Method and apparatus for monitoring a product manufacturing process based on a resin transfer molding process

Abstract

This invention discloses a method and apparatus for monitoring the product manufacturing process based on resin transfer molding, comprising: monitoring the resin flow front according to a first regression model and a second regression model during resin flow; inputting the monitored fiber optic signal into a pre-trained curing stage recognition model to obtain the current curing stage during resin curing, and determining the current degree of curing based on the fused image obtained from the fiber optic signal and the ultrasonic guided wave signal; determining the dry spot region based on the monitored fiber optic signal when resin curing is complete, and determining the quantitative information of the dry spot based on the ultrasonic guided wave signal monitored in the dry spot region. During resin injection, the acquired ultrasonic guided wave signal and fiber optic signal are analyzed to monitor the resin flow front, degree of curing, and dry spot. The fiber optic monitoring results are cross-validated with the ultrasonic monitoring results to improve the precision of product manufacturing and the quality of finished products, thereby realizing intelligent manufacturing of composite materials.

Description

Technical Field

[0001] This invention relates to the field of liquid molding composite material manufacturing technology, and in particular to a method and apparatus for monitoring the product manufacturing process based on resin transfer molding. Background Technology

[0002] In resin transfer molding (RTM), the resin flow front is typically invisible inside the mold. If the resin impregnation of the fibers is inadequate, defects such as voids, dry spots, and localized resin deficiency can easily occur within the composite material. These defects severely reduce the mechanical properties and quality stability of the product, and may even lead to the failure of the entire molding process. Therefore, real-time monitoring of the resin flow front and the degree of curing is a crucial step in ensuring product quality during composite liquid molding processes.

[0003] Existing monitoring methods in carbon fiber composite manufacturing processes mostly focus on monitoring flat components. These methods are limited and struggle to handle complex, irregularly shaped components. In these methods, the spatial density, size, and number of sensors have a decisive impact on monitoring effectiveness. However, these methods typically cannot provide a comprehensive assessment of the composite component's condition and the location of manufacturing defects. For example, while embedded sensors can capture local information in real time, their uneven spatial distribution often fails to accurately and comprehensively reflect the overall quality status of the component. Increasing the number of sensors and optimizing their distribution often increases cost and complexity. Furthermore, existing monitoring system verification methods are mostly limited to verifying the surface condition of the component and cannot effectively detect potential defects hidden inside the mold. Summary of the Invention

[0004] This invention provides a method and apparatus for monitoring the product manufacturing process based on resin transfer molding, so as to realize the monitoring of product manufacturing based on resin transfer molding.

[0005] According to a first aspect of the present invention, a method for monitoring the product manufacturing process based on resin transfer molding (RTM) is provided, applied to an RTM manufacturing system, the system including a sealed mold, a fiber preform, an optical fiber sensor, and a piezoelectric sensor located within the sealed mold, the method comprising:

[0006] During resin injection into the fiber preform in the sealing mold using the RTM process, the fiber optic signal of the fiber optic sensor and the ultrasonic guided wave signal of the piezoelectric sensor are continuously monitored.

[0007] A first regression model is established based on the fiber optic signal to establish the resin arrival time and the fiber wetting area during resin flow. A second regression model is established based on the ultrasonic guided wave signal to establish the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. The resin flow front is monitored based on the first regression model and the second regression model.

[0008] During resin curing, the monitored optical fiber signal is input into a pre-trained curing stage recognition model to obtain the current curing stage, and the current curing degree is determined based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal.

[0009] When the resin curing is complete, the dry spot area is determined based on the monitored fiber optic signal, and the quantitative information of the dry spot is determined based on the ultrasonic guided wave signal monitored in the dry spot area.

[0010] According to another aspect of the present invention, a product manufacturing process monitoring device based on resin transfer molding is provided. The device includes: a sensor signal acquisition module for continuously monitoring the fiber optic signal of the fiber optic sensor and the ultrasonic guided wave signal of the piezoelectric sensor when resin is injected into the fiber preform in the sealed mold using the RTM process.

[0011] The flow front monitoring module is used to establish a first regression model of resin arrival time and fiber wetting area based on optical fiber signal when resin flows, establish a second regression model of ultrasonic guided wave stable amplitude and resin penetration thickness based on ultrasonic guided wave signal, and monitor the resin flow front based on the first regression model and the second regression model.

[0012] The curing monitoring module is used to input the monitored optical fiber signal into a pre-trained curing stage recognition model to obtain the current curing stage during resin curing, and to determine the current curing degree based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal.

[0013] The dry spot monitoring module is used to determine the dry spot area based on the monitored fiber optic signal when the resin curing is completed, and to determine the quantitative information of the dry spot based on the ultrasonic guided wave signal monitored in the dry spot area.

[0014] According to another aspect of the present invention, a terminal device is provided, the terminal device comprising: one or more processors;

[0015] Storage device for storing one or more programs.

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a storage medium for computer-executable instructions is provided, on which a computer program is stored, which, when executed by a processor, implements the method as described in any of the embodiments of the present invention.

[0018] The technical solution of this invention analyzes the acquired ultrasonic guided wave signals and fiber optic signals during the resin injection process to monitor the resin flow front, degree of curing, and dry spots. The fiber optic monitoring results are cross-validated with the ultrasonic monitoring results to improve the precision of product manufacturing and the quality of finished products, thereby realizing intelligent manufacturing of composite materials.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a product manufacturing process monitoring method based on resin transfer molding technology according to Embodiment 1 of the present invention;

[0022] Figure 2 This is a schematic diagram of the structure of the RTM process manufacturing system provided in Embodiment 1 of the present invention;

[0023] Figure 3 This is a schematic diagram of a fully transparent flow front visualization verification experiment based on the RTM process provided in Embodiment 1 of the present invention;

[0024] Figure 4 This is a flowchart of a product manufacturing process monitoring method based on resin transfer molding technology according to Embodiment 2 of the present invention;

[0025] Figure 5 This is a schematic diagram of a product manufacturing process monitoring device based on resin transfer molding technology according to Embodiment 3 of the present invention;

[0026] Figure 6 This is a structural block diagram of a terminal device provided in Embodiment 4 of the present invention. Specific Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or terminal device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or terminal devices.

[0029] Example 1

[0030] Figure 1 This is a flowchart illustrating a product manufacturing process monitoring method based on resin transfer molding, provided as an embodiment of the present invention. This embodiment is applicable to monitoring product manufacturing processes based on resin transfer molding. The method can be executed by a product manufacturing process monitoring device based on resin transfer molding. This device can be implemented in hardware and / or software, and can be integrated into a terminal device. Figure 1 As shown, the method includes:

[0031] In step S101, when resin is injected into the fiber preform in the sealed mold using the RTM process, the fiber optic signal of the fiber optic sensor and the ultrasonic guided wave signal of the piezoelectric sensor are continuously monitored.

[0032] Specifically, such as Figure 2The diagram shows the structure of the RTM manufacturing system. The fiber preform is shaped by an upper mold, a sensor upper cover plate, a sensor lower cover plate, and a mold base. A customized flexible piezoelectric smart interlayer is glued to the underside of the sensor upper cover plate with high-temperature adhesive. Note that the piezoelectric ceramic is glued towards the fiber preform. After the piezoelectric sensor is glued, the sensor upper cover plate and sensor lower cover plate are assembled and installed inside the mold base using screws. High-temperature resistant wires are welded to the flexible piezoelectric smart interlayer at their terminals, and the high-temperature resistant wires are led out from the left side. The sensor upper cover plate, sensor lower cover plate, and flexible piezoelectric smart interlayer together constitute the piezoelectric sensor. For the fiber optic sensor, it is laid out according to the shape of the fiber preform, in the center of the sensor upper cover plate (i.e., the center of the lower surface of the fiber preform), wraps around to the right side, and is positioned at the twist strip on the upper surface of the fiber preform. The distributed fiber optic sensor is led out from the left side. Finally, the upper mold is installed. A glue injection device and a glue collection device are connected to the glue injection port of the upper mold and the glue outlet of the mold base, respectively. After the RTM process product mold is installed, it is sealed with sealant and packaging bags, and then sent into a high-temperature heating furnace for product manufacturing. In this embodiment, a high-temperature resistant wire is connected to an ultrasonic guided wave monitoring platform through a through-hole in the furnace wall, and a distributed fiber optic sensor is connected to the distributed fiber optic sensing monitoring platform. The monitoring platform performs real-time data acquisition and processing, and monitors the resin injection process based on the acquired fiber optic signals and ultrasonic guided wave signals.

[0033] It should be noted that, for Figure 2 In this embodiment, a flexible piezoelectric smart sandwich layer is used to embed and integrate the piezoelectric sensor. Flexible wiring and pre-wiring simplify the number of cable connections and installation steps, enabling precise sensor positioning and ensuring the repeatability of the guided wave signal. An ultrasonic guided wave monitoring platform is used to excite a five-peak signal modulated by a Hanning window to generate and receive ultrasonic guided waves. Before resin injection, the optimal excitation frequency for each sensing path is determined by frequency sweeping. Then, during the resin injection process, Lamb wave signals are continuously acquired.

[0034] Among them, such as Figure 3 The diagram shown is a visualization verification experiment of a fully transparent flow front manufactured using the RTM process. Due to the limitations of the technology used in actual manufacturing... Figure 2 The RTM process manufacturing system shown is hermetically sealed, while the relevant thresholds used in this embodiment can be determined by... Figure 2 The results were obtained from the visual verification experiment shown. Figure 3As shown, multi-layered fiber woven fabric 33 is stacked and laid to form a stepped fiber preform 25, which is used to monitor and verify resin flow in different thicknesses and directions. The fiber preform 25 is laid on the upper surface of a high-temperature tempered glass plate 23, with a release agent 29 applied in the middle. Optical fibers are laid on the glass plate 23 and the preform 25, and then covered with a release cloth 24, a flow guide net 26, and a vacuum bag 27. Negative pressure is applied by a vacuum pump 21, and resin 32 is injected through the injection seat 30 and wets the preform 25. Excess resin flows into a resin collector 22, which is sealed with sealant 31 to ensure pressure stability. In addition, high-temperature resistant high-precision test scales 35 are attached to the upper and lower surfaces of the glass along the shape of the fiber preform 25. The entire test equipment is placed in a high-temperature furnace, and a high-temperature resistant industrial camera 36 is placed in the furnace to record the actual resin flow position during the test. The position of the resin flow front at the time point of interest is read by the scale. During the experiment, the flexible piezoelectric smart interlayer 28 will be excited and receive ultrasonic guided wave signals, while the distributed fiber optic sensor 34 will collect fiber optic strain signals. This experiment can be used to verify... Figure 2 The effectiveness of monitoring the actual manufacturing process.

[0035] In step S102, a first regression model is established based on the fiber optic signal to establish the resin arrival time and the fiber wetting area during resin flow. A second regression model is established based on the ultrasonic guided wave signal to establish the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. The resin flow front is monitored based on the first and second regression models.

[0036] Optionally, a first regression model is established based on the fiber optic signal to establish the resin arrival time and fiber impregnation area during resin flow, including: reconstructing the RTM fiber strain field based on the fiber optic signal; when the strain value in the RTM fiber strain field exceeds a first preset threshold, the position corresponding to the strain value is taken as the resin fully impregnation position; the intersection of the strain value and the threshold is taken as the resin arrival time, and a first regression model is established based on the impregnation position and the arrival time, wherein the first regression model is used to represent the resin flow in the horizontal direction.

[0037] Optionally, a second regression model is established based on the ultrasonic guided wave signal to determine the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. This includes: extracting the amplitude of the A0 mode signal in the ultrasonic guided wave signal; calculating the amplitude energy coefficient for ultrasonic guided wave signals whose amplitude has not reached a stable state; determining the resin arrival time when the amplitude energy coefficient reaches a stable state; and establishing a second regression model based on the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. The second regression model is used to represent the resin flow in the thickness direction.

[0038] Specifically, there is a significant difference in strain between the resin-wetted and unwetted regions. Therefore, by continuously monitoring the fiber optic signal during the resin flow process and acquiring the fiber optic strain signal based on the light signal, the magnitude of the strain field can be obtained. The RTM fiber optic strain field can be reconstructed based on a distributed fiber optic sensor. Since the strain signal of the fiber optic cable when the resin is fully permeated differs from the strain signal when the resin has just begun to permeate, this difference can be observed through... Figure 3 The RTM process manufacturing fully transparent flow front visualization verification experiment shown was conducted through multiple experiments and analyses to set a first preset threshold. At a certain moment, the point where the strain value in the RTM fiber strain field exceeds the first preset threshold is taken as the position where the resin is fully impregnated. The intersection of the strain value and the threshold is taken as the actual position of the flow front at that moment. When the fiber strain at the tail end of the component reaches its maximum value exceeding the threshold, it indicates that the resin impregnation of the fiber preform is complete. Thus, the entire fiber preform impregnation time is obtained, and a regression model between the resin arrival time and the fiber impregnation area is established. Here, the impregnation area mainly refers to the horizontal plane area; therefore, the first regression model in this embodiment is used to represent the resin flow in the horizontal direction.

[0039] In this embodiment, a multifunctional ultrasonic guided wave monitoring device is used to excite a five-peak signal modulated by a Hanning window to generate and receive ultrasonic guided wave signals. Before resin injection, the optimal excitation frequency for each sensing path is determined by frequency sweeping. Then, during the resin injection process, Lamb wave signals are continuously acquired. After acquiring the ultrasonic guided wave signals, the amplitude and phase characteristics of the A0 mode signal are extracted and analyzed. After sorting the signals according to the acquisition time, the signals gradually decay. The time when the amplitude begins to decrease is the time when the resin reaches the corresponding sensing path, and the time when the signal amplitude tends to stabilize is the time when the sensing path is completely covered by the resin. When the signal amplitude does not stabilize during resin injection, slight changes in system airflow and pressure are inevitable, resulting in poor repeatability of the received ultrasonic guided wave signal. To solve this problem, the amplitude energy coefficient of the differential signal is used to monitor the resin flow in the thickness direction. Subsequently, the change in guided wave signal characteristics can be determined based on the arrival time of the resin flow front. A second regression model between the amplitude of the ultrasonic guided wave and the resin penetration thickness of different sensing paths is constructed using a cubic interpolation algorithm. Therefore, the second regression model in this embodiment is used to represent the resin flow in the thickness direction.

[0040] It should be noted that, in this embodiment, after constructing a first regression model representing resin flow in the horizontal direction and a second regression model representing resin flow in the thickness direction, a three-dimensional resin flow front trajectory can be constructed by combining the two models, and the resin flow front can be monitored based on the constructed three-dimensional resin flow front trajectory. Furthermore, in this embodiment, by... Figure 2After the RTM process manufacturing system shown monitors the flow front position, it can also use... Figure 3 The fully transparent flow front visualization experiment shown verifies the flow front location results. The verification process first employs… Figure 3 The fully transparent RTM experiment shown utilizes a simplified RTM mold designed and manufactured from high-temperature resistant hard glass. High-temperature resistant, high-precision experimental flexible measuring tapes are laid on the upper and lower surfaces of the mold and adhered to the high-temperature resistant glass surface according to the mold's shape. Distributed fiber optic sensors and a flexible piezoelectric smart interlayer are laid on the inner and outer surfaces of the high-temperature glass according to monitoring requirements. A fiber preform and release cloth are then placed on the high-temperature glass plate, followed by a three-tiered stepped preform. A porous membrane and adhesive-absorbing felt are then sequentially covered on top. The mold and materials are then sealed using vacuum bags and sealant while simultaneously applying vacuum pressure. The entire mold and materials are placed in a high-temperature furnace, and high-temperature resistant industrial cameras are positioned directly below and above the glass plate for imaging. Resin is injected by opening valves, and the data corresponding to the flexible measuring tape in the camera feed is monitored. The captured data is then used to verify the flow front position results monitored by the fiber optic piezoelectric sensors.

[0041] Step S103: During resin curing, the monitored optical fiber signal is input into a pre-trained curing stage recognition model to obtain the current curing stage, and the current curing degree is determined based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal.

[0042] Optionally, during resin curing, the monitored optical fiber signal is input into a pre-trained curing stage identification model to obtain the current curing stage, including: obtaining an optical fiber strain signal based on the monitored optical fiber signal during resin curing; and inputting the optical fiber strain signal into the curing stage identification model to obtain the current curing stage, wherein the curing stage includes a viscoelastic stage, a rubberization stage, and a vitrification stage.

[0043] Optionally, the current curing degree is determined based on the fused image obtained from the fiber optic signal and the ultrasonic guided wave signal, including: integrating the S0 mode signal in the ultrasonic guided wave signal on the time axis and plotting the actual curing degree curve based on the integration result; dividing the curing degree into a specified number of levels on the actual curing degree curve, and performing feature fusion of the ultrasonic guided wave signal and the fiber optic signal within the time period corresponding to each level to obtain a fused image; and inputting the fused image into a neural network model for recognition to determine the current curing degree.

[0044] Specifically, in this embodiment, since the amplitude of the ultrasonic guided wave A0 mode almost completely attenuates during the resin injection stage, the S0 mode characteristics are used to capture curing information after the resin injection stage is completed. This includes physical properties such as degree of curing and key phase transition stages like gelation, vitrification, and completion of curing. The ultrasonic guided wave S0 mode signals along different sensing paths are normalized and plotted as curing time-normalized amplitude curves. Based on the changing trend of the S0 mode amplitude, the inflection points (gelation point and vitrification point) are used to divide the process into three stages: viscoelastic stage, rubberization stage, and vitrification stage. The ultrasonic guided wave velocity along different sensing paths is calculated, and a group velocity curve of curing time-S0 mode is plotted. Based on the changing trend of the group velocity, three stages are defined at the inflection point: the gel point, the glass transition point, and the viscoelastic stage. The times corresponding to the gel point and the glass transition point are averaged, and the calculated gel point and glass transition point times are correlated with the distributed optical fiber strain signal to divide the optical fiber strain signal into three stages. The strain signals monitored at each measuring point in the three stages are labeled to obtain sample data, and the curing stage identification model is trained based on the obtained sample data. Therefore, the training of the curing stage identification model in this embodiment requires the application of ultrasonic guided wave signals. Subsequently, when the optical fiber strain signal is monitored, it can be input into the trained curing stage identification model to obtain the current curing stage. Of course, this embodiment is only an example and does not limit the curing stage identification process.

[0045] Furthermore, in this embodiment, the S0 mode signal in the ultrasonic guided wave signal can be integrated on the time axis to track the change trend of the degree of curing during the actual curing process. Based on the integration result, an actual degree of curing curve is plotted, which can be divided into 10 levels: 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and 100%. Of course, this embodiment is merely an example and does not limit the number of levels. By clearly defining each time period corresponding to the ten levels, the ultrasonic guided wave signal and fiber optic strain signal within each time period are fused to create a two-dimensional image. The advantages of convolutional neural networks in image processing are then utilized to extract higher-level features to achieve accurate degree of curing monitoring. Therefore, the degree of curing monitoring in this embodiment mainly includes monitoring of the curing stage and more detailed monitoring of the degree of curing, to achieve monitoring of the curing process from multiple dimensions.

[0046] Step S104: When the resin curing is complete, the dry spot area is determined based on the monitored fiber optic signal, and the quantitative information of the dry spot is determined based on the ultrasonic guided wave signal monitored in the dry spot area.

[0047] Optionally, when the resin curing is complete, the dry spot region is determined based on the monitored optical fiber signal, including: reconstructing the RTM fiber strain field based on the optical fiber signal, and accumulating and normalizing the strain values ​​in the reconstructed RTM fiber strain field at each time point; and taking the region where the processed strain value is less than a second preset threshold as the dry spot region.

[0048] Specifically, in this embodiment, dry spot monitoring is further performed on the cured resin. During dry spot monitoring, the fiber optic signal is continuously monitored, and the fiber optic strain signal is acquired based on the light signal. The RTM fiber strain field is reconstructed based on the fiber optic signal, and the strain values ​​in the reconstructed RTM fiber strain field at each time point are accumulated and normalized. Because the fiber at the dry spot location is not wetted or has a low degree of wettability, the strain collected from the fiber at the dry spot location is almost non-existent or changes very little. Therefore, by... Figure 3 The RTM process was used to create a fully transparent flow front visualization verification experiment to obtain a second preset threshold, and the area where the strain value after processing is less than the second threshold was taken as the dry spot area.

[0049] Optionally, quantitative information about the dry spots is determined based on the ultrasonic guided wave signals monitored in the dry spot region, including: determining the probability density function of each grid point in the dry spot region based on the ultrasonic guided wave signals; when the probability density function is greater than a third threshold, the grid point is determined as a damage point; the size and location of the dry spots are determined based on the damage points, and the prime number and location are used as quantitative information.

[0050] Optionally, the probability density function of each grid point in the dry spot region is determined based on the ultrasonic guided wave signal, including: determining the relative distance from the piezoelectric sensing path to each grid point in the dry spot region based on the ultrasonic guided wave signal; determining the weighted distribution function based on the dynamic adaptive factor and obtaining the damage sensitivity index of each piezoelectric sensor in the dry spot region; and determining the probability density of each grid point based on the damage sensitivity index, the weighted distribution function and the relative distance.

[0051] Specifically, in this embodiment, an ultrasonic excitation array is selected to focus on scanning the speckle area. Elliptical weighted imaging processing is used to quantitatively characterize the location and size of the speckle. A dynamic adaptive factor is introduced into the elliptical weighted imaging algorithm to improve imaging accuracy and clarify the size and location of the speckle, thereby achieving quantitative characterization. For example, N ZPT sensors are deployed in the monitoring area, and any grid point in the monitoring area... All of these could be potential damage locations. Therefore, in this embodiment, the probability density function of each grid point in the dry spot region is obtained. When the probability density function is greater than the third threshold, the grid point is determined to be a damage point. Specifically, the relative distance from the piezoelectric sensing path to each grid point in the dry spot region is determined based on the ultrasonic guided wave signal. The relative distance is obtained using the following formula (1):

[0052]

[0053] in, It is the distance between the sensor and the driver in the r-th sensor path. It is the distance between the grid point (x, y) and the driver. Grid points The distance between the sensor and the sensor, It is determined based on the ultrasonic guided wave signal monitored by the piezoelectric sensor. In addition, in this embodiment, the weighted distribution function is also determined according to the dynamic adaptive factor, as shown in the following formula (2):

[0054]

[0055] Among them, the weighted distributed function It is a function of relative distance. This represents the relative distance from the piezoelectric sensing path to the grid point. For dynamic adaptive factors, dynamic adaptive factors The damage factor DI of each sensing path is negatively correlated, therefore the ratio between the two should be less than 1. Considering that the minimum value of this parameter cannot be 0, therefore... The minimum value is set to 0.1, and its definition is shown in the following formula (3):

[0056]

[0057] in, This means normalizing the parameter to a value between 0 and 1. Let represent the dynamic damage index of the r-th sensing path, defined as shown in formula (4):

[0058]

[0059] Where N is the number of sensing paths, As a damage factor, It is the weight coefficient of the r-th sensing path, and ,according to The value assigns a specific weight to each sensing path. It is a constant, representing The exponential decay rate, compared to Take the damage localization results at times 2, 4, and 6, select the optimal value, and determine the damage factor. The definition is shown in the following formula (5):

[0060]

[0061] in, and These are the current signal and baseline signal of the r-th sensing path, respectively, and T is the length of the intercepted signal. Additionally, in this embodiment, the following formula (6) can be used to obtain each grid point. probability density:

[0062]

[0063] Where N is the number of sensors. It is the damage sensitivity index of the r-th sensing path. For weighted distributed functions, This represents the relative distance from the piezoelectric sensing path to the grid point. Of course, this embodiment is merely an example and does not represent all grid points. The specific calculation method for the probability density is limited.

[0064] Specifically, in this embodiment, when the probability density function is greater than the third threshold, the grid point is determined as the damage point, and the size of the dry spot is determined based on all the damage points determined in the dry spot region. The location of the dry spot is determined based on the location information of all the damage points. Of course, this embodiment is only an example and does not specifically limit the method of determining the size and location of the dry spot.

[0065] The technical solution of this invention analyzes the acquired ultrasonic guided wave signal and fiber optic signal during the resin injection process to monitor the resin flow front, degree of curing and dry spots. The fiber optic monitoring results are cross-validated with the ultrasonic monitoring results to improve the precision of product manufacturing and the quality of finished products, thereby realizing intelligent manufacturing of composite materials.

[0066] Example 2

[0067] Figure 4 This is a flowchart of a product manufacturing process monitoring method based on resin transfer molding, provided by an embodiment of the present invention. Based on the above embodiments, after determining the quantitative information of the dry spot based on the ultrasonic guided wave signal monitored in the dry spot area, this embodiment further includes generating a monitoring report based on the flow front monitoring results, curing monitoring results, and dry spot monitoring results, and visually displaying the monitoring report. Figure 4 As shown, the method includes:

[0068] In step S201, when resin is injected into the fiber preform in the sealed mold using the RTM process, the fiber optic signal of the fiber optic sensor and the ultrasonic guided wave signal of the piezoelectric sensor are continuously monitored.

[0069] In step S202, a first regression model is established based on the fiber optic signal to establish the resin arrival time and the fiber wetting area during resin flow. A second regression model is established based on the ultrasonic guided wave signal to establish the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. The resin flow front is monitored based on the first and second regression models.

[0070] Optionally, a first regression model is established based on the fiber optic signal to establish the resin arrival time and fiber impregnation area during resin flow, including: reconstructing the RTM fiber strain field based on the fiber optic signal; when the strain value in the RTM fiber strain field exceeds a first preset threshold, the position corresponding to the strain value is taken as the resin fully impregnation position; the intersection of the strain value and the threshold is taken as the resin arrival time, and a first regression model is established based on the impregnation position and the arrival time, wherein the first regression model is used to represent the resin flow in the horizontal direction.

[0071] Optionally, a second regression model is established based on the ultrasonic guided wave signal to determine the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. This includes: extracting the amplitude of the A0 mode signal in the ultrasonic guided wave signal; calculating the amplitude energy coefficient for ultrasonic guided wave signals whose amplitude has not reached a stable state; determining the resin arrival time when the amplitude energy coefficient reaches a stable state; and establishing a second regression model based on the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. The second regression model is used to represent the resin flow in the thickness direction.

[0072] Step S203: During resin curing, the monitored optical fiber signal is input into a pre-trained curing stage recognition model to obtain the current curing stage, and the current curing degree is determined based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal.

[0073] Optionally, during resin curing, the monitored optical fiber signal is input into a pre-trained curing stage identification model to obtain the current curing stage, including: obtaining an optical fiber strain signal based on the monitored optical fiber signal during resin curing; and inputting the optical fiber strain signal into the curing stage identification model to obtain the current curing stage, wherein the curing stage includes a viscoelastic stage, a rubberization stage, and a vitrification stage.

[0074] Optionally, the current curing degree is determined based on the fused image obtained from the fiber optic signal and the ultrasonic guided wave signal, including: integrating the S0 mode signal in the ultrasonic guided wave signal on the time axis and plotting the actual curing degree curve based on the integration result; dividing the curing degree into a specified number of levels on the actual curing degree curve, and performing feature fusion of the ultrasonic guided wave signal and the fiber optic signal within the time period corresponding to each level to obtain a fused image; and inputting the fused image into a neural network model for recognition to determine the current curing degree.

[0075] Step S204: When the resin curing is complete, the dry spot area is determined based on the monitored fiber optic signal, and the quantitative information of the dry spot is determined based on the ultrasonic guided wave signal monitored in the dry spot area.

[0076] Optionally, when the resin curing is complete, the dry spot region is determined based on the monitored optical fiber signal, including: reconstructing the RTM fiber strain field based on the optical fiber signal, and accumulating and normalizing the strain values ​​in the reconstructed RTM fiber strain field at each time point; and taking the region where the processed strain value is less than a second preset threshold as the dry spot region.

[0077] Optionally, quantitative information about the dry spots is determined based on the ultrasonic guided wave signals monitored in the dry spot region, including: determining the probability density function of each grid point in the dry spot region based on the ultrasonic guided wave signals; when the probability density function is greater than a third threshold, the grid point is determined as a damage point; the size and location of the dry spots are determined based on the damage points, and the prime number and location are used as quantitative information.

[0078] Optionally, the probability density function of each grid point in the dry spot region is determined based on the ultrasonic guided wave signal, including: determining the relative distance from the piezoelectric sensing path to each grid point in the dry spot region based on the ultrasonic guided wave signal; determining the weighted distribution function based on the dynamic adaptive factor and obtaining the damage sensitivity index of each piezoelectric sensor in the dry spot region; and determining the probability density of each grid point based on the damage sensitivity index, the weighted distribution function and the relative distance.

[0079] Step S205: Generate a monitoring report based on the flow front monitoring results, solidification monitoring results, and dry spot monitoring results, and then visualize the monitoring report.

[0080] Specifically, this embodiment performs flow front monitoring, curing monitoring, and dry spot monitoring on the RTM-based product manufacturing process to achieve real-time monitoring of the manufacturing process and finished product quality inspection without affecting the fiber preform. Therefore, this embodiment acquires flow front monitoring results, curing monitoring results, and dry spot monitoring results, and analyzes each monitoring result to obtain manufacturing parameters and anomaly information for each time period. In addition, this embodiment summarizes and generates a monitoring report based on the above-acquired analysis information, and the above analysis information can be displayed in the monitoring report in the form of text or images, so that users can intuitively understand the RTM-based product manufacturing process based on the displayed monitoring report, so as to provide feedback on the manufacturing process parameters and ensure that the finished product RTM process meets the high-quality intelligent manufacturing of composite materials. Of course, this embodiment is only an example and does not limit the specific display format of the analysis information in the monitoring report.

[0081] It should be noted that when the monitoring parameters in the monitoring report exceed the normal range, the equipment will automatically generate alarm information and issue an alarm using a specified alarm method. This specified alarm method can be a voice alarm or a visual alarm; the specific form of the specified alarm method is not limited in this embodiment. This facilitates timely user intervention in the generation process to manually adjust abnormal parameters and prevent an increase in the number of defective or faulty parts on the production line.

[0082] The technical solution of this invention analyzes the acquired ultrasonic guided wave signal and fiber optic signal during the resin injection process to monitor the resin flow front, degree of curing and dry spots. The fiber optic monitoring results are cross-validated with the ultrasonic monitoring results to improve the precision of product manufacturing and the quality of finished products, thereby realizing intelligent manufacturing of composite materials.

[0083] Example 3

[0084] Figure 5 A schematic diagram of a product manufacturing process monitoring device based on resin transfer molding technology is provided as an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes: a sensor signal acquisition module 310, a flow front monitoring module 320, a solidification monitoring module 330, and a dry spot monitoring module 340.

[0085] Among them, the sensor signal acquisition module 310 is used to continuously monitor the fiber optic signal of the fiber optic sensor and the ultrasonic guided wave signal of the piezoelectric sensor when resin is injected into the fiber preform in the sealing mold using the RTM process.

[0086] The flow front monitoring module 320 is used to establish a first regression model of resin arrival time and fiber wetting area based on optical fiber signal when resin flows, establish a second regression model of ultrasonic guided wave stable amplitude and resin penetration thickness based on ultrasonic guided wave signal, and monitor the resin flow front based on the first regression model and the second regression model.

[0087] The curing monitoring module 330 is used to input the monitored optical fiber signal into a pre-trained curing stage recognition model to obtain the current curing stage during resin curing, and to determine the current curing degree based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal.

[0088] The dry spot monitoring module 340 is used to determine the dry spot area based on the monitored fiber optic signal when the resin curing is completed, and to determine the quantitative information of the dry spot based on the ultrasonic guided wave signal monitored in the dry spot area.

[0089] Optionally, the flow front monitoring module includes a first regression model building unit, which is used to reconstruct the RTM fiber strain field based on the fiber optic signal. When the strain value in the RTM fiber strain field exceeds a first preset threshold, the position corresponding to the strain value is taken as the position where the resin is completely impregnated.

[0090] The point where the strain value intersects with the threshold is taken as the resin arrival time, and a first regression model is established based on the impregnation location and arrival time, wherein the first regression model is used to represent the resin flow in the horizontal direction.

[0091] Optionally, the flow front monitoring module includes a second regression model building unit, which is used to extract the amplitude of the A0 mode signal in the ultrasonic guided wave signal and calculate the amplitude energy coefficient for ultrasonic guided wave signals whose amplitude has not reached a stable state.

[0092] When the amplitude energy coefficient tends to stabilize, the resin arrival time is determined, and a second regression model is established based on the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. The second regression model is used to represent the resin flow in the thickness direction.

[0093] Optionally, the curing monitoring module includes a curing stage acquisition unit, used to acquire fiber strain signals based on the monitored fiber signals during resin curing.

[0094] The fiber strain signal is input into the curing stage identification model to obtain the current curing stage, which includes the viscoelastic stage, rubberization stage and vitrification stage.

[0095] Optionally, the curing stage acquisition unit includes a curing degree determination unit, which is used to integrate the S0 mode signal in the ultrasonic guided wave signal on the time axis and plot the actual curing degree curve based on the integration result;

[0096] On the actual curing degree curve, the curing degree is divided into a specified number of levels, and the ultrasonic guided wave signal and the optical fiber signal within the time period corresponding to each level are fused to obtain a fused image.

[0097] The fused image is input into a neural network model for identification to determine the current degree of solidification.

[0098] Optionally, the speckle monitoring module includes a speckle region determination unit, which is used to reconstruct the RTM fiber strain field based on the fiber signal, and to accumulate and normalize the strain values ​​in the reconstructed RTM fiber strain field at each time.

[0099] The region where the strain value after processing is less than the second preset threshold is designated as the dry spot region.

[0100] Optionally, the dry spot monitoring module includes a dry spot quantitative information determination unit, which is used to determine the probability density function of each grid point in the dry spot region based on the ultrasonic guided wave signal;

[0101] When the probability density function is greater than the third threshold, the grid point is determined to be a damage point;

[0102] The size and location of the dry spots are determined based on the damage points, and the prime number and location are used as quantitative information.

[0103] Optionally, a dry spot quantitative information determination unit is used to determine the relative distance from the piezoelectric sensing path to each grid point in the dry spot region based on the ultrasonic guided wave signal.

[0104] The weighted distribution function is determined based on the dynamic adaptive factor, and the damage sensitivity index of each piezoelectric sensor in the dry spot region is obtained.

[0105] The probability density of each grid point is determined based on the damage sensitivity index, the weighted distribution function, and the relative distance.

[0106] The product manufacturing process monitoring device based on resin transfer molding provided in this embodiment of the invention can execute the product manufacturing process monitoring method based on resin transfer molding provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0107] Example 4

[0108] Figure 6 A schematic diagram of a terminal device 10 that can be used to implement embodiments of the present invention is shown. The terminal device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The terminal device can also represent various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0109] The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0110] like Figure 6As shown, the terminal device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the terminal device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0111] Multiple components in terminal device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows terminal device 10 to exchange information / data with other terminal devices through computer networks such as the Internet and / or various telecommunications networks.

[0112] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a product manufacturing process monitoring method based on resin transfer molding.

[0113] In some embodiments, the product manufacturing process monitoring method based on resin transfer molding can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on terminal device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the product manufacturing process monitoring method based on resin transfer molding described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the product manufacturing process monitoring method based on resin transfer molding by any other suitable means (e.g., by means of firmware).

[0114] Various embodiments of the apparatuses and techniques described above herein can be implemented in digital electronic circuit devices, integrated circuit devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), device-on-a-chip (SoCs), complex programmable logic terminal devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable device including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage device, at least one input device, and at least one output device, and transmitting data and instructions to the storage device, the at least one input device, and the at least one output device.

[0115] Computer programs used to implement the product manufacturing process monitoring method based on resin transfer molding of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other business-on-demand data migration device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution apparatus, device, or terminal device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage terminal devices, magnetic storage terminal devices, or any suitable combination thereof.

[0117] To provide interaction with a user, the apparatus and techniques described herein can be implemented on a terminal device having: a display device (e.g., a touchscreen) for displaying information to the user; and buttons through which the user can provide input to the terminal device. Other types of apparatus can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and input from the user can be received in any form (including voice input, speech input, or haptic input).

[0118] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0119] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for monitoring the product manufacturing process based on resin transfer molding, characterized in that, A method applicable to a manufacturing system based on resin transfer molding (RTM) process, the system comprising a sealed mold, a fiber preform, an optical fiber sensor, and a piezoelectric sensor located within the sealed mold, the method comprising: During resin injection into the fiber preform in the sealing mold using the RTM process, the fiber optic signal of the fiber optic sensor and the ultrasonic guided wave signal of the piezoelectric sensor are continuously monitored. A first regression model is established based on the fiber optic signal to establish the resin arrival time and the fiber wetting area during resin flow. A second regression model is established based on the ultrasonic guided wave signal to establish the stable amplitude of the ultrasonic guided wave and the resin penetration thickness. The resin flow front is monitored based on the first regression model and the second regression model. During resin curing, the monitored optical fiber signal is input into a pre-trained curing stage recognition model to obtain the current curing stage, and the current curing degree is determined based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal. When the resin curing is complete, the dry spot area is determined based on the monitored fiber optic signal, and the quantitative information of the dry spot is determined based on the ultrasonic guided wave signal monitored in the dry spot area.

2. The method according to claim 1, characterized in that, The establishment of a first regression model based on the fiber optic signal to establish the resin arrival time and fiber wetting area during resin flow includes: The RTM fiber strain field is reconstructed based on the fiber signal. When the strain value in the RTM fiber strain field exceeds a first preset threshold, the position corresponding to the strain value is taken as the position where the resin is completely impregnated. The intersection of the strain value and the threshold is taken as the resin arrival time, and a first regression model is established based on the impregnation location and the arrival time, wherein the first regression model is used to represent the resin flow in the horizontal direction.

3. The method according to claim 2, characterized in that, The establishment of a second regression model based on the ultrasonic guided wave signal to correlate the stable amplitude of the ultrasonic guided wave with the resin penetration thickness includes: The amplitude of the A0 mode signal in the ultrasonic guided wave signal is extracted, and the amplitude energy coefficient is calculated for ultrasonic guided wave signals whose amplitude has not reached a stable state. When the amplitude energy coefficient tends to stabilize, the resin arrival time is determined, and a second regression model is established based on the stable amplitude of the ultrasonic guided wave and the resin penetration thickness, wherein the second regression model is used to represent the resin flow in the thickness direction.

4. The method according to claim 1, characterized in that, The step of inputting the monitored fiber optic signal into a pre-trained curing stage recognition model during resin curing to obtain the current curing stage includes: During resin curing, fiber strain signals are acquired based on the monitored fiber signals. The fiber strain signal is input into the curing stage identification model to obtain the current curing stage, wherein the curing stage includes a viscoelastic stage, a rubberization stage, and a vitrification stage.

5. The method according to claim 4, characterized in that, Determining the current curing degree based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal includes: The S0 mode signal in the ultrasonic guided wave signal is integrated on the time axis, and the actual curing degree curve is plotted based on the integration result; The curing degree is divided into a specified number of levels on the actual curing degree curve, and the ultrasonic guided wave signal and the optical fiber signal within the time period corresponding to each level are fused to obtain a fused image. The fused image is input into a neural network model for identification to determine the current solidification level.

6. The method according to claim 1, characterized in that, The process of determining the dry spot area based on the monitored fiber optic signal upon completion of resin curing includes: The RTM fiber strain field is reconstructed based on the fiber signal, and the strain values ​​in the reconstructed RTM fiber strain field at each time moment are accumulated and normalized. The region where the strain value after processing is less than the second preset threshold is designated as the dry spot region.

7. The method according to claim 1, characterized in that, The step of determining quantitative information about the dry spots based on the ultrasonic guided wave signals monitored in the dry spot region includes: The probability density function of each grid point in the dry spot region is determined based on the ultrasonic guided wave signal. When the probability density function is greater than the third threshold, the grid point is determined to be a damage point; The size and location of the dry spots are determined based on the damage points, and the prime number and location are used as the quantitative information.

8. The method according to claim 7, characterized in that, The step of determining the probability density function of each grid point in the dry spot region based on the ultrasonic guided wave signal includes: The relative distance from the piezoelectric sensing path to each grid point in the dry spot region is determined based on the ultrasonic guided wave signal. The weighted distribution function is determined based on the dynamic adaptive factor, and the damage sensitivity index of each piezoelectric sensor in the dry spot region is obtained. The probability density of each grid point is determined based on the damage sensitivity index, the weighted distribution function, and the relative distance.

9. A product manufacturing process monitoring device based on resin transfer molding technology, characterized in that, The device includes: The sensor signal acquisition module is used to continuously monitor the fiber optic signal of the fiber optic sensor and the ultrasonic guided wave signal of the piezoelectric sensor when resin is injected into the fiber preform in the sealed mold using the RTM process. The flow front monitoring module is used to establish a first regression model of resin arrival time and fiber wetting area based on optical fiber signal when resin flows, establish a second regression model of ultrasonic guided wave stable amplitude and resin penetration thickness based on ultrasonic guided wave signal, and monitor the resin flow front based on the first regression model and the second regression model. The curing monitoring module is used to input the monitored optical fiber signal into a pre-trained curing stage recognition model to obtain the current curing stage during resin curing, and to determine the current curing degree based on the fused image obtained from the optical fiber signal and the ultrasonic guided wave signal. The dry spot monitoring module is used to determine the dry spot area based on the monitored fiber optic signal when the resin curing is completed, and to determine the quantitative information of the dry spot based on the ultrasonic guided wave signal monitored in the dry spot area.

10. A terminal device, characterized in that, The terminal device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-8.

11. A storage medium for computer-executable instructions, wherein a computer program is stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-8.

Images