the flat material device of the present invention;

[0057] Figure 2 Design diagram for surface analysis system expansion;

[0058] Figure 3 A flow chart for determining the level classification module;

[0059] Figure 4 Design diagram for the process of difference determination and distribution detection;

[0060] Figure 5 This is a flow chart for difference determination and distribution detection. DETAILED DESCRIPTION

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0062] See also Figure 1-Figure 5 The present invention relates to an intelligent control system for a flattening device, comprising a material identification module, a parameter processing module, a grading module, a storage unit, a strategy generation module, a status monitoring module, a distribution detection module, and a difference determination module. These modules work together to achieve intelligent control of the flattening device. The specific implementation is as follows:

[0063] During system operation, the material identification module first divides the material stack into zones, accurately identifying flattened areas and areas to be processed, providing a foundation for subsequent flattening operations. The parameter processing module controls the flattening device, initiating the flattening operation upon receiving instructions. During the initial flattening phase (step 1), the condition monitoring module begins collecting basic morphological data for the material stack, including but not limited to physical characteristic parameters such as thickness deviation and humidity fluctuation. This data is then transmitted in real time to the grading module. Simultaneously, historical characteristic data for the material stack stored in the storage unit (such as the number of historical thickness fluctuations and the corresponding adjustment time for each fluctuation) is also transmitted to the grading module.

[0064] The grading module determines the characteristic grade and flatness grade of the material stack based on the received basic morphological data and historical characteristic data (step 2). Specifically, the historical thickness fluctuation times of each material stack are first obtained, and then the adjustment time corresponding to each fluctuation is obtained. The average adjustment time is obtained by cumulative calculation. Then, the characteristic coefficient is calculated based on the historical thickness fluctuation times and the average adjustment time. The characteristic coefficient is compared with the preset characteristic threshold to determine whether the historical characteristic grade is level one, level two, or level three. The complexity corresponding to the level three feature is higher than that of the level two, and the level two is higher than that of the level one. Simultaneously, the flatness coefficient is calculated based on the thickness deviation value and the humidity fluctuation value. After comparison with the preset flatness threshold, the flatness grade is determined to be level one, level two, or level three. The finishing requirement corresponding to the level three flatness is higher than that of the level two, and the level two is higher than that of the level one. The generated historical characteristic grade and flatness grade are transmitted to the strategy generation module.

[0065] The strategy generation module generates a dynamic adjustment strategy for the flattening device based on the received flatness level and historical feature level (step 3). This module prioritizes flatness level as the first priority factor, historical feature level as the second priority factor, and the distance between the flattening device's current position and the operation starting point as the third priority factor. The specific rules are as follows: Starting from the current operation starting point, if multiple material stacks with the same flatness level exist near the starting point, the stack with the higher historical feature level is prioritized for processing. If both the flatness level and the historical feature level are the same, the stack closest to the starting point is selected. When the flattening device reaches a demarcation point, if the demarcation point connects only a single material stack, that stack is processed directly. If it connects two or more stacks, the stack with the higher flatness level is prioritized. If the levels are the same, the stack with the higher historical feature level is prioritized. If both levels are the same, a random selection is made. If the demarcation point is not connected to any other stacks and there are unprocessed areas, the closest unprocessed area is prioritized. Once all areas have been processed, the device returns to its initial position and stops. Furthermore, the flattening device operates at different intensities in areas corresponding to different flatness levels or three-level features. After the dynamic adjustment strategy is generated, it is transmitted to the parameter processing module, which controls the flattening device to perform the corresponding operation.

[0066] While the flattening device executes the flattening operation according to the dynamic adjustment strategy (step 4), the status monitoring module is also responsible for collecting the flattening device's real-time motion trajectory and transmitting this trajectory data to the difference determination module. The material stack distribution difference characteristics (such as the core coordinate point, baseline fluctuation amplitude, attenuation change rate, and other fluctuation data) pre-stored in the storage unit are also transmitted to the difference determination module. The difference determination module calculates the displacement difference between the real-time motion trajectory and the core coordinate point of the distribution difference characteristics. Combining the baseline fluctuation amplitude and attenuation change rate in the fluctuation data, the module calculates the adjustment radius (adjustment radius = baseline fluctuation amplitude / attenuation change rate). An adjustment area is constructed with the core coordinate point as the center and the adjustment radius as the coverage area. When the displacement difference is greater than the adjustment radius, the flattening device operates outside the adjustment area and maintains its current operating state. When the displacement difference is less than or equal to the adjustment radius, the flattening device is determined to have entered the adjustment area, a trajectory correction signal is generated, and the real-time motion trajectory is transmitted to the distribution detection module. The distribution detection module sets the standard pressure range and allowable offset threshold for the flat material device operation. If the pressure sensor feedback value is within the allowable offset threshold and the travel speed is in the standard pressure range, the current operation parameters are maintained; if it exceeds the allowable offset threshold or the speed deviates from the standard pressure range, a motion trajectory correction instruction is sent to the parameter processing module, and the parameter processing module controls the flat material device to adjust the motion trajectory.

[0067] The present invention will be further described below in conjunction with Examples 1 to 5:

[0068] Example 1: Based on the above overall scheme, this embodiment further includes a surface analysis module and an operation terminal. In addition to collecting basic morphological data and motion trajectories, the condition monitoring module is also responsible for collecting real-time surface data of the material stack, including 3D point cloud data and infrared thermal imaging data, and transmitting this data to the surface analysis module. The surface analysis module analyzes the real-time surface data: first, it captures the 3D point cloud data and converts it into a 2D projection image. A median filter is used to eliminate noise. A filtering threshold is set based on the height difference between the material surface and the background to extract the valid surface area. Morphological closing operations are applied to fill small holes, preserving the complete surface contour features. A Hough transform is used to detect straight edges, match geometric structural features, and filter out non-structural interference areas. Infrared thermal imaging data is simultaneously acquired, a temperature gradient range is set to identify abnormally heated areas, and pseudo-color enhancement technology is used to enhance the display of temperature differences. Combined with an edge detection algorithm, temperature mutation boundaries are extracted to identify internal structural anomalies in the material. If both the 3D point cloud data and the infrared thermal imaging data show an anomaly, a defect signal is generated and the corresponding coordinates are marked. If neither data shows an anomaly, the normal operation process is maintained. If either data shows an anomaly, a deformation signal is generated and the corresponding coordinates are marked. The surface analysis module transmits the generated coordinate marks and the corresponding real-time surface data to the operation terminal, which visualizes the real-time surface data of the material stack so that the operator can monitor the material status in real time.

[0069] The surface analysis module receives the real-time surface data of the material stack transmitted by the status monitoring module, where the three-dimensional point cloud data is obtained by a three-dimensional laser scanner installed on the flat material device. The scanner scans the surface of the material stack at a certain frequency, obtains the three-dimensional coordinate information of a large number of discrete points, and forms point cloud data. The point cloud data contains geometric information such as the shape and contour of the material surface, but due to interference from the scanning environment, equipment accuracy and other factors, there will be noise points in the point cloud data. The surface analysis module first converts the three-dimensional point cloud data into a two-dimensional projection image for subsequent processing. During the conversion process, the appropriate projection plane and resolution are determined based on the distribution range and density of the point cloud data, and the points in the three-dimensional space are mapped to the two-dimensional plane to form a grayscale image.

[0070] To improve image quality, a median filter algorithm was used to denoise the two-dimensional projection image. Median filtering is a nonlinear filtering method that replaces the grayscale value of each pixel in the image with the median value of its neighborhood. Choosing an appropriate filter window size is crucial during this process. A window that is too small will not effectively remove noise, while a window that is too large will lose image detail. Through repeated experiments and empirical analysis, a window size was selected that effectively removes noise while preserving image detail. After median filtering, the noise in the image is significantly suppressed, providing an excellent foundation for subsequent region extraction.

[0071] Based on the height difference between the material surface and the background, an appropriate filtering threshold is set to binarize the 2D projection image and extract the valid surface area. In a stack of materials, there is a significant height difference between the material surface and the surrounding background (such as the ground, equipment supports, etc.), which is reflected as different depth values in the point cloud data. By analyzing the depth distribution of the point cloud data, an appropriate threshold is determined. Points with depth values within the threshold range are identified as material surface points, while all other points are identified as background points. In the 2D projection image, material surface points are marked as foreground (white), and background points are marked as background (black), resulting in a binary image. Binary images may contain small holes and discontinuous areas, which can affect subsequent analysis and processing.

[0072] To fill these tiny holes and preserve the complete surface contour features, a morphological closing operation is used to process the binary image. This morphological closing operation involves performing a dilation operation followed by an erosion operation. The dilation operation expands the foreground area outward, filling the holes; the erosion operation shrinks the expanded area back to its original size while removing some small noise points. By selecting the appropriate structuring element and number of operations, tiny holes can be effectively filled, making the material surface area more continuous and complete. The surface of a stack of materials may contain regular geometric features, such as edges and planes. These features are crucial for identifying the material's morphology and structure. To detect these geometric features, the Hough transform algorithm is used to perform edge detection on the processed binary image.

[0073] The Hough transform is a method for finding geometric shapes such as lines and circles in images. During processing, each point in the image is converted into a parameter space, and possible line parameters are determined through voting. By setting an appropriate threshold, qualified line edges are screened. Detected line edges are matched against a predefined geometric structure template to identify the geometric features of the material surface. Non-structural interference areas, such as bumps and depressions on the material surface, are filtered out by analyzing their geometric features and contextual information, retaining only feature areas relevant to the material structure.

[0074] While acquiring the three-dimensional point cloud data, the surface analysis module receives the infrared thermal imaging data transmitted by the status monitoring module. The infrared thermal imaging data is acquired by an infrared thermal imager installed on the flat material device. The thermal imager can detect the infrared radiation energy on the surface of the object and convert it into a temperature value to form a thermal imaging image. Structural abnormalities inside the material stack, such as uneven density and the presence of voids, may cause abnormal surface temperature distribution. By analyzing the infrared thermal imaging data, these abnormal areas can be identified. First, set an appropriate temperature gradient range to identify abnormal heating areas. Under normal circumstances, the temperature distribution on the surface of the material stack should be relatively uniform, with a certain temperature gradient. If the temperature of a certain area is significantly higher or lower than the surrounding area and exceeds the set temperature gradient range, it is considered that there is an abnormality in that area.

[0075] In order to display the temperature difference more clearly, pseudo-color enhancement technology is used to process the infrared thermal imaging data. Pseudo-color enhancement maps different grayscale values in the grayscale image to different colors to make the temperature difference more intuitive. By selecting a suitable color mapping table, the low-temperature area is displayed as blue, the medium-temperature area is displayed as green, the high-temperature area is displayed as red, and so on. In this way, the operator can quickly identify the abnormal temperature area by observing the color distribution of the image. Combined with the edge detection algorithm, the temperature mutation boundary is extracted. The temperature mutation boundary usually corresponds to the change of the internal structure of the material, such as the sudden change of density, the existence of the interface, etc. By detecting the temperature mutation boundary, the abnormal internal structure of the material can be identified more accurately. During the processing, the Canny edge detection algorithm is used. This algorithm has good edge detection performance and can detect weak edges in the image.

[0076] By setting an appropriate threshold, edges related to temperature mutations are screened out to form temperature mutation boundaries. Based on the extracted temperature mutation boundaries and the identified abnormal heating areas, the abnormalities in the internal structure of the material are analyzed. For the detected abnormal areas, further analysis and classification are performed to determine the type and severity of the abnormality. The analysis results are comprehensively compared with the analysis results of the 3D point cloud data to determine whether there are any abnormalities on the surface and internal structure of the material stack. After independently analyzing the 3D point cloud data and infrared thermal imaging data, it is necessary to comprehensively compare the analysis results of the two to more accurately determine the status of the material stack. If the 3D point cloud data shows that the material surface has obvious unevenness, abnormal geometric structure, etc., and the infrared thermal imaging data shows that the corresponding area has temperature anomalies, then the area is considered to be defective, a defect signal is generated, and the coordinates of the area are marked.

[0077] The defect signal contains information such as the type, location, and severity of the defect, providing a basis for subsequent processing. If neither the three-dimensional point cloud data nor the infrared thermal imaging data show any abnormalities, it is considered that the surface and internal structure of the material stack are normal, and the normal operation process is maintained. The flattening device continues to operate according to the preset parameters and trajectory, and the status monitoring module continues to collect data in real time. If only one of the three-dimensional point cloud data or infrared thermal imaging data shows an abnormality, it is considered that the material stack is deformed, a deformation signal is generated, and the coordinates of the corresponding area are marked. The deformation signal contains information such as the type, location, and degree of deformation. For deformation conditions, it is necessary to further analyze the extent of its impact on the flattening operation to determine whether it is necessary to adjust the operating parameters or take other measures.

[0078] The surface analysis module transmits the generated coordinate markers and corresponding real-time surface data to the operating terminal. After receiving this data, the operating terminal visualizes the real-time surface data of the material stack. Using 3D visualization technology, the 3D point cloud data is reconstructed into a stereo model, visually displaying the surface morphology of the material stack. Detected abnormal areas are marked on the 3D model, and defects and deformation areas are represented by different colors and symbols for quick identification by operators. Simultaneously, infrared thermal imaging data is integrated with the 3D model to display the temperature distribution on the 3D model. Different temperature zones are intuitively displayed using color gradients, allowing operators to simultaneously understand the surface morphology and temperature distribution of the material stack.

[0079] The operation terminal provides an interactive interface, allowing operators to manipulate and analyze visualized data. Operators can zoom, rotate, and pan to observe the three-dimensional model of the material stack from different angles. They can also query detailed information about specific areas, such as temperature and geometric dimensions. They can also replay and compare historical data to analyze changing trends in the material stack's status. By monitoring material status in real time, operators can promptly identify anomalies and take appropriate measures. Minor anomalies can be addressed by adjusting the operating parameters of the flattening device. Severe anomalies can be promptly stopped for inspection and resolution, preventing further escalation and improving the efficiency and quality of flattening operations.

[0080] Example 2: In this embodiment, the basic morphological data is specifically the thickness deviation value and humidity fluctuation value of the material stack, and the historical characteristic data is the number of historical thickness fluctuations of the material stack and the adjustment time corresponding to each fluctuation. The system collects, processes, and analyzes this data to accurately determine the characteristic level and flatness level of the material stack. The specific implementation process is as follows:

[0081] The condition monitoring module uses high-precision sensors installed on the flattening mechanism to collect basic morphological data of the material stack in real time. Thickness deviation data is collected using multiple sets of laser ranging sensors located at the front of the flattening mechanism. Each sensor set consists of multiple transmitting and receiving units arranged in an array, enabling simultaneous height measurement of multiple points on the material stack. For example, a set of sensors is placed at regular intervals (e.g., 20 cm) in the direction of travel of the flattening mechanism, with each set of sensors spaced 10 cm apart transversely to the direction of travel, forming a dense measurement network. Each laser ranging sensor emits a laser beam at the material surface and measures the time it takes for the beam to reflect back, calculating the distance between the sensor and the material surface and the height of each measured point. The height values of each point within the same sensor set are compared, and the difference between the maximum and minimum values is calculated to determine the thickness deviation value for the area corresponding to that sensor set. Comprehensive analysis of data from all sensor sets provides a comprehensive picture of the thickness deviation distribution across the entire material stack.

[0082] Humidity fluctuations are collected using humidity sensors integrated into the flattening mechanism. These sensors utilize an insertable design, automatically inserting into the material stack at various depths (e.g., surface, middle, and bottom layers) for sampling during flattening operation. Each humidity sensor is equipped with a microprobe coated with a moisture-sensitive electrolyte material. The probe measures changes in the electrolyte's conductivity to reflect the material's humidity. To ensure data accuracy and representativeness, multiple humidity sensors are located in different areas of the material stack (e.g., edges, center, and corners). Data is collected at regular intervals (e.g., 5 seconds) to create a humidity fluctuation curve over time and space. The condition monitoring module transmits the collected thickness deviation and humidity fluctuation values to the grading module in real time, providing data support for determining the flatness level.

[0083] The historical characteristic data stored in the storage unit is derived from the system's records of past flattening operations. During each flattening operation, the status monitoring module monitors the thickness changes of the material stack in real time. When the thickness value deviates from the preset normal range (e.g., exceeding ±5 mm), it is determined to be a thickness fluctuation, and the time and duration of the fluctuation (i.e., the adjustment time) are recorded. The number of historical thickness fluctuations is the total number of thickness fluctuations that have occurred in a particular material stack during past operations, and the adjustment time is the time it takes for each fluctuation to return to normal. For example, a material stack may have experienced three thickness fluctuations in the past 10 operations, with the adjustment time for each fluctuation being 10 minutes, 8 minutes, and 12 minutes, respectively. This data will be fully recorded by the storage unit, forming the historical characteristic data for the material stack. When the material stack is processed again, the storage unit will transmit this historical data to the grading module as the basis for determining the characteristic grade.

[0084] The determination process of the grading module is divided into two parts: feature grade determination and flatness grade determination. In the feature grade determination, the historical thickness fluctuation times and corresponding adjustment time data of each material stack are first obtained from the storage unit. For each material stack, the adjustment time of each fluctuation is accumulated and then divided by the number of fluctuations to obtain the average adjustment time. For example, the three adjustment times of a material stack are 10 minutes, 8 minutes and 12 minutes respectively, which is 30 minutes after accumulation, and the average time is 10 minutes. The average adjustment time reflects the average recovery speed of the thickness fluctuation of the material stack in past operations. The longer the average time, the more difficult it is to process the material.

[0085] Next, a pre-set comprehensive evaluation logic is used to calculate the characteristic coefficient based on the number of historical thickness fluctuations and the average adjustment time. This evaluation logic combines the weights of the number of fluctuations and the average adjustment time. For example, the number of fluctuations contributes 60% to the characteristic complexity, while the average adjustment time contributes 40%. Specifically, the number of historical thickness fluctuations is divided into different intervals, such as 0-2, 3-5, and 6 and above, each corresponding to a different base coefficient. Simultaneously, the average adjustment time is divided into different intervals, such as 0-5 minutes, 6-10 minutes, and 11 minutes and above, each corresponding to a different correction coefficient. The final characteristic coefficient is obtained by multiplying or weighting the base coefficient and the correction coefficient. For example, if the historical thickness fluctuations of a material stack are 4 (in the 3-5 interval, with a base coefficient of 0.8) and the average adjustment time is 9 minutes (in the 6-10 minute interval, with a correction coefficient of 0.9), the characteristic coefficient is 0.8 × 0.9 = 0.72.

[0086] The calculated characteristic coefficient is compared with the preset characteristic threshold. The preset threshold is set in advance based on factors such as material type and operating experience. For example, the first-level characteristic threshold is set to below 0.5, the second-level characteristic threshold is set to 0.5-0.8, and the third-level characteristic threshold is set to above 0.8. If the characteristic coefficient is less than 0.5, the historical characteristic level is determined to be level one, indicating that the thickness fluctuation characteristic complexity of the material stack is low and the processing difficulty is relatively simple; if the characteristic coefficient is between 0.5-0.8, it is determined to be level two, indicating that the characteristic complexity is medium; if the characteristic coefficient is greater than or equal to 0.8, it is determined to be level three, indicating that the characteristic complexity is high and a more sophisticated processing strategy is required.

[0087] When determining the flatness grade, the grading module simultaneously acquires the thickness deviation and humidity fluctuation values transmitted by the status monitoring module. The thickness deviation reflects the degree of undulation on the surface of the material stack; the larger the deviation, the worse the surface flatness; the humidity fluctuation reflects the uniformity of the moisture distribution within the material; the larger the fluctuation, the worse the humidity uniformity, which may affect the effectiveness of the flattening operation. Using a preset comprehensive evaluation logic, the thickness deviation and humidity fluctuation values are normalized and converted into values of a unified dimension. The flatness coefficient is then calculated through a weighted summation. For example, the thickness deviation value is weighted at 70%, and the humidity fluctuation value is weighted at 30%. The thickness deviation coefficient is obtained by dividing the thickness deviation value by the maximum allowable deviation value, and the humidity fluctuation coefficient is obtained by dividing the humidity fluctuation value by the maximum allowable humidity fluctuation value. The flatness coefficient = thickness deviation coefficient × 0.7 + humidity fluctuation coefficient × 0.3.

[0088] The calculated flatness coefficient is compared with the preset flatness threshold. The preset threshold is also set according to the material characteristics and operation requirements. For example, the level 1 flatness threshold is below 0.3, the level 2 is 0.3-0.6, and the level 3 is above 0.6. If the flatness coefficient is less than 0.3, the flatness level is determined to be level 1, indicating that the flatness of the material stack is relatively high and the finishing requirements are relatively low. If it is between 0.3-0.6, it is determined to be level 2, indicating that the flatness is medium and some degree of finishing is required. If it is greater than or equal to 0.6, it is determined to be level 3, indicating that the flatness is poor and the finishing requirements are relatively high.

[0089] Through this process, the grading module generates accurate historical characteristic and flatness grades for each material stack. This grade information is then transmitted to the strategy generation module, serving as the core basis for generating dynamic adjustment strategies. For example, for a material stack with a characteristic grade of Level 3 and a flatness grade of Level 3, the strategy generation module prioritizes this operation and applies high-intensity flattening parameters (such as increasing the pressure of the flattening device and reducing the travel speed). For a material stack with a characteristic grade of Level 1 and a flatness grade of Level 1, it can be scheduled for a subsequent operation and utilize conventional flattening parameters. This enables intelligent and refined control of flattening operations, improving both efficiency and quality.

[0090] Example 3: Within the overall architecture of intelligent flattening control, the strategy generation module dynamically generates the optimal operation strategy based on multi-dimensional parameters such as the flatness level of the material stack, historical feature level, and the distance between the flattening device's current position and the operation starting point. This process involves complex priority decision logic and path planning algorithms.

[0091] Upon system startup, the strategy generation module first receives the flatness grade and historical characteristic grade data for each material stack from the grading module. Flatness grades are categorized into levels one, two, and three, corresponding to different finishing requirements; historical characteristic grades are also categorized into three levels, reflecting the complexity of material handling. Simultaneously, a positioning system installed on the flattening device acquires the device's current position coordinates in real time. Combined with the pre-stored coordinates of each material stack's starting point in the storage unit, the distance between the flattening device and each starting point is calculated.

[0092] During the job priority decision-making process, the strategy generation module constructs a three-dimensional decision space. Flatness level is the first priority factor, and the system prioritizes material stacks with higher flatness levels. This is because areas with poor flatness (such as level 3 flatness) typically require more finishing operations, and addressing these areas early can prevent interference with subsequent operations. Historical feature level is the second priority factor. When encountering material stacks with the same flatness level, the system prioritizes the one with the higher historical feature level. For example, if there are two areas with level 2 flatness, but one has a level 3 historical feature (higher processing complexity) and the other has a level 1 historical feature, the system will prioritize the area with the level 3 feature, concentrating resources on resolving the complex problem. The third priority factor is the distance between the current position of the flattening device and the starting point of the operation. When both the flatness and historical feature levels are the same, the system will select the closest material stack for processing, reducing equipment movement time and improving overall operation efficiency.

[0093] The specific operation process is as follows: The flattening device begins operation at the current operation starting point, first scanning the material stacks within a certain range to obtain their flatness level and historical feature level information. If there are multiple stacks with the same flatness level, the system will further compare their historical feature levels and prioritize the one with the higher level for processing. For example, in a certain operation scenario, there are three stacks of materials with a second-level flatness around the flattening device, one of which has a historical feature level of third and the other two have a second level. In this case, the system will prioritize dispatching the flattening device to process the stack with the third level feature.

[0094] When the flattening device reaches a demarcation point in the work area, the system makes a decision based on the material stacks connected to the demarcation point. If the demarcation point connects only a single material stack, the flattening device directly applies the corresponding strategy. If the demarcation point connects multiple material stacks, the system first compares their flatness levels and prioritizes the one with the higher level. If the flatness levels are the same, the system then compares the historical feature levels and prioritizes the one with the higher level. If all levels are the same, a random number generation algorithm is used to randomly select a material stack for processing.

[0095] If the demarcation point is not connected to other stacks and there are untreated areas, the system uses the positioning system to determine the location of each untreated area, calculates the distance between the flattening device and these areas, and selects the closest one for processing. When all areas are processed, the flattening device returns to its initial position and stops using the built-in navigation system.

[0096] Throughout the entire operation, the strategy generation module continuously updates the operation strategy based on real-time data. For example, if the condition monitoring module reports a change in the flatness or feature level of a certain area while the flattening device is processing the material stack, the strategy generation module will reassess the priority of that area and adjust the operation sequence if necessary.

[0097] In order to quantify this priority decision-making process, the system introduces a priority evaluation function:

[0098]

[0099] in, Indicates the comprehensive priority score of the material stack; Indicates the flatness grade (1 for level one, 2 for level two, 3 for level three); Indicates the level of historical characteristics (level 1 is 1, level 2 is 2, and level 3 is 3); Indicates the distance from the current position of the flattening device to the starting point of the material stacking operation; Indicates the farthest distance from the leveling device among all the stacks of materials to be processed; 、 、 are the weight coefficients of each factor ( , , This function calculates a priority score for each material stack by comprehensively considering the flatness level, historical feature level, and distance. The system prioritizes stacks with higher scores, optimizing the order of operations.

[0100] Through this dynamic adjustment strategy, the flattening device can automatically adjust the operation sequence and intensity according to the actual material conditions, improving operation efficiency and quality. The entire process requires no human intervention, achieving intelligent control of the flattening operation.

[0101] Example 4: During material leveling, the distribution differences of the stacked material significantly impact the leveling effect. By collecting, analyzing, and applying fluctuation data, dynamic corrections to the leveling device's trajectory are achieved, ensuring operational accuracy. The following details the implementation of this embodiment.

[0102] The condition monitoring module continuously collects real-time data from the material stack during operation of the flattening device. This data includes 3D point cloud information of the material surface, temperature distribution, humidity changes, and other multi-dimensional features. The distribution detection module extracts fluctuation data from this real-time data, specifically including core coordinates, baseline fluctuation amplitude, and attenuation rate. The core coordinates are determined by 3D modeling of the material stack and represent the center of the distribution difference feature; the baseline fluctuation amplitude is the fluctuation range of the feature under ideal conditions; and the attenuation rate reflects the rate at which the feature fluctuation decays with spatial distance.

[0103] After receiving the real-time motion trajectory data and fluctuation data from the storage unit transmitted by the condition monitoring module, the difference determination module first calculates the displacement difference between the real-time position of the flattening device and the core coordinate point of the distribution difference feature. This process is implemented by the positioning system, which uses multi-sensor fusion technology, combining GPS positioning, inertial navigation, and visual SLAM algorithms to ensure high-precision acquisition of the flattening device's position data. For example, in a certain material handling scenario, the core coordinate point is determined by 3D modeling to be (50, 30, 20) (unit: meter), and the real-time position coordinates of the flattening device are (52, 31, 19). The displacement difference calculated using the Euclidean distance formula is approximately 2.45 meters.

[0104] The difference determination module then extracts the baseline fluctuation amplitude and attenuation rate of change corresponding to the distribution difference characteristics from the fluctuation data. The baseline fluctuation amplitude is determined by material characteristics and historical operation data. For example, for a certain granular material, the baseline fluctuation amplitude is set at 3 meters. The attenuation rate is determined by analyzing how the characteristic fluctuation changes with distance. For example, a setting of 0.5 m / m means that the fluctuation amplitude attenuates by 0.5 meters for every meter away from the core coordinate point. By dividing the baseline fluctuation amplitude by the attenuation rate of change, the adjustment radius is calculated to be 6 meters (3 meters ÷ 0.5 m / m).

[0105] An adjustment zone is constructed with the core coordinate point as the center and a radius of 6 meters. When the displacement difference of the flattening device is greater than 6 meters, it is determined to be operating outside the adjustment zone. At this time, the material characteristics are relatively stable and the current operating state is maintained. If the displacement difference is less than or equal to 6 meters, the flattening device is determined to have entered the adjustment zone and a trajectory correction signal is generated. For example, when the flattening device moves to coordinates (54, 32, 18), the displacement difference is calculated to be 5.1 meters, which is less than the adjustment radius, and the system immediately generates a trajectory correction signal.

[0106] The trajectory correction signal contains information about the correction direction and amount. The correction direction is determined by the type of distribution difference feature. For example, for feature differences caused by uneven density, the correction direction is directed toward the area with higher density. The correction amount is related to the ratio of the displacement difference to the adjustment radius. The larger the ratio, the greater the correction amount. In the above example, the ratio of the displacement difference to the adjustment radius is 5.1 ÷ 6 ≈ 0.85, and the system calculates the corresponding correction amount accordingly.

[0107] After receiving the trajectory correction signal, the distribution detection module analyzes the real-time motion trajectory of the flattening device. This module pre-sets the standard operating pressure range and permissible deviation threshold. For example, the standard pressure range is [80, 120] kPa, and the permissible deviation threshold is ±10 kPa. The pressure sensor provides real-time feedback on the operating pressure value, while the speed sensor monitors the travel speed. If the pressure value is within the range of 70-130 kPa and the travel speed matches the pressure value (for example, when the pressure is 100 kPa, the speed should be between 0.5-0.7 m / s), the operation is considered normal and the current parameters are maintained.

[0108] If the pressure sensor feedback exceeds the permissible deviation threshold, or the travel speed deviates from the acceptable range corresponding to the standard pressure range, the distribution detection module determines that the motion trajectory needs to be adjusted. For example, if the pressure reaches 140 kPa and the travel speed is 0.9 m / s, the system determines that the current operating parameters may lead to over-compaction of the material and generates a motion trajectory correction instruction.

[0109] After receiving the correction command, the parameter processing module controls the flattening device to adjust its trajectory. Adjustments include changing the travel direction, adjusting the operating speed, and adjusting the pressure. In the aforementioned pressure anomaly example, the system first reduced the travel speed to 0.4 m / s and simultaneously fine-tuned the flattening device's angle to better conform to the material surface. After these adjustments, the pressure sensor feedback gradually returned to the standard range, and the system continued operation while maintaining the new operating parameters.

[0110] Throughout the trajectory correction process, the condition monitoring module continuously collects data, and the distribution detection module evaluates the adjustment results in real time. If the adjusted parameters still fail to meet the target, the system further optimizes the correction strategy until the operation returns to normal. This closed-loop feedback mechanism enables the flattening device to adapt to material distribution differences, ensuring stable operation quality.

[0111] In practice, different types of material stacks may exhibit multiple distribution differences. The system calculates an adjustment zone for each characteristic and dynamically determines the zone within it based on the real-time position of the flattening device. For example, a material stack exhibits both density and humidity differences. The corresponding core coordinates are (45, 28, 19) and (55, 32, 21), with adjustment radii of 5 meters and 7 meters, respectively. When the flattening device is located at (50, 30, 20), it falls within both adjustment zones. The system then combines the effects of both characteristics to generate a composite correction signal.

[0112] For complex material scenarios, the system employs a tiered processing strategy. First, it ranks distribution difference features based on their importance and impact, prioritizing those with greater impact. For example, when processing materials with both density and humidity differences, if the density difference has a more significant impact on flattening, the system prioritizes trajectory correction for the density difference feature. Once that feature's impact decreases, the humidity difference feature will be processed.

[0113] During trajectory correction, the system also considers the mechanical limitations of the flattening device. For example, excessive adjustment angles can cause equipment imbalance, while sudden changes in travel speed can cause vibration and other issues. Therefore, when generating correction instructions, the system incorporates the device's dynamic model to ensure a smooth and controllable adjustment process. For example, when a significant change in direction is required, the system employs a gradual adjustment strategy, making multiple, small changes in direction to avoid the adverse effects of sudden changes in the device.

[0114] Example 5: During the flattening operation, the distribution detection module precisely controls the flattening device's trajectory through real-time monitoring and intelligent analysis of operating pressure and travel speed. This module pre-determines the standard operating pressure range and permissible deviation threshold. These parameters are determined through extensive experimentation and empirical analysis based on factors such as material properties and flattening process requirements. For example, for a certain type of ore material with uniform particle size, the standard pressure range is set at 80-120 kPa, with a permissible deviation threshold of ±10 kPa, corresponding to a reasonable travel speed range of 0.5-0.7 m / s.

[0115] When the material leveling device begins operation, a pressure sensor mounted on its base collects real-time pressure data 10 times per second, while a speed sensor simultaneously monitors travel speed. This data is transmitted to the distribution detection module for analysis. During the leveling operation of a certain material stack, the pressure sensor reported an initial pressure of 105 kPa and a travel speed of 0.6 m / s, both within the standard range. The system determined that the operation was normal, and the material leveling device continued operating along the preset trajectory.

[0116] As the operation progressed, when the flattening device reached the edge of the material stack, the pressure sensor feedback value suddenly increased to 135 kPa, exceeding the upper limit of the allowable deviation threshold (130 kPa). The distribution detection module immediately analyzed this abnormal data and, combined with the speed sensor's feedback of 0.65 m / s, determined that uneven material stacking density may exist. At this point, the system generated a Level 1 warning signal and triggered a preliminary trajectory correction strategy.

[0117] Upon receiving the warning signal, the parameter processing module first controls the flattening device to reduce its speed to 0.4 m / s and simultaneously increases the damping coefficient of the pressure regulation system to smooth out pressure fluctuations. After these adjustments, the system monitors the pressure for five seconds. If the pressure still does not return to the normal range, a depth correction strategy is initiated. In this example, the pressure briefly dropped to 128 kPa after the speed reduction, but then rebounded to 132 kPa, prompting the system to determine that further adjustment is needed.

[0118] The distribution detection module retrieves historical data from the storage unit and analyzes the material characteristics in that area. Comparison reveals that this edge area has previously exhibited density gradient variations during previous operations. Based on this information, the system generates targeted correction instructions: the flattening device scans a spiral trajectory with a radius of 0.5 meters, centered on the current position. Simultaneously, the pressure sensor collects encrypted data at a rate of 20 times per second. During this scanning process, the system creates a three-dimensional map of pressure variations, clearly demonstrating the increasing density from the center to the edge of the material.

[0119] Based on the results of the map analysis, the parameter processing module calculates the optimal operation path. This new path avoids high-density areas and gradually advances toward the edge using a circuitous approach. During the advancement process, the system dynamically adjusts the pressure value, adaptively adjusting it within the range of 85-115 kPa based on real-time density changes. The travel speed is also adjusted synchronously with the pressure changes, ensuring that the pressure-speed matching relationship remains within the reasonable range corresponding to the standard pressure range.

[0120] When the flattening device entered the center of the material stack, the pressure sensor feedback value stabilized at around 95 kPa, but the speed sensor indicated a drop to 0.4 m / s, below the lower limit of the standard speed range. The distribution detection module analyzed that the high material humidity in this area might be causing increased friction. The system immediately generated a humidity anomaly warning and instructed the humidity detection probe installed on the flattening device to conduct multi-point sampling.

[0121] Sampling results showed that humidity in the center was 20% higher than in the outer areas. The system quickly invoked a pre-stored humidity-pressure correction model, adjusting the standard pressure range to 90-130 kPa while allowing the travel speed to fluctuate within a range of 0.4-0.6 m / s. After this adjustment, the flattening device's operating pressure in that area automatically increased to 110 kPa, maintaining a travel speed of 0.5 m / s, and normal operation resumed.

[0122] Throughout the operation, the distributed detection module continuously analyzes the correlation between pressure and velocity data. By establishing a dynamic data window (e.g., the most recent 30 seconds of data), it calculates the pressure-velocity rate of change. If the rate of change exceeds a preset threshold (e.g., a pressure change exceeding 15 kPa per minute and a velocity change exceeding 0.2 m / s), the system identifies an abnormal operating condition and immediately triggers an emergency correction procedure.

[0123] For example, during a certain operation, the pressure suddenly dropped from 100 kPa to 75 kPa, while the speed simultaneously soared from 0.6 m / s to 0.9 m / s. The distribution detection module detected this abnormal change within 0.3 seconds and quickly generated an emergency braking command. Upon receiving the command, the parameter processing module first cut off the power output and simultaneously activated the electromagnetic braking system, bringing the flattening device to a safe stop within a 0.5-meter range.

[0124] The system then entered troubleshooting mode. By comparing 3D point cloud data with historical operation records, it discovered a hidden depression in the area. The distribution detection module automatically generated a filling plan based on the size and depth of the depression: the flattening device first pre-pressed the edges of the depression with a low pressure (60 kPa), then filled the material in a spiral trajectory toward the center, gradually increasing the pressure to the standard range during the filling process.

[0125] During trajectory correction, the distributed detection module uses multi-sensor fusion technology to ensure accuracy. In addition to pressure and velocity sensors, it also integrates data from laser rangefinders, inclinometers, and accelerometers for comprehensive judgment. For example, if pressure rises abnormally, the system simultaneously analyzes changes in material surface height as measured by the laser rangefinder and equipment posture data from the inclinometer to eliminate misjudgments caused by equipment tilt.

[0126] In a complex material scenario, the leveling device encountered an irregularly shaped protrusion. The pressure sensor reported large fluctuations in pressure (80-140 kPa), and the laser rangefinder indicated that the height of the area was 15 cm higher than the surrounding area. After comprehensive analysis, the distribution detection module determined it to be a hard agglomerate. The system immediately switched to a special processing mode: the leveling device first performed a circular cut around the edge of the agglomerate to reduce the connection between the agglomerate and the surrounding material; then, the pressure was gradually increased to 150 kPa (a short-term over-limit) while the travel speed was reduced to 0.3 m / s to break up the agglomerate; finally, the broken area was leveled using standard pressure.

[0127] The distribution detection module also features adaptive learning capabilities. After each operation, the system compares actual operating parameters with preset standards and builds a deviation database. Machine learning algorithms analyze this deviation data to continuously optimize the standard pressure range and allowable deviation thresholds. For example, after repeatedly processing a certain type of material, the system may discover that the optimal pressure range in actual operation is 5-10 kPa lower than the preset value. It will then automatically adjust the standard parameters to improve operation efficiency and quality.

[0128] During long, continuous operations, the distributed detection module monitors equipment status parameters (such as motor temperature and hydraulic system pressure) in real time and correlates them with operating pressure and speed data. If abnormal equipment status parameters are detected, accompanied by fluctuations in operating parameters, the system will issue an early warning of a potential fault. For example, if the motor temperature rises by 10°C and the pressure value fluctuates periodically, the system predicts that the drive belt may be loose, prompting the operator to perform maintenance.

[0129] Through this intelligent, coordinated pressure-speed control mechanism, the flattening device automatically adapts to uneven material distribution, effectively avoiding problems such as excessive compaction due to overpressure or poor flattening due to underpressure. The entire operation requires no human intervention, achieving fully closed-loop automated control from data collection and analysis to decision-making and execution. This significantly improves the accuracy and efficiency of flattening operations while reducing labor costs and equipment wear.

[0130] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0131] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control system for a flat material device, characterized in that: It includes material identification module, parameter processing module, grade classification module, storage unit, strategy generation module, status monitoring module, distribution detection module and difference determination module; The material identification module is used to divide the flattened area and the area to be processed of the material stack; the parameter processing module is used to control the flattening device to start the flattening operation after receiving the instruction; when performing the initial flattening operation, the state monitoring module is used to collect the basic morphological data of the material stack and transmit it to the grade classification module; the storage unit is used to store the historical characteristic data of the material stack and transmit it to the grade classification module; the grade classification module is used to determine the characteristic grade and flatness grade of the material stack, generate the historical characteristic grade and the flatness grade and transmit them to the strategy generation module; the strategy generation module is used to generate the dynamic adjustment strategy of the flattening device during operation according to the flatness grade and the historical characteristic grade, and transmit the dynamic adjustment strategy to the parameter processing module; When the flattening device performs the flattening operation according to the dynamic adjustment strategy, the state monitoring module is further used to collect the real-time motion trajectory of the flattening device and transmit it to the difference determination module; the storage unit is further used to store the distribution difference characteristics in the material stack and the fluctuation data corresponding to the distribution difference characteristics and transmit them to the difference determination module; The difference determination module is used to determine whether the flattening device has entered the adjustment area. If a trajectory correction signal is generated, the real-time motion trajectory of the flattening device in the adjustment area is transmitted to the distribution detection module. The distribution detection module is used to determine whether the flattening device deviates from the reference path during operation in the adjustment area based on the real-time motion trajectory. If deviated, the motion trajectory correction instruction is sent to the parameter processing module. The method for obtaining the characteristic level is as follows: obtaining the number of historical thickness fluctuations of each material stack, then obtaining the adjustment time corresponding to each fluctuation, and accumulating the values to obtain the average adjustment time; and calculating the characteristic coefficient based on the number of historical thickness fluctuations and the average adjustment time. Compare the feature coefficient with the preset feature threshold to determine the feature level; The flatness grade is obtained by calculating a flatness coefficient based on a thickness deviation value and a humidity fluctuation value, and comparing the flatness coefficient with a preset flatness threshold value to determine the flatness grade. The difference determination module calculates the displacement difference between the real-time motion trajectory and the core coordinate point of the distribution difference feature, and calculates the adjustment radius based on the baseline fluctuation amplitude and attenuation change rate in the fluctuation data. The adjustment area is constructed with the core coordinate point as the center and the adjustment radius as the coverage range. When the displacement difference is greater than the adjustment radius, the flattening device operates outside the adjustment area and maintains the current operating state; when the displacement difference is less than or equal to the adjustment radius, it is determined that the flattening device enters the adjustment area; The working process of the strategy generation module is as follows: The flatness level of the material stack is used as the first priority factor, the historical characteristic level of the material stack is used as the second priority factor, and the distance between the current position of the flattening device and the operation starting point of the material stack is used as the third priority factor. The flattening device starts working from the current operation starting point. If there are multiple material stacks with the same flatness level near the starting point, the material stack with a higher historical feature level will be processed first. If the flatness level and historical characteristic level of the material stack are the same, the material stack closest to the operation starting point is selected for processing; When the flat material device reaches the dividing point: If the dividing point is connected to only a single material stack, the flattening device will directly process the material stack; If the demarcation point connects two or more material stacks, the material stack with the higher flatness grade will be processed first; if the flatness grades of multiple material stacks connected by the demarcation point are the same, the material stack with the higher historical characteristic grade will be processed first; if the flatness grades and historical characteristic grades of the material stacks connected by the demarcation point are the same, a material stack will be randomly selected for processing; If the dividing point is not connected to other material stacks and there are unprocessed areas, the nearest unprocessed area will be processed first; when the flattening device reaches any dividing point, if other areas have been processed, it will return to the initial position and stop; Generate dynamic adjustment strategies for flat material device operation according to the above rules; When the flattening device operates according to the dynamic adjustment strategy, it performs operations with different working intensities in areas corresponding to different flatness levels or third-level features.

2. The intelligent control system of a flat material device according to claim 1, characterized in that: It also includes a surface analysis module and an operation terminal. The status monitoring module is also used to collect real-time surface data of the material stack and transmit it to the surface analysis module. The surface analysis module is used to analyze the real-time surface data of the material stack in real time. If the analysis generates a defect signal or a deformation signal, the coordinate mark and the corresponding real-time surface data are transmitted to the operation terminal. The operation terminal is used for visual processing of the real-time surface data of the material stack.

3. The intelligent control system of a flat material device according to claim 1, characterized in that: Basic morphological data include thickness deviation and humidity fluctuation of material stacks; The historical characteristic data is the number of historical thickness fluctuations of the material stack and the adjustment time corresponding to each fluctuation.

4. The intelligent control system of a flat material device according to claim 3, characterized in that: The determination process of the grading module is as follows: Obtain the historical thickness fluctuation times of each material stack, then obtain the adjustment time corresponding to each fluctuation of each material stack, and accumulate the adjustment time corresponding to each fluctuation to calculate the average adjustment time of each material stack; Calculate the characteristic coefficient of each material stack based on the number of historical thickness fluctuations and the average adjustment time; Compare the characteristic coefficient with the preset characteristic threshold to determine whether the historical characteristic level of the material stack is a primary characteristic, a secondary characteristic, or a tertiary characteristic; Synchronously obtain the thickness deviation and humidity fluctuation values of each material stack and calculate the flatness coefficient of each material stack; The flatness coefficient is compared with a preset flatness threshold to determine whether the flatness level of the material stack is level one, level two, or level three.

5. The intelligent control system of a flat material device according to claim 4, characterized in that: The complexity corresponding to the third-level features is higher than that of the second-level features, and the complexity corresponding to the second-level features is higher than that of the first-level features; The finishing requirements for level 3 flatness are higher than those for level 2 flatness, and the finishing requirements for level 2 flatness are higher than those for level 1 flatness.

6. The intelligent control system of a flat material device according to claim 1, characterized in that: The fluctuation data are the core coordinate points of the distribution difference characteristics, the baseline fluctuation amplitude and the attenuation change rate.

7. The intelligent control system of a flat material device according to claim 6, characterized in that: The determination process of the difference determination module is as follows: Calculate the displacement difference between the real-time motion trajectory of the flattening device and the core coordinate point of the distribution difference feature; Obtain the fluctuation data corresponding to the distribution difference characteristics in the material stack, extract the core coordinate point, the baseline fluctuation amplitude and the attenuation change rate, and calculate the adjustment radius of the distribution difference characteristics by dividing the baseline fluctuation amplitude by the attenuation change rate; With the core coordinate point as the center point and the adjustment radius as the coverage range, an adjustment area with distribution difference characteristics is constructed; When the displacement difference is greater than the adjustment radius, the flattening device performs operations outside the adjustment area and maintains the current operating state; When the displacement difference is less than or equal to the adjustment radius, the flattening device enters the adjustment area to perform operations and generates a trajectory correction signal.

8. The intelligent control system of a flat material device according to claim 7, characterized in that: The judgment process of the distribution detection module is as follows: Set the standard pressure range and allowable deviation threshold for the flat material device operation; If the pressure sensor feedback value is within the allowable deviation threshold and the flat material device travel speed is within the standard pressure range, the current operating parameters are maintained; If the pressure sensor feedback value exceeds the allowable deviation threshold or the flat material device travel speed deviates from the standard pressure range, a motion trajectory correction instruction is generated.

9. The intelligent control system of a flat material device according to claim 2, characterized in that: The analysis process of the surface analysis module is as follows: Capture 3D point cloud data of material stacks; The point cloud data is converted into a two-dimensional projection image. The median filter is used to eliminate noise. The filter threshold is set according to the height difference between the material surface morphology and the background to extract the effective surface area of the material stack. The morphological closing operation is applied to fill small holes and retain the complete surface contour features. Detect straight line edges through Hough transform, match the geometric structure features of the material stack, and filter out non-structural interference areas; Synchronously acquire infrared thermal imaging data of material stacks, set the temperature gradient range to identify abnormal heating areas, use pseudo-color enhancement technology to enhance the display of temperature differences, and combine edge detection algorithms to extract temperature mutation boundaries and identify abnormal internal structures of materials; If the 3D point cloud data and infrared thermal imaging data show abnormalities at the same time, a defect signal is generated and the corresponding coordinates are marked; If both data are normal, maintain normal operation process; If any of the data is abnormal, a deformation signal is generated and the corresponding coordinates are marked.

Images