A high-performance carbon fiber preform injection molding detection system and detection method

Abstract

The present invention relates to the technical field of preform injection molding detection technology, and specifically discloses a high-performance carbon fiber preform injection molding detection system and detection method, which can realize real-time analysis of high-performance carbon fiber preform injection molding process parameters, ensure corresponding adjustment of the injection molding process and injection molding automation data generation process. The system includes: a data acquisition unit collects injection molding process parameters and screw speed data of automated handling equipment in real time through a multi-sensor; a preform injection molding recognition unit automatically identifies abnormal areas in the image information of the injection molding surface of the preform online; a data analysis unit statistically analyzes abnormal areas in image information obtained at different time points at the same detection position within a historical time period, compares and judges the processing quality of the injection molding surface of the preform, and adjusts the injection molding process parameters according to the comparison results; a process detection unit detects the matching degree of the preform and the mold under the adjusted injection molding process parameters online, and adjusts the screw speed according to the detection and analysis results.

Description

Technical Field

[0001] The invention relates to the technical field of preform injection molding processing detection, and in particular to a high-performance carbon fiber preform injection molding processing detection system and detection method. Background Art

[0002] High-performance carbon fiber preform injection molding is a manufacturing technology that combines carbon fiber with other materials (such as thermoplastic resins) to produce composite parts with high strength, high rigidity and light weight. It has broad application prospects in the fields of aviation, automobiles, sports equipment and medical devices. This type of processing technology can improve production efficiency, reduce costs, and maintain or improve the performance of the final product.

[0003] Modern injection molding inspection technology is developing towards automation, intelligence and high precision. For example, machine vision-based inspection systems can provide fast and continuous inspections, reduce manual intervention, and improve the accuracy and repeatability of inspections. In addition, non-destructive inspection technologies, such as industrial CT scanning, can provide detailed images of the internal structure of injection molded products, helping to discover imperceptible defects.

[0004] In the existing technologies for realizing high-performance carbon fiber preform injection molding processing detection, most of them adopt a single automated detection system, which realizes the standardized process through parameter control of each process of high-performance carbon fiber preform injection molding processing based on real-time observation and detection. However, in the existing high-performance carbon fiber preform injection molding, it is necessary to consider in advance whether the carbon fiber surface injection molding conditions are qualified, and it is also necessary to monitor the injection molding process of each preform in real time. This operation process lacks automation and systematization, and it is difficult to coordinate and adjust the injection molding images and injection molding parameter data acquired in real time. There is also a lack of systematic detection and analysis process for each injection molding process and the next step of operation, resulting in a low degree of automation in the overall detection system. Summary of the invention

[0005] The purpose of the present invention is to provide a high-performance carbon fiber preform injection molding processing detection system and detection method to solve the following technical problems:

[0006] How to analyze the injection molding process parameters of high-performance carbon fiber preforms in real time to achieve corresponding adjustments to the injection molding process and generate injection molding automation data.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A high-performance carbon fiber preform injection molding processing detection system, comprising:

[0009] A data acquisition unit, which is used to collect injection molding process parameters and screw speed data of automated handling equipment in real time through multi-sensors;

[0010] The preform injection molding recognition unit is used to automatically identify abnormal areas in the image information of the injection molding surface of the preform online; the data analysis unit is used to statistically analyze the abnormal areas in the image information obtained at different time points at the same detection position within a historical time period, compare and judge the processing quality of the injection molding surface of the preform, and adjust the injection molding process parameters according to the comparison results;

[0011] The process detection unit is used to detect the matching degree between the preform and the mold under the injection molding process parameters after online adjustment, and adjust the screw speed according to the detection and analysis results.

[0012] Preferably, the specific steps of the preform injection molding identification unit include:

[0013] graying the surface image of the unprocessed preform;

[0014] The Canny algorithm is used to extract the injection boundary line and abnormal area contour in the preform surface image.

[0015] Preferably, the data analysis unit comprises:

[0016] Calculate the vertical distance from the center of the abnormal area contour to the injection boundary line to form the first set A;

[0017] Comparing a first set A of preform injection molding surface images at the same position at different time points, and forming a second set B with overlapping elements;

[0018] Compare the element x in the second set B with the standard set C:

[0019] If x C, then it is determined that the injection molding surface quality of the preform in the abnormal area corresponding to x is normal;

[0020] If x C, it is determined that there is a problem with the injection molding surface quality of the preform in the abnormal area corresponding to x, and the injection molding process parameters are adjusted according to the result of the surface quality problem judgment.

[0021] Preferably, the data analysis unit also includes determining the surface quality problem:

[0022] Calculate the area S and perimeter C of the abnormal area where the quality of the preform injection molding surface is problematic, and calculate the abnormal area structure value i through the formula;

[0023] The abnormal area structure value i and the preset threshold and For comparison, < :

[0024] If i≤ , then the abnormal area on the injection molding surface of the preform is judged to be a narrow crack;

[0025] like <i< , then the abnormal area on the injection molding surface of the preform is judged to be a wide crack;

[0026] If i≥ , then it is judged that the abnormal area on the injection molding surface of the preform is a depression or a convex block.

[0027] Preferably, the process detection unit comprises:

[0028] By formula Calculate the The matching coefficient between the preform and its mold under similar injection molding process parameters ;in, Adjust the total amount for the injection molding process parameters, and ∈ ; A preset matching application coefficient for adjusting and processing abnormal areas on the injection molding surface of the preform under the 𝑘th type of injection molding process parameters; For the Adjust the matching application coefficient of injection molding process parameters; For the Adjust the weight coefficient of injection molding process parameters.

[0029] Preferably, it also includes:

[0030] The matching coefficient The preset matching coefficient threshold interval To compare:

[0031] like ∈ , then the current process detection match is judged to be appropriate, and the detection process continues;

[0032] like < , it is judged that the current is lower than the process detection matching range, and the number of process adjustments is increased and the screw speed is increased;

[0033] like > , it is judged that the current process exceeds the process detection matching range, and the number of process adjustments and screw speed are reduced.

[0034] Preferably, the system further comprises:

[0035] The handling information collection unit is used to collect the current screw speed and obtain the handling information of the current process;

[0036] The transport information feedback unit is used to determine the transport processing efficiency based on the transport information.

[0037] Preferably, the transport information is obtained in the following manner:

[0038] By formula Calculate the transport coefficient ;in, is the preset weight coefficient; is the number of transports; is the screw speed, is the standard value of screw speed; is the centrifugal acceleration of the screw speed, is the standard value of centrifugal acceleration of screw speed;

[0039] The transport factor With the preset standard handling coefficient To compare:

[0040] like < , then it is judged that the current handling and processing efficiency meets the requirements;

[0041] Otherwise, it is judged that the current handling and processing efficiency does not meet the requirements.

[0042] A high-performance carbon fiber preform injection molding processing detection method is applied to a high-performance carbon fiber preform injection molding processing detection system, and the method includes:

[0043] Step 1: Use multi-sensor to collect injection molding process parameters and screw speed data of automated handling equipment in real time;

[0044] Step 2: Automatically identify abnormal areas in the image information of the injection molding surface of the preform online;

[0045] Step 3: Analyze abnormal areas in the image information obtained at different time points at the same detection position within the historical time period, compare and judge the processing quality of the preform injection molding surface, and adjust the injection molding process parameters according to the comparison results;

[0046] Step 4: Online detection and adjustment of the matching degree between the preform and the mold under the injection molding process parameters, and adjustment of the screw speed according to the detection and analysis results.

[0047] Beneficial effects of the present invention:

[0048] (1) The present invention sets a data acquisition unit, a preform injection molding recognition unit, a data analysis unit, and a process detection unit. According to the real-time acquisition of injection molding process parameters and screw speed data, the present invention determines and automatically identifies abnormal areas in the image information of the preform injection molding surface, analyzes and detects the surface information of the abnormal areas of the preform, determines the processing quality of the preform injection molding surface by comparison, and adjusts the injection molding process parameters according to the comparison results; accurately determines the image area information through the parameter data comparison and analysis process, realizes the adjustment of the online injection molding process, and ensures the uniformity and quality control of the preform injection molding surface; realizes the surface injection molding detection and intelligent detection data abnormality analysis in the high-performance carbon fiber injection molding process, and realizes the quality detection process of high-performance carbon fiber injection molding products.

[0049] (2) The present invention also adjusts the matching degree between the preform and the mold under the injection molding process parameters through online detection, and adjusts the screw speed according to the detection and analysis results, thereby realizing flexible adjustment of process parameters such as processing speed, temperature, pressure, and humidity.

[0050] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0052] Figure 1 This is a module diagram of a high-performance carbon fiber preform injection molding processing detection system of the present invention;

[0053] Figure 2 This is a step diagram of a high-performance carbon fiber preform injection molding processing detection method of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1 As shown, the present invention is a high-performance carbon fiber preform injection molding processing detection system, comprising:

[0056] A data acquisition unit, which is used to collect injection molding process parameters and screw speed data of automated handling equipment in real time through multi-sensors;

[0057] A preform injection molding recognition unit is used to automatically recognize abnormal areas in the preform injection molding surface image information online;

[0058] A data analysis unit is used to statistically analyze abnormal areas in image information obtained at different time points at the same detection position within a historical time period, compare and judge the processing quality of the injection molding surface of the preform, and adjust the injection molding process parameters according to the comparison results;

[0059] The process detection unit is used to detect the matching degree between the preform and the mold under the injection molding process parameters after online adjustment, and adjust the screw speed according to the detection and analysis results.

[0060] In the above technical scheme, the present invention realizes surface injection molding detection and intelligent detection data abnormality analysis during the high-performance carbon fiber injection molding process by setting: a data acquisition unit, a preform injection molding identification unit, a data analysis unit, and a process detection unit, thereby realizing the quality detection process of high-performance carbon fiber injection molding products.

[0061] Specifically, firstly, a data acquisition unit is set to collect injection molding process parameters and screw speed data of automated handling equipment in real time through multi-element sensors; the hardware equipment required in the injection molding process usually includes injection molding machines, automated handling devices, high-precision multi-element sensors, etc., and the software required in injection molding calculations usually involves data processing, model simulation and control algorithms. The injection molding process parameters such as injection temperature, injection pressure and injection time are collected in real time through multi-element sensors, and the screw speed data of automated handling equipment is obtained, so as to realize the real-time acquisition of high-performance carbon fiber preform injection molding process data and the automatic data generation process.

[0062] Secondly, a preform injection molding recognition unit is provided for automatically identifying abnormal areas in the image information of the preform injection molding surface online; the collected image data of the preform injection molding surface is analyzed by utilizing an image processing algorithm, and the surface information of the preform is analyzed and detected, such as key parameters such as the brightness of the injection molding surface, the direction of the injection molding surface, and the distribution of the injection molding surface, so as to ensure the uniformity and quality control of the preform injection molding surface.

[0063] Thirdly, a data analysis unit is provided to statistically analyze abnormal areas in the image information obtained at different time points at the same detection position within a historical time period, compare and judge the surface processing quality of the preform injection molding, and adjust the injection molding process parameters according to the comparison results; and accurate judgment of the image area information is achieved through the comparison and analysis process of parameter data.

[0064] Fourthly, a process detection unit is set up to detect the matching degree of the preform and the mold under the injection molding process parameters after online adjustment, and the screw speed is adjusted according to the detection and analysis results, thereby realizing flexible adjustment of process processing speed, temperature, pressure, humidity and other parameters.

[0065] As an embodiment of the present invention, the specific steps of the preform injection molding identification unit include:

[0066] graying the surface image of the unprocessed preform;

[0067] The Canny algorithm is used to extract the injection boundary line and abnormal area contour in the preform surface image.

[0068] In the above technical scheme, in this embodiment, the surface image of the carbon fiber preform is preprocessed to eliminate interference information of the surface image information and optimize the image information, so as to realize the data analysis process of the surface injection molding state, and the process of setting the preform injection molding recognition unit for recognition is as follows: first, the surface image of the unprocessed preform is grayed, and then the injection molding boundary line and the abnormal area contour in the preform surface image are extracted by the Canny algorithm to provide basic conditions for the subsequent data analysis of the injection molding surface.

[0069] As an embodiment of the present invention, the data analysis unit includes:

[0070] Calculate the vertical distance from the center of the abnormal area contour to the injection boundary line to form the first set A;

[0071] Comparing a first set A of preform injection molding surface images at the same position at different time points, and forming a second set B with overlapping elements;

[0072] Compare the element x in the second set B with the standard set C:

[0073] If x C, then it is determined that the injection molding surface quality of the preform in the abnormal area corresponding to x is normal;

[0074] If x C, it is determined that there is a problem with the injection molding surface quality of the preform in the abnormal area corresponding to x, and the injection molding process parameters are adjusted according to the result of the surface quality problem judgment.

[0075] In the above technical scheme, the data analysis unit in this embodiment performs data calculation on the preprocessed image information, and calculates the vertical distance between the center of the abnormal area contour and the injection surface boundary. The specific calculation process here is to determine several boundary lines by analyzing the injection area and injection boundary line of the current detection area image, and select no less than three vertical distance sizes. Of course, for the specific calculation, the number of target points from the specific vertical abnormal area center to the selected injection boundary line is determined according to the injection range and injection conditions, and then the number of data sets of the first set of vertical distances is determined corresponding to the target number of points; then the first set A of the preform injection surface images at different time points at the same position is compared, and the overlapping elements are formed into a second set B. For the injection molding detection at the current position, the distance information of the abnormal information of the preform injection surface image at different time points is obtained. Finally, through the comparison and analysis process, the element x in the second set B is compared with the standard set C to determine if x C, then it is determined that the injection molding surface quality of the preform in the abnormal area corresponding to x is normal; if x C, it is determined that there is a problem with the injection molding surface quality of the preform in the abnormal area corresponding to x, and the injection molding process parameters are adjusted according to the result of the surface quality problem judgment.

[0076] As an embodiment of the present invention, the data analysis unit further includes determining the surface quality problem:

[0077] Calculate the area S and perimeter C of the abnormal area where the quality of the preform injection molding surface is problematic, and calculate the abnormal area structure value i through the formula;

[0078] The abnormal area structure value i and the preset threshold and For comparison, < :

[0079] If i≤ , then the abnormal area on the injection molding surface of the preform is judged to be a narrow crack;

[0080] like <i< , then the abnormal area on the injection molding surface of the preform is judged to be a wide crack;

[0081] If i≥ , then it is judged that the abnormal area on the injection molding surface of the preform is a depression or a convex block.

[0082] In the above technical solution, the surface quality problem is specifically determined by the data analysis unit, and the abnormal region structure value i is determined by calculating the area of ​​the abnormal region where the preform injection molding surface obviously has structural problems; the state of the obvious abnormal region on the preform injection molding surface is determined according to the state of the abnormal region structure value i. Because the injection molding surface may have obvious structural differences due to the injection molding amount and the matching state of the injection molding object mold during the injection molding process, the abnormal region structure value i is compared with the standard value to determine if <i< , then the abnormal area on the injection molding surface of the preform is judged to be a wide crack; if i≥ , then it is judged that the abnormal area on the injection molding surface of the preform is a depression or a convex block.

[0083] As an embodiment of the present invention, the process detection unit includes:

[0084] By formula Calculate the The matching coefficient between the preform and its mold under similar injection molding process parameters ;in, Adjust the total amount for the injection molding process parameters, and ∈ ; A preset matching application coefficient for adjusting and processing the abnormal area on the injection molding surface of the preform under the 𝑘th type of injection molding process parameters; For the Adjust the matching application coefficient of injection molding process parameters; For the Adjust the weight coefficient of injection molding process parameters.

[0085] In the above technical solution, the process detection unit in this embodiment obtains the matching coefficient of the preform and its mold through calculation by a formula, and the matching coefficients of different types of injection molding process parameters are different. Specifically, the matching coefficients are obtained by the formula Calculate the The matching coefficient between the preform and its mold under similar injection molding process parameters , determined by the size of the matching application coefficient under the cumulative number of process parameter adjustments and the weight coefficient corresponding to the previous cumulative adjustments of the injection molding process parameters, and each injection molding adjustment corresponding to the current injection molding process parameters leads to are different, so the weight coefficient It is obtained by simulation based on parameter data of historical adjustment times.

[0086] As an embodiment of the present invention, it also includes:

[0087] The matching coefficient The preset matching coefficient threshold interval To compare:

[0088] like ∈ , then the current process detection match is judged to be appropriate, and the detection process continues;

[0089] like < , it is judged that the current is lower than the process detection matching range, and the number of process adjustments is increased and the screw speed is increased;

[0090] like > , it is judged that the current process exceeds the process detection matching range, and the number of process adjustments and screw speed are reduced.

[0091] In the above technical solution, in this embodiment, the matching coefficient of the process detection unit is also The analysis process is to compare it with the preset matching coefficient threshold interval Compare the size, if it does not meet the current interval, that is, it does not belong to the preset matching coefficient threshold interval When it is less than the minimum value of the current interval, < When , it is judged that the current process detection matching range is too low, and it is necessary to improve the current process adjustment order, increase the injection volume or injection speed in the current area, and adjust the injection uniformity, that is, speed up the screw speed; on the contrary, for > If the current process detection matching range is too large, it is necessary to reduce the injection adjustment times, reduce the injection volume, or reduce the current injection thickness and injection volume when the setting matching is exceeded, and grind the exceeding part evenly and reduce its screw speed, increase the grinding time or grinding intensity. This process is realized by equipment such as grinders or scrapers, which are set at the process equipment of the injection molding matching mold and configured corresponding to the position of the injection molding machine.

[0092] As an embodiment of the present invention, the system further includes:

[0093] The handling information collection unit is used to collect the current screw speed and obtain the handling information of the current process;

[0094] The transport information feedback unit is used to determine the transport processing efficiency based on the transport information.

[0095] In the above technical scheme, the system of this embodiment is also equipped with a handling information collection unit and a handling information feedback unit to ensure the judgment and analysis of the transportation and adjustment of the high-performance carbon fiber after injection molding. Specifically, the handling information collection unit is set to ensure the collection of the current screw speed and obtain the handling information of the current process; the handling information feedback unit is set to judge the handling processing efficiency based on the handling information.

[0096] As an implementation mode of the present invention, the method of obtaining the transport information is as follows:

[0097] By formula Calculate the transport coefficient ;in, is the preset weight coefficient; is the number of transports; is the screw speed, is the standard value of screw speed; is the centrifugal acceleration of the screw speed, is the standard value of centrifugal acceleration of screw speed;

[0098] The transport factor With the preset standard handling coefficient To compare:

[0099] like < , then it is judged that the current handling and processing efficiency meets the requirements;

[0100] Otherwise, it is judged that the current handling and processing efficiency does not meet the requirements.

[0101] In the above technical solution, whether the current transport status is suitable is determined by obtaining the transport information, specifically by calculating the formula Calculate the transport coefficient , judge the difference between the screw speed and acceleration under the current handling state to judge whether the handling efficiency is normal; specifically, by With the preset standard handling coefficient Compare the sizes, make adjustments to situations that do not meet the current handling and processing efficiency, adjust the handling speed, and improve the handling efficiency.

[0102] Among them, it needs further explanation that the standard value , It is obtained by simulating historical data and will not be described in detail here; the preset weight coefficient The fitting weights are calculated in advance based on empirical data to ensure a qualitative analysis of the impact of multiple handling on the current handling efficiency and its impact on the final result, and the results of machine learning operations are performed through statistics. They are not described in detail here.

[0103] See also Figure 2 As shown, the present invention designs a high-performance carbon fiber preform injection molding processing detection method, which is applied to a high-performance carbon fiber preform injection molding processing detection system, and the method includes:

[0104] Step 1: Use multi-sensor to collect injection molding process parameters and screw speed data of automated handling equipment in real time;

[0105] Step 2: Automatically identify abnormal areas in the image information of the injection molding surface of the preform online;

[0106] Step 3: Analyze abnormal areas in the image information obtained at different time points at the same detection position within the historical time period, compare and judge the processing quality of the preform injection molding surface, and adjust the injection molding process parameters according to the comparison results;

[0107] Step 4: Online detection and adjustment of the matching degree between the preform and the mold under the injection molding process parameters, and adjustment of the screw speed according to the detection and analysis results.

[0108] The overall technical process of the present invention is: by setting up a data acquisition unit, a preform injection molding recognition unit, a data analysis unit, and a process detection unit in sequence. First, the data acquisition unit is set to collect injection molding process parameters and screw speed data in real time, and then the preform injection molding recognition unit is set to judge the abnormal area in the preform injection molding surface image information online automatically, and then the data analysis unit is set to analyze and detect the surface information of the abnormal area of ​​the preform, judge the preform injection molding surface processing quality by comparison, and adjust the injection molding process parameters according to the comparison results; and realize the accurate judgment of the image area information through the parameter data comparison and analysis process, realize the adjustment of the online injection molding process, and ensure the uniformity and quality control of the preform injection molding surface; realize the surface injection molding detection and intelligent detection data abnormality analysis in the high-performance carbon fiber injection molding process, and realize the quality detection process of high-performance carbon fiber injection molding products; finally, the process detection unit is set. The present invention also adjusts the screw speed according to the detection and analysis results through online detection of the matching degree of the preform and the mold under the injection molding process parameters after adjustment, and then realizes the flexible adjustment of process processing speed, temperature, pressure, humidity and other parameters.

[0109] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0110] The above specific embodiments of this specification are described. Other embodiments are within the scope of the attached documents. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. A high-performance carbon fiber preform injection molding processing detection system, characterized in that: include: A data acquisition unit, which is used to collect injection molding process parameters and screw speed data of automated handling equipment in real time through multi-sensors; A preform injection molding recognition unit is used to automatically recognize abnormal areas in the preform injection molding surface image information online; A data analysis unit is used to statistically analyze abnormal areas in image information obtained at different time points at the same detection position within a historical time period, compare and judge the processing quality of the injection molding surface of the preform, and adjust the injection molding process parameters according to the comparison results; The process detection unit is used to detect the matching degree between the preform and the mold under the adjusted injection molding process parameters online, and adjust the screw speed according to the detection and analysis results; The specific steps of the preform injection molding identification unit include: graying the surface image of the unprocessed preform; The Canny algorithm is used to extract the injection boundary line and abnormal area contour in the preform surface image; The data analysis unit comprises: Calculate the vertical distance from the center of the abnormal area contour to the injection boundary line to form the first set A; Comparing a first set A of preform injection molding surface images at the same position at different time points, and forming a second set B with overlapping elements; Compare the element x in the second set B with the standard set C: If x C, then it is determined that the injection molding surface quality of the preform in the abnormal area corresponding to x is normal; If x C, it is determined that there is a problem with the injection molding surface quality of the preform in the abnormal area corresponding to x, and the injection molding process parameters are adjusted according to the result of the surface quality problem judgment.

2. A high-performance carbon fiber preform injection molding detection system according to claim 1, characterized in that: The data analysis unit also includes determining the surface quality problem: Calculate the area S and perimeter C of the abnormal area where the quality of the preform injection molding surface is problematic, and calculate the abnormal area structure value i through the formula; The abnormal area structure value i and the preset threshold and For comparison, < : If i≤ , then the abnormal area on the injection molding surface of the preform is judged to be a narrow crack; like <i< , then the abnormal area on the injection molding surface of the preform is judged to be a wide crack; If i≥ , then it is judged that the abnormal area on the injection molding surface of the preform is a depression or a convex block.

3. A high-performance carbon fiber preform injection molding detection system according to claim 1, characterized in that: The process detection unit comprises: By formula Calculate the The matching coefficient between the preform and its mold under similar injection molding process parameters ;in, Adjust the total amount for the injection molding process parameters, and ∈ ; A preset matching application coefficient for adjusting and processing the abnormal area on the injection molding surface of the preform under the 𝑘th type of injection molding process parameters; For the Adjust the matching application coefficient of injection molding process parameters; For the Adjust the weight coefficient of injection molding process parameters.

4. A high-performance carbon fiber preform injection molding detection system according to claim 3, characterized in that: The process detection unit also includes: The matching coefficient The preset matching coefficient threshold interval To compare: like ∈ , then the current process detection match is judged to be appropriate, and the detection process continues; like < , it is judged that the current is lower than the process detection matching range, and the number of process adjustments is increased and the screw speed is increased; like > , it is judged that the current process exceeds the process detection matching range, and the number of process adjustments and screw speed are reduced.

5. A high-performance carbon fiber preform injection molding detection system according to claim 1, characterized in that: The system further comprises: The handling information collection unit is used to collect the current screw speed and obtain the handling information of the current process; The transport information feedback unit is used to determine the transport processing efficiency based on the transport information.

6. A high-performance carbon fiber preform injection molding processing detection system according to claim 5, characterized in that: The method for obtaining the transport information is as follows: By formula Calculate the transport coefficient ;in, is the preset weight coefficient; is the number of transports; is the screw speed, is the standard value of screw speed; is the centrifugal acceleration of the screw speed, is the standard value of centrifugal acceleration of screw speed; The transport factor With the preset standard handling coefficient To compare: like < , then it is judged that the current handling and processing efficiency meets the requirements; Otherwise, it is judged that the current handling and processing efficiency does not meet the requirements.

7. A high-performance carbon fiber preform injection molding detection method, applied to a high-performance carbon fiber preform injection molding detection system as described in any one of claims 1 to 6, characterized in that: The method comprises: Step 1: Use multi-sensor to collect injection molding process parameters and screw speed data of automated handling equipment in real time; Step 2: Automatically identify abnormal areas in the image information of the injection molding surface of the preform online; Step 3: Analyze abnormal areas in the image information obtained at different time points at the same detection position within the historical time period, compare and judge the processing quality of the preform injection molding surface, and adjust the injection molding process parameters according to the comparison results; Step 4: Online detection and adjustment of the matching degree between the preform and the mold under the injection molding process parameters, and adjustment of the screw speed according to the detection and analysis results.

Images