An industrial cr image analysis optimization system

Abstract

The application discloses an industrial CR image analysis optimization system, and belongs to the technical field of industrial nondestructive testing. The system comprises initialization, image acquisition, performance calculation, feedback adjustment, stable operation and data storage modules. The initialization module calibrates initial parameters and configures a hardware environment. The image acquisition module sets exposure parameters, acquires original images and physical parameters. The performance calculation module calculates a system comprehensive performance index based on the data. The feedback adjustment module dynamically adjusts quantum dot density gradient parameters according to the difference between the performance index and a threshold value, and optimizes the noise characteristics of an imaging plate. The application objectively reflects the system state through a multi-parameter comprehensive performance evaluation model, provides a quantitative basis for parameter adjustment, realizes real-time optimization, improves detection efficiency and adaptability by automatically adjusting quantum dot density gradient parameters, monitors the environment and equipment state in real time, dynamically calibrates parameters, and guarantees stable operation and detection precision of the system.

Description

Technical Field

[0001] This invention relates to the field of industrial nondestructive testing technology, and in particular to an industrial CR image analysis and optimization system. Background Technology

[0002] Industrial computer X-ray imaging (CR) is a non-destructive testing technology that combines X-ray inspection technology with computer digital processing. It captures X-ray energy through a reusable imaging plate (IP plate), converts it into digital signals through laser scanning, and then processes it with a computer to generate a visual inspection image. This technology has become a core means of detecting internal defects in materials and ensuring product quality in aerospace, automobile manufacturing, petrochemical and other fields.

[0003] Currently, mainstream industrial CR systems have achieved digital imaging and basic image post-processing functions, but significant technical bottlenecks still exist, making it difficult to meet the modern industrial demand for high-precision, high-efficiency, and high-stability detection.

[0004] The performance evaluation of existing industrial CR systems often uses a single signal-to-noise ratio or spatial resolution index, which is insufficient to reflect the coupling relationship between noise density, hardware throughput, and imaging resolution. This leads to a one-sided judgment of system status. Due to the lack of a comprehensive evaluation system, the judgment of system status is often too one-sided, resulting in parameter adjustments that rely heavily on human experience, are highly subjective, and have a delayed response. It is difficult to make precise adjustments based on the real-time status of the system. In terms of noise control, traditional systems rely on the inherent material properties of the imaging plate, and the quantum dot density is fixed, making it difficult to dynamically adjust the noise attenuation coefficient according to the detection scenario. When facing complex detection objects such as low-contrast defects and thin-walled thick workpieces, the defect identification accuracy is low. These problems not only increase maintenance costs but also make it difficult to maintain stable detection accuracy, seriously affecting the efficiency and reliability of industrial inspection. Summary of the Invention

[0005] To address the issues of one-sided performance evaluation and lagging parameter adjustment mentioned in the background, we propose an industrial CR image analysis and optimization system.

[0006] The technical solution mainly consists of: an industrial CR image analysis and optimization system, including:

[0007] The initialization module is used to calibrate the initial parameters of the imaging plate, configure the hardware working environment, and establish a system performance evaluation benchmark.

[0008] The image acquisition module is used to control the exposure of the X-ray source and read the imaging plate data to obtain raw image information and physical parameters;

[0009] The performance calculation module calculates the equivalent noise quantum number, processing throughput, and overall system performance index based on the acquired parameters to evaluate the current imaging quality.

[0010] The feedback adjustment module dynamically adjusts the quantum dot density gradient parameters based on the difference between the performance index and the threshold, thereby optimizing the noise characteristics of the imaging plate.

[0011] The stable operation module monitors the system status in real time and dynamically calibrates parameters to ensure long-term detection accuracy.

[0012] The data storage module is used to store system operation data, image data, and performance evaluation results, providing data support for system optimization.

[0013] Preferably, the initialization module includes:

[0014] The parameter calibration unit is configured to measure the initial inherent noise density of the imaging plate, calculate the initial noise reference value by taking the square root of the sum of the squares of dark current noise, readout noise and quantum noise, and output the result to the performance calculation module and the feedback adjustment module.

[0015] The hardware configuration unit is configured to read parameters such as the FPGA clock frequency and data bus width, configure the initial operating mode, and output the configuration to the performance calculation module.

[0016] The environmental preparation unit is configured to control the temperature and humidity of the detection environment to a preset range, and output the controlled temperature and humidity parameters, as well as the preheating status information of the X-ray source and scanner, to the stable operation module.

[0017] Preferably, the image acquisition module includes:

[0018] The exposure control unit is configured to set the exposure time parameters according to the material and thickness of the object being inspected, start the X-ray source to complete the exposure, and output the set exposure time parameters to the performance calculation module;

[0019] The data reading unit is configured to read the latent image information of the imaging plate through a scanner, convert it into a digital signal, and measure the incident X-ray signal-to-noise ratio, the output image signal-to-noise ratio, and the spatial resolution. The read digital signal, the measured incident X-ray signal-to-noise ratio, the output image signal-to-noise ratio, and the spatial resolution data are then output to the performance calculation module and the feedback adjustment module.

[0020] The raw data storage unit is configured to save the raw image data and acquisition parameters, and output them to the data storage module for subsequent performance calculation and analysis.

[0021] Preferably, the performance calculation module includes:

[0022] The noise quantum number calculation unit is configured to calculate the equivalent noise quantum number based on the incident X-ray signal-to-noise ratio, the output image signal-to-noise ratio, and the calibration coefficient, by the square ratio of the output signal-to-noise ratio to the input signal-to-noise ratio, and output the result to the throughput calculation unit and the comprehensive performance evaluation unit.

[0023] The throughput calculation unit is configured to calculate the real-time processing throughput based on the FPGA clock frequency, data bus width, and single-pixel processing cycle, combined with the hardware efficiency coefficient.

[0024] The comprehensive performance evaluation unit is configured to generate a comprehensive system performance index through the coupled calculation of the real-time processing throughput, spatial resolution and noise density, and compare it with a preset threshold. When the comprehensive system performance index fails to meet the standard, the comprehensive system performance index is output to the feedback adjustment module to provide a performance evaluation basis for parameter adjustment and system status monitoring.

[0025] Preferably, the comprehensive performance evaluation unit specifically comprises:

[0026] The effective resolution is calculated by the difference between the spatial resolution and the resolution loss caused by noise. Combined with the real-time processing throughput, effective resolution, and exposure time, a system comprehensive performance index is generated through normalization.

[0027] Preferably, the feedback adjustment module includes:

[0028] The noise difference calculation unit is configured to obtain the current noise density and the target noise density, calculate the noise density difference through the difference, and output the noise density difference to the gradient adjustment unit;

[0029] The gradient adjustment unit is configured to calculate the adjustment amount of the quantum dot density gradient based on the noise difference, the reference quantum dot density, and the noise attenuation coefficient, and output the quantum dot density gradient adjustment amount to the parameter update unit.

[0030] The parameter update unit is configured to dynamically adjust the quantum dot distribution of the imaging plate, remeasure the noise density and update the system parameters. It outputs the adjusted quantum dot distribution parameters of the imaging plate and the remeasured noise density data to the image acquisition module and the stable operation module, providing optimized parameters for the next image acquisition and system status monitoring.

[0031] If the recalculated system performance index is still less than the threshold, the feedback adjustment module continues to adjust the quantum dot density gradient parameter until the system performance index is greater than the threshold, the change in quantum dot density gradient has reached the physical limit of the imaging plate, or the change in noise density is less than the set threshold after three consecutive adjustments, at which point the module stops operating.

[0032] Preferably, the gradient adjustment unit specifically comprises:

[0033] Obtain the initial intrinsic noise density, target noise density, scaling factor, and initial quantum dot density, and calculate the noise attenuation coefficient.

[0034] By combining the noise attenuation coefficient, the scaling factor, the initial quantum dot density, the target noise density, and the current noise density, the amount of quantum dot density gradient change required to achieve the target noise is calculated.

[0035] Preferably, the stable operation module includes:

[0036] The status monitoring unit is configured to collect environmental parameters, equipment load and performance index in real time, record parameter drift trends, and output the collected parameters to the dynamic calibration unit and the periodic maintenance unit.

[0037] The dynamic calibration unit is configured to automatically compensate for the noise attenuation coefficient and quantum dot density parameters when the ambient temperature or humidity changes beyond a threshold, and output the calibrated noise attenuation coefficient and quantum dot density parameters to the initialization module and the feedback adjustment module.

[0038] The periodic maintenance unit is configured to periodically calibrate parameters, test imaging plate performance, generate maintenance reports, and output the maintenance reports to the data storage module to provide maintenance data support for system optimization and performance analysis.

[0039] Specifically, the dynamic calibration unit is:

[0040] When the ambient temperature change exceeds a certain range, the noise attenuation coefficient is automatically adjusted. When the noise density drift of the imaging plate exceeds a certain proportion, the feedback adjustment module is triggered to recalculate the quantum dot density gradient adjustment amount.

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] In this invention, a multi-parameter comprehensive performance evaluation model covering throughput, spatial resolution, and noise density is established. The performance calculation module reflects the system noise characteristics through the equivalent noise quantum number and reflects the hardware processing capability through real-time throughput processing. Finally, a comprehensive system performance index is generated, which more comprehensively and objectively reflects the system state and provides a quantitative basis for parameter adjustment. When the performance index is lower than the threshold, a feedback adjustment mechanism is automatically triggered to achieve real-time optimization of system performance, avoiding the subjectivity and lag of traditional manual experience judgment.

[0043] In this invention, the gradient adjustment unit calculates the quantum dot density gradient adjustment amount based on the noise difference, the reference quantum dot density, and the noise attenuation coefficient. The parameter update unit automatically adjusts the quantum dot distribution on the imaging plate, which greatly improves the accuracy of defect detection. At the same time, the parameter adjustment time is significantly shortened, the detection efficiency is significantly improved, and the labor cost and detection cycle are reduced.

[0044] In this invention, the stable operation module monitors environmental parameters, equipment load, and performance index in real time, and records parameter drift trends. When the change in ambient temperature or humidity exceeds the threshold, the noise attenuation coefficient and quantum dot density parameters are automatically compensated. By dynamically adjusting the noise attenuation coefficient, the noise reduction is automatically enhanced in high-noise environments to ensure that tiny defects are clearly visible. In low-noise scenarios, the attenuation coefficient is automatically reduced to avoid signal loss caused by excessive noise reduction. When the noise density drift exceeds the preset value, the feedback adjustment module is triggered to recalculate the adjustment amount, thus achieving the optimal balance between imaging quality and detection efficiency in different detection scenarios.

[0045] The periodic maintenance unit performs parameter calibration and performance testing on a regular basis, generates maintenance reports and stores them in the data storage module, providing data support for system optimization, significantly improving the long-term operational stability of the system, extending the service life of equipment and reducing maintenance costs.

[0046] In this invention, the modules work closely together. The data storage module comprehensively stores system operation data, image data, and performance evaluation results. This not only provides rich data support for subsequent performance calculation and analysis and facilitates the traceability of the detection process and results, but also provides a basis for further system optimization through long-term data accumulation, thereby promoting continuous improvement of system performance.

[0047] In this invention, each step, from image acquisition to performance evaluation, parameter adjustment, and system calibration, is automated, reducing manual intervention and improving detection efficiency. At the same time, the system automatically adjusts parameters based on real-time data through complex algorithms and intelligent decision-making mechanisms, achieving intelligent optimization. This enables the system to quickly adapt to different detection scenarios and objects, enhancing the flexibility and adaptability of detection. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating the overall operation of the present invention.

[0049] Figure 2 This is a flowchart of the stable operation module in this invention. Detailed Implementation

[0050] The present invention will now be described in further detail with reference to the accompanying drawings and preferred embodiments.

[0051] Example 1, refer to Figure 1-2As shown, an industrial CR image analysis and optimization system includes an initialization module, an image acquisition module, a performance calculation module, a feedback adjustment module, a stable operation module, and a data storage module.

[0052] The initialization module includes a parameter calibration unit, a hardware configuration unit, and an environment preparation unit. First, the parameter calibration unit measures the initial noise density of the imaging plate. Then, the initial noise baseline value is calculated by taking the square root of the sum of the squares of dark current noise, readout noise, and quantum noise. The specific calculation formula is as follows:

[0053] ;

[0054] In the formula, N d0 N represents the initial inherent noise density, indicating the noise baseline value of the imaging plate without any parameter adjustments. da For dark current noise, N re To read noise, N q Quantum noise, all measured by the parameter calibration unit;

[0055] Furthermore, the hardware configuration unit reads hardware parameters such as FPGA clock frequency and data bus width, configures initial operating parameters, and outputs these parameters to the performance calculation module. The environment preparation unit places the imaging plate in a standard detection environment to ensure that environmental parameters such as temperature and humidity are stable, preheats the X-ray source and scanner to bring them to working status, and outputs the controlled detection environment temperature and humidity parameters, as well as the preheating status information of the X-ray source and scanner, to the stable operation module.

[0056] In this embodiment, the accurate measurement by the parameter calibration unit establishes an accurate performance evaluation benchmark for the system, the hardware configuration unit configures hardware parameters reasonably to ensure efficient operation of edge computing, and the environment preparation unit provides a stable detection environment for the system. Through these steps, the system achieves accurate initialization, laying a solid foundation for subsequent image acquisition and performance evaluation, and improving the detection accuracy and stability of the system.

[0057] Example 2, refer to Figure 1-2 As shown, the image acquisition module includes an exposure control unit, a data reading unit, and a raw data storage unit. The exposure control unit sets an appropriate exposure time according to the material and thickness of the object being detected, starts the X-ray source to expose the object being detected, and the imaging plate receives X-ray photons.

[0058] The data reading unit reads the latent image information on the imaging plate through the scanner, converts it into a digital signal, and measures the incident X-ray signal-to-noise ratio, output image signal-to-noise ratio, and spatial resolution. It then outputs the read digital signal, incident X-ray signal-to-noise ratio, output image signal-to-noise ratio, and spatial resolution to the performance calculation module and the feedback adjustment module, providing a reliable data foundation for performance calculation. At the same time, it saves the original image data and acquisition parameters to the original data storage unit and outputs them to the data storage module.

[0059] By setting appropriate parameters for the exposure control unit, clear image data is ensured, and the data reading unit accurately reads and measures key parameters, providing a reliable data foundation for performance calculations.

[0060] Example 3, referring to Figure 1-2 As shown, the performance calculation module receives data output from the initialization module and the image acquisition module, and calculates the equivalent noise quantum number through the noise quantum number calculation unit. The specific calculation formula is as follows:

[0061] ;

[0062] In the formula, N eq K is the equivalent noise quantum number, reflecting the noise characteristics of the imaging plate. cal The noise characteristic calibration coefficients for the imaging plate as specified at the factory, SNR out The signal-to-noise ratio (SNR) of the digital image output by the acquired imaging plate. in The signal-to-noise ratio of the incident X-rays collected;

[0063] In this embodiment, the calculated equivalent noise quantum number N eq Then, the throughput calculation unit combines the equivalent noise quantum number N eq The real-time processing throughput is calculated based on parameters such as FPGA clock frequency and data bus width. The calculation process is as follows:

[0064] First, perform a theoretical maximum throughput T. hl Calculation:

[0065] ;

[0066] Secondly, calculate the hardware efficiency coefficient η:

[0067] ;

[0068] Finally, combining the theoretical maximum throughput T hl Calculate the real-time processing throughput T using the hardware efficiency coefficient η. h :

[0069] T h =η×T hl ;

[0070] In the formula, T h To process throughput in real time and reflect the system's processing capacity, T hl This represents the theoretical maximum throughput.

[0071] At the theoretical maximum throughput T hl In the calculation formula, f c W is the FPGA clock frequency. b C is the data bus width. p The processing cycle is per pixel and is determined by the hardware design.

[0072] In the formula for calculating the hardware efficiency coefficient η, T hs The actual throughput is obtained through actual measurement;

[0073] In this embodiment, after calculating the real-time processing throughput T h Then, the throughput T will be processed in real time. h Parameters such as spatial resolution and noise density are normalized using the max-min normalization method and converted to the International System of Units (SI). The comprehensive performance evaluation unit then calculates the system's comprehensive performance index based on the normalized parameters. The specific calculation formula is as follows:

[0074] ;

[0075] ;

[0076] In the formula, P s S is the overall system performance index. r For spatial resolution, S n N represents the resolution loss caused by noise. d t represents the current noise density collected. e Exposure time;

[0077] At the resolution loss S n In the calculation formula, N eq The calculated equivalent noise quantum number;

[0078] The calculated system comprehensive performance index P s Compared with a preset threshold, when the system's overall performance index P... s When the value is less than the threshold, a feedback adjustment mechanism is triggered;

[0079] In this embodiment, the performance calculation module comprehensively evaluates the system's noise characteristics, processing capabilities, and overall performance through precise formula calculations. These steps enable efficient imaging of the detected object and accurate evaluation of system performance, providing a basis for subsequent feedback adjustment and stable operation, thereby improving the system's detection efficiency and accuracy.

[0080] Example 4, refer to Figure 1-2 As shown, the feedback adjustment module includes three units: noise difference calculation, gradient adjustment, and parameter update. First, the noise difference calculation unit obtains the current noise density N. d and target noise density N dm The noise density difference ΔN is calculated by the difference. d The details are as follows:

[0081] △N d =N dm -N d ;

[0082] In the above implementation scheme, △N d This is a noise density difference measure, reflecting the gap between the current noise density and the target noise density. The larger the value, the greater the adjustment required.

[0083] Furthermore, the gradient adjustment unit calculates the adjustment amount of the quantum dot density gradient based on the noise difference, the reference quantum dot density, and the noise attenuation coefficient. The specific calculation steps are as follows:

[0084] First, calculate the noise attenuation coefficient α:

[0085] ;

[0086] Then, the quantum dot density gradient adjustment amount Δρ is calculated:

[0087] ;

[0088] In the formula, Δρ is the quantum dot density gradient adjustment amount, representing the change in quantum dot density gradient that needs to be adjusted; k is a proportionality coefficient used to adjust the magnitude of the quantum dot density gradient adjustment amount Δρ, the value of k is determined by experimental debugging; ρ0 is the initial quantum dot density, obtained through experimental measurement; d is the depth or distance of the quantum dot (depending on the actual experimental scenario and measurement method), obtained through experimental measurement; N d0 N is the initial intrinsic noise density. d Given the current noise density, and N d0 >N d N dm Target noise density;

[0089] Furthermore, α is the noise attenuation coefficient, which is the core parameter for quantizing the noise suppression capability of quantum dots in the imaging plate. It reflects the noise attenuation efficiency of the quantum dot density gradient change. At the same time, when the noise attenuation coefficient α is calculated for the first time, the value of Δρ is set by empirical value (determined according to the material and model of the imaging plate) or obtained by experimental measurement. In subsequent feedback adjustment loops, it is calculated by the gradient adjustment formula of the previous loop. Through feedback adjustment loops, the values ​​of Δρ and α are continuously updated, so that the system performance is gradually optimized and finally meets the requirements.

[0090] The parameter update unit receives the calculated quantum dot density gradient adjustment Δρ and dynamically adjusts the spatial distribution density of quantum dots on the imaging plate through methods such as electric field manipulation, optical manipulation, or chemical manipulation. This changes the noise attenuation coefficient α, ultimately reducing the system noise density N. d Approaching the target value N dm Remeasure the noise density N d The system parameters are updated, and the adjusted quantum dot distribution parameters of the imaging plate, as well as the remeasured noise density data, are output to the image acquisition module and the stable operation module.

[0091] The image acquisition module reacquires image data, and the performance calculation module recalculates N. eq T h and P s If the calculated P s If the value is still less than the threshold, the feedback adjustment module repeats the above process, continuously adjusting the quantum dot density gradient parameter until P... s The system will stop operating when the value exceeds the threshold, the quantum dot density gradient change reaches the physical limit of the imaging plate, or the noise density change is less than the set threshold after three consecutive adjustments.

[0092] In this embodiment, the accurate calculation by the noise difference calculation unit provides a clear direction for parameter adjustment. The gradient adjustment unit determines the adjustment amount of the quantum dot density gradient through precise formula calculation. The parameter update unit optimizes the system parameters through actual adjustment and remeasurement. Through these steps, the dynamic optimization of system performance is achieved, improving imaging quality and detection accuracy, and enabling the system to adapt to different detection needs and environmental changes.

[0093] Example 5, refer to Figure 1-2 As shown, the stable operation module includes three units: condition monitoring, dynamic calibration, and periodic maintenance. First, the condition monitoring unit collects environmental parameters (such as temperature and humidity), equipment load, and the system's overall performance index P in real time. s It records parameter drift trends and outputs the collected parameters to the dynamic calibration unit and the periodic maintenance unit;

[0094] Furthermore, when the dynamic calibration unit detects that the ambient temperature change exceeds the threshold, it automatically adjusts the noise attenuation coefficient α. If the temperature rises, leading to an increase in thermal noise of the imaging plate, the noise attenuation coefficient α is increased to enhance the noise suppression capability of the quantum dots and offset the additional noise caused by the temperature rise. When the temperature decreases, the system thermal noise decreases, and the noise attenuation coefficient α is reduced to avoid signal loss caused by excessive noise reduction and maintain the balance between imaging sensitivity and noise control. The adjusted noise attenuation coefficient α is synchronously output to the initialization module and the feedback adjustment module to update the system parameter benchmark and provide a basis for subsequent performance calculation and quantum dot density gradient adjustment.

[0095] When the noise density drift of the imaging plate is detected to exceed the preset value, the feedback adjustment module is triggered to recalculate the quantum dot density gradient adjustment amount Δρ, and the calibrated noise attenuation coefficient and quantum dot density parameters are output to the initialization module and the feedback adjustment module.

[0096] The periodic maintenance unit performs parameter calibration on a cyclical basis, repeats the parameter calibration process, checks the performance of the imaging board, generates a maintenance report, and outputs the maintenance report to the data storage module to provide a reference for subsequent system maintenance. At the same time, it periodically analyzes system performance data, predicts device lifespan and performance degradation trends, optimizes the feedback adjustment algorithm based on historical data, and improves the system's adaptive capability.

[0097] In this embodiment, the real-time monitoring of the status monitoring unit promptly detects changes in the system status. The dynamic calibration unit automatically adjusts parameters to offset the impact of environmental factors and equipment aging on system performance. The periodic maintenance unit ensures that the system is always in optimal operating condition through periodic parameter calibration and performance testing. Through these steps, the long-term stable operation of the system is achieved, the service life of the equipment is extended, maintenance costs are reduced, and the reliability and adaptability of the system are improved.

[0098] Furthermore, the data storage module stores system operation data (such as exposure time and FPGA clock frequency), image data (such as raw images and digital signals), and performance evaluation results, providing data support for subsequent system optimization.

[0099] It should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should also be within the scope of protection of this invention.

Claims

1. An industrial CR image analysis and optimization system, characterized in that: include: The initialization module is used to calibrate the initial parameters of the imaging plate, configure the hardware working environment, and establish a system performance evaluation benchmark. The image acquisition module is used to control the exposure of the X-ray source and read the imaging plate data to obtain raw image information and physical parameters; The performance calculation module calculates the equivalent noise quantum number, processing throughput, and overall system performance index based on the acquired parameters to evaluate the current imaging quality. The feedback adjustment module dynamically adjusts the quantum dot density gradient parameters based on the difference between the performance index and the threshold, thereby optimizing the noise characteristics of the imaging plate. The stable operation module monitors the system status in real time and dynamically calibrates parameters to ensure long-term detection accuracy. The data storage module is used to store system operation data, image data, and performance evaluation results, providing data support for system optimization.

2. The industrial CR image analysis and optimization system according to claim 1, characterized in that: The initialization module includes: The parameter calibration unit is configured to measure the initial inherent noise density of the imaging plate, calculate the initial noise reference value by taking the square root of the sum of the squares of dark current noise, readout noise and quantum noise, and output the result to the performance calculation module and the feedback adjustment module. The hardware configuration unit is configured to read parameters such as the FPGA clock frequency and data bus width, configure the initial operating mode, and output the configuration to the performance calculation module. The environmental preparation unit is configured to control the temperature and humidity of the detection environment to a preset range, and output the controlled temperature and humidity parameters, as well as the preheating status information of the X-ray source and scanner, to the stable operation module.

3. The industrial CR image analysis and optimization system according to claim 2, characterized in that: The image acquisition module includes: The exposure control unit is configured to set the exposure time parameters according to the material and thickness of the object being inspected, start the X-ray source to complete the exposure, and output the set exposure time parameters to the performance calculation module; The data reading unit is configured to read the latent image information of the imaging plate through a scanner, convert it into a digital signal, and measure the incident X-ray signal-to-noise ratio, the output image signal-to-noise ratio, and the spatial resolution. The read digital signal, the measured incident X-ray signal-to-noise ratio, the output image signal-to-noise ratio, and the spatial resolution data are then output to the performance calculation module and the feedback adjustment module. The raw data storage unit is configured to save the raw image data and acquisition parameters, and output them to the data storage module for subsequent performance calculation and analysis.

4. The industrial CR image analysis and optimization system according to claim 3, characterized in that: The performance calculation module includes: The noise quantum number calculation unit is configured to calculate the equivalent noise quantum number based on the incident X-ray signal-to-noise ratio, the output image signal-to-noise ratio, and the calibration coefficient, by the square ratio of the output signal-to-noise ratio to the input signal-to-noise ratio, and output the result to the throughput calculation unit and the comprehensive performance evaluation unit. The throughput calculation unit is configured to calculate the real-time processing throughput based on the FPGA clock frequency, data bus width, and single-pixel processing cycle, combined with the hardware efficiency coefficient. The comprehensive performance evaluation unit is configured to generate a comprehensive system performance index through the coupled calculation of the real-time processing throughput, spatial resolution and noise density, and compare it with a preset threshold. When the comprehensive system performance index fails to meet the standard, the comprehensive system performance index is output to the feedback adjustment module to provide a performance evaluation basis for parameter adjustment and system status monitoring.

5. The industrial CR image analysis and optimization system according to claim 4, characterized in that: The comprehensive performance evaluation unit is specifically: The effective resolution is calculated by the difference between the spatial resolution and the resolution loss caused by noise. Combined with the real-time processing throughput, effective resolution, and exposure time, a system comprehensive performance index is generated through normalization.

6. The industrial CR image analysis and optimization system according to claim 5, characterized in that: The feedback adjustment module includes: The noise difference calculation unit is configured to obtain the current noise density and the target noise density, calculate the noise density difference through the difference, and output the noise density difference to the gradient adjustment unit; The gradient adjustment unit is configured to calculate the adjustment amount of the quantum dot density gradient based on the noise difference, the reference quantum dot density, and the noise attenuation coefficient, and output the quantum dot density gradient adjustment amount to the parameter update unit. The parameter update unit is configured to dynamically adjust the quantum dot distribution of the imaging plate, remeasure the noise density and update the system parameters. It outputs the adjusted quantum dot distribution parameters of the imaging plate and the remeasured noise density data to the image acquisition module and the stable operation module, providing optimized parameters for the next image acquisition and system status monitoring. If the recalculated system performance index is still less than the threshold, the feedback adjustment module continues to adjust the quantum dot density gradient parameter until the system performance index is greater than the threshold, the change in quantum dot density gradient has reached the physical limit of the imaging plate, or the change in noise density is less than the set threshold after three consecutive adjustments, at which point the module stops operating.

7. The industrial CR image analysis and optimization system according to claim 6, characterized in that: The gradient adjustment unit is specifically: Obtain the initial intrinsic noise density, target noise density, scaling factor, and initial quantum dot density, and calculate the noise attenuation coefficient. By combining the noise attenuation coefficient, the scaling factor, the initial quantum dot density, the target noise density, and the current noise density, the amount of quantum dot density gradient change required to achieve the target noise is calculated.

8. The industrial CR image analysis and optimization system according to claim 6, characterized in that: The stable operation module includes: The status monitoring unit is configured to collect environmental parameters, equipment load and performance index in real time, record parameter drift trends, and output the collected parameters to the dynamic calibration unit and the periodic maintenance unit. The dynamic calibration unit is configured to automatically compensate for the noise attenuation coefficient and quantum dot density parameters when the ambient temperature or humidity changes beyond a threshold, and output the calibrated noise attenuation coefficient and quantum dot density parameters to the initialization module and the feedback adjustment module. The periodic maintenance unit is configured to periodically calibrate parameters, test imaging plate performance, generate maintenance reports, and output the maintenance reports to the data storage module to provide maintenance data support for system optimization and performance analysis. Specifically, the dynamic calibration unit is: When the ambient temperature change exceeds a certain range, the noise attenuation coefficient is automatically adjusted. When the noise density drift of the imaging plate exceeds a certain proportion, the feedback adjustment module is triggered to recalculate the quantum dot density gradient adjustment amount.

Images