A method and system for intelligent temperature monitoring and control in composite material production

Abstract

The application belongs to the technical field of composite material production control, and specifically relates to a temperature intelligent monitoring control method and system for composite material production. The temperature intelligent monitoring control system comprises a monitoring point planning module, a temperature monitoring analysis module, a temperature control module and a dynamic adjustment module. The monitoring point planning is combined with three-dimensional scanning of a mold and material thickness data to quantitatively identify corners, abnormal material area blind spots and accurately lay out sensors to eliminate monitoring loopholes. Temperature monitoring is subjected to abnormal data filtering and distance weighted modeling to ensure data reliability and model fitting to reality. Temperature control is subjected to deviation grading decision making, quantitative adjustment of heating / cooling power, avoidance of temperature fluctuations and guarantee of material forming quality. Dynamic adjustment of monitoring temperature change rate and pressure timely plans monitoring points to adapt to dynamic changes in production. The system is modularly designed, and a process is closed loop controllable, suitable for different processes, helps intelligentization of composite material production, and improves product qualification rate and production stability.

Description

Technical Field

[0001] This invention belongs to the field of composite material production control technology, specifically a method and system for intelligent temperature monitoring and control in composite material production. Background Technology

[0002] In the process of composite material molding and production, precise control of the temperature field inside the mold is the core factor that determines the curing degree, mechanical properties and appearance quality of the product. If the local temperature is too high or too low, it is easy to cause stress concentration and uneven curing inside the product, which can lead to defects such as cracking, delamination and bubbles, seriously affecting the service life and safety performance of the product. Therefore, the temperature monitoring system is a key component of the composite material production line.

[0003] Existing temperature monitoring systems for composite material production generally employ a fixed-point deployment of temperature sensors: that is, during the mold installation stage, the sensor positions are determined based on experience or a simple principle of uniform distribution, and these sensor positions remain fixed throughout the entire production cycle. However, this approach is difficult to adapt to the complex working conditions required for composite material molding.

[0004] On the one hand, composite material molding dies often contain multiple irregularly shaped areas such as corners, grooves, and bosses. The heat conduction paths in these areas differ significantly from those in planar areas, making heat prone to accumulation or dissipation. Simultaneously, the distribution of material within the die is influenced by the feeding method and flow characteristics, easily leading to localized thicker or thinner accumulations—thicker material areas have higher heat capacity and slower heating rates, while thinner material areas heat up faster, exhibiting significantly different temperature change patterns. Sensors deployed at fixed points cannot adjust their monitoring positions based on the die's structural characteristics and material distribution differences, easily creating monitoring blind spots in critical areas such as die corners and areas with thicker material accumulations, resulting in ineffective temperature data collection in these areas.

[0005] On the other hand, monitoring blind spots directly lead to incomplete temperature monitoring data: the system cannot fully reflect the actual temperature state during the production process and can only make judgments based on temperature data from local, non-critical areas, thus lacking accurate basis for subsequent temperature control decisions. For example, when the temperature in the corner area of ​​the mold exceeds the standard and is not detected due to a monitoring blind spot, it may lead to over-curing of the product in that area; while when the temperature in areas with thick material accumulation does not reach the target value, it will cause insufficient curing, ultimately leading to batch product quality problems, increasing production costs, and raising the rework rate. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for intelligent temperature monitoring and control in composite material production, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent temperature monitoring and control in composite material production, comprising the following steps:

[0008] Step 1: Monitoring Point Planning

[0009] A 3D scan of the composite material molding die structure was performed to obtain the die's 3D coordinate data. Simultaneously, a mesh generation method was used to divide the die area into several square mesh thickness measurement regions. Then, by simulating or actually measuring the initial material distribution within the die, thickness data of the material distribution was collected. Based on the die's 3D coordinate data and the material distribution thickness data, the corner areas of the die and the material distribution areas were identified and analyzed to identify areas prone to blind spots in monitoring. Finally, the sensor placement locations were determined by combining the identification and analysis results of the die's corner areas and the material distribution areas.

[0010] Step 2: Temperature Monitoring and Analysis

[0011] Temperature sensors are installed inside the mold according to their locations, and the temperature at each location is collected in real time. Then, a temperature distribution model inside the mold is established based on the temperature data. The target temperature of each area inside the mold is extracted, and the deviation between the actual temperature and the target temperature of each small grid unit is calculated.

[0012] Step 3: Temperature Control

[0013] When the absolute value of the deviation between the actual temperature of the small grid cell and the target temperature is less than or equal to the preset temperature deviation threshold, the current working state of the heating or cooling equipment is maintained.

[0014] If the actual temperature of a small grid cell deviates from the target temperature by more than the temperature deviation threshold, then the heating power should be reduced or the cooling power increased.

[0015] When the deviation between the actual temperature of a small grid cell and the target temperature is less than a negative temperature deviation threshold, the heating power is increased or the cooling power is decreased.

[0016] As a further aspect of the present invention: the three-dimensional coordinate data set of the mold is labeled as M={m1,m2,……,m n}, where m i Let represent the three-dimensional coordinates of the i-th feature point on the mold, and n be the number of feature points; simultaneously, the thickness data set of the material distribution is labeled as T={t1,t2,……,t}. p}, where t j This represents the material thickness in the j-th thickness measurement area within the mold, where p is the number of thickness measurement areas.

[0017] As a further aspect of the present invention, the method for identifying and analyzing corner areas is as follows:

[0018] For each corner region, extract the radius of curvature r of the corner region, and then... The curvature C of the corresponding corner region is then obtained.

[0019] The curvature C of each corner region is compared with a pre-set curvature threshold C0:

[0020] When C > C0, the corresponding corner area is determined to be an area prone to forming a monitoring blind zone. Then, the area prone to forming a monitoring blind zone is used as a candidate location for sensor deployment, forming a candidate location set, denoted as S1 = {s11, s12, ..., s1}. u}, where s1 i1 Let i represent the coordinates of the i-th candidate sensor position at the corner of the mold, i1=1, 2, ..., u, where u is the number of candidate sensor positions in the corner area of ​​the mold.

[0021] As a further aspect of the present invention, the method for identifying and analyzing the material distribution area is as follows:

[0022] For material distribution areas, through Calculate the material thickness t for each material distribution area. j The difference Δt between the average material thickness tP and the average material thickness tP j ;

[0023] The differences Δt j The absolute values ​​are compared with the pre-set difference threshold T0:

[0024] When |Δt j When the value exceeds the set threshold T0, the area prone to forming a monitoring blind zone is selected as a candidate location for sensor deployment, forming a set of candidate locations, denoted as S2 = {s21, s22, ..., s2}. v}, where sm i2 The coordinates of the i-th candidate sensor location in the material distribution area are represented by i2 = 1, 2, ..., v; v is the number of candidate sensor locations in the material distribution area.

[0025] As a further aspect of the present invention, the method for determining the sensor deployment location is as follows:

[0026] The candidate sensor placement locations S1 in the mold corner area and S2 in the material distribution area are merged, that is, the sensor placement location set S = {s1, s2, ... s2} is obtained by S = S1 ∪ S2. q}, and at the same time remove duplicate coordinate positions in S;

[0027] Among them, sk Let q represent the coordinates of the k-th sensor, where k = 1, 2, ..., q, and q is the number of sensors.

[0028] As a further aspect of the present invention, it also includes preprocessing of the temperature data, the method of which is as follows:

[0029] For the k-th temperature sensor, take the temperature data at each of the w time points before and after time e, where w is the window size, which is a preset value;

[0030] Then through

[0031] Calculate the local mean GP of the temperature data collected by each temperature sensor. k,e and variance GF k,e ;

[0032] In the formula, r=ew,...e,...e+w;

[0033] When |G k,e -GP k,e |>3GF k,e When, determine G k,e It is an outlier, and then... Calculate the temperature replacement value G0 of the k-th sensor at time e. k,e ;

[0034] The temperature distribution model inside the mold is established based on the pre-processed temperature data.

[0035] As a further aspect of the present invention: real-time monitoring of local temperature changes in the mold and material distribution changes during the composite material production process, and replanning of monitoring points to achieve dynamic adjustment of the sensors;

[0036] The monitoring methods for local temperature changes in the mold are as follows:

[0037] Temperature sensors pre-installed inside the mold are used to collect the temperature at different locations inside the mold in real time.

[0038] Then through Calculate the temperature difference ΔP between the same temperature monitoring point at two adjacent acquisition times, and then... Calculate the temperature change rate GB at the corresponding location inside the mold;

[0039] Among them, G f G is the temperature value at the current time t. f−Δf It is the temperature value of f−Δf at the previous moment;

[0040] Then, the temperature change rate GB at each location within the mold is compared with the preset temperature change threshold GB0:

[0041] When GB > GB0, it indicates that the temperature change at the corresponding location inside the mold is relatively drastic. The original sensors may not be able to capture the temperature change in a timely and accurate manner, and the placement of the temperature sensors needs to be adjusted, that is, the monitoring points need to be replanned.

[0042] The methods for monitoring changes in material distribution are as follows:

[0043] Pressure sensors pre-installed inside the mold are used to collect pressure data at different locations within the mold in real time.

[0044] Then through Calculate the pressure difference ΔP at the same pressure monitoring point at two adjacent data acquisition times;

[0045] Among them, P f P is the pressure value at the current moment f. f−Δf It is the pressure value at the previous moment f−Δf, where Δf is the time interval between two adjacent sampling moments;

[0046] Then the pressure difference ΔP is compared with a preset pressure difference threshold P0:

[0047] When ΔP>P0, it indicates that the distribution of material in the area has changed significantly. This may be due to the accumulation and flow of material causing changes in local pressure. In this case, it is necessary to re-evaluate the placement of pressure sensors, i.e., to re-plan the monitoring points.

[0048] Both the temperature sensor and the pressure sensor are located at the sensor placement location set S.

[0049] As a further aspect of the present invention: the temperature distribution model is established as follows:

[0050] First, let the temperature collected by the k-th sensor at time e be labeled as G. k,e Where k = 1, 2, ..., q, e = 1, 2, ..., N, and N is the total number of data collection times;

[0051] The mold is then divided into several small grid cells, and the center coordinates of each small grid cell are taken and labeled as (x, y, z). For each small grid cell, temperature data from surrounding sensors are used, and a distance-weighted method is applied. Calculate the temperature G(x,y,z) of the corresponding small grid cell;

[0052] Where, d k G represents the distance from the k-th sensor to the corresponding small grid cell (x, y, z). k This represents the average temperature collected by the k-th sensor at N time points.

[0053] As a further aspect of the present invention: the formula for calculating the deviation between the actual temperature and the target temperature of the small grid cell is as follows: ;

[0054] Where GM(x,y,z) is the target temperature for each region, and ΔG(x,y,z) is the deviation between the actual temperature and the target temperature of the small grid cell.

[0055] As a further aspect of the present invention: wherein:

[0056] The relationship between the adjustment amount ΔPJ of heating power and the temperature deviation is as follows: Where β1 is the preset heating power adjustment coefficient;

[0057] The relationship between the cooling power adjustment ΔPL and the temperature deviation is as follows: , where β2 is the preset cooling power adjustment coefficient.

[0058] A temperature intelligent monitoring and control system for composite material production, used to execute the aforementioned temperature intelligent monitoring and control method for composite material production, comprising:

[0059] The monitoring point planning module is used to perform three-dimensional scanning of the composite material molding die structure and obtain the three-dimensional coordinate data of the die. The die area is divided into several square grid thickness measurement areas using a grid division method. Material distribution thickness data is collected through simulation or actual measurement. At the same time, based on the three-dimensional coordinate data of the die and the material distribution thickness data, the corner areas of the die and the material distribution areas are identified and analyzed to identify areas that are prone to forming monitoring blind spots, and the sensor deployment location set S is determined.

[0060] The temperature monitoring and analysis module is used to deploy temperature sensors in the mold according to the sensor deployment location set S, collect the temperature at each location in real time using the temperature sensors, preprocess the collected temperature data, establish a temperature distribution model in the mold based on the preprocessed temperature data, extract the target temperature of each area in the mold, and calculate the deviation between the actual temperature and the target temperature.

[0061] The temperature control module is used to control the temperature of the composite material molding die based on the deviation between the actual temperature and the target temperature and the preset temperature deviation threshold.

[0062] The dynamic adjustment module is used to monitor local temperature changes in the mold and material distribution changes in real time during the composite material production process, thereby determining whether the monitoring points need to be replanned.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] By acquiring mold coordinates through 3D scanning and combining mesh generation with material thickness analysis, the system accurately identifies two types of locations prone to monitoring blind spots: high-curvature areas at corners and areas with abnormal material thickness. Sensor placement points are then determined through aggregation and merging. This method avoids the blind placement inherent in traditional methods, ensuring sensor coverage of critical areas and providing comprehensive and accurate foundational data for subsequent temperature distribution model building. It effectively solves the problem of inadequate monitoring of localized mold temperatures.

[0065] A preprocessing step was implemented for temperature data, identifying outliers through local mean and variance calculations and replacing them with appropriate values ​​to eliminate interference from abnormal data in the model. Simultaneously, a temperature distribution model was constructed using a distance-weighted method combined with multi-time-time temperature averages. This model accurately reflects the temperature of each small grid cell, making the calculation of the deviation between the actual and target temperatures more accurate. This provides reliable data support for subsequent temperature control and reduces control deviations caused by data errors.

[0066] In the temperature control stage, the solution takes measures such as maintaining equipment status and adjusting heating or cooling power based on the relationship between deviation and threshold, and clarifies the quantitative relationship between power adjustment and temperature deviation. This hierarchical and quantitative control method avoids the blindness and lag of power adjustment in traditional control, and can quickly control temperature deviation within the threshold, ensuring temperature stability during composite material molding and improving product quality consistency.

[0067] A dynamic adjustment module is incorporated to monitor the pressure difference between the local temperature change rate of the mold and the material distribution in real time. When the change exceeds a threshold, the monitoring points are re-planned. This design breaks through the limitations of traditional fixed monitoring points and can promptly respond to situations such as drastic fluctuations in mold temperature and changes in material distribution during production. It ensures that the sensors are always in the optimal monitoring position, allowing temperature monitoring and control to continuously adapt to production dynamics and improving the applicability of the solution in complex production scenarios. Attached Figure Description

[0068] Figure 1 This is a system block diagram of a temperature intelligent monitoring and control system for composite material production according to the present invention.

[0069] Figure 2 This is a schematic flowchart of a temperature intelligent monitoring and control method for composite material production according to the present invention. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0071] Please see Figure 1 and Figure 2 As shown, the embodiments of the present invention provide the following technical solutions:

[0072] Example 1

[0073] A method for intelligent temperature monitoring and control in composite material production includes the following steps:

[0074] Step A1: Mold structure and material distribution information collection:

[0075] First, a 3D scan of the molding die structure of the composite material is performed to obtain the 3D coordinate data of the die, and the set of 3D coordinate data of the die is labeled as M={m1,m2,……,m n}, where m i This represents the three-dimensional coordinates of the i-th feature point on the mold, where n is the number of feature points.

[0076] Simultaneously, a grid division method is used to divide the mold area into several square grid thickness measurement areas; then, by simulating or actually measuring the initial distribution of material within the mold, thickness data of the material distribution are collected, and the set of thickness data of the material distribution is labeled as T={t1,t2,……,t p}, where t j This represents the material thickness in the j-th thickness measurement area within the mold, where p is the number of thickness measurement areas.

[0077] Step A2: Predicting blind spots and determining sensor requirements:

[0078] Based on the three-dimensional coordinate data set M of the mold, the corner areas of the mold are identified as follows:

[0079] For each corner region, extract the radius of curvature r of the corner region, and then... The curvature C of the corresponding corner region is then obtained.

[0080] The curvature C of each corner region is compared with a pre-set curvature threshold C0:

[0081] When C > C0, the corresponding corner area is determined to be an area prone to forming a monitoring blind zone. Then, the area prone to forming a monitoring blind zone is used as a candidate location for sensor deployment, forming a candidate location set, denoted as S1 = {s11, s12, ..., s1}. u}, where s1 i1 The coordinates of the i-th candidate sensor position at the corner of the mold are given, i1 = 1, 2, ..., u, where u is the number of candidate sensor positions in the corner area of ​​the mold.

[0082] For material distribution areas, through Calculate the material thickness t for each material distribution area. j The difference Δt between the average material thickness tP and the average material thickness tP j ;

[0083] The differences Δt j The absolute values ​​are compared with the pre-set difference threshold T0:

[0084] When |Δt j When the value exceeds the set threshold T0, the area prone to forming a monitoring blind zone is selected as a candidate location for sensor deployment, forming a set of candidate locations, denoted as S2 = {s21, s22, ..., s2}. v}, where sm i2 The coordinates of the i-th candidate sensor location in the material distribution area are represented by i2 = 1, 2, ..., v; v is the number of candidate sensor locations in the material distribution area.

[0085] Based on the analysis results of the corner area of ​​the mold and the material distribution area, the set of sensor placement locations S = {s1, s2, ... s} is determined. q}, where s k This represents the deployment coordinates of the k-th sensor, where k = 1, 2, ..., q, and q is the number of sensors.

[0086] The method is as follows: merge the candidate sensor placement location set S1 in the corner area of ​​the mold and the candidate sensor placement location set S2 in the material distribution area, that is, obtain the sensor placement location set S by S=S1∪S2, and remove duplicate coordinate positions in S.

[0087] Example 1 uses 3D scanning to acquire mold structure data and combines it with a mesh generation method to collect material thickness information. This accurately identifies high-curvature areas at mold corners and areas with abnormal material thickness as sensor placement points, achieving a scientific sensor layout. This method effectively avoids monitoring blind spots, ensuring temperature monitoring coverage of key areas in composite material molding. It provides a precise data acquisition foundation for subsequent temperature control, improving the comprehensiveness and reliability of temperature monitoring during composite material production and helping to reduce product quality problems caused by insufficient monitoring.

[0088] Example 2

[0089] Compared to Embodiment 1, the only difference between the technical solution of this embodiment and Embodiment 1 is that this embodiment also includes a dynamic adjustment step for the sensor: real-time monitoring of local temperature changes in the mold and monitoring of material distribution changes during the composite material production process;

[0090] The monitoring methods for local temperature changes in the mold are as follows:

[0091] Temperature sensors pre-installed inside the mold are used to collect the temperature at different locations inside the mold in real time.

[0092] Then through Calculate the temperature difference ΔP between the same temperature monitoring point at two adjacent acquisition times, and then... Calculate the temperature change rate GB at the corresponding location inside the mold;

[0093] Among them, G f G is the temperature value at the current time t. f−Δf It is the temperature value of f−Δf at the previous moment;

[0094] Then, the temperature change rate GB at each location within the mold is compared with the preset temperature change threshold GB0:

[0095] When GB > GB0, it indicates that the temperature change at the corresponding location inside the mold is relatively drastic, and the original sensor may not be able to capture the temperature change in a timely and accurate manner, so the placement of the temperature sensor needs to be adjusted.

[0096] The methods for monitoring changes in material distribution are as follows:

[0097] Pressure sensors pre-installed inside the mold are used to collect pressure data at different locations within the mold in real time.

[0098] Then through Calculate the pressure difference ΔP at the same pressure monitoring point at two adjacent data acquisition times;

[0099] Among them, P f P is the pressure value at the current moment f. f−Δf It is the pressure value at the previous moment f−Δf, where Δf is the time interval between two adjacent sampling moments;

[0100] Then the pressure difference ΔP is compared with a preset pressure difference threshold P0:

[0101] When ΔP>P0, it indicates that the distribution of material in the area has changed significantly. This may be due to the accumulation and flow of material causing changes in local pressure. In this case, it is necessary to re-evaluate the placement of the pressure sensor.

[0102] Both the temperature sensor and the pressure sensor are located at the sensor placement location set S.

[0103] The sensor placement was adjusted by re-collecting information on mold structure and material distribution, followed by re-predicting blind spots and determining sensor demand points, and then dynamically adjusting the sensor placement.

[0104] Example 2 adds a dynamic adjustment mechanism for the sensors based on Example 1. By monitoring the local temperature change rate and material pressure changes in the mold in real time, it can promptly detect areas of drastic temperature fluctuations and abnormal material distribution, and dynamically adjust the sensor placement accordingly. This improvement enables the temperature monitoring system to adapt to dynamic changes in the production process, avoiding the monitoring lag or inaccuracy problems that occur when the fixed sensor layout is used during material flow or sudden temperature changes. It further enhances the real-time performance and flexibility of temperature monitoring, ensuring the stability of the composite material production process.

[0105] Example 3

[0106] Compared to Embodiment 1 and Embodiment 2, the technical solution of this embodiment is to combine the solutions of Embodiment 1 and Embodiment 2. The difference between the technical solution of this embodiment and Embodiment 1 and Embodiment 2 lies only in that this embodiment also includes the following steps:

[0107] Step B1, Temperature Data Acquisition:

[0108] Based on the set of sensor locations S, temperature sensors are installed inside the mold, and the temperature at each location is collected in real time using the temperature sensors.

[0109] The temperature collected by the k-th sensor at time e is labeled as G. k,e Where k = 1, 2, ..., q, e = 1, 2, ..., N, and N is the total number of data collection times;

[0110] Step B2, Temperature Distribution Model Establishment:

[0111] Based on the temperature data, a temperature distribution model within the mold is established as follows:

[0112] The mold is divided into several small grid units, and the center coordinates of each small grid unit are taken and labeled as (x, y, z);

[0113] For each small grid cell, temperature data from surrounding sensors is used, employing a distance-weighted method. Calculate the temperature G(x,y,z) of the corresponding small grid cell;

[0114] Where, d k G represents the distance from the k-th sensor to the corresponding small grid cell (x, y, z). k This represents the average temperature collected by the k-th sensor at N time points;

[0115] Step B3, Temperature Deviation Calculation:

[0116] Extract the pre-set target temperature GM(x,y,z) for each region within the mold;

[0117] Then through Calculate the deviation ΔG(x,y,z) between the actual temperature and the target temperature for each small grid cell;

[0118] Step B4, Temperature Control:

[0119] Different control methods are adopted according to the magnitude of the temperature deviation ΔG(x,y,z);

[0120] The ΔG(x,y,z) of each small grid cell is compared with the preset temperature deviation threshold ΔG0:

[0121] When |ΔG(x,y,z)|≤ΔG0, the current operating state of the heating or cooling equipment is maintained;

[0122] If ΔG(x,y,z)>ΔG0, it means that the actual temperature is higher than the target temperature, and the heating power needs to be reduced or the cooling power increased.

[0123] When ΔG(x,y,z)<−ΔG0, it means that the actual temperature is lower than the target temperature, and the heating power needs to be increased or the cooling power needs to be reduced.

[0124] in:

[0125] The relationship between the adjustment amount ΔPJ of heating power and the temperature deviation is as follows: Where β1 is the preset heating power adjustment coefficient;

[0126] The relationship between the cooling power adjustment ΔPL and the temperature deviation is as follows: , where β2 is the preset cooling power adjustment coefficient.

[0127] Example 3 integrates the advantages of the first two examples. It not only scientifically deploys sensors but also establishes a temperature distribution model to accurately characterize the temperature across the entire mold area. Furthermore, it implements a tiered control strategy based on the deviation between the actual and target temperatures. This solution comprehensively understands the temperature distribution within the mold, quantifies temperature deviations, and adjusts heating or cooling power accordingly, achieving refined temperature control. This effectively reduces the performance differences in composite materials caused by uneven temperature distribution, significantly improving the consistency and stability of product quality.

[0128] Example 4

[0129] Compared to Embodiments 1, 2, and 3, the only difference between this embodiment and Embodiments 1, 2, and 3 is that, in addition to Embodiment 3, this embodiment also includes preprocessing of the temperature data, as follows:

[0130] For the k-th temperature sensor, take the temperature data at each of the w time points before and after time e, where w is the window size, which is a preset value;

[0131] Then through Calculate the local mean GP of the temperature data collected by each temperature sensor. k,e and variance GF k,e ;

[0132] In the formula, r=ew,...e,...e+w;

[0133] When |G k,e -GP k,e |>3GF k,e When, determine G k,e It is an outlier, and then... Calculate the temperature replacement value G0 of the k-th sensor at time e. k,e ;

[0134] In this embodiment, the temperature distribution model inside the mold is established based on the preprocessed temperature data;

[0135] Example 4 adds a temperature data preprocessing step to Example 3. It identifies and corrects abnormal temperature data through local mean and variance analysis, ensuring the accuracy of the input temperature distribution model. This improvement avoids interference from abnormal data in temperature model construction and control decisions, enhances the reliability of the temperature distribution model and the effectiveness of temperature control strategies, further reduces production risks caused by data errors, and provides stronger data support for high-quality composite material production.

[0136] Example 5

[0137] Compared with Embodiment 1, Embodiment 2, Embodiment 3 and Embodiment 4, the technical solution of this embodiment is to combine and implement the solutions of Embodiment 1, Embodiment 2, Embodiment 3 and Embodiment 4.

[0138] Example 5 integrates all the technical solutions of the previous four examples, covering the complete process of sensor optimization, dynamic adjustment, temperature model construction, data preprocessing, and refined control. This solution achieves full-process optimization from data acquisition, processing, modeling to control, adapting to the dynamic changes in the production process while ensuring the accuracy of temperature monitoring and the scientific nature of control. It minimizes monitoring blind spots and data errors, significantly improving the intelligence level and product quality of composite material production, and possesses comprehensive and efficient technical advantages.

[0139] The present invention also provides a temperature intelligent monitoring and control system for composite material production, for executing the above-described temperature intelligent monitoring and control method for composite material production, comprising:

[0140] The monitoring point planning module is used to perform three-dimensional scanning of the composite material molding die structure and obtain the three-dimensional coordinate data of the die. The die area is divided into several square grid thickness measurement areas using a grid division method. Material distribution thickness data is collected through simulation or actual measurement. At the same time, based on the three-dimensional coordinate data of the die and the material distribution thickness data, the corner areas of the die and the material distribution areas are identified and analyzed to identify areas that are prone to forming monitoring blind spots, and the sensor deployment location set S is determined.

[0141] The temperature monitoring and analysis module is used to deploy temperature sensors in the mold according to the sensor deployment location set S, collect the temperature at each location in real time using the temperature sensors, preprocess the collected temperature data, establish a temperature distribution model in the mold based on the preprocessed temperature data, extract the target temperature of each area in the mold, and calculate the deviation between the actual temperature and the target temperature.

[0142] The temperature control module is used to control the temperature of the composite material molding die based on the deviation between the actual temperature and the target temperature and the preset temperature deviation threshold.

[0143] The dynamic adjustment module is used to monitor local temperature changes in the mold and material distribution changes in real time during the composite material production process, so as to determine whether the monitoring points need to be replanned.

[0144] It should be stated that all user data collected in this invention is collected with the user's consent and authorization, and the use of user data is legal and compliant, and the use and processing of user data comply with the relevant laws, regulations and standards of the relevant regions.

[0145] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0146] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0147] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0148] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A temperature intelligent monitoring control method for composite production, characterized by, The method comprises the following steps: First step, monitoring point planning: Three-dimensional scanning is performed on the forming mold structure of the composite material to obtain three-dimensional coordinate data of the mold. Meanwhile, the mold area is divided into a plurality of square grid thickness measurement areas by using a grid division method. Then, initial distribution of the material in the mold is simulated or actually measured to collect thickness data of the material distribution. Then, corner areas and material distribution areas of the mold are identified and analyzed for easy formation of monitoring blind areas according to the three-dimensional coordinate data of the mold and the thickness data of the material distribution. Finally, the positions of the sensors are determined based on the identification and analysis results of the corner areas and the material distribution areas of the mold. Second step, temperature monitoring analysis: Temperature sensors are arranged in the mold according to the positions of the sensors, and the temperature sensors are used to collect the temperature of each position in real time. Then, a temperature distribution model in the mold is established according to the temperature data. The target temperature of each area in the mold is extracted in advance. The deviation between the actual temperature and the target temperature is obtained by subtracting the target temperature from the actual temperature. Third step, temperature control: When the absolute value of the deviation between the actual temperature and the target temperature of the small grid unit is less than or equal to the preset temperature deviation threshold, the working state of the current heating device or cooling device is maintained. If the deviation between the actual temperature and the target temperature of the small grid unit is greater than the temperature deviation threshold, the heating power is reduced or the cooling power is increased. When the deviation between the actual temperature and the target temperature of the small grid unit is less than the negative temperature deviation threshold, the heating power is increased or the cooling power is reduced.

2. The temperature intelligent monitoring control method for composite production according to claim 1, characterized in that, The identification and analysis method of the corner area is as follows: For each corner area, the curvature radius r of the corner area is extracted, the curvature of the corner area is obtained by calculating the reciprocal of the curvature radius r of the corner area, and is denoted as C. The curvatures C of the corner areas are compared with the pre-set curvature threshold C0 respectively. When C > C0, it is determined that the corresponding corner region is a region prone to form a monitoring blind area, and then the region prone to form a monitoring blind area is taken as a candidate position for sensor arrangement, and a candidate position set is formed, denoted as S1={s11, s12, … s1 u}, wherein s1 i1 represents the coordinates of the i-th sensor candidate position at the mold corner, i1=1, 2, … u, and u is the number of sensor arrangement candidate positions at the mold corner region.

3. The temperature intelligent monitoring control method for composite production according to claim 2, characterized in that, The identification and analysis method of the material distribution area is as follows: For the material distribution area, the thickness data set of the material distribution is marked as T = {t1, t2, …, t p}, wherein t j j represents the material thickness of the jth thickness measurement area in the mold, j = 1, 2, …, p, and p is the number of thickness measurement areas; the difference between the material thickness of each area and the corresponding average material thickness of all areas is calculated and marked as Δt j ; The absolute values of the respective differences Δt j are compared with a pre-set difference threshold value T0. When |Δt j | is greater than a set threshold value To, the area prone to forming a monitoring blind area is taken as a candidate position for sensor deployment, and a candidate position set is formed, denoted as S2={s21, s22, … s2 v} where sm i2 represents the coordinates of the i-th sensor candidate position in the material distribution area, i2=1, 2, … v; v is the number of sensor deployment candidate positions in the material distribution area.

4. The temperature intelligent monitoring control method for composite production according to claim 3, characterized in that, The determination method of the sensor arrangement position is as follows: The sensor layout candidate position set S1 of the mold corner region and the sensor layout candidate position set S2 of the material distribution region are merged, that is, the position set S of the sensor layout is obtained through S=S1∪S2={s1,s2,……s q}, while removing the repeated coordinate positions in S; wherein s k represents the layout coordinates of the kth sensor, k = 1, 2, …, q, q being the number of sensors.

5. The temperature intelligent monitoring control method for composite production according to claim 1, characterized in that, The local temperature change of the mold and the material distribution change are monitored in real time during the production process of the composite material. The monitoring method of the local temperature change of the mold is as follows: The temperature at different positions in the mold is collected in real time by using the temperature sensors arranged in the mold in advance. At the same monitoring point, the temperature difference value of the same monitoring point at adjacent two collection time points is obtained by subtracting the temperature at the previous collection time from the temperature at the current time. Then, the temperature change rate of the corresponding position in the mold is obtained by dividing the temperature difference value by the time interval between the two collection time points, and is denoted as GB. Then, the temperature change rates GB of the positions in the mold are compared with the pre-set temperature change threshold GB0 respectively. When GB > GB0, the monitoring point planning is re-performed. The monitoring method of the material distribution change is as follows: The pressure at different positions in the mold is collected in real time by using the pressure sensors arranged in the mold in advance. At the same monitoring point, the pressure difference value of the same monitoring point at adjacent two collection time points is obtained by subtracting the pressure at the previous collection time from the pressure at the current time, and is denoted as ΔP. Then, the pressure difference value ΔP is compared with the pre-set pressure difference threshold P0. When ΔP > P0, the monitoring point planning is re-performed.

6. The temperature intelligent monitoring control method for composite production according to claim 5, characterized in that, Wherein, The temperature sensor and the pressure sensor are arranged at the set of sensor arrangement positions S.

7. The temperature intelligent monitoring control method for composite production according to claim 1, characterized in that, The temperature distribution model is established in the following manner: First, the temperature collected by the kth sensor at time e is marked as G k,e where k = 1, 2, … q, e = 1, 2, … N, and N is the total number of collection times; Then the mold is divided into several small grid units, and the center coordinates of each small grid unit are taken and marked as (x, y, z); for each small grid unit, the temperature data of the surrounding sensors are used to calculate the temperature G(x, y, z) of the corresponding small grid unit by a distance-weighted method the temperature G(x, y, z) of the corresponding small grid unit is calculated where d k is the distance of the kth sensor to the corresponding small mesh cell (x, y, z), G k is the average value of the temperature collected by the kth sensor at N time instants.

8. The temperature intelligent monitoring control method for composite production according to claim 1, characterized in that, Wherein: The relationship between the adjustment amount ΔPJ of the heating power and the temperature deviation is where β1 is a preset heating power adjustment coefficient. The relationship between the adjustment amount ΔPL of the cooling power and the temperature deviation is where β2 is a preset cooling power adjustment coefficient.

9. The temperature intelligent monitoring control method for composite production according to claim 1, characterized in that, The temperature data is preprocessed in the following manner: For the kth temperature sensor, the temperature data of each of the w time points before and after the time point e is taken, wherein w is the window size, which is a preset value; Then the local mean and variance of the temperature data collected by each temperature sensor within a window size w are calculated and denoted as GP k,e and GF k,e respectively. When |G k,e −GP k,e |>3GF k,e , it is determined that G k,e is an abnormal value, then the average value of the temperatures at the two adjacent time points before and after the time point e is calculated, and the average value is taken as the replacement value G0 k,e of the temperature at the time point e. The temperature distribution model in the mold is established according to the preprocessed temperature data.

10. A temperature intelligent monitoring control system for composite production for performing the temperature intelligent monitoring control method for composite production according to any one of claims 1 to 9, characterized in that, Comprise: The monitoring point planning module is used for three-dimensional scanning of the composite material forming mold structure to obtain mold three-dimensional coordinate data; The mold area is divided into a plurality of square grid thickness measurement areas by using a grid division method, and material distribution thickness data is collected by simulation or actual measurement; at the same time, the mold corner area and the material distribution area are identified and analyzed to be prone to form monitoring blind areas according to the mold three-dimensional coordinate data and the material distribution thickness data, and a set of sensor arrangement positions S is determined; The temperature monitoring and analysis module is used for arranging temperature sensors in the mold according to the set of sensor arrangement positions S, collecting the temperature of each position in real time by using the temperature sensors, preprocessing the collected temperature data, then establishing a temperature distribution model in the mold according to the preprocessed temperature data, and extracting the target temperature of each area in the mold to calculate the deviation between the actual temperature and the target temperature; The temperature control module is used for controlling the temperature of the composite material forming mold according to the deviation between the actual temperature and the target temperature and the preset temperature deviation threshold value; The dynamic adjustment module is used for monitoring the local temperature change of the mold and the material distribution change in real time during the production of the composite material, so as to determine whether to re-plan the monitoring points.

Images