A blow molding detection method and system for wind turbine plastic blade production

Abstract

The present application relates to the technical field of plastic production detection, and particularly relates to a blow molding detection method and system for wind turbine plastic blade production, which comprises the following steps: obtaining profile outer diameter measurement values of a to-be-detected plastic blade at multiple different heights along the vertical direction of the to-be-detected plastic blade; continuously tracking the change trend of the multiple profile outer diameter measurement values during the movement of the to-be-detected plastic blade, and calculating the instantaneous deviation of each profile outer diameter measurement value relative to a recent average value, wherein the recent average value is the average value of recent historical profile outer diameter measurement values of the to-be-detected plastic blade at the corresponding height; judging whether the instantaneous deviations of the multiple profile outer diameter measurement values simultaneously satisfy a preset negative jump threshold value, and whether the mutual difference between the instantaneous deviations is less than a preset difference threshold value; if yes, outputting warning information of measurement deviation offset; this technical solution can effectively solve the measurement deviation problem of a visual detection system caused by local brightness attenuation of an illumination light source or changes in the optical properties of raw materials.

Description

Technical Field

[0001] This invention relates to the field of plastic production testing technology, and in particular to a blow molding testing method and system for the production of plastic blades for wind turbine units. Background Technology

[0002] In the field of wind turbine structure manufacturing, blow molding is a common method for producing large plastic blades (such as hollow blade structures), and precise control of product specifications is crucial to ensuring quality. Therefore, blow molding production lines are typically equipped with vision inspection systems to inspect the dimensions of the molded blades, such as their outer diameter. A typical inspection system includes a ring-shaped LED light strip, which provides uniform illumination to help the camera capture a clear blade outline, laying the foundation for subsequent image processing and dimensional calculations. However, during long-term operation, the performance of electronic components degrades over time. For example, a section of the ring-shaped LED light strip may experience a slow, gradual decrease in brightness due to aging. This subtle change is easily masked by surrounding normal LED sections or does not reach the visual detection threshold, making it difficult to detect during routine inspections. When the wind turbine blade rotates at a constant speed through the inspection area, the dimmed LED section forms weak longitudinal dark stripes on the blade surface. These stripes appear as slight localized reductions in brightness in the camera image, which are initially easily filtered out by the system's noise reduction mechanism and do not cause any abnormalities.

[0003] Visual inspection systems often use fixed brightness thresholds to identify blade outline boundaries to calculate outer diameter. When a blade rotates to a specific angle, if the dark stripes just sweep across the outline boundary area and the brightness is below a preset threshold, the system may mistakenly identify the inner boundary of the dark stripes as the true outline boundary, resulting in a calculated outer diameter that is smaller than the actual size. This misjudgment only occurs at specific angles, causing the system to intermittently and irregularly report dimensional deviation alarms, making diagnosis difficult for technicians and potentially misleading them into suspecting other issues such as camera focusing or ambient lighting. Faced with occasional alarms, technicians usually adjust software parameters (such as increasing image contrast) to optimize image quality and enhance blade outline clarity. However, this operation also amplifies the brightness difference of the dark stripes, making them more prominent, causing the system to frequently trigger false alarms when the blade rotates to a specific angle, leading to frequent production line shutdowns. To quickly restore production, technicians often artificially relax the lower limit of the acceptable outer diameter tolerance, allowing the smaller measurement value to fall within the tolerance range and temporarily avoiding alarms.

[0004] However, the aging process of the light source that initially caused the problem continues. Weeks or months later, the brightness of that LED strip will further decrease, causing the dark stripes it creates in the image to become wider and darker. At this point, the visual inspection system's misjudgment of the blade's outer diameter is no longer intermittent, but rather forms a persistent dimensional calculation bias; that is, the measurement result of all inspected products is consistently smaller than the actual value by a fixed amount. Because the tolerance range had been relaxed previously, even with this persistent measurement bias, the system appears to be functioning normally, no longer issuing any alarms, giving the false impression that the inspection system is operating stably.

[0005] Meanwhile, upstream blow molding processes may experience production fluctuations due to mold wear, raw material variations, etc., resulting in products whose actual dimensions are near the lower limit of the original tolerance. These blades are already smaller than expected, and when combined with the continuous calculation errors caused by light source aging and parameter misadjustment within the vision inspection system, the final measurement result will appear even smaller. However, because the lower limit of the acceptable tolerance of the inspection system has been artificially relaxed by technicians, even after being "reduced" by the system, the measured value of these products still "appears" to fall within the relaxed acceptable range, thus being incorrectly judged as "acceptable" and released by the system.

[0006] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0007] The purpose of this invention is to address the shortcomings of existing technologies by proposing a blow molding inspection method and system for the production of plastic blades for wind turbine units.

[0008] In a first aspect, the present invention provides a blow molding inspection method for the production of plastic blades for wind turbine generators, the method comprising the following steps:

[0009] Obtain the measured outer diameter of the plastic blade under test at multiple different heights along its vertical direction;

[0010] The changing trends of multiple profile outer diameter measurements are continuously tracked during the movement of the plastic blade under test, and the instantaneous deviation of each profile outer diameter measurement relative to the recent average value is calculated. The recent average value is the mean of the recent historical profile outer diameter measurements of the plastic blade under test at the corresponding height.

[0011] Determine whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the mutual differences between the instantaneous deviations are less than a preset difference threshold;

[0012] If the conditions are met, a warning message indicating measurement offset will be output.

[0013] Secondly, a blow molding inspection system for the production of plastic blades for wind turbine generators is provided, the system comprising:

[0014] The acquisition module is used to acquire the measured outer diameter of the plastic blade under test at multiple different heights along its vertical direction.

[0015] The tracking and calculation module is used to continuously track the changing trend of multiple profile outer diameter measurements during the movement of the plastic blade under test, and calculate the instantaneous deviation of each profile outer diameter measurement relative to the recent average value, wherein the recent average value is the mean of the recent historical profile outer diameter measurements of the plastic blade under test at the corresponding height.

[0016] The judgment module is used to determine whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the mutual difference between the instantaneous deviations is less than a preset difference threshold.

[0017] The warning module is used to output a warning message indicating a deviation in the measurement basis if the conditions are met.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] By acquiring the outer diameter measurements of the plastic blade under test at multiple different heights and continuously tracking the changing trends of these measurements, the instantaneous deviation relative to the recent average value is calculated. When multiple instantaneous deviations simultaneously meet a preset negative jump threshold and their differences are less than a preset difference threshold, the system outputs a warning message indicating a measurement deviation. This technical solution effectively solves the measurement deviation problem in existing visual inspection systems caused by local brightness attenuation of the lighting source or changes in the optical properties of the raw materials. Attached Figure Description

[0020] Figure 1 This is a flowchart of the method of the present invention.

[0021] Figure 2 This is a schematic diagram of the system structure of the present invention.

[0022] In the diagram: 201, Acquisition Module; 202, Tracking and Calculation Module; 203, Judgment Module; 204, Warning Module. Detailed Implementation

[0023] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0024] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] This application provides a method for effectively identifying and alerting to measurement deviations in a blow molding inspection system, thereby avoiding inspection errors caused by light source aging or changes in raw material characteristics and ensuring product quality. To better understand the blow molding inspection method proposed in this application, the following will elaborate on some key terms and implementation environments. "Outer diameter measurement value" refers to the data reflecting the external dimensions of the product obtained after image acquisition and processing of the plastic blade using a vision inspection system. These measurements are typically acquired at multiple preset heights along the vertical direction of the product to comprehensively reflect its overall dimensional characteristics. For example, an industrial camera combined with image processing algorithms can be used to identify the product's edges in the image and calculate the diameter or width at the corresponding height. "Recent average value" refers to the arithmetic mean of the recent historical outer diameter measurements of the plastic blade under test at a specific height. This average value serves as a benchmark for assessing the fluctuation of the current measurement value. For example, a time window or product quantity window can be set, and the outer diameter measurements at the corresponding heights of all qualified products within that window can be averaged to obtain the recent average value at that height. "Instantaneous deviation" refers to the difference between the currently acquired outer diameter measurement value and the corresponding recent average value. This deviation reflects the immediate change in the current product size relative to the historical average. For example, if the current measurement is D and the recent average is D_avg, then the instantaneous deviation is D - D_avg. The "negative jump threshold" is a preset negative value used to determine whether the instantaneous deviation has experienced a significant negative shift. When the instantaneous deviation is less than or equal to this negative jump threshold, it indicates a significant decrease in the measured value. For example, a negative jump threshold, such as -0.5mm, can be set based on historical data and experience, meaning that a negative jump is considered to have occurred when the measured value is 0.5mm or more smaller than the recent average. The "difference threshold" is a preset positive value used to determine whether the differences between the instantaneous deviations of multiple profile outer diameter measurements are within an acceptable range. When the maximum difference between these instantaneous deviations is less than or equal to the difference threshold, it indicates that these deviations are consistent and may originate from a systematic shift in measurement basis. For example, a difference threshold, such as 0.1mm, can be set, meaning that when the maximum difference between instantaneous deviations at different heights does not exceed 0.1mm, these deviations are considered to have occurred synchronously.

[0026] The implementation environment of this application typically includes a plastic blade production line with a vision inspection station. This station is equipped with an industrial camera, a lighting source (such as a ring-shaped LED light strip), and a computer system for data processing and analysis. The plastic blade to be tested moves at a constant speed on the production line and passes through the inspection station, where the camera captures images, leading to dimensional measurements. The core principle is to continuously track and analyze the measured outer diameter of the plastic blade profile to promptly detect and alert to deviations in the measurement data.

[0027] like Figure 1 The method shown is a blow molding inspection method for use in the production of plastic blades for wind turbine generators. The method includes the following steps:

[0028] S101. Obtain the measured outer diameter of the plastic blade under test at multiple different heights along its vertical direction.

[0029] It should be noted that this step can be achieved in several ways. For example, a high-resolution industrial camera can be used to acquire images of the plastic blades, and image processing algorithms, such as edge detection and sub-pixel positioning, can be used to accurately identify the contour boundaries of the product at different heights, thereby calculating the corresponding outer diameter. Another method is to use a laser rangefinder array to acquire distance data at multiple heights in real time as the product passes by, and convert this data into a contour outer diameter measurement. Alternatively, contact-type measuring devices, such as multi-point displacement sensors, can be used to acquire dimensional data at multiple points through mechanical contact as the product passes by, and then calculate the contour outer diameter.

[0030] S102. Continuously track the changing trend of multiple profile outer diameter measurements during the movement of the plastic blade under test, and calculate the instantaneous deviation of each profile outer diameter measurement relative to the recent average value. The recent average value is the mean of the recent historical profile outer diameter measurements of the plastic blade under test at the corresponding height.

[0031] It should be noted that, in this step described above, for example, the system can maintain a sliding window to store the outer diameter measurements at the corresponding height of the N most recent qualified products, and calculate their average value in real time as the recent average. When a new measurement value arrives, it is compared with this recent average to obtain the instantaneous deviation. This method of continuously tracking and calculating instantaneous deviation can reflect the current dimensional fluctuations of the product in real time.

[0032] S103. Determine whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet the preset negative jump threshold, and whether the mutual difference between the instantaneous deviations is less than the preset difference threshold.

[0033] It should be noted that in this step, for example, the system can set a negative jump threshold, such as -0.5mm, and a difference threshold, such as 0.1mm. The judgment condition is considered met when the instantaneous deviations at all measured heights are less than or equal to -0.5mm, and the difference between the maximum and minimum values ​​of these instantaneous deviations does not exceed 0.1mm. This judgment mechanism aims to identify a specific abnormal pattern: that is, the measured values ​​at multiple heights simultaneously and synchronously show negative shifts, and the shift amounts are highly consistent. This pattern usually indicates a systematic shift in the measurement basis, rather than a dimensional fluctuation in the product itself.

[0034] S104. If satisfied, output a warning message indicating measurement basis offset.

[0035] It should be noted that such warning messages can be presented in various forms, such as displaying a prominent warning on the operating interface, issuing an alarm via an audible and visual alarm, sending an anomaly notification to the production management system, or notifying relevant technical personnel via SMS / email. The purpose of outputting warning messages is to promptly remind operators or maintenance personnel that the detection system may have potential measurement errors and requires further inspection and calibration to prevent unqualified products from being mistakenly released.

[0036] This application proposes a blow molding inspection method for wind turbine plastic blade production. By introducing a synchronous judgment mechanism for the instantaneous deviation of multiple contour outer diameter measurements, it effectively solves the problem of measurement basis deviation caused by light source aging or changes in the optical properties of raw materials in existing technologies. Traditional blow molding inspection methods typically rely on a single dimensional deviation judgment; that is, the system only issues an alarm when a certain dimensional measurement of the product exceeds a preset acceptable range. However, this method has significant limitations when faced with localized brightness decay of the light source or changes in the optical properties of the raw materials. For example, when the local brightness of the ring-shaped LED light strip slowly decays, the faint dark areas and stripes formed on the product surface may cause the vision system to misidentify the edge of the dark area inside the bottle as the contour boundary, thus calculating an outer diameter smaller than the actual value. This deviation may not be obvious initially, or may only appear at specific angles, leading to sporadic alarms that are difficult to diagnose. More seriously, when technicians artificially relax the tolerance lower limit to cope with frequent alarms, this continuous measurement deviation will cause unqualified products to be wrongly released, while the system appears "normal" and fails to issue an alarm.

[0037] This application overcomes these limitations in the following ways: First, it doesn't just focus on the deviation of a single measurement value, but acquires the outer diameter measurements of the plastic blade under test at multiple different heights along its vertical direction, thus obtaining more comprehensive dimensional information. Second, this application continuously tracks the changing trends of these measurements during product movement and calculates the instantaneous deviation of each measurement value relative to the recent average. This dynamic benchmark based on historical data allows the system to more sensitively capture subtle changes in the measurements. Most importantly, this application introduces a judgment on whether the instantaneous deviations of multiple outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the difference between the instantaneous deviations is less than a preset difference threshold. This synchronous and consistent negative jump pattern is a typical manifestation of measurement basis deviation caused by light source aging or changes in the optical properties of raw materials. When this pattern is identified, the system immediately outputs a warning message about the measurement basis deviation, thus issuing an early warning in the early stages of the problem and avoiding the risk of problems being masked and accumulated in traditional methods.

[0038] As one embodiment of the present invention, the step of determining whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the mutual difference between the instantaneous deviations is less than a preset difference threshold, includes:

[0039] Determine whether the instantaneous deviations of multiple outer diameter measurements simultaneously meet the preset negative jump threshold, and whether the mutual difference between the instantaneous deviations is less than the preset difference threshold.

[0040] If the conditions are met, the cause of the instantaneous deviation is identified, and a warning message and the cause of the measurement deviation are output. The cause of the instantaneous deviation is identified as follows: acquiring the background illumination image when there is no plastic leaf to be measured in the detection area.

[0041] Analyze the brightness distribution of the background illumination image based on the background illumination image;

[0042] Acquire an image of the plastic blade to be tested within the detection area, perform background correction on the image, and identify optical artifacts in the corrected image of the plastic blade to be tested.

[0043] Based on the brightness distribution and optical artifacts of the background illumination image, the causes of instantaneous deviations can be distinguished. These causes include local brightness decay of the illumination source and optical properties of the raw materials.

[0044] Specifically, when the system determines that the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and the mutual difference between the instantaneous deviations is less than a preset difference threshold, it is considered that there is a measurement basis offset. At this time, in order to provide more accurate diagnostic information, the system will initiate a cause differentiation process. This process first acquires a background illumination image when there is no plastic blade to be tested in the detection area. This image is used to establish a benchmark to evaluate the uniformity and stability of the illumination source. Subsequently, based on the acquired background illumination image, the brightness distribution of the background illumination image is analyzed. For example, it can detect whether there are areas that are too dark or too bright, or whether the brightness distribution is uniform. At the same time, the system acquires an image containing the plastic blade to be tested within the detection area and performs background correction on the image of the plastic blade to be tested to eliminate the influence of uneven background illumination on the product image, thereby extracting product features more accurately. In the corrected image of the plastic blade under test, the system identifies the presence of optical artifacts. These artifacts may manifest as abnormal light spots, streaks, or blurred areas within or around the product's outline. They are not physical defects in the product itself, but rather caused by optical phenomena such as scattering, refraction, or absorption of light as it propagates through the product material. Finally, the system comprehensively analyzes the brightness distribution characteristics of the background illumination image and the identified optical artifacts to determine the specific causes of the instantaneous deviation. These causes may include localized brightness attenuation of the lighting source, such as insufficient light in certain areas due to aging or damage to a lighting fixture; or changes in the optical properties of the raw materials, such as variations in the optical transparency, refractive index, or internal uniformity of different batches of raw materials.

[0045] This application's solution addresses the problem of only outputting general warning information without pinpointing the specific fault source by introducing a mechanism to differentiate the causes of instantaneous deviations. Specifically, by acquiring and analyzing background illumination images without the plastic blade under test, a benchmark can be established to evaluate the stability and uniformity of the lighting source. When local brightness decay occurs in the lighting source, the brightness distribution of the background illumination image will exhibit corresponding anomalies, such as local darkening or unevenness. Simultaneously, by performing background correction on the image containing the plastic blade under test and identifying optical artifacts, visual anomalies caused by the optical properties of the raw material itself (such as transparency, refractive index, internal impurities, etc.) can be effectively distinguished from lighting problems. For example, the optical properties of certain raw materials may cause light to scatter or refract within the product, thus forming specific optical artifacts in the image. These artifacts are unrelated to the actual contour of the product but may affect contour measurement. By comprehensively analyzing the brightness distribution of the background illumination image and the optical artifacts in the corrected product image, the system can intelligently determine whether the instantaneous deviation is mainly caused by lighting source problems, changes in the optical properties of the raw material, or a combination of both. This provides a clear basis for subsequent fault diagnosis and handling.

[0046] In some preferred embodiments, a specific example is given below. Assume that on a blow molding production line, a vision inspection system continuously monitors the outer diameter of a plastic blade at multiple heights. When the system detects a significant negative jump in the outer diameter measurements at all heights simultaneously, and the differences between these jump values ​​are small, meeting preset negative jump thresholds and difference thresholds, the system triggers further diagnostic procedures. First, the system acquires a background illumination image of the current detection area when there is no product and analyzes its brightness distribution. If it finds that the brightness of the background illumination image in a specific area is significantly lower than normal, or that there are uneven dark areas, it initially determines that there may be a problem with local brightness attenuation of the lighting source. Simultaneously, the system acquires an image of the plastic blade currently being tested and performs background correction to eliminate the influence of uneven illumination. Subsequently, the corrected product image is analyzed to identify whether there are optical artifacts that are not part of the product's outline features, such as abnormal light spots or stripes inside the product, which may indicate optical property problems such as bubbles, impurities, or uneven refractive index within the raw material. By comprehensively comparing the abnormal brightness distribution of the background lighting image with the optical artifact features in the product image, the system can ultimately output clear warning information, such as: "Measurement basis deviation: caused by local brightness attenuation of the lighting source," or "Measurement basis deviation: caused by optical properties of raw materials," or even "Measurement basis deviation: caused by the superposition of local brightness attenuation of the lighting source and optical properties of raw materials." This precise diagnostic information allows maintenance personnel to quickly locate the problem, such as checking and replacing the corresponding lighting fixtures, or tracing and replacing the problematic batch of raw materials, thereby avoiding unnecessary downtime and resource waste.

[0047] As one embodiment of the present invention, the step of distinguishing the cause of instantaneous deviation based on the brightness distribution of the background illumination image and optical artifacts includes:

[0048] Based on the brightness distribution of the background illumination image, the contribution of local brightness decay of the illumination source to the instantaneous deviation is quantified;

[0049] It should be noted that the above step refers to analyzing the brightness distribution characteristics of the background lighting image, such as brightness non-uniformity, local dark or bright areas, to assess the deviation of the brightness output of the lighting source in a specific area from the ideal state, and converting this deviation into the degree of influence on the instantaneous deviation of the contour outer diameter measurement. This can be achieved by establishing a mathematical model between the brightness of the lighting source and the measurement deviation, for example, by pre-calibrating the impact of different brightness attenuation levels on the measured value, thereby deriving a quantitative index.

[0050] Based on optical artifacts, the contribution of the optical properties of raw materials to instantaneous deviations is quantified;

[0051] It should be noted that the above step can be understood as assessing the degree of interference of the optical properties of the raw material itself (such as transparency, refractive index, surface roughness, etc.) on image acquisition and contour recognition by identifying optical artifacts in the image of the plastic blade under test, such as refraction, reflection, and scattering, and converting them into an impact on instantaneous deviation. This can be quantified by analyzing the intensity, shape, and location of the artifacts, combined with a preset optical model or empirical data.

[0052] Based on the contribution of local brightness attenuation of the lighting source and the contribution of optical properties of the raw materials, determine whether the instantaneous deviation is caused by local brightness attenuation of the lighting source, by optical properties of the raw materials, or by the combination of both.

[0053] It should be noted that the above step refers to making a comprehensive judgment after quantifying the contributions of the two factors separately. For example, a threshold can be set: if the contribution of one factor far exceeds that of the other, it is determined that the fault is caused by that factor; if the contributions of both factors are close and both reach a certain level, it is determined that the fault is caused by the combination of the two factors. This method of determination makes the diagnosis of the cause of the fault more accurate and detailed.

[0054] This application's solution addresses the ambiguity that may exist when only distinguishing the cause type by introducing the quantification of the contribution of local brightness attenuation of the lighting source and the optical properties of raw materials to instantaneous deviations. Specifically, when an instantaneous deviation in the outer diameter measurement is detected, it no longer simply determines whether it originates from the lighting or the raw materials, but rather conducts a deeper analysis. Through a detailed analysis of the brightness distribution of the background lighting image, the attenuation degree of the lighting source in a specific area and its impact on the measurement results can be quantified. Simultaneously, through the identification and analysis of optical artifacts in the product image, the interference of the optical properties of the raw materials on the measurement results can be quantified. Thus, by quantitatively comparing and comprehensively judging these two contribution levels, the dominant factors causing instantaneous deviations can be identified more accurately, and even complex situations caused by the combined effects of multiple factors can be identified. This quantification and determination mechanism elevates fault diagnosis from qualitative judgment to quantitative analysis, providing solid data support for subsequent precise intervention.

[0055] In some preferred embodiments, a specific example is given below. Suppose that during a blow molding inspection, the system detects multiple contour outer diameter measurements simultaneously exhibiting negative jumps with relatively small differences, triggering an alert. According to the solution of this application, the system first acquires an image of the background illumination within the detection area and analyzes its brightness distribution. It finds that the brightness of a specific area is significantly lower than normal. Using a preset model, it calculates that this local brightness attenuation contributes 70% to the instantaneous deviation. Simultaneously, the system acquires an image of the plastic blade under test and identifies obvious refraction artifacts. By analyzing the characteristics of these artifacts, it quantifies that the optical properties of the raw material contribute 30% to the instantaneous deviation. Based on these two quantifications, the system determines that the main cause of this instantaneous deviation is the local brightness attenuation of the illumination source, supplemented by the secondary influence of the optical properties of the raw material. Therefore, the system's alert message will clearly state "Measurement basis deviation: mainly caused by local brightness attenuation of the illumination source, and secondarily by the optical properties of the raw material," thus guiding operators to prioritize checking and calibrating the lighting system and consider sampling inspection of the raw material to ensure the stability of the production process and product quality.

[0056] In one embodiment of the present invention, the background illumination images are multiple sets, generated based on multiple preset brightness levels of lighting sources, and the same set of background illumination images is generated based on the same preset brightness level of lighting sources. The step of quantifying the contribution of local brightness attenuation of the lighting sources to the instantaneous deviation includes:

[0057] Based on multiple sets of background illumination images, for each preset region in the background image, the brightness response curve of the corresponding region is constructed according to its average gray value at different brightness levels.

[0058] It should be noted that the acquisition method of the background lighting images is optimized to multiple sets, and each set of background lighting images is generated based on a lighting source with a different preset brightness level. This multi-set, multi-brightness-level background lighting image acquisition method aims to comprehensively capture the optical characteristics of the lighting source under different operating conditions, providing a sufficient data foundation for subsequent accurate quantization. Specifically, the preset area refers to several small regions in the background image, and the average gray value of each region can be calculated independently to reflect the local brightness of that region. The brightness response curve is constructed by recording the change in the average gray value of the corresponding preset area under different brightness levels of the lighting source. This curve can characterize the relationship between the output brightness of the lighting source and the input control signal, revealing its linearity, saturation, and other characteristics.

[0059] Calculate the deviation between the brightness response curve and the ideal response curve, and use the deviation as a nonlinear contribution to the local brightness decay of the illumination source; calculate the fluctuation of pixel grayscale values ​​in each preset area in the same set of background illumination images, and use the fluctuation as a contribution to transient flicker.

[0060] The ambient temperature at the time of capturing the background image is obtained, and the nonlinear contribution and transient flicker contribution are correlated with the ambient temperature;

[0061] By combining the nonlinear contribution, transient flicker contribution, and correlation with ambient temperature, the contribution of local brightness decay of the lighting source to the instantaneous deviation is determined.

[0062] It's important to note that nonlinear contribution refers to the deviation between the actual luminance response curve of a lighting source and its ideal linear response curve. The ideal response curve is typically set to exhibit a perfect linear relationship across the entire luminance range, while actual light sources, due to their physical characteristics, often exhibit nonlinear behavior, such as response hysteresis or saturation in low or high brightness regions. Calculating this deviation allows for the quantification of the impact of the lighting source's nonlinear characteristics on measurement results. Transient flicker contribution refers to the degree of fluctuation in the pixel grayscale value of each preset area over time or between frames within the same set of background illumination images. This fluctuation reflects the instantaneous stability of the lighting source, such as rapid brightness changes caused by power fluctuations or LED aging. Quantifying this fluctuation as transient flicker contribution helps identify measurement deviations caused by light source instability. Furthermore, ambient temperature has a significant impact on the performance of lighting sources; for example, increased temperature may lead to accelerated luminance decay or decreased stability. Therefore, obtaining the ambient temperature when capturing the background image and correlating the nonlinear and transient flicker contributions with ambient temperature provides a more comprehensive understanding of the light source decay mechanism and provides a basis for subsequent correction and compensation. Finally, by comprehensively considering the correlation results of nonlinear contribution, transient flicker contribution, and ambient temperature, the overall contribution of local brightness decay of the lighting source to the instantaneous deviation can be determined more accurately.

[0063] This application's solution, by introducing multiple sets of background illumination images at multiple brightness levels and constructing brightness response curves based on these images, can comprehensively characterize the dynamic characteristics of the lighting source. By calculating the deviation between the brightness response curve and the ideal response curve, the impact of the nonlinear attenuation of the lighting source on the measurement results can be accurately quantified. Simultaneously, by analyzing the fluctuation of pixel grayscale values ​​in the same set of background illumination images, the transient flicker characteristics of the lighting source can be effectively captured. More importantly, this application correlates the nonlinear contribution and transient flicker contribution with ambient temperature, fully considering the influence of environmental factors on the light source performance, making the quantification of local brightness attenuation of the lighting source more comprehensive and accurate. Therefore, this application can effectively distinguish between measurement deviations caused by the inherent characteristics of the lighting source (such as nonlinearity and flicker) and environmental factors (such as temperature) and deviations caused by the optical characteristics of the raw materials, thereby avoiding misjudging light source problems as product quality problems.

[0064] In some preferred embodiments, a specific example is given below. Suppose that on a blow molding production line, the detection system frequently reports negative jumps in the measured outer diameter of the contour over a period of time. According to the above scheme, the system first acquires multiple sets of background illumination images at different preset brightness levels (e.g., 20%, 40%, 60%, 80%, 100% brightness). For each preset region in the image (e.g., the image is divided into a 10x10 grid), its average grayscale value at different brightness levels is calculated, and a brightness response curve for that region is constructed accordingly. For example, the brightness response curve of a certain region exhibits significant nonlinearity at low brightness and tends to saturate at high brightness. Simultaneously, the system calculates the transient fluctuation of the pixel grayscale values ​​in that region at the same brightness level, for example, quantifying flicker by calculating the standard deviation of grayscale values ​​between consecutive frames. Furthermore, the system records the ambient temperature at each background image acquisition. By comprehensively analyzing this data, for example, it is found that when the ambient temperature increases, both the nonlinear contribution and the transient flicker contribution of a certain region significantly increase. Based on these quantitative results, the system can determine, for example, that 70% of instantaneous deviations are caused by the nonlinear decay of the lighting source at the current ambient temperature, 20% by transient flicker, and the remaining 10% may be related to the optical properties of the raw materials. This precise quantification and attribution allows maintenance personnel to directly inspect and maintain the lighting source, such as replacing aging lamps or optimizing the heat dissipation system, rather than blindly adjusting raw material formulations or blow molding process parameters, thereby improving the efficiency and accuracy of problem solving.

[0065] As one embodiment of the present invention, the step of calculating the contribution of local brightness attenuation of the lighting source to the instantaneous deviation, combining nonlinear contribution, transient flicker contribution, and correlation results with ambient temperature, includes:

[0066] Transient flicker characteristics corresponding to different brightness levels are obtained based on multiple sets of background illumination images;

[0067] It should be noted that the above step refers to capturing multiple sets of background lighting images at different preset brightness levels and analyzing these images to quantify the transient fluctuation behavior of the lighting source at each brightness level. For example, the variance or standard deviation of the pixel grayscale values ​​in a preset area of ​​the background image over time can be calculated at a specific brightness level, which can be used as the transient flicker characteristics at that brightness level. The purpose is to comprehensively capture the dynamic instability of the lighting source under different operating conditions.

[0068] The correlation between transient flicker characteristics and brightness response curves at different brightness levels was analyzed to determine the coupling relationship between nonlinear brightness decay and transient flicker.

[0069] It should be noted that the above step can be understood as using data analysis and modeling to reveal whether there is a mutual influence or dependency between the nonlinear brightness decay of the lighting source (i.e., the nonlinear relationship between brightness output and input signal) and transient flicker (i.e., rapid fluctuations in brightness over time). For example, this association can be quantified by calculating the correlation index between the two or by constructing a regression model. The purpose is to gain a deeper understanding of the decay mechanism of the lighting source and provide a basis for subsequent corrections.

[0070] Based on the coupling relationship, the nonlinear contribution and transient scintillation contribution are corrected;

[0071] It should be noted that this step specifically refers to adjusting the previously calculated nonlinear and transient flicker contributions once the coupling relationship between nonlinear brightness decay and transient flicker is determined. For example, if it is found that nonlinear decay exacerbates transient flicker, then both need to be synergistically corrected when calculating the total contribution to avoid double counting or omission of effects. The purpose is to eliminate or reduce evaluation errors caused by coupling effects, making the quantification of each contribution more accurate.

[0072] By combining the corrected nonlinear contribution, the corrected transient flicker contribution, and the correlation results with ambient temperature, the contribution of local brightness decay of the lighting source to the instantaneous deviation is calculated.

[0073] It should be noted that the above step refers to, after correcting for the nonlinear and transient flicker contributions, comprehensively considering the correlation results of these corrected values ​​with ambient temperature (e.g., the temperature-brightness influence model), ultimately obtaining a more accurate assessment of the contribution of local brightness attenuation of the lighting source to the instantaneous deviation. The aim is to provide a comprehensive and highly accurate evaluation result of lighting source attenuation.

[0074] This application addresses the problem of inaccurate contribution assessment caused by neglecting this complex interaction in traditional methods by introducing an analysis of the coupling relationship between nonlinear brightness decay and transient flicker. Specifically, firstly, by acquiring transient flicker characteristics at different brightness levels, the dynamic instability of the light source at different operating points can be comprehensively captured. Secondly, by analyzing the correlation between these transient flicker characteristics and the brightness response curve, a coupling model describing their mutual influence can be constructed. Due to this coupling relationship, nonlinear decay and transient flicker are not completely independent contribution sources; they may have enhancement or suppression effects. Therefore, correcting the nonlinear and transient flicker contributions based on the determined coupling relationship eliminates errors caused by simple superposition, ensuring that the quantification of each contribution is closer to reality. Finally, combining the corrected contributions with the correlation results of ambient temperature allows for a more comprehensive and accurate calculation of the actual contribution of local brightness decay of the lighting source to the instantaneous deviation.

[0075] Through the above technical solution, this application can more accurately quantify the contribution of local brightness attenuation of the lighting source to the instantaneous deviation in the measurement of the outer diameter of the plastic blade profile. Compared with the method of simply superimposing the contributions, this application effectively avoids the evaluation bias caused by ignoring this complex interaction by identifying and correcting the coupling relationship between nonlinear brightness attenuation and transient flicker. Therefore, it can provide more accurate warning information on measurement basis deviations, enabling operators to more timely and accurately determine whether abnormalities in the blow molding process originate from lighting source problems or raw material optical property problems, thereby significantly improving the accuracy of fault diagnosis and the stability of the production process.

[0076] As one embodiment of the present invention, the step of analyzing the correlation between transient flicker characteristics and brightness response curves at different brightness levels, and determining the coupling relationship between nonlinear brightness decay and transient flicker, includes:

[0077] Calculate the correlation index between transient flicker characteristics and brightness response curves at different brightness levels;

[0078] It should be noted that the above step refers to quantifying the correlation between transient flicker characteristics and the luminance response curve at different luminance levels using statistical methods. For example, indicators such as Pearson correlation coefficient, Spearman rank correlation coefficient, or mutual information can be used to assess the linear or nonlinear correlation between the two. The purpose is to provide a data foundation for subsequently constructing an accurate regression model.

[0079] Based on correlation indices, a regression model is constructed between transient flicker characteristics and brightness response curves;

[0080] It should be noted that the above step refers to establishing a mathematical model using the calculated correlation indicators to describe how transient flicker characteristics change with the brightness response curve. This regression model can be a linear regression model, a multinomial regression model, a nonlinear regression model, or even a model based on machine learning algorithms (such as support vector regression or neural networks). Its purpose is to capture the inherent laws between the two through mathematical forms, thereby achieving a quantitative description of the coupling relationship.

[0081] Based on the regression model, the coupling relationship between nonlinear brightness decay and transient flicker was determined.

[0082] It should be noted that the above step refers to using the constructed regression model to derive the specific functional relationship or mapping rule between nonlinear brightness decay and transient flicker. This coupling relationship can be a mathematical formula, a lookup table, or a set of parameters, used to describe how the nonlinear brightness decay of the lighting source interacts with transient flicker under different operating conditions. Its purpose is to provide a precise basis for subsequent corrections to the nonlinear and transient flicker contributions.

[0083] This application's approach first calculates the correlation index between transient flicker characteristics and the luminance response curve, enabling an objective assessment of the strength and direction of their association. Based on this, a regression model is constructed to transform this statistical correlation into an operable mathematical expression, thus accurately predicting or describing the behavior of transient flicker characteristics under different luminance response conditions. Finally, based on this regression model, the coupling relationship between nonlinear luminance decay and transient flicker can be systematically determined, making the calculation of the contribution to local luminance decay of the lighting source more accurate and reliable. This step-by-step refinement method ensures the scientific rigor and accuracy of the coupling relationship determination, providing a solid foundation for subsequent correction steps.

[0084] As one embodiment of the present invention, the step of determining the coupling relationship between nonlinear brightness decay and transient flicker includes:

[0085] Obtain the real-time brightness output corresponding to the transient flicker characteristics;

[0086] It should be noted that the above step refers to monitoring the brightness output of the lighting source in real time using sensors or image acquisition devices during normal system operation or routine maintenance, and extracting characteristic data related to transient flicker. This real-time brightness output data may include the average grayscale value, brightness fluctuation amplitude, frequency, etc. of a specific area.

[0087] Compare real-time brightness output and transient flicker characteristics with established coupling relationships;

[0088] It should be noted that this step can be understood as substituting the currently monitored brightness output and transient flicker characteristics data into the previously established coupling model to predict its expected performance, and then comparing the predicted value with the actual observed value. For example, the statistical deviation between the real-time data and the model prediction value can be calculated and compared with a preset threshold to determine whether there is a significant difference.

[0089] If the comparison results show that there is a preset difference between the real-time brightness output and transient flicker characteristics and the established coupling relationship, then the brightness response data and transient fluctuation data of the lighting source at multiple preset brightness levels are reacquired.

[0090] It should be noted that if the comparison results show a preset difference between the real-time brightness output and transient flicker characteristics and the established coupling relationship, a recalibration or re-determination process will be triggered. This preset difference can be a fixed numerical threshold or a confidence interval determined based on statistical methods. Once such a difference is detected, the system will automatically or manually reacquire brightness response data and transient fluctuation data of the lighting source at multiple preset brightness levels. This data is typically obtained by progressively adjusting the brightness level of the lighting source in a controlled environment while simultaneously acquiring image data.

[0091] Based on the reacquired luminance response data and transient fluctuation data, the correlation index between transient flicker characteristics and luminance response curves at different luminance levels is recalculated. This step is similar to the calculation method used when initially determining the coupling relationship, but uses the latest data that reflects the current state of the light source.

[0092] Based on the recalculated correlation index, a regression model between transient flicker characteristics and luminance response curve is reconstructed; this regression model will more accurately reflect the actual coupling relationship between the nonlinear luminance decay and transient flicker of the current lighting source.

[0093] Based on the reconstructed regression model, the coupling relationship between nonlinear brightness decay and transient flicker is redefined. This ensures more accurate differentiation of the causes of subsequent biases and quantification of their contributions.

[0094] This application's solution effectively addresses the problem of model inaccuracy caused by the performance drift of lighting sources over time by introducing a real-time monitoring and adaptive update mechanism for established coupling relationships. Specifically, by continuously acquiring the real-time brightness output corresponding to transient flicker characteristics and comparing it with the currently used coupling relationship, the system can promptly detect whether the coupling relationship deviates from the actual situation. Once a preset difference is detected, indicating that the original coupling relationship is no longer accurate, the system triggers an automated recalibration process. In this process, the latest brightness response data and transient fluctuation data are re-acquired, and the correlation index is recalculated and the regression model is rebuilt based on this new data, ultimately obtaining an updated coupling relationship that better reflects the current actual state of the lighting source. This dynamic adjustment mechanism ensures that the quantification of the contribution to local brightness attenuation of the lighting source is always based on the most accurate coupling relationship throughout the entire blow molding inspection process, thereby improving the accuracy and robustness of the system's judgment on the cause of transient deviations.

[0095] As one embodiment of the present invention, the step of comparing real-time brightness output and transient flicker characteristics with a determined coupling relationship includes:

[0096] Based on the established coupling relationship, the predicted values ​​corresponding to the real-time brightness output and transient flicker characteristics are obtained;

[0097] It should be noted that this step can be understood as using a regression model previously built based on historical data (e.g., a regression model built based on correlation indicators in the above embodiment) as input to the current real-time brightness output and transient flicker characteristics, thereby obtaining the values ​​that these characteristics should have under ideal or expected conditions. These predicted values ​​represent the theoretical coupling behavior between the nonlinear brightness decay and transient flicker of the lighting source under normal operating conditions.

[0098] Calculate the statistical deviation between the real-time brightness output and transient flicker characteristics and the predicted values;

[0099] It should be noted that the above step refers to quantifying the difference between actual observed values ​​and theoretical predictions. This statistical bias can be measured in various ways, such as calculating absolute bias, relative bias, mean square error (MSE), or root mean square error (RMSE). Its purpose is to provide a quantitative indicator to assess whether the current operating state of the lighting source deviates from its established stable coupling relationship.

[0100] Compare the statistical deviation with a preset threshold.

[0101] It should be noted that the above step aims to determine whether this deviation has reached a level requiring attention or action. The preset threshold is pre-set based on the system's requirements for accuracy and stability; for example, it can be determined based on historical data analysis, empirical values, or the needs of a specific application scenario. If the statistical deviation exceeds this threshold, it indicates that the coupling relationship between the nonlinear brightness decay and transient flicker of the lighting source may have changed significantly, requiring recalibration or further diagnostics.

[0102] This application's solution establishes a benchmark by first obtaining predicted values ​​of real-time brightness output and transient flicker characteristics based on a pre-determined coupling relationship. This benchmark measures the expected performance of the current system behavior. Subsequently, by calculating the statistical deviation between actual observations and these predicted values, the degree of any deviation from the normal coupling relationship can be quantified. Finally, this statistical deviation is compared to a preset threshold, providing a clear criterion for determining whether the coupling relationship of the lighting source needs to be reassessed or updated. This mechanism ensures continuous monitoring and verification of the lighting source performance, thereby guaranteeing the accuracy and reliability of subsequent differentiation of the causes of transient deviations (such as local brightness decay of the lighting source or optical properties of raw materials).

[0103] As one embodiment of the present invention, the step of comparing the statistical deviation with a preset threshold includes:

[0104] Obtain the preset confidence interval for statistical bias;

[0105] It should be noted that the above step can be understood as the range of values ​​that the statistical deviation might fall into at a certain confidence level. This confidence interval is usually determined based on historical data, statistical models, or empirical values, aiming to reflect the inherent volatility of the statistical deviation. For example, a 95% or 99% confidence interval can be calculated based on the distribution characteristics of historical statistical deviation data (such as the mean and standard deviation). This confidence interval can be a symmetrical interval, such as [μ - kσ, μ + kσ], where μ is the expected value of the statistical deviation, σ is the standard deviation, and k is a coefficient related to the confidence level; it can also be an asymmetrical interval, depending on the distribution characteristics of the statistical deviation.

[0106] Determine whether the statistical bias exceeds the confidence interval.

[0107] It should be noted that the above step refers to comparing the currently calculated statistical deviation with the upper and lower limits of the preset confidence interval. If the statistical deviation falls outside the confidence interval, the deviation is considered significant, potentially indicating an anomaly; conversely, if the statistical deviation falls within the confidence interval, the deviation is considered to be within the acceptable range of normal fluctuation. For example, an upper limit and a lower limit can be set; when the statistical deviation is greater than the upper limit or less than the lower limit, it is considered to have exceeded the confidence interval.

[0108] This application's solution introduces a confidence interval for statistical deviation and determines whether the statistical deviation exceeds this interval, thereby enabling a more refined and robust evaluation of the differences between real-time brightness output and transient flicker characteristics and the established coupling relationship. Traditional simple threshold comparisons may not effectively distinguish between normal fluctuations and actual anomalies, easily leading to misjudgments. By constructing a confidence interval, the randomness and uncertainty of statistical deviation can be fully considered, ensuring that anomalies are only identified when the deviation significantly exceeds the normal fluctuation range. This avoids unnecessary recalibration triggered by accidental fluctuations, improving the accuracy and stability of the judgment.

[0109] like Figure 2 The system shown is a blow molding inspection system for the production of plastic blades for wind turbine generators. The system includes:

[0110] The acquisition module 201 is used to acquire the measured values ​​of the outer diameter of the plastic blade under test at multiple different heights along its vertical direction.

[0111] The tracking and calculation module 202 is used to continuously track the changing trend of multiple profile outer diameter measurements during the movement of the plastic blade under test, and calculate the instantaneous deviation of each profile outer diameter measurement relative to the recent average value, where the recent average value is the mean of the recent historical profile outer diameter measurements of the plastic blade under test at the corresponding height.

[0112] The judgment module 203 is used to determine whether the instantaneous deviation of multiple contour outer diameter measurement values ​​simultaneously meets the preset negative jump threshold, and the mutual difference between the instantaneous deviations is less than the preset difference threshold.

[0113] The warning module 204 is used to output a warning message indicating that the measurement basis has deviated if the conditions are met.

[0114] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention.

Claims

1. A blow molding inspection method for use in the production of plastic blades for wind turbine generators, characterized in that, The method includes the following steps: Obtain the measured outer diameter of the plastic blade under test at multiple different heights along its vertical direction; The changing trends of multiple profile outer diameter measurements are continuously tracked during the movement of the plastic blade under test, and the instantaneous deviation of each profile outer diameter measurement relative to the recent average value is calculated. The recent average value is the mean of the recent historical profile outer diameter measurements of the plastic blade under test at the corresponding height. Determine whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the mutual differences between the instantaneous deviations are less than a preset difference threshold; If satisfied, output a warning message indicating measurement offset. The step of determining whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the mutual differences between the instantaneous deviations are less than a preset difference threshold, includes: Determine whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the mutual differences between the instantaneous deviations are less than a preset difference threshold; If the conditions are met, the cause of the instantaneous deviation is identified, and a warning message indicating measurement deviation and the cause are output. The cause of the instantaneous deviation is identified by: acquiring a background illumination image when there is no plastic leaf to be tested in the detection area. Analyze the brightness distribution of the background lighting image based on the background lighting image; Acquire an image of the plastic blade to be tested within the detection area, perform background correction on the image of the plastic blade to be tested, and identify optical artifacts in the corrected image of the plastic blade to be tested; Based on the brightness distribution of the background illumination image and the optical artifacts, the causes of the instantaneous deviation are distinguished, including those caused by local brightness attenuation of the illumination source and those caused by the optical properties of the raw materials.

2. The blow molding testing method for wind turbine plastic blades according to claim 1, characterized in that, The step of distinguishing the cause of the instantaneous deviation based on the brightness distribution of the background illumination image and the optical artifacts includes: Based on the brightness distribution of the background illumination image, the contribution of the local brightness attenuation of the illumination source to the instantaneous deviation is quantified; Based on the optical artifacts, quantify the contribution of the optical properties of the raw material to the instantaneous deviation; Based on the contribution of the local brightness attenuation of the lighting source and the contribution of the optical properties of the raw materials, it is determined whether the instantaneous deviation is caused by the local brightness attenuation of the lighting source, by the optical properties of the raw materials, or by the combination of both.

3. The blow molding inspection method for wind turbine plastic blades according to claim 2, characterized in that, The background lighting images are generated in multiple sets based on multiple preset brightness levels of illumination sources. Each set of background lighting images is generated based on the same preset brightness level of illumination source. The step of quantifying the contribution of the local brightness attenuation of the illumination source to the instantaneous deviation includes: Based on multiple sets of background illumination images, for each preset region in the background illumination image, a brightness response curve for the corresponding region is constructed according to its average gray value at different brightness levels. The deviation between the brightness response curve and the ideal response curve is calculated, and the deviation is used as a nonlinear contribution to the local brightness decay of the illumination source; the fluctuation degree of the pixel gray value in each preset area in the same set of background illumination images is calculated, and the fluctuation degree is used as a transient flicker contribution. The ambient temperature at which the background illumination image was captured is obtained, and the nonlinear contribution and the transient flicker contribution are correlated with the ambient temperature; By combining the nonlinear contribution, the transient flicker contribution, and the correlation with ambient temperature, the degree of contribution of the local brightness decay of the lighting source to the instantaneous deviation is determined.

4. The blow molding inspection method for wind turbine plastic blades according to claim 3, characterized in that, The step of calculating the contribution of the local brightness attenuation of the lighting source to the instantaneous deviation by combining the nonlinear contribution, the transient flicker contribution, and the correlation result with ambient temperature includes: Transient flicker characteristics corresponding to different brightness levels are obtained based on multiple sets of background illumination images; The correlation between the transient flicker characteristics at different brightness levels and the brightness response curves was analyzed to determine the coupling relationship between nonlinear brightness decay and transient flicker. Based on the coupling relationship, the nonlinear contribution and the transient scintillation contribution are corrected; By combining the corrected nonlinear contribution, the corrected transient flicker contribution, and the correlation results with ambient temperature, the contribution of the local brightness decay of the lighting source to the instantaneous deviation is calculated.

5. The blow molding inspection method for producing plastic blades for wind turbine units according to claim 4, characterized in that, The step of analyzing the correlation between the transient flicker characteristics at different brightness levels and the brightness response curve, and determining the coupling relationship between the nonlinear brightness decay and transient flicker, includes: Calculate the correlation index between the transient flicker characteristics at different brightness levels and the brightness response curve; Based on the correlation index, a regression model is constructed between the transient flicker characteristics and the brightness response curve; Based on the regression model, the coupling relationship between the nonlinear brightness decay and the transient flicker is determined.

6. The blow molding inspection method for wind turbine plastic blades according to claim 5, characterized in that, The step of determining the coupling relationship between the nonlinear brightness attenuation and transient flicker includes: Obtain the real-time brightness output corresponding to the transient flicker characteristics; Compare the real-time brightness output and transient flicker characteristics with the established coupling relationship; If the comparison results show that there is a preset difference between the real-time brightness output and transient flicker characteristics and the determined coupling relationship, then the brightness response data and transient fluctuation data of the lighting source at multiple preset brightness levels are reacquired. Based on the reacquired brightness response data and transient fluctuation data, the correlation index between the transient flicker characteristics and the brightness response curve at different brightness levels is recalculated. Based on the recalculated correlation index, a regression model between the transient flicker characteristics and the brightness response curve is reconstructed; Based on the reconstructed regression model, the coupling relationship between the nonlinear brightness decay and transient flicker is redefined.

7. The blow molding inspection method for wind turbine plastic blades according to claim 6, characterized in that, The step of comparing the real-time brightness output and transient flicker characteristics with the established coupling relationship includes: Based on the established coupling relationship, the predicted values ​​corresponding to the real-time brightness output and transient flicker characteristics are obtained; Calculate the statistical deviation between the real-time brightness output and transient flicker characteristics and the predicted value; The statistical deviation is compared with a preset threshold.

8. The blow molding inspection method for wind turbine plastic blades according to claim 7, characterized in that, The step of comparing the statistical deviation with a preset threshold includes: Obtain the preset confidence interval for statistical bias; Determine whether the statistical deviation exceeds the confidence interval.

9. A blow molding inspection system for the production of plastic blades for wind turbine generators, used to perform a blow molding inspection method for the production of plastic blades for wind turbine generators as described in any one of claims 1-8, characterized in that, The system includes: The acquisition module is used to acquire the measured outer diameter of the plastic blade under test at multiple different heights along its vertical direction. The tracking and calculation module is used to continuously track the changing trend of multiple profile outer diameter measurements during the movement of the plastic blade under test, and calculate the instantaneous deviation of each profile outer diameter measurement relative to the recent average value, wherein the recent average value is the mean of the recent historical profile outer diameter measurements of the plastic blade under test at the corresponding height. The judgment module is used to determine whether the instantaneous deviations of multiple contour outer diameter measurements simultaneously meet a preset negative jump threshold, and whether the mutual difference between the instantaneous deviations is less than a preset difference threshold. The warning module is used to output a warning message indicating a deviation in the measurement basis if the conditions are met.

Images