Multi-dimensional flatness digital imaging acceptance system for aviation composite floors

Abstract

The present invention relates to the field of aviation composite material detection technology, and discloses a digital imaging acceptance system for the multi-dimensional flatness of aviation composite floors. The system includes feature acquisition, imaging parameter calibration, environmental adaptation adjustment, deviation threshold setting, imaging prediction, and acceptance feedback control modules. The feature acquisition module analyzes the multi-dimensional flatness difference to obtain a feature distribution state value; the imaging parameter calibration module selects the optimal angle and resolution combination to obtain an imaging calibration parameter set; the environmental adaptation adjustment module matches the environmental factors and the imaging combination to obtain an environmental adaptation parameter set; the deviation threshold setting module sets the threshold to obtain a deviation load threshold; the imaging prediction module infers the imaging change trend to obtain an imaging distribution prediction value; and the acceptance feedback control module analyzes the error and adjusts the parameters to obtain an acceptance control plan. Through the collaboration of multiple modules, the system improves the accuracy and adaptability of the flatness acceptance of aviation composite floors and solves many problems existing in traditional detection.

Description

Technical Field

[0001] The present invention relates to the technical field of aviation composite material detection, and in particular to a multi-dimensional flatness digital imaging acceptance system for aviation composite material floors. Background Art

[0002] In the aviation industry, composite flooring, due to its high strength, lightweight, and corrosion resistance, is widely used in key areas such as airport runways, aprons, and maintenance workshops. The flatness of these floors directly impacts aircraft takeoff and landing safety, equipment operational stability, and maintenance efficiency, making their acceptance a key component of the industry. Traditional floor flatness acceptance methods rely on manual inspection or single-dimensional mechanical measurement, such as using tools like rulers and levels to perform local sampling, followed by manual recording and calculation of flatness data.

[0003] However, manual inspection has significant limitations. Differences in operator experience can lead to subjective deviations in measurement results. For large floor surfaces, point-by-point inspection is not only time-consuming and labor-intensive, but also difficult to achieve full coverage, making it easy to miss localized flatness defects. Furthermore, single-dimensional mechanical measurement can only capture linear or localized flatness data, failing to reflect the overall distribution of the floor surface and failing to meet the high-precision floor flatness requirements of the aviation industry.

[0004] With the advancement of digital technology, some acceptance inspections have begun to incorporate imaging equipment, capturing images of floor surfaces for analysis. However, existing imaging inspection systems face numerous practical challenges. The angle and resolution settings of the imaging equipment lack scientific basis, and improper parameter selection often leads to image distortion and an inability to accurately capture flatness details. Environmental factors have also not been effectively addressed. Changes in temperature, humidity, and light intensity can alter the reflective properties of the floor surface and the operating state of the imaging equipment, resulting in a lack of consistency in inspection data from different environments and making effective comparison and analysis difficult.

[0005] Existing systems often use fixed standards to set thresholds for flatness deviation, without considering the differences in functional requirements of different areas of the floor and the dynamic changes in real-time imaging data. This results in a lack of targeted threshold application and is prone to misjudgments or missed judgments. In terms of imaging prediction, traditional methods can only simply summarize the imaging data of known sampling points, and cannot effectively infer flatness change trends in combination with digital imaging logic, making it difficult to detect potential flatness problems in advance. The lack of an acceptance feedback mechanism results in a lack of linkage between test results and imaging equipment parameter adjustments, making it impossible to correct deviations in the test process in a timely manner, affecting the reliability of the final acceptance results. These problems jointly restrict the efficiency and accuracy of the flatness acceptance of aviation composite floors, making it difficult to adapt to the increasingly stringent requirements of the modern aviation industry for floor quality. Summary of the Invention

[0006] The purpose of the present invention is to provide a multi-dimensional flatness digital imaging acceptance system for aviation composite floors to solve the problems raised in the above background technology.

[0007] To achieve the above objectives, the present invention provides a multi-dimensional flatness digital imaging acceptance system for aviation composite floors, the system comprising:

[0008] The feature acquisition module analyzes multi-dimensional flatness differences based on floor surface images and structural data, calculates inter-regional deviation differences, integrates them into a feature distribution parameter set, and obtains the feature distribution state value;

[0009] The imaging parameter calibration module extracts the parameter combination of the imaging device angle and resolution based on the characteristic distribution state value, selects the optimal angle and resolution combination, and obtains the imaging calibration parameter set;

[0010] The environmental adaptation adjustment module extracts the change of the current environmental factors based on the imaging calibration parameter set, analyzes the relationship between the imaging angle and the resolution, matches the environmental factors with the imaging combination, and obtains the environmental adaptation parameter set;

[0011] The deviation threshold setting module extracts the current flatness change value based on the environmental adaptation parameter set, combines the real-time imaging data, distributes the flatness and imaging, sets a threshold, and applies the threshold to the distribution of regional deviation to obtain a deviation load threshold;

[0012] The imaging prediction module captures the imaging data of the flatness sampling points based on the deviation load threshold, performs logical inference on the imaging changes of the flatness sampling points in combination with digital imaging logic, analyzes the imaging change trends corresponding to the deviation load, classifies and organizes the imaging change trends based on the inference results, and performs digital imaging logic adjustment and analysis on the classified data in combination with the imaging change information to obtain the imaging distribution prediction value;

[0013] The acceptance feedback control module analyzes the error between flatness and imaging based on the imaging distribution prediction value and real-time flatness and imaging data, adjusts the imaging equipment parameters based on the error value, and obtains the digital imaging acceptance control plan for floor flatness.

[0014] Preferably, the characteristic distribution state value includes an image parameter set, a structural parameter set, and a deviation difference parameter set; the imaging calibration parameter set includes a screening angle parameter and a resolution parameter; the environmental adaptation parameter set includes an environmental factor change parameter and an imaging parameter matching parameter; the deviation load threshold includes a flatness change parameter, an imaging matching parameter, and a threshold setting parameter; the imaging distribution prediction value includes an imaging trend analysis parameter and a flatness imaging relationship parameter; and the floor flatness digital imaging acceptance and control scheme includes an error analysis parameter and an imaging adjustment parameter.

[0015] Preferably, the feature acquisition module includes:

[0016] The data acquisition submodule performs regional collection of image and structure values ​​based on the floor surface image and structure data, locates invalid data, removes abnormal data, and arranges the extracted image and structure values ​​in regional order to generate a regional image structure data set;

[0017] The difference analysis submodule analyzes the images and structures between regions based on the regional image structure dataset, calculates the regional parameter change ratio, sorts the regional difference values ​​by weight, marks the regions with excessive fluctuation differences, and obtains regional deviation difference data;

[0018] The distribution integration submodule calls the regional deviation difference values ​​for multi-dimensional aggregation based on the regional deviation difference data, screens the regional deviation numerical differences, classifies them according to the deviation numerical values, and arranges the regional deviation values ​​in order to generate characteristic distribution state values.

[0019] Preferably, the imaging parameter calibration module includes:

[0020] The parameter extraction submodule identifies the working status of the imaging device in each area based on the characteristic distribution state value, records the angle and resolution of the device, standardizes the recorded data, organizes the standardized data and classifies them by angle and resolution to generate an imaging parameter data set;

[0021] The imaging parameter optimization submodule analyzes the angle and resolution values ​​in the data set according to the imaging parameter data set, selects the parameter combination with the high matching degree with the deviation state, adjusts the parameter combination through pattern matching and records the matching results, and generates the parameter combination optimization result;

[0022] The parameter selection submodule retrieves the parameter combination optimization result, determines the optimal matching angle and resolution combination, adjusts the imaging device control parameters, inputs the control configuration, verifies the stability of the parameter set, and generates an imaging calibration parameter set.

[0023] Preferably, the environment adaptation adjustment module includes:

[0024] The environmental factor analysis submodule collects key data, including light, temperature, humidity, and vibration, through environmental monitoring based on the imaging calibration parameter set, performs time series analysis on the data, removes outliers, and partitions the remaining data to obtain environmental factor analysis data;

[0025] The parameter matching submodule analyzes the environmental factors and the impact of environmental variables on the angle and resolution of the imaging device through the environmental factor analysis data, calculates the degree of influence of each environmental factor change on the parameter adjustment, determines the optimal matching parameter setting based on the impact score, adjusts the parameters cyclically to capture the optimal combination, and obtains the parameter matching results;

[0026] The response parameter integration submodule selects an angle and resolution combination that matches the current environmental conditions from the parameter docking results, performs parameter adjustment tests, optimizes parameter settings through multiple adjustments and verifications, determines and solidifies the parameters as operating standards, and generates an environmental adaptation parameter set.

[0027] Preferably, the deviation threshold setting module includes:

[0028] The flatness extraction submodule locates the flatness change monitoring point based on the environmental adaptation parameter set, extracts the flatness change value in the monitoring area, continuously records the flatness increase and decrease rate, extracts multiple key change nodes corresponding to the change rate, sorts the node values ​​in order, and obtains the current flatness change characteristic value;

[0029] The imaging matching submodule analyzes the node change value and the real-time imaging data based on the current flatness change characteristic value, performs calibration according to a predetermined matching criterion, calls the matching criterion to perform distribution redistribution within the imaging interval, and obtains a flatness imaging matching structure;

[0030] The load distribution submodule is based on the flatness imaging matching structure and adopts a digital threshold dynamic adjustment method to measure the distribution of imaging between flatness change nodes, set the upper and lower limits of the node threshold, apply the threshold to the regional deviation value, and distribute it to obtain the deviation load threshold.

[0031] Preferably, the digital threshold dynamic adjustment method matches the distribution deviation value of the flatness change node, combines the imaging data and flatness height measured by the real-time node, performs dynamic adjustment according to a predetermined weight coefficient, and sets the node threshold lower limit to control the minimum deviation.

[0032] Preferably, the imaging prediction module includes:

[0033] The imaging data capture submodule applies a digital imaging logic algorithm based on the deviation load threshold to capture the imaging data of the sampling points, remove outliers and correct errors, store them in layers by intervals, perform logical processing, and generate a logical imaging data set;

[0034] The deviation load analysis submodule divides the intervals according to the deviation load based on the logical imaging data set, extracts the change trend and fluctuation characteristics, and generates a deviation load and imaging change feature set;

[0035] The imaging distribution inference submodule adjusts characteristic parameters and calibrates trend data based on the deviation load and the imaging change feature set, extracts distribution intervals, and performs numerical prediction to obtain an imaging distribution prediction value.

[0036] Preferably, the digital imaging logic algorithm generates a logicized imaging data set by calculating the imaging logic value, combining the original imaging value, flatness value and deviation coefficient of the sampling point, and performing weighted integration according to the total number of sampling points.

[0037] Preferably, the acceptance feedback control module includes:

[0038] The error analysis submodule extracts real-time flatness and imaging data based on the imaging distribution prediction value, analyzes the real-time imaging value and the prediction value, matches the imaging difference value with the current flatness information, and generates a flatness imaging error value;

[0039] The parameter adjustment submodule sets the parameter adjustment parameters of the imaging device based on the flatness imaging error value, sets the adjustment range for areas with large errors, and performs fine-tuning on areas with low errors. By comparing the parameter adjustment effects, matching parameter sets are screened and integrated to generate an imaging adjustment parameter set.

[0040] Based on the imaging adjustment parameter set, the parameter control submodule applies the adjustment parameters at each imaging device position, implements the parameter adjustment operation item by item, synchronously monitors the flatness and imaging, gradually adjusts the parameter adjustment order of each area, and generates a digital imaging acceptance and control plan for floor flatness.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The feature acquisition module extracts multi-dimensional flatness differences from floor surface images and structural data, integrating inter-regional deviations into a set of feature distribution parameters. This provides comprehensive foundational data for subsequent imaging calibration and analysis, changing the fragmented and one-sided data found in traditional inspections. The imaging parameter calibration module selects the optimal combination of imaging device angle and resolution to ensure that the imaging data accurately reflects floor flatness characteristics, avoiding image distortion caused by improper parameter selection and improving the accuracy of inspection data.

[0043] The environmental adaptation adjustment module dynamically matches environmental factors with imaging combinations based on changes in environmental factors such as temperature, humidity, and lighting, generating an environmental adaptation parameter set. This resolves the issue of inconsistent detection data across different environments, ensuring stable detection performance in complex and changing environments. The deviation threshold setting module combines real-time imaging data with the current flatness change value and applies a set threshold to regional deviation allocation, making the threshold setting more aligned with actual detection needs, avoiding misjudgments or missed detections caused by fixed thresholds, and improving the targetedness and flexibility of deviation judgment.

[0044] The imaging prediction module uses digital imaging logic to infer imaging changes at flatness sampling points, analyzes imaging change trends corresponding to deviation loads, and adjusts and analyzes classified data. This allows for early identification of potential flatness issues, breaking the limitations of traditional methods that can only passively record data and shifting inspection work from passive detection to active prediction. The acceptance feedback control module adjusts imaging equipment parameters through error analysis of real-time data, forming a complete closed-loop control loop. This ensures that deviations during the inspection process can be corrected promptly, making the final acceptance and control plan more consistent with the actual floor flatness condition, and overall improving the intelligence level and overall efficiency of aviation composite floor flatness acceptance. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a working principle diagram of the multi-dimensional flatness digital imaging acceptance system for aviation composite floors according to the present invention;

[0046] Figure 2 Flowchart for classification and association of parameter sets;

[0047] Figure 3 This is the flow chart of the feature acquisition module;

[0048] Figure 4 is a flowchart of the imaging parameter calibration module;

[0049] Figure 5 Flowchart of adapting the module to the environment. DETAILED DESCRIPTION

[0050] 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.

[0051] See also Figure 1-Figure 5 The present invention provides a multi-dimensional flatness digital imaging acceptance system for aviation composite floors, and the system includes:

[0052] The feature acquisition module analyzes multi-dimensional flatness differences based on floor surface images and structural data, calculates inter-regional deviation differences, integrates them into a feature distribution parameter set, and obtains the feature distribution state value;

[0053] The imaging parameter calibration module extracts the parameter combination of the imaging device angle and resolution based on the characteristic distribution state value, selects the optimal angle and resolution combination, and obtains the imaging calibration parameter set;

[0054] The environmental adaptation adjustment module extracts the change of the current environmental factors based on the imaging calibration parameter set, analyzes the relationship between the imaging angle and the resolution, matches the environmental factors with the imaging combination, and obtains the environmental adaptation parameter set;

[0055] The deviation threshold setting module extracts the current flatness change value based on the environmental adaptation parameter set, combines the real-time imaging data, distributes the flatness and imaging, sets a threshold, and applies the threshold to the distribution of regional deviation to obtain a deviation load threshold;

[0056] The imaging prediction module captures the imaging data of the flatness sampling points based on the deviation load threshold, performs logical inference on the imaging changes of the flatness sampling points in combination with digital imaging logic, analyzes the imaging change trends corresponding to the deviation load, classifies and organizes the imaging change trends based on the inference results, and performs digital imaging logic adjustment and analysis on the classified data in combination with the imaging change information to obtain the imaging distribution prediction value;

[0057] The acceptance feedback control module analyzes the error between flatness and imaging based on the imaging distribution prediction value and real-time flatness and imaging data, adjusts the imaging equipment parameters based on the error value, and obtains the digital imaging acceptance control plan for floor flatness.

[0058] Example 1

[0059] In the multi-dimensional flatness digital imaging acceptance system for aviation composite floors, the feature acquisition module analyzes multi-dimensional flatness differences based on floor surface images and structural data, calculates inter-regional deviation differences, and integrates these into a feature distribution parameter set to obtain a feature distribution state value. The feature distribution state value includes an image parameter set, a structural parameter set, and a deviation difference parameter set.

[0060] The feature acquisition module includes a data acquisition submodule, a difference analysis submodule, and a distribution integration submodule. The data acquisition submodule performs regional acquisition of image values ​​and structural values ​​based on the floor surface image and structural data. During the acquisition process, the floor surface is divided into regions, and a specific acquisition range and acquisition point density are set for each region to ensure that the floor surface can be fully covered. The image value of each region is obtained by the image acquisition device, and the structural value of the corresponding region is collected by the structure detection device. After the acquisition is completed, the acquired data is processed to locate invalid data. These invalid data may be missing or blurred data due to equipment failure, occlusion, etc. Abnormal data is removed. Abnormal data usually refers to data that deviates too much from the surrounding data and does not conform to the normal distribution pattern. The extracted image values ​​and structural values ​​are arranged in regional order to generate a regional image structure dataset, which fully records the image and structural information of each region.

[0061] The difference analysis submodule analyzes the images and structures between regions based on the regional image structure dataset. Image values ​​from different regions are compared to observe differences in color, texture, brightness, and other aspects. At the same time, structural values ​​from different regions are compared to analyze changes in structural features such as floor thickness and material distribution. Regional parameter change ratios are calculated, i.e., the proportion of changes in image parameters and structural parameters between adjacent or designated regions. Regional difference values ​​are sorted by weight, with weights set based on the importance and functional requirements of different regions in aviation composite floors. Important regions have higher weights for difference values. Areas with excessive fluctuations are marked; these areas may have flatness issues and require special attention, thereby obtaining regional deviation difference data.

[0062] The distribution integration submodule uses regional deviation difference data and calls regional deviation difference values ​​for multi-dimensional aggregation. Deviation difference values ​​are counted and integrated from multiple dimensions such as length, width, and height to fully reflect the flatness of the floor surface. Regional deviation value differences are screened to distinguish different degrees of deviation. Deviation values ​​are classified according to their magnitude, for example, they can be divided into categories such as slight deviation, moderate deviation, and severe deviation. Regional deviation values ​​are arranged in an orderly manner, from large to small or from small to large, to clearly present the distribution of deviations and generate characteristic distribution state values. This characteristic distribution state value integrates parameter information from multiple aspects such as image, structure, and deviation differences.

[0063] The imaging parameter calibration module extracts the parameter combination of imaging device angle and resolution based on the characteristic distribution state value, selects the optimal angle and resolution combination, and obtains the imaging calibration parameter set, which includes the selection angle parameter and resolution parameter. The environmental adaptation adjustment module extracts the current environmental factor change based on the imaging calibration parameter set, analyzes the relationship between imaging angle and resolution, and matches the environmental factors with the imaging combination to obtain the environmental adaptation parameter set, which includes the environmental factor change parameter and the imaging parameter matching parameter.

[0064] The deviation threshold setting module extracts the current flatness change value based on the environmental adaptation parameter set. Combined with real-time imaging data, it distributes flatness and imaging, sets a threshold, and applies it to the distribution of regional deviations to obtain a deviation load threshold. The deviation load threshold includes flatness change parameters, imaging matching parameters, and threshold setting parameters. The imaging prediction module captures imaging data from flatness sampling points based on the deviation load threshold. Combined with digital imaging logic, it logically infers the imaging changes at these points, analyzes the imaging change trends corresponding to the deviation load, and categorizes and organizes these trends based on the inference results. Combined with imaging change information, the classified data undergoes digital imaging logic adjustment and analysis to obtain an imaging distribution prediction value. The imaging distribution prediction value includes imaging trend analysis parameters and flatness-imaging relationship parameters.

[0065] The acceptance feedback control module analyzes the error values ​​of flatness and imaging based on the predicted imaging distribution value and real-time flatness and imaging data. It adjusts the imaging equipment parameters based on the error values ​​to obtain a digital imaging acceptance control plan for floor flatness, which includes error analysis parameters and imaging adjustment parameters.

[0066] During the entire system operation process, various modules work together. The feature acquisition module provides the basic feature distribution state value for subsequent modules. The imaging parameter calibration module optimizes the imaging parameters based on the state value. The environmental adaptation adjustment module enables the system to adapt to different environmental conditions. The deviation threshold setting module provides judgment criteria for acceptance. The imaging prediction module predicts the imaging distribution. The acceptance feedback control module adjusts the parameters according to the actual situation, forming a complete acceptance and control process to achieve accurate and efficient acceptance of the multi-dimensional flatness of aviation composite floors.

[0067] Example 2

[0068] During the operation of the multi-dimensional flatness digital imaging acceptance system for aviation composite floors, the imaging parameter calibration module works based on the characteristic distribution state value. This module includes a parameter extraction submodule, an imaging parameter optimization submodule, and a parameter selection submodule. Through a series of operations, it extracts the parameter combination of the imaging device angle and resolution, screens the optimal combination, and obtains the imaging calibration parameter set, which includes the screening angle parameter and resolution parameter.

[0069] The parameter extraction submodule identifies the operating status of the imaging device in each region based on the characteristic distribution state values. Using the device's built-in sensors and monitoring program, it captures various operating indicators of the imaging device in real time, determining whether the device is operating normally and whether it is experiencing any faults or abnormal operation. While identifying the operating status, it also records the device's angle and resolution data. Angle data includes specific values ​​such as horizontal rotation angle and vertical pitch angle, while resolution data includes the number of horizontal and vertical pixels in the image. The recorded data is standardized to unify the units and formats. For example, angle data is converted to degrees, and resolution data is expressed in the format of "horizontal pixels x vertical pixels." The standardized data is then sorted by angle and resolution, with data of the same angle or resolution grouped together to generate an imaging parameter dataset that comprehensively captures the angle and resolution information for the imaging devices in different regions.

[0070] The imaging parameter optimization submodule conducts an in-depth analysis of the angle and resolution values ​​in the imaging parameter data set based on the imaging parameter data set. The degree of match between the imaging results and the deviation state in the feature distribution state value is calculated under different angle and resolution combinations. The calculation of the matching degree involves multiple indicators such as image clarity, recognition of the deviation area, and data integrity. Parameter combinations with a high degree of match with the deviation state are screened out. These combinations can more accurately reflect the flatness differences of the floor surface. Through the pattern matching algorithm, each parameter combination is compared with the regional deviation difference data, and various data and results of the matching process are recorded, including the number of successful matches and the matching accuracy. The parameter combination is adjusted according to the matching results. For example, when a certain angle and resolution combination does not perform well in matching a certain type of deviation area, the angle value or resolution value is appropriately fine-tuned to generate a parameter combination optimization result, which contains multiple sets of optimized angle and resolution combinations and their corresponding matching effect information.

[0071] The parameter selection submodule retrieves the parameter combination optimization results and conducts a comprehensive evaluation of all optimized parameter combinations. Evaluation indicators include imaging quality stability, data processing efficiency, and energy consumption of equipment operation. A comprehensive score for each parameter combination is obtained through weighted calculation. The optimal angle and resolution combination with the highest comprehensive score is determined, and this combination performs well in all indicators. The imaging device control parameters are adjusted, and the selected angle and resolution parameters are input into the device's control system to complete the initial configuration of the parameters. The stability of the parameter set is verified. The working conditions of the imaging device and the consistency of the imaging data are monitored under different working periods and continuous operation conditions to ensure that the parameter set does not fluctuate significantly during long-term operation. After verification, an imaging calibration parameter set is generated, which serves as the baseline parameter for subsequent imaging device operation.

[0072] The environmental adaptation adjustment module works based on the imaging calibration parameter set. The module includes an environmental factor analysis submodule, a parameter matching submodule, and a response parameter integration submodule. By extracting the current environmental factor change, analyzing the relationship between the imaging angle and resolution, and matching the environmental factors with the imaging combination, the environmental adaptation parameter set is obtained. The environmental adaptation parameter set includes environmental factor change parameters and imaging parameter matching parameters.

[0073] The environmental factors analysis submodule, based on an imaging calibration parameter set, collects key data from environmental monitoring equipment deployed at the acceptance site. This data includes light intensity, ambient temperature, relative humidity, and vibration frequency. Light intensity data is recorded in lux, recording light values ​​in different areas and at different times. Temperature data is recorded in degrees Celsius, and humidity data is recorded in percentage, all recorded chronologically. Vibration frequency data is recorded in hertz, reflecting vibrations caused by equipment operation and the external environment. Time series analysis is performed on the collected data to observe trends over time and identify periodic patterns and abnormal fluctuations. Outliers are removed, as they may be caused by monitoring equipment failures or sudden environmental disturbances, such as sudden strong light exposure or sudden temperature changes. The remaining data is partitioned, and environmental data is assigned to corresponding areas according to the floor's different zones. This generates environmental factor analysis data, which clearly presents the specific environmental factors in each area.

[0074] The parameter matching submodule analyzes data based on environmental factors, examining how these variables influence the imaging device's angle and resolution. Excessive light intensity can cause overexposure in images, necessitating adjustment of the imaging device's pitch angle to avoid direct light. High temperatures can affect the device's optical components, resulting in reduced resolution, requiring appropriate increases in resolution parameters to compensate. Excessive humidity can cause fogging of the device's lens, requiring adjustment of the angle to mitigate the effects of fog. Vibration can cause image blur, requiring corresponding resolution adjustments to maintain image clarity. The module calculates the impact of each environmental factor on parameter adjustments, sets a scoring criteria for each impact, and determines the optimal matching parameter settings based on the scores. Environmental factors with higher scores receive higher priority during parameter matching. Parameter adjustments are iterated to identify the optimal combination. By repeatedly varying the angle and resolution parameters and observing the changes in the imaging results, the module finds the parameter combination that provides the best imaging quality under the current environmental conditions and obtains the parameter matching results.

[0075] The response parameter integration submodule selects angle and resolution combinations that match the current environmental conditions from the parameter docking results. These combinations can stably output high-quality imaging data in the current environment. Conduct parameter adjustment tests. In the actual acceptance environment, set the imaging equipment according to the selected parameter combination, and continuously collect imaging data and environmental data for multiple time periods. Optimize parameter settings through multiple adjustments and verifications, compare imaging effects in different tests, analyze the relationship between parameter settings and imaging quality, and make subtle adjustments to parameters to further improve the effect. Determine and solidify parameters as operating standards, write the verified optimal parameter combination into the equipment's operating manual as the standard working parameters under the environmental conditions, and generate an environmental adaptation parameter set. This parameter set ensures that the imaging equipment can always maintain a good working condition in the current environment and accurately obtain imaging data on floor flatness.

[0076] Example 3

[0077] The deviation threshold setting module works based on the environmental adaptation parameter set. The module includes a flatness extraction submodule, an imaging matching submodule, and a load distribution submodule. By extracting the current flatness change value and combining it with real-time imaging data, the module distributes flatness and imaging, sets the threshold, and applies the threshold to the distribution of regional deviation to obtain the deviation load threshold. The deviation load threshold includes flatness change parameters, imaging matching parameters, and threshold setting parameters.

[0078] The flatness extraction submodule locates flatness change monitoring points on the surface of the aviation composite floor based on an environmental adaptation parameter set. The distribution of monitoring points is determined based on the floor's area and structural characteristics, covering key areas of the floor, including the edge, center, and areas where different materials meet. Flatness change values ​​within the monitoring area are extracted. High-precision sensors continuously measure the elevation of each monitoring point to obtain flatness values ​​at different times. The difference between the flatness values ​​at adjacent times is calculated as the flatness change value. The flatness increase / deceleration rate is continuously recorded, expressed as the flatness change value per unit time. A positive value indicates an increase in flatness, while a negative value indicates a decrease in flatness. Multiple key change nodes corresponding to the change rate are extracted. These nodes are typically the moments or locations where the flatness increase / deceleration rate changes significantly, such as turning points where the rate changes from positive to negative or points where the absolute value of the rate suddenly increases. Sort the node values ​​in order, arrange them in time sequence or spatial position sequence, and obtain the current flatness change characteristic value. The flatness change parameter includes the position information of these key nodes, the corresponding flatness value, the increase / deceleration rate, etc.

[0079] The imaging matching submodule analyzes node change values ​​against real-time imaging data based on the current flatness variation eigenvalue. Real-time imaging data, collected by imaging devices deployed around the floor, includes floor surface images at various angles and resolutions. The flatness variation values ​​of key nodes are correlated with imaging data at corresponding locations and times, and the relationship between these values ​​and imaging data parameters such as pixel value, contrast, and clarity is analyzed. Calibration is performed according to predefined matching criteria, which include the correspondence between node change values ​​and imaging clarity, and the proportional relationship between flatness variation amplitude and imaging contrast. This calibration eliminates systematic errors introduced by the imaging device itself, ensuring a more accurate correlation between node change values ​​and imaging data. The matching criteria are then applied to perform distribution redistribution within the imaging interval. The imaging area is divided into intervals based on the flatness variation eigenvalues, each corresponding to a specific flatness variation range. The weights of the imaging data within each interval are adjusted according to the matching criteria to ensure that the distribution of the imaging data more closely matches the actual flatness variation. This results in a flatness imaging matching structure. The imaging matching parameters include the interval division criteria, the weighting of the imaging data, and the matching coefficients between node change values ​​and imaging parameters.

[0080] The load distribution submodule is based on the flatness imaging matching structure and adopts a digital threshold dynamic adjustment method. This method matches the distribution deviation value of the flatness change node, combines the imaging data and flatness height measured by the real-time node, and performs dynamic adjustment according to the predetermined weight coefficient. The lower limit of the node threshold is set to control the minimum deviation. The distribution of imaging between the flatness change nodes is measured, and the number, distribution density and degree of correlation with the flatness change of each node are counted to determine the distribution pattern of imaging data between nodes. The upper and lower limits of the node threshold are set. The upper limit of the threshold is determined according to the acceptance standard of the flatness of aviation composite floors and represents the maximum acceptable deviation range. The lower limit of the threshold is set by the digital threshold dynamic adjustment method to ensure that even in the case of small deviations, the flatness change can be effectively monitored. Apply the threshold to the regional deviation value and distribute it. According to the importance and usage requirements of different areas of the floor, the threshold is reasonably distributed among the areas. For key areas, a stricter threshold is set (that is, the threshold range is smaller), and for non-key areas, the threshold can be appropriately relaxed to obtain the deviation load threshold. The threshold setting parameters include the upper and lower limits of the threshold for each area, the threshold distribution ratio, the dynamically adjusted weight coefficient, etc.

[0081] The specific calculation process of the digital threshold dynamic adjustment method is as follows:

[0082]

[0083] in, represents the threshold setting value of the jth node in the i-th region; represents the allocation deviation value of the jth node in the i-th region; represents the real-time imaging data parameters of the jth node in the i-th region; Indicates the flatness height value of the jth node in the i-th region; and represents the predetermined weight coefficient, Used to measure the impact of the allocation deviation value on the threshold setting, It is used to measure the influence of the product of real-time imaging data and flatness height on the threshold setting, with the sum of the two being 1. This formula is used to calculate the threshold setting value for each node, and combined with the distribution of nodes, it forms the deviation load threshold for the entire floor.

[0084] In practical applications, for areas with high flatness requirements, such as aircraft docking areas on aviation composite floors, and The value of will tend to make the threshold setting value smaller to strictly control the deviation range; for areas with relatively low flatness requirements, such as channel areas, and The value of will appropriately increase the threshold setting value, reducing unnecessary monitoring costs while ensuring basic acceptance requirements. In this way, the deviation load threshold can be more closely aligned with actual acceptance requirements, accurately reflecting the flatness conditions of each area of ​​the floor, and providing a reliable threshold reference for subsequent imaging prediction and acceptance control. At the same time, during the threshold application process, real-time flatness and imaging data will be continuously collected, and the threshold setting value will be dynamically updated. When environmental conditions change significantly or the floor usage status changes, the weight coefficient and threshold setting value will be recalculated to ensure that the deviation load threshold remains reasonable and effective.

[0085] Example 4

[0086] The imaging prediction module works based on the deviation load threshold. The module includes an imaging data capture submodule, a deviation load analysis submodule, and an imaging distribution inference submodule. By capturing the imaging data of the flatness sampling points and combining the digital imaging logic, the imaging changes of the flatness sampling points are logically inferred, the imaging change trends corresponding to the deviation load are analyzed, and the imaging change trends are classified and sorted according to the inference results. Combined with the imaging change information, the classified data is adjusted and analyzed by digital imaging logic to obtain the imaging distribution prediction value. The imaging distribution prediction value includes imaging trend analysis parameters and flatness imaging relationship parameters.

[0087] The imaging data capture submodule applies a digital imaging logic algorithm based on a deviation load threshold. This algorithm calculates a logicalized imaging value, combines the raw imaging values, flatness values, and deviation coefficients at the sampling points, and performs a weighted integration based on the total number of sampling points to generate a logicalized imaging dataset. In the actual acceptance scenario for aviation composite flooring, flatness sampling points are evenly distributed across the floor surface at 50 cm x 50 cm intervals, covering the entire area to be inspected. Each sampling point corresponds to a unique spatial coordinate. The raw imaging values ​​are captured by a high-definition industrial camera and include information such as the RGB color channel pixel values ​​and image grayscale values ​​for each sampling point. The flatness values ​​are measured by a laser rangefinder, expressing the height difference of the sampling point relative to the reference plane in millimeters. The deviation coefficient is determined based on the deviation load threshold of the area where the sampling point is located. Regions with higher deviation load thresholds have larger deviation coefficients. For example, if the deviation load threshold in one area is ±3 mm, the deviation coefficient is set to 1.2; if the deviation load threshold in another area is ±5 mm, the deviation coefficient is set to 0.8. The digital imaging logic algorithm first normalizes the raw image values, converting RGB values ​​to normalized values ​​between 0 and 1. The smoothness value is then multiplied by the deviation coefficient to obtain a correction value. Finally, a weighted integration is performed based on the total number of sampling points, n. The weight of each sampling point in the calculation formula is the ratio of its deviation coefficient to the sum of the deviation coefficients of all sampling points. When capturing imaging data at a sampling point, the acquisition time and ambient temperature are simultaneously recorded. Outliers such as blurred image data caused by camera shutter malfunctions and missing smoothness values ​​caused by laser rangefinder signal interruptions are removed. Measurement errors in edge regions are corrected through interpolation of adjacent sampling points. The processed imaging data is stored in tiers according to deviation load threshold intervals. For example, data for sampling points with deviation load thresholds of ±2mm, ±2-4mm, and above ±4mm are stored in separate data partitions. Logical processing is then performed to generate a logical imaging dataset, which contains the normalized image value, corrected smoothness value, and the threshold interval label for each sampling point.

[0088] The deviation load analysis submodule is based on a logicalized imaging dataset and is divided into intervals based on deviation load. Each interval corresponds to a specific deviation load threshold range, for example, interval 1 corresponds to ±1mm, interval 2 corresponds to ±1-3mm, interval 3 corresponds to ±3-5mm, and interval 4 corresponds to ±5mm or more. The trend and fluctuation characteristics of the imaging data within each interval are extracted. The trend is calculated through linear fitting, with the slope representing the direction and rate of change of the imaging value with the flatness value. A positive slope indicates that the imaging value increases with the flatness value, while a negative slope indicates that the two change in opposite directions. The fluctuation characteristics are determined by calculating the standard deviation and coefficient of variation. The standard deviation reflects the degree of dispersion of the imaging value within the interval, and the coefficient of variation is the ratio of the standard deviation to the mean, which is used to eliminate dimensional effects. In a specific area, the imaging values ​​of sampling points within interval 2 show a clear upward trend with increasing flatness values, with a slope of 0.7, a standard deviation of 0.15, and a coefficient of variation of 0.2. The imaging values ​​of sampling points within interval 4 fluctuate significantly, with a standard deviation of 0.3, a coefficient of variation of 0.45, and a trend line slope of 0.3, indicating that the correlation between imaging values ​​and flatness values ​​weakens under high deviation loads. By analyzing all intervals, a feature set of deviation load and imaging change was generated, which includes parameters such as trend slope, standard deviation, coefficient of variation, and sample size for each interval.

[0089] The imaging distribution inference submodule adjusts feature parameters and calibrates trend data based on the deviation load and imaging variation feature set. During feature parameter adjustment, trend slopes are tested for significance, and non-significant trend lines with R² values ​​below 0.6 are eliminated, retaining statistically significant trends. Fluctuation feature parameters are smoothed using a moving average method to eliminate short-term random fluctuations, ensuring that the standard deviation and coefficient of variation better reflect the overall characteristics of the interval. When calibrating trend data, consistency is checked against the trend slopes of adjacent intervals. If the trend slope of an interval differs from that of an adjacent interval by more than 20%, the linear fit results for that interval are recalculated to ensure continuity of trend change. Distribution intervals are extracted. Based on the calibrated trend data and fluctuation characteristics, the imaging values ​​are divided into multiple distribution intervals, such as low imaging value range (0-0.3), medium imaging value range (0.3-0.7), and high imaging value range (0.7-1.0). Each distribution interval corresponds to a specific range of flatness values. When performing numerical predictions, a regression analysis method is used to establish a prediction model with flatness values ​​as the independent variable and imaging values ​​as the dependent variable. Inputting a given flatness value yields the corresponding imaging value prediction. In edge transition regions, the prediction results of adjacent intervals are fused using a weighted average method. For example, for a sampling point located at the junction of intervals 2 and 3, its prediction value is the sum of 60% of the model output value for interval 2 and 40% of the model output value for interval 3. This yields an imaging distribution prediction value, which includes imaging trend analysis parameters such as the imaging value range for each distribution interval, the corresponding flatness value interval, and the prediction model's coefficient of determination. Furthermore, parameters related to the flatness-imaging relationship, such as the regression equation and correlation coefficient, are used to determine the relationship between imaging values ​​and flatness values ​​within different intervals.

[0090] In actual operation, for sampling points in the runway area, due to the strict deviation load threshold requirements, the interval division is more refined, with a total of 6 deviation load intervals set, each with a sample size of no less than 50 to ensure prediction accuracy. For the apron edge area, the deviation load threshold requirements are relatively loose, and setting 3 deviation load intervals can meet the requirements. The imaging distribution prediction value will generate a visual heat map according to the spatial coordinates. Different colors represent different imaging value prediction ranges. It is superimposed on the flatness contour map to clearly show the corresponding relationship between the two. When the predicted imaging value of a certain area deviates from the historical data by more than the preset range, the re-collection mechanism will be triggered to supplement the sampling point data in the area and re-analyze and predict to ensure that the imaging distribution prediction value can accurately reflect the actual imaging characteristics of the floor flatness.

[0091] Example 5

[0092] The acceptance feedback control module works based on the imaging distribution prediction value. The module includes an error analysis submodule, a parameter adjustment submodule and a parameter control submodule. It uses real-time flatness and imaging data to analyze the error values ​​of flatness and imaging, and adjusts the imaging equipment parameters based on the error values ​​to obtain a digital imaging acceptance and control plan for floor flatness. The plan includes error analysis parameters and imaging adjustment parameters.

[0093] The error analysis submodule extracts real-time flatness and imaging data based on the imaging distribution prediction values. Real-time flatness data is collected by displacement sensors distributed across the floor surface. The elevation values ​​of each monitoring point are recorded every 10 seconds in millimeters, covering real-time height changes in all areas of the floor. Real-time imaging data is acquired by high-definition cameras deployed at multiple angles, generating a frame of image data containing RGB channels every 30 seconds. The image resolution is set according to pre-calibrated parameters to ensure that the subtle texture of the floor surface can be clearly presented. The real-time imaging values ​​are compared with the corresponding parameters in the imaging distribution prediction values, and the difference between the two in terms of pixel brightness, contrast, edge clarity, and other indicators is calculated. The deviation between the real-time flatness values ​​and the flatness imaging relationship parameters in the imaging distribution prediction values ​​is also extracted. The imaging difference is matched with the current flatness information to establish an error matrix. The rows of the matrix represent different flatness intervals, the columns represent different imaging parameters, and the matrix elements are the error values ​​of the corresponding intervals and parameters. The error matrix is ​​used to analyze the distribution of errors. For example, in areas with large flatness deviations, does the image clarity error show a synchronous increase? During periods of significant illumination change, the correlation between the image brightness error and the flatness value is analyzed. Flatness imaging error values ​​are generated. Error analysis parameters include the error matrix, the mean error value for each area, the location and time of the maximum error, and the correlation coefficient between imaging parameter errors and flatness deviations.

[0094] The parameter adjustment submodule sets the imaging device's parameter adjustment parameters based on the flatness imaging error value. Adjustable parameters for the imaging device include lens focal length, aperture, exposure time, sensor sensitivity, and shooting angle. For areas with large errors, such as where the flatness imaging error value exceeds 150% of the preset range, a larger adjustment is set: the corresponding camera lens focal length is adjusted from 50mm to 70mm, the aperture from f / 8 to f / 5.6, and the exposure time is shortened from 1 / 100s to 1 / 200s. This reduces the error by increasing light intake and improving image sharpness. For areas with low error (i.e., those with error values ​​within 50% of the preset range), fine-tuning is performed, maintaining the focal length at approximately 50mm while fine-tuning the aperture by only ±0.3 and the exposure time by ±1 / 200s. This avoids frequent adjustments that could affect imaging stability. Imaging data and corresponding flatness data are collected under different parameter adjustment schemes. By comparing and analyzing the error improvement effects of different schemes, the parameter set that best matches the current error distribution is selected. For example, the error reduction when the focal length is adjusted to 5mm and 10mm is compared, and the differences in the impact of aperture adjustment on errors under different lighting conditions are analyzed. The screened effective parameters are integrated to generate an imaging adjustment parameter set. This parameter set clearly marks the number of each imaging device, the corresponding control area, the adjustment direction and specific value of each parameter.

[0095] The parameter control submodule applies the adjustment parameters at each imaging device location based on the imaging adjustment parameter set. The adjustment parameters are sent to the corresponding imaging device via the device control system, controlling the lens motor to change the focal length, adjusting the aperture blade opening to set the aperture size, and adjusting the electronic shutter time to determine the exposure duration. Parameter adjustments are performed item by item, and after each parameter adjustment, imaging data and corresponding flatness data are immediately collected to verify the adjustment results. Flatness and imaging are monitored simultaneously using a dual-channel data acquisition card to ensure that the timestamp error between flatness and imaging data does not exceed 10ms. Monitoring includes the deviation between the actual and target values ​​of the adjusted imaging parameters, fluctuations in the real-time flatness values, and trends in imaging error values. The parameter adjustment order for each area is gradually adjusted based on the monitoring results. If the imaging error in a particular area is significantly reduced after adjusting the focal length, aperture adjustment is prioritized for other areas. If new noise interference is detected after adjusting the exposure time for a device, further parameter adjustments are suspended and sensor sensitivity adjustments are made instead. Through multiple rounds of parameter adjustment and monitoring, the flatness imaging error of each area is gradually converged to a reasonable range, and a digital imaging acceptance and control plan for floor flatness is generated. The plan includes the final parameter settings of each imaging device, the order of parameter adjustment, the control priority of different areas, synchronous monitoring data and error change curves, abnormal situation handling records and other imaging adjustment parameters.

[0096] In actual application, for critical areas of aviation composite floors, such as aircraft wheel tracks, the parameter control submodule shortens the monitoring interval to 5 seconds to ensure that parameter adjustments can quickly respond to subtle changes in flatness. For non-critical areas, such as channel edges, the monitoring interval can be extended to 30 seconds to reduce data processing. When encountering sudden environmental changes, such as short bursts of strong light or equipment vibration, the parameter control submodule temporarily activates a backup parameter set, gradually switching back to the regular control plan after the environment stabilizes. This ensures that the imaging equipment is always in optimal working condition throughout the acceptance process. The generated digital imaging acceptance and control plan for floor flatness can accurately reflect the acceptance status of different areas and provide a specific parameter basis for subsequent floor finishing.

[0097] 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," "comprising," 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.

[0098] 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. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring is characterized by: The system comprises: The feature acquisition module analyzes multi-dimensional flatness differences based on floor surface images and structural data, calculates inter-regional deviation differences, integrates them into a feature distribution parameter set, and obtains the feature distribution state value; The imaging parameter calibration module extracts the parameter combination of the imaging device angle and resolution based on the characteristic distribution state value, selects the optimal angle and resolution combination, and obtains the imaging calibration parameter set; The environmental adaptation adjustment module extracts the change of the current environmental factors based on the imaging calibration parameter set, analyzes the relationship between the imaging angle and the resolution, matches the environmental factors with the imaging combination, and obtains the environmental adaptation parameter set; The deviation threshold setting module extracts the current flatness change value based on the environmental adaptation parameter set, combines the real-time imaging data, distributes the flatness and imaging, sets a threshold, and applies the threshold to the distribution of regional deviation to obtain a deviation load threshold; The imaging prediction module captures the imaging data of the flatness sampling points based on the deviation load threshold, performs logical inference on the imaging changes of the flatness sampling points in combination with digital imaging logic, analyzes the imaging change trends corresponding to the deviation load, classifies and organizes the imaging change trends based on the inference results, and performs digital imaging logic adjustment and analysis on the classified data in combination with the imaging change information to obtain the imaging distribution prediction value; The acceptance feedback control module analyzes the error between flatness and imaging based on the imaging distribution prediction value and real-time flatness and imaging data, adjusts the imaging equipment parameters based on the error value, and obtains the digital imaging acceptance control plan for floor flatness.

2. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 1 is characterized in that: The characteristic distribution state value includes an image parameter set, a structural parameter set, and a deviation difference parameter set; the imaging calibration parameter set includes a screening angle parameter and a resolution parameter; the environmental adaptation parameter set includes an environmental factor change parameter and an imaging parameter matching parameter; the deviation load threshold includes a flatness change parameter, an imaging matching parameter, and a threshold setting parameter; the imaging distribution prediction value includes an imaging trend analysis parameter and a flatness imaging relationship parameter; and the floor flatness digital imaging acceptance and control plan includes an error analysis parameter and an imaging adjustment parameter.

3. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 1 is characterized in that: The feature acquisition module includes: The data acquisition submodule performs regional collection of image and structure values ​​based on the floor surface image and structure data, locates invalid data, removes abnormal data, and arranges the extracted image and structure values ​​in regional order to generate a regional image structure data set; The difference analysis submodule analyzes the images and structures between regions based on the regional image structure dataset, calculates the regional parameter change ratio, sorts the regional difference values ​​by weight, marks the regions with excessive fluctuation differences, and obtains regional deviation difference data; The distribution integration submodule calls the regional deviation difference values ​​for multi-dimensional aggregation based on the regional deviation difference data, screens the regional deviation numerical differences, classifies them according to the deviation numerical values, and arranges the regional deviation values ​​in order to generate characteristic distribution state values.

4. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 1 is characterized in that: The imaging parameter calibration module includes: The parameter extraction submodule identifies the working status of the imaging device in each area based on the characteristic distribution state value, records the angle and resolution of the device, standardizes the recorded data, organizes the standardized data and classifies them by angle and resolution to generate an imaging parameter data set; The imaging parameter optimization submodule analyzes the angle and resolution values ​​in the data set according to the imaging parameter data set, selects the parameter combination with the high matching degree with the deviation state, adjusts the parameter combination through pattern matching and records the matching results, and generates the parameter combination optimization result; The parameter selection submodule retrieves the parameter combination optimization result, determines the optimal matching angle and resolution combination, adjusts the imaging device control parameters, inputs the control configuration, verifies the stability of the parameter set, and generates an imaging calibration parameter set.

5. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 1 is characterized in that: The environment adaptation adjustment module includes: The environmental factor analysis submodule collects key data, including light, temperature, humidity, and vibration, through environmental monitoring based on the imaging calibration parameter set, performs time series analysis on the data, removes outliers, and partitions the remaining data to obtain environmental factor analysis data; The parameter matching submodule analyzes the environmental factors and the impact of environmental variables on the angle and resolution of the imaging device through the environmental factor analysis data, calculates the degree of influence of each environmental factor change on the parameter adjustment, determines the optimal matching parameter setting based on the impact score, adjusts the parameters cyclically to capture the optimal combination, and obtains the parameter matching results; The response parameter integration submodule selects an angle and resolution combination that matches the current environmental conditions from the parameter docking results, performs parameter adjustment tests, optimizes parameter settings through multiple adjustments and verifications, determines and solidifies the parameters as operating standards, and generates an environmental adaptation parameter set.

6. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 1 is characterized in that: The deviation threshold setting module includes: The flatness extraction submodule locates the flatness change monitoring point based on the environmental adaptation parameter set, extracts the flatness change value in the monitoring area, continuously records the flatness increase and decrease rate, extracts multiple key change nodes corresponding to the change rate, sorts the node values ​​in order, and obtains the current flatness change characteristic value; The imaging matching submodule analyzes the node change value and the real-time imaging data based on the current flatness change characteristic value, performs calibration according to a predetermined matching criterion, calls the matching criterion to perform distribution redistribution within the imaging interval, and obtains a flatness imaging matching structure; The load distribution submodule is based on the flatness imaging matching structure and adopts a digital threshold dynamic adjustment method to measure the distribution of imaging between flatness change nodes, set the upper and lower limits of the node threshold, apply the threshold to the regional deviation value, and distribute it to obtain the deviation load threshold.

7. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 6 is characterized in that: The digital threshold dynamic adjustment method matches the distribution deviation value of the flatness change node, combines the imaging data and flatness height measured by the real-time node, performs dynamic adjustment according to the predetermined weight coefficient, and sets the node threshold lower limit to control the minimum deviation.

8. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 1 is characterized in that: The imaging prediction module includes: The imaging data capture submodule applies a digital imaging logic algorithm based on the deviation load threshold to capture the imaging data of the sampling points, remove outliers and correct errors, store them in layers by intervals, perform logical processing, and generate a logical imaging data set; The deviation load analysis submodule divides the intervals according to the deviation load based on the logical imaging data set, extracts the change trend and fluctuation characteristics, and generates a deviation load and imaging change feature set; The imaging distribution inference submodule adjusts characteristic parameters and calibrates trend data based on the deviation load and the imaging change feature set, extracts distribution intervals, and performs numerical prediction to obtain an imaging distribution prediction value.

9. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 8 is characterized in that: The digital imaging logic algorithm generates a logic imaging data set by calculating the imaging logic value, combining the original imaging value, flatness value and deviation coefficient of the sampling point, and performing weighted integration according to the total number of sampling points.

10. The multi-dimensional flatness digital imaging acceptance system for aviation composite flooring according to claim 1 is characterized in that: The acceptance feedback control module includes: The error analysis submodule extracts real-time flatness and imaging data based on the imaging distribution prediction value, analyzes the real-time imaging value and the prediction value, matches the imaging difference value with the current flatness information, and generates a flatness imaging error value; The parameter adjustment submodule sets the parameter adjustment parameters of the imaging device based on the flatness imaging error value, sets the adjustment range for areas with large errors, and performs fine-tuning on areas with low errors. By comparing the parameter adjustment effects, matching parameter sets are screened and integrated to generate an imaging adjustment parameter set. Based on the imaging adjustment parameter set, the parameter control submodule applies the adjustment parameters at each imaging device position, implements the parameter adjustment operation item by item, monitors the flatness and imaging synchronously, gradually adjusts the parameter adjustment order of each area, and generates a digital imaging acceptance and control plan for floor flatness.

Images