Automobile parts defect detection method and system based on internet of things

Abstract

The present application relates to the technical field of defect detection, and specifically discloses a method and system for detecting defects in automobile parts based on the Internet of Things, which obtains first and second temperature distribution parameters of a mold, monitors first working parameters of a solution during a casting process based on a flow meter, constructs a temperature change recognition model based on the first and second temperature distribution parameters, discriminates abnormal longitudinal and transverse temperature rate changes of the mold, outputs a final value of the temperature rate change of the mold according to the discrimination result, and builds a linkage control strategy based on the final value of the temperature rate change of the mold and historical first working parameters to dynamically balance the quality and production capacity of automobile parts. The present application can realize intelligent control of the production process of automobile parts, so that process parameter adjustment no longer depends on experience or manual judgment, and helps to improve the controllability and reliability of the production process.

Description

Technical Field

[0001] This invention relates to the field of defect detection technology, and more specifically, to a method and system for detecting defects in automotive parts based on the Internet of Things. Background Technology

[0002] In modern automotive parts manufacturing, precision casting and injection molding processes are widely used in the production of engine components, chassis parts, and electronic components. In these processes, molten or slurry materials are poured into molds to form the desired part shape. However, due to the significant temperature difference between the mold material and the solution, the pouring process often generates local or global temperature gradients. This temperature difference not only causes non-uniform distribution of internal stress in the parts but may also lead to the formation of microcracks, voids, or pores, thus affecting the mechanical properties and fatigue resistance of the parts. In the long term, this accumulation of thermal stress reduces the lifespan and reliability of parts in actual use environments, especially under conditions of high engine temperatures, chassis loads, or frequent vibrations. Structural weaknesses caused by temperature differences are more likely to become the source of premature part failure. Therefore, understanding and controlling the temperature difference effect when the solution is poured into the mold is of great significance for improving the quality and service life of automotive parts.

[0003] Therefore, it is necessary to provide an IoT-based method and system for detecting defects in automotive parts to solve the above-mentioned technical problems. In order to solve the above problems, a technical solution is provided. Summary of the Invention

[0004] To overcome the aforementioned deficiencies of the prior art, this invention provides an Internet of Things-based method and system for detecting defects in automotive parts. This system addresses the problem in the existing automotive parts production process where temperature differences between the mold and the solution lead to uneven internal stress and defect formation in the parts, thereby affecting the mechanical properties and service life of the automotive parts.

[0005] To achieve the above objectives, the present invention provides the following technical solution: The Internet of Things-based method for detecting defects in automotive parts includes the following steps: By uniformly arranging multiple thermocouples from top to bottom inside the mold along the casting direction, a multi-dimensional temperature acquisition network is constructed to obtain the first temperature distribution parameters of the mold. By arranging an infrared thermal imaging camera on the outside of the mold, the second temperature distribution parameters of the mold are obtained. The first working parameters of the solution during the casting process are monitored based on a flow meter. The first working parameters include the flow rate and the casting time. A temperature change identification model is constructed based on the first temperature distribution parameter and the second temperature distribution parameter. Anomalies are identified in the longitudinal and transverse temperature rate changes of the mold. The final value of the mold temperature rate change is output based on the identification result. By establishing a linkage control strategy based on the final value of the mold temperature rate change and the historical first working parameters, the quality and production capacity of automotive parts can be dynamically balanced.

[0006] As a further aspect of the present invention, a temperature change identification model is constructed based on the first temperature distribution parameter and the second temperature distribution parameter to identify anomalies in the longitudinal and transverse temperature rate changes of the mold. Based on the identification results, the final value of the mold temperature rate change is output. The specific steps are as follows: The first temperature change sequence is constructed by obtaining the first temperature distribution parameters of the same monitoring point i during the monitoring process. ,in, Let i be the first temperature distribution parameter at the initial time of monitoring point i. Let be the first temperature distribution parameter of monitoring point i at time t. Let i be the first temperature distribution parameter at monitoring point i at time n. The total duration of the monitoring process; the second temperature distribution parameters of monitoring point j are obtained to form the second temperature change sequence. ,in, The second temperature distribution parameter at monitoring point j at the initial time. Let be the second temperature distribution parameter of monitoring point j at time t. The second temperature distribution parameter at monitoring point j at time n; Based on the first temperature change sequence and the second temperature change sequence, the lateral temperature rate change of the mold is analyzed and a first-level abnormal temperature is identified. Based on the first temperature change sequence and the second temperature change sequence, the longitudinal temperature rate change of the mold is analyzed, and a secondary abnormal temperature is identified. Based on the transverse and longitudinal temperature rate changes of the mold, the final value of the mold temperature rate change is output.

[0007] As a further aspect of the present invention, based on the first temperature change sequence and the second temperature change sequence, the lateral temperature rate change of the mold is analyzed in combination, and a first-level abnormal temperature discrimination is performed. The specific steps are as follows: Obtain the first temperature change sequence at monitoring point i. And the second temperature change sequence at monitoring point j Calculate the temperature difference between the inside and outside of the mold at the same time point t. The lateral temperature rate change of the mold is obtained based on the temperature difference between the inside and outside at adjacent time points. ; Extract the lateral temperature rate change of the mold and compare it with a preset threshold range. If the lateral temperature rate change of the mold is within the preset threshold range, then the lateral temperature rate change of the mold is normal; if the lateral temperature rate change of the mold is not within the preset threshold range, then the lateral temperature rate change of the mold has a level one anomaly.

[0008] As a further aspect of the present invention, the longitudinal temperature rate change of the mold is analyzed based on the first temperature change sequence and the second temperature change sequence, and a secondary abnormal temperature discrimination is performed. The specific steps are as follows: Obtain the first temperature change sequence at monitoring point i. And the second temperature change sequence at monitoring point j Obtain the first temperature change sequence at monitoring point i-1. and the second temperature change sequence at monitoring point j-1 ; Extract the first temperature distribution parameters of the mold at the same time point t and monitoring point i. and the first temperature distribution parameters of monitoring point i-1 The difference in the first temperature distribution parameter between adjacent monitoring points is calculated as the first longitudinal temperature rate change. ; Extract the second temperature distribution parameters of the mold at the same time point t and monitoring point j. and the second temperature distribution parameters of monitoring point j-1 The difference in the second temperature distribution parameter between adjacent monitoring points is calculated as the second longitudinal temperature rate change. ; The longitudinal temperature rate change is obtained by averaging the first and second longitudinal temperature rate changes. ; Extract the longitudinal temperature rate change of the mold and compare it with a preset threshold range. If the longitudinal temperature rate change of the mold is within the preset threshold range, then the longitudinal temperature rate change of the mold is normal; if the longitudinal temperature rate change of the mold is not within the preset threshold range, then the longitudinal temperature rate change of the mold has a secondary abnormality.

[0009] As a further aspect of the present invention, monitoring point i and monitoring point j are located on the same horizontal line on the inner and outer sides of the mold, and the positions of the monitoring points on the same horizontal line on the mold are marked as follows: .

[0010] As a further aspect of the present invention, a linkage control strategy is established by using the final value of the mold temperature rate change and the historical first working parameters to dynamically balance the quality and production capacity of automotive parts. The specific steps for establishing the linkage control strategy are as follows: Obtain the final value of the mold temperature rate change at all monitoring points of the mold. , forming a temperature rate change sequence ,in, The position at time t is The final value of the rate of temperature change. The position at time n is The final value of the rate of temperature change; Based on the casting and cooling processes during monitoring, the temperature rate change sequence is divided into a first rate change sequence and a second rate change sequence. Based on the joint analysis of the first rate change sequence and the second rate change sequence, the mold temperature change is analyzed to determine whether the first flow velocity needs to be adjusted.

[0011] As a further aspect of the present invention, the first rate change sequence is: The second rate change sequence is ,in, The position at time p is The final value of the rate of temperature change. for The time position is The final value of the rate of temperature change. For casting time, for The time position is The final value of the rate of temperature change. for The time position is The final value of the rate of temperature change. This refers to the cooling time.

[0012] As a further aspect of the present invention, based on the joint analysis of the mold temperature change using the first rate change sequence and the second rate change sequence, it is determined whether the first flow velocity needs to be adjusted. The specific steps are as follows:

[0013] Extracting the first rate change sequence Calculate the first temperature deviation value and compare it with a preset threshold. If the first temperature deviation value is greater than the preset threshold, the first flow rate needs to be adjusted. Second rate change sequence Calculate the second temperature deviation value and compare it with a preset threshold. If the second temperature deviation value is greater than the preset threshold, the first flow rate needs to be adjusted.

[0014] As a further aspect of the present invention, the first rate change sequence is the temperature rate change sequence of the mold during the casting process, and the second rate change sequence is the temperature rate change sequence of the mold during the cooling process, wherein... .

[0015] The IoT-based automotive parts defect detection system includes: a parameter acquisition module, a temperature rate change detection module, and a parameter linkage control module. The parameter acquisition module is used to acquire the first temperature distribution parameters of the mold by uniformly arranging multiple thermocouples from top to bottom along the casting direction inside the mold to construct a multi-dimensional temperature acquisition network, and to acquire the second temperature distribution parameters of the mold by arranging an infrared thermal imaging camera on the outside of the mold. It also monitors the first working parameters of the solution during the casting process based on a flow meter. The first working parameters include the flow rate and the casting time. The temperature rate change detection module is used to construct a temperature change recognition model based on the first temperature distribution parameter and the second temperature distribution parameter, to identify anomalies in the longitudinal and transverse temperature rate changes of the mold, and to output the final value of the mold temperature rate change based on the identification result.

[0016] The parameter linkage control module is used to build a linkage control strategy based on the final value of the mold temperature rate change and the historical first working parameters, so as to dynamically balance the quality and production capacity of automotive parts.

[0017] The technical effects and advantages of this invention's IoT-based method and system for detecting defects in automotive parts are as follows: This invention utilizes a multi-dimensional temperature acquisition network composed of internal thermocouples and external infrared thermal imaging cameras, along with casting parameters recorded by a flow meter, to construct a temperature change recognition model and output the final value of the temperature rate change. This enables real-time, continuous monitoring of the mold's internal and surface temperatures. By identifying anomalies in the lateral and longitudinal temperature rate changes, it can promptly detect localized overheating or uneven temperature distribution in the mold, preventing shrinkage cavities, porosity, or surface defects in the castings, thereby significantly improving the yield and quality stability of the parts. Furthermore, by jointly analyzing the final value of the temperature rate change with historical first-stage working parameters, a linkage control strategy is established to dynamically adjust the casting flow rate and casting time, resulting in a more uniform temperature distribution during production. This avoids affecting part performance due to excessively high or low local temperatures, optimizing production capacity while ensuring part quality, reducing unnecessary reprocessing and scrap rates, and ultimately improving production efficiency.

[0018] This invention achieves intelligent control of the automotive parts production process through multi-point data fusion and model analysis. This eliminates the need for process parameter adjustments to rely on experience or manual judgment, instead enabling scientific decision-making based on real-time data and historical experience. This not only improves the controllability and reliability of the production process but also provides strong support for subsequent process optimization, mold maintenance, and production data accumulation. Attached Figure Description

[0019] Figure 1A flowchart of an IoT-based defect detection method for automotive parts provided in an embodiment of the present invention; Figure 2 This is a system block diagram of an Internet of Things-based automotive parts defect detection system provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described technical solutions are only a part of this invention, and not all of it. All other technical solutions obtained by those skilled in the art based on the technical solutions of this invention without inventive effort are within the scope of protection of this invention.

[0021] Example 1: As Figure 1 The diagram shown is a flowchart of an IoT-based defect detection method for automotive parts provided in an embodiment of the present invention. Figure 1 The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S3 are detailed as follows: S1, by uniformly arranging multiple thermocouples from top to bottom inside the mold along the casting direction, a multi-dimensional temperature acquisition network is constructed to obtain the first temperature distribution parameters of the mold. By arranging an infrared thermal imaging camera on the outside of the mold, the second temperature distribution parameters of the mold are obtained. The first working parameters of the solution during the casting process are monitored based on a flow meter. The first working parameters include the flow rate and the casting time. In this embodiment of the invention, during the casting process of automotive parts, to monitor the temperature changes inside and on the surface of the mold in real time, the production team evenly arranges multiple thermocouples from top to bottom inside the mold along the casting direction. For example, three thermocouples are arranged in a mold, located at the top, middle, and bottom, respectively, to obtain the initial temperature distribution parameters at each location. These thermocouples can collect temperature data of the contact points between the molten metal and the mold in real time. For example, at t=5 seconds, the top thermocouple records 120°C, the middle thermocouple records 135°C, and the bottom thermocouple records 140°C. These data are combined to form the initial temperature change sequence of the mold, which is used to analyze the temperature changes inside the mold.

[0022] Meanwhile, to obtain the temperature distribution on the mold surface, an infrared thermal imaging camera was placed on the outside of the mold, which can scan the entire mold surface and extract the second temperature distribution parameters. For example, at the same time t=5 seconds, the camera captured the temperature of the top surface of the mold as 115℃, the middle as 130℃, and the bottom as 138℃. These data were used to form a second temperature change sequence, which was then analyzed in conjunction with the internal temperature sequence.

[0023] During the casting process, the flow meter is used to monitor the primary operating parameters of the solution, including flow rate and casting time. Assuming the flow rate is set at 10 L / min and the casting time at 20 seconds, the system records the actual flow rate data in real time and analyzes it in conjunction with temperature change data. By combining the internal and surface temperature sequences of the mold with the primary operating parameters recorded by the flow meter, the system can determine temperature fluctuations at different locations within the mold and adjust the flow rate or casting time accordingly. This ensures uniform surface and internal temperature of the parts, thereby improving casting quality and optimizing production capacity. For example, if an excessively large temperature rate change is detected in the middle of the mold, and the flow meter indicates a high flow rate, it can be recommended to appropriately reduce the flow rate or extend the casting time to reduce the risk of localized overheating and ensure the quality of the finished parts.

[0024] S2, Based on the first temperature distribution parameter and the second temperature distribution parameter, a temperature change identification model is constructed to identify anomalies in the longitudinal and transverse temperature rate changes of the mold, and the final value of the mold temperature rate change is output according to the identification result. In this embodiment of the invention, during the casting production of automotive parts, multiple thermocouples are arranged inside the mold along the casting direction to acquire a first temperature distribution parameter in real time. Simultaneously, an infrared thermal imaging camera is installed on the outside of the mold to acquire a second temperature distribution parameter. These two types of temperature data comprehensively reflect the temperature changes inside and on the surface of the mold.

[0025] First, based on the internal and external temperatures at the same time point, the temperature difference in the mold in the lateral direction is calculated. Then, the changes in the lateral temperature difference at adjacent time points are analyzed to obtain a sequence of lateral temperature rate changes. These lateral temperature rate changes are compared with preset thresholds. If the changes are within the threshold range, the lateral temperature is considered normal; if they exceed the threshold, it is judged as a level one anomaly, indicating possible local overheating or excessive temperature fluctuations, requiring further attention.

[0026] Next, the longitudinal temperature rate change is analyzed. By comparing the internal and external temperature differences at adjacent monitoring points at the same time point, the longitudinal temperature rate change sequence is calculated. Similarly, the longitudinal temperature rate change is compared with a set threshold. If it is within the threshold range, the longitudinal temperature change is considered normal; if it exceeds the threshold, it is judged as a level two anomaly, indicating that there may be uneven temperature or unstable flow in the casting direction.

[0027] Finally, the transverse and longitudinal temperature rate changes are calculated together to obtain the final value of the temperature rate change at each monitoring point. This final value reflects the intensity of temperature change in the mold at various locations, and is used for subsequent process optimization, flow rate adjustment, and part quality control to ensure uniform mold temperature distribution and improve casting yield and production stability.

[0028] S3 uses the final value of the mold temperature rate change and the historical first working parameters to build a linkage control strategy, dynamically balancing the quality and production capacity of automotive parts.

[0029] In this embodiment of the invention, multiple monitoring points are arranged inside and outside the mold during the casting production of automotive parts. Temperature data is collected in real time using thermocouples and infrared thermal imaging cameras. The final value of the temperature rate change at each monitoring point is obtained after calculating the lateral and longitudinal temperature rate changes. In one production run, the final value of the temperature rate change at the middle monitoring point is 2℃ / s, at the bottom monitoring point it is 3.5℃ / s, and at the top monitoring point it is 1.8℃ / s. Simultaneously, historical first-run parameters are read, including the casting flow rate set for previous batches at 10L / min and the casting duration at 20 seconds.

[0030] The final value of the temperature rate change in this production run was analyzed in conjunction with historical operating parameters. For example, it was found that the final value of the temperature rate change in the middle and bottom of the mold was significantly higher than the historical average, indicating that the molten metal flowed too fast in these areas, which may lead to localized overheating or shrinkage cavities, thus affecting part quality. Conversely, the final value of the temperature rate change at the top was slightly lower than the average, indicating that the casting speed was slightly slower and the production capacity was not fully utilized.

[0031] Based on this analysis, a linkage control strategy was initiated: the casting flow rate was automatically adjusted via an algorithm, changing the original setting of 10L / min to 8L / min in the middle and bottom regions, while maintaining 10L / min in the top region. Simultaneously, the casting time was slightly extended to ensure uniform filling of the parts. This suppressed temperature fluctuations in the middle and bottom of the mold, resulting in a more uniform temperature distribution on the surface and inside of the parts, reducing the risk of defects, and ensuring overall production capacity remained unaffected. This linkage control strategy dynamically balances part quality and production capacity: when the final value of the temperature rate change is too high, the flow rate is automatically reduced; when the temperature rate change is too low, the flow rate is maintained or slightly increased, achieving intelligent control of the production process, improving yield, and ensuring production efficiency.

[0032] Preferably, a temperature change identification model is constructed based on the first temperature distribution parameter and the second temperature distribution parameter to identify anomalies in the longitudinal and transverse temperature rate changes of the mold. The final value of the mold temperature rate change is output based on the identification result. The specific steps are as follows: The first temperature change sequence is constructed by obtaining the first temperature distribution parameters of the same monitoring point i during the monitoring process. ,in, Let i be the first temperature distribution parameter at the initial time of monitoring point i. Let be the first temperature distribution parameter of monitoring point i at time t. Let i be the first temperature distribution parameter at monitoring point i at time n. The total duration of the monitoring process; the second temperature distribution parameters of monitoring point j are obtained to form the second temperature change sequence. ,in, The second temperature distribution parameter at monitoring point j at the initial time. Let be the second temperature distribution parameter of monitoring point j at time t. The second temperature distribution parameter at monitoring point j at time n; Based on the first temperature change sequence and the second temperature change sequence, the lateral temperature rate change of the mold is analyzed and a first-level abnormal temperature is identified. Based on the first temperature change sequence and the second temperature change sequence, the longitudinal temperature rate change of the mold is analyzed, and a secondary abnormal temperature is identified. Based on the transverse and longitudinal temperature rate changes of the mold, the final value of the mold temperature rate change is output.

[0033] In this embodiment of the invention, multiple monitoring points are arranged on the mold surface during the temperature monitoring process. Monitoring point i is used to record a first temperature distribution parameter, and monitoring point j is used to record a second temperature distribution parameter. As the mold is heated and dissipated during the production process, the temperature data of monitoring point i at different time periods are recorded, forming a first temperature change sequence. For example, at the initial moment when the mold has just entered the heating stage... =50℃, at time t is =120℃, at the final moment is =180℃. Similarly, the second temperature distribution parameters at monitoring point j were also continuously collected, forming a second temperature change sequence, in which... =48℃, =110℃, final =175℃.

[0034] After obtaining the two temperature change sequences mentioned above, the two sets of data are first mixed and analyzed to determine the rate of temperature change in the transverse direction of the mold. For example, if the temperature rise trends at monitoring point i and monitoring point j are significantly different, within the same time period... The heating rate is 2℃ / s, while If the heating rate is 0.8℃ / s, it indicates an uneven temperature distribution in the mold's transverse direction, thus classifying it as a Level 1 abnormal temperature. Next, the first and second temperature change sequences are analyzed separately to assess the temperature rate change in the longitudinal direction. For example, if in the first sequence... If the temperature change maintains a steady increase in the first half, but suddenly increases at a rapid rate in the second half, such as from 1.5℃ / s to 3.5℃ / s, it is considered a longitudinal anomalous temperature change. Similarly, if in the second sequence... If the temperature drops too quickly during the cooling phase, the system will identify it as an abnormal longitudinal temperature change.

[0035] Finally, by combining the judgment results of the transverse and longitudinal temperature rate changes, the final value of the mold temperature rate change is output. For example, when the transverse temperature difference exceeds a preset threshold of 30% and the longitudinal rate mutation exceeds 2℃ / s, the final output value of the mold temperature rate change is "abnormal," and a specific abnormality category is given, such as transverse imbalance + longitudinal mutation, providing a basis for subsequent mold process adjustments.

[0036] Preferably, based on the first temperature change sequence and the second temperature change sequence, the lateral temperature rate change of the mold is analyzed in combination, and a first-level abnormal temperature judgment is performed. The specific steps are as follows: Obtain the first temperature change sequence at monitoring point i. And the second temperature change sequence at monitoring point j Calculate the temperature difference between the inside and outside of the mold at the same time point t. The lateral temperature rate change of the mold is obtained based on the temperature difference between the inside and outside at adjacent time points. ;

[0037] Extract the lateral temperature rate change of the mold and compare it with a preset threshold range. If the lateral temperature rate change of the mold is within the preset threshold range, then the lateral temperature rate change of the mold is normal; if the lateral temperature rate change of the mold is not within the preset threshold range, then the lateral temperature rate change of the mold has a level one anomaly.

[0038] During mold operation monitoring, assuming monitoring point i is arranged on the inner side of the mold surface and monitoring point j is arranged on the outer side, a first temperature change sequence and a second temperature change sequence are collected respectively. For example, during a certain heating process, the temperatures of monitoring point i at t=1, 2, and 3 seconds are respectively... =100℃ =120℃ =150℃, the temperature at monitoring point j is respectively =90℃ =110℃, =130℃. Calculate the temperature difference between the inside and outside at the same time point: at t=1s, At t=2s, At t=3s, Then, the rate of change of the lateral temperature of the mold is calculated based on the difference in temperature between adjacent time points. , The obtained lateral temperature rate change value is compared with a preset threshold. The threshold range is set to [0,5]. At time t=2, the lateral temperature rate change is 0℃, which is within the threshold range and is judged as no abnormality. However, at time t=3, the lateral temperature rate change is 10℃, which exceeds the upper limit of the threshold and is judged as a level one abnormality.

[0039] Preferably, based on the first temperature change sequence and the second temperature change sequence, the longitudinal temperature rate change of the mold is analyzed, and a secondary abnormal temperature judgment is performed. The specific steps are as follows: Obtain the first temperature change sequence at monitoring point i. And the second temperature change sequence at monitoring point j Obtain the first temperature change sequence at monitoring point i-1. and the second temperature change sequence at monitoring point j-1 ; Extract the first temperature distribution parameters of the mold at the same time point t and monitoring point i. and the first temperature distribution parameters of monitoring point i-1 The difference in the first temperature distribution parameter between adjacent monitoring points is calculated as the first longitudinal temperature rate change. ; Extract the second temperature distribution parameters of the mold at the same time point t and monitoring point j. and the second temperature distribution parameters of monitoring point j-1 The difference in the second temperature distribution parameter between adjacent monitoring points is calculated as the second longitudinal temperature rate change. ; The longitudinal temperature rate change is obtained by averaging the first and second longitudinal temperature rate changes. ; Extract the longitudinal temperature rate change of the mold and compare it with a preset threshold range. If the longitudinal temperature rate change of the mold is within the preset threshold range, then the longitudinal temperature rate change of the mold is normal; if the longitudinal temperature rate change of the mold is not within the preset threshold range, then the longitudinal temperature rate change of the mold has a secondary abnormality.

[0040] It should be noted that monitoring point i and monitoring point j are located on the same horizontal line on the inner and outer sides of the mold. The positions of the monitoring points on the same horizontal line on the mold are marked as follows: .

[0041] It should be noted that, based on the transverse and longitudinal temperature rate changes of the mold, the final value of the mold temperature rate change is output. The formula for calculating the final value of the mold temperature rate change is as follows: ,in, For position is The final value of the rate of temperature change.

[0042] In this embodiment of the invention, during the mold heating process, it is assumed that monitoring points i and j are arranged on the same horizontal line on the inner and outer sides of the mold, and their positions are denoted as follows: Simultaneously, two adjacent monitoring points, i-1 and j-1, were set vertically downwards. At the actual operating time t=10s, the following temperature data were recorded: the temperature of monitoring point i-1 inside the mold was 100℃, and the temperature of monitoring point i was 130℃; the temperature of monitoring point j-1 outside the mold was 95℃, and the temperature of monitoring point j was 125℃.

[0043] First, calculate the transverse temperature difference between the inner and outer sides at the same time point, and then obtain the transverse temperature rate of change. For example, at t=10s, the temperature difference between the inner and outer sides increases from 10℃ in the previous moment to 20℃, and the transverse temperature rate of change... =10℃. Compared with the preset threshold range [0,5], the result exceeds the threshold, therefore it is determined that the mold has a first-level lateral anomaly at this moment.

[0044] Next, the longitudinal temperature rate change is analyzed. On the inner side, the temperature difference between monitoring point i and monitoring point i-1 is |130−100| = 30℃; on the outer side, the temperature difference between monitoring point j and j-1 is |125−95| = ​​30℃. The longitudinal temperature rate change is obtained by averaging these differences. =0℃, falling within the preset range [0,5], at which point the longitudinal temperature rate change is normal. If at another moment the temperature difference inside the mold is 40℃ and the temperature difference outside the mold is 25℃, then the calculated... =7.5℃, exceeding the preset range [0,5], at which point it is judged as a longitudinal level two anomaly. Finally, the mold position is calculated by combining the transverse and longitudinal temperature rate changes. final value of temperature rate change .

[0045] Preferably, a linkage control strategy is established by using the final value of the mold temperature rate change and the historical first working parameters to dynamically balance the quality and production capacity of automotive parts. The specific steps for establishing the linkage control strategy are as follows: Obtain the final value of the mold temperature rate change at all monitoring points of the mold. , forming a temperature rate change sequence ,in, The position at time t is The final value of the rate of temperature change. The position at time n is The final value of the rate of temperature change; Based on the casting and cooling processes monitored, the temperature rate change sequence is divided into the first rate change sequence. and the second rate change sequence ,in, The position at time p is The final value of the rate of temperature change. for The time position is The final value of the rate of temperature change. For casting time, for The time position is The final value of the rate of temperature change. for The time position is The final value of the rate of temperature change. Cooling time; Based on the joint analysis of the first rate change sequence and the second rate change sequence, the mold temperature change is analyzed to determine whether the first flow velocity needs to be adjusted.

[0046] It should be noted that the first rate change sequence is the temperature rate change sequence of the mold during the casting process, and the second rate change sequence is the temperature rate change sequence of the mold during the cooling process. .

[0047] In this embodiment of the invention, multiple monitoring points are arranged on the surface of the mold during the casting process of automotive parts, and the final value of the temperature rate change at each monitoring point is acquired in real time. And form a temperature rate change sequence. Each term corresponds to the final value of the temperature rate change at a certain location at time t. Assuming that the total monitoring time of the mold is 60 seconds during a single part production cycle, then n=60, and the final value of the temperature rate change at each location is recorded every second.

[0048] Based on the technological characteristics of the casting process, the system divides the temperature rate change sequence into two stages: the first stage is the casting stage, lasting for the first 20 seconds, constituting the first rate change sequence; the second stage is the cooling stage, lasting for the last 40 seconds, constituting the second rate change sequence. During the casting stage, the mold temperature rises rapidly, and the final value of the temperature rate change shows some fluctuation at different locations. For example, at a certain location, the final temperature rate change is 12℃ / s at t=5s, but rises to 18℃ / s at t=10s. During the cooling stage, the mold temperature drops rapidly, but the rate of temperature drop varies at different locations. For example, at a certain location, the rate is 5℃ / s at t=30s, but drops to 2℃ / s at t=50s.

[0049] Based on the joint analysis of the first and second rate change sequences, the mold temperature change is assessed by comparing the final value of the temperature rate change at each location with historical first working parameters, such as preset temperature curves or flow rate reference values. If the temperature rate change at certain locations during the casting stage is found to be significantly higher than the historical reference value, it indicates that the molten metal is flowing too fast, which may lead to surface defects in the parts. The system will automatically determine that the first flow rate needs to be adjusted to reduce local temperature fluctuations and ensure a balance between part quality and production capacity. For example, in one production run, if the final value of the temperature rate change at a monitoring point inside the mold during the casting stage continuously exceeds the historical reference value by 15%, and the temperature drops too quickly during the cooling stage, combining the data from both stages, it is determined that the casting flow rate is too high. The system will automatically suggest adjusting the first flow rate from the original 10L / min to 8L / min, thereby reducing the risk of local overheating and shrinkage cavities, ensuring the quality of the finished parts while maintaining production efficiency.

[0050] Preferably, based on the joint analysis of the mold temperature change using the first rate change sequence and the second rate change sequence, it is determined whether the first flow velocity needs to be adjusted. The specific steps are as follows: Extracting the first rate change sequence Calculate the first temperature deviation value and compare it with a preset threshold. If the first temperature deviation value is greater than the preset threshold, the first flow rate needs to be adjusted. Second rate change sequence Calculate the second temperature deviation value and compare it with a preset threshold. If the second temperature deviation value is greater than the preset threshold, the first flow rate needs to be adjusted.

[0051] Preferably, the formula for calculating the first temperature deviation value is as follows: ; In the formula: This is the first temperature deviation value.

[0052] The formula for calculating the second temperature deviation value is: ; In the formula: This is the second temperature deviation value.

[0053] In this embodiment of the invention, multiple monitoring points are arranged on the mold surface during the casting production process of automotive parts. The final value of the temperature rate change at each monitoring point is collected in real time and divided into two stages according to the casting process: the casting stage and the cooling stage. The temperature rate change sequence of the casting stage is denoted as... The temperature rate change sequence during the cooling phase is denoted as... Assume that in one production run, the casting stage lasts for 20 seconds, the cooling stage lasts for 40 seconds, and the total monitoring time is 60 seconds.

[0054] First, for the casting stage, calculate the first temperature deviation value. Specifically, the final value of the temperature rate change at each monitoring point during the casting stage is compared with the average value for that stage to calculate the first temperature deviation value. The first temperature deviation value Compared with the preset threshold, the first temperature deviation value was found. Exceeding the threshold indicates excessive temperature rate fluctuations at certain locations during the casting stage, suggesting that the molten metal flow may be too fast or uneven, necessitating adjustment of the first flow rate. Subsequently, the cooling stage is analyzed, and the second temperature deviation value is calculated. By combining the casting and cooling stages, it is possible to dynamically determine whether the first flow rate needs to be adjusted. For example, in this production run, the system automatically suggested adjusting the originally set first flow rate from 10L / min to 8L / min to reduce local overheating and temperature fluctuations, thereby balancing part quality and production capacity, improving the finished product qualification rate, and maintaining production efficiency.

[0055] Preferably, when it is necessary to adjust the first flow velocity, the specific adjustment steps are as follows: Obtain the first temperature deviation value, the second temperature deviation value, and the first flow velocity. A flow velocity regulation calculation model is constructed, and the calculation formula of the flow velocity regulation calculation model is as follows: ; In the formula: The adjusted flow rate.

[0056] In the manufacturing process of automotive parts casting, this invention analyzes the temperature rate changes during the casting and cooling stages to identify a first temperature deviation value. Second temperature deviation value When the flow rate exceeds the preset threshold, it indicates significant local temperature fluctuations in the mold, necessitating adjustment of the first flow rate. Assume the current first flow rate is... =10L / min, first temperature deviation value is =1.5, the second temperature deviation value is =0.8, which can be obtained from the flow rate regulation calculation model. 3L / min, calculation results The adjusted flow rate is 3 L / min. The system then sends this flow rate value to the flow control device, automatically adjusting the flow rate of the molten metal during the casting stage. This reduces localized temperature fluctuations, prevents casting defects, and maintains production continuity and efficiency. In this way, the flow rate adjustment process achieves dynamic control based on real-time temperature deviations, ensuring uniform mold temperature changes, guaranteeing part quality, and allowing for flexible adjustment of the initial flow rate according to different batches or workpiece shapes, thus realizing intelligent production control.

[0057] Example 2: An IoT-based automotive parts defect detection system, comprising a parameter acquisition module, a temperature rate change detection module, and a parameter linkage control module; the parameter acquisition module is connected to the temperature rate change detection module, and the temperature rate change detection module is connected to the parameter linkage control module. The parameter acquisition module is used to acquire the first temperature distribution parameters of the mold by uniformly arranging multiple thermocouples from top to bottom along the casting direction inside the mold to construct a multi-dimensional temperature acquisition network, and to acquire the second temperature distribution parameters of the mold by arranging an infrared thermal imaging camera on the outside of the mold. It also monitors the first working parameters of the solution during the casting process based on a flow meter. The first working parameters include the flow rate and the casting time. The temperature rate change detection module is used to construct a temperature change recognition model based on the first temperature distribution parameter and the second temperature distribution parameter, to identify anomalies in the longitudinal and transverse temperature rate changes of the mold, and to output the final value of the mold temperature rate change based on the identification result. The parameter linkage control module is used to build a linkage control strategy based on the final value of the mold temperature rate change and the historical first working parameters, so as to dynamically balance the quality and production capacity of automotive parts.

[0058] like Figure 2 The diagram shown is a system block diagram of an IoT-based automotive parts defect detection system according to an embodiment of the present invention, which can be used to execute... Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0059] Through the above embodiments, this invention utilizes a multi-dimensional temperature acquisition network consisting of internal thermocouples and external infrared thermal imaging cameras, along with casting parameters recorded by a flow meter, to construct a temperature change recognition model and output the final value of the temperature rate change. This enables real-time and continuous monitoring of the internal and surface temperatures of the mold. By identifying anomalies in the lateral and longitudinal temperature rate changes, it can promptly detect localized overheating or uneven temperature distribution in the mold, preventing shrinkage cavities, porosity, or surface defects in the castings, thereby significantly improving the yield and quality stability of the parts. By jointly analyzing the final value of the temperature rate change with historical first-stage working parameters, a linkage control strategy is established to dynamically adjust the casting flow rate and casting time, making the temperature distribution more uniform during production. This avoids affecting part performance due to excessively high or low local temperatures, optimizing production capacity while ensuring part quality, reducing unnecessary reprocessing and scrap rates, and ultimately improving production efficiency.

[0060] This invention achieves intelligent control of the automotive parts production process through multi-point data fusion and model analysis. This eliminates the need for process parameter adjustments to rely on experience or manual judgment, instead enabling scientific decision-making based on real-time data and historical experience. This not only improves the controllability and reliability of the production process but also provides strong support for subsequent process optimization, mold maintenance, and production data accumulation.

[0061] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

[0062] In conclusion, the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for detecting defects in automotive parts based on the Internet of Things, characterized in that, Includes the following steps: By uniformly arranging multiple thermocouples from top to bottom inside the mold along the casting direction, a multi-dimensional temperature acquisition network is constructed to obtain the first temperature distribution parameters of the mold. By arranging an infrared thermal imaging camera on the outside of the mold, the second temperature distribution parameters of the mold are obtained. The first working parameters of the solution during the casting process are monitored based on a flow meter. The first working parameters include the flow rate and the casting time. A temperature change identification model is constructed based on the first and second temperature distribution parameters. Anomalies are detected in the longitudinal and transverse temperature rate changes of the mold. The final value of the mold temperature rate change is output based on the detection results. The specific steps are as follows: The first temperature distribution parameters of the same monitoring point i are obtained during the monitoring process to form the first temperature change sequence; the second temperature distribution parameters of the monitoring point j are obtained to form the second temperature change sequence. Based on the first temperature change sequence and the second temperature change sequence, the lateral temperature rate change of the mold is analyzed, and a first-level abnormal temperature is identified. Based on the first temperature change sequence and the second temperature change sequence, the longitudinal temperature rate change of the mold is analyzed, and a secondary abnormal temperature is identified. Based on the transverse and longitudinal temperature rate changes of the mold, the final value of the mold temperature rate change is output. The formula for calculating the final value of the mold temperature rate change is as follows: ,in, For position is The final value of the rate of temperature change. The transverse temperature rate change at monitoring points i and j of the mold. The longitudinal temperature rate changes at monitoring points i and j of the mold; Among them, monitoring point i and monitoring point j are located on the same horizontal line on the inner and outer sides of the mold, and the positions of the monitoring points on the same horizontal line on the mold are marked as follows: A linkage control strategy is established based on the final value of the mold temperature rate change and the historical first operating parameter. The historical first operating parameter is a preset temperature curve or a flow velocity reference value. The specific steps for establishing the linkage control strategy are as follows: Obtain the final value of the mold temperature rate change at all monitoring points of the mold. This constitutes a sequence of temperature rate changes: Based on the casting and cooling processes during monitoring, the temperature rate change sequence is divided into a first rate change sequence and a second rate change sequence. Based on the joint analysis of the first rate change sequence and the second rate change sequence, the mold temperature change is analyzed to determine whether the first flow velocity needs to be adjusted.

2. The method for detecting defects in automotive parts based on the Internet of Things according to claim 1, characterized in that, Based on the first and second temperature change sequences, the transverse temperature rate change of the mold is analyzed, and a first-level abnormal temperature detection is performed. The specific steps are as follows: Obtain the first temperature change sequence at monitoring point i. and the second temperature change sequence at monitoring point j Calculate the temperature difference between the inside and outside of the mold at the same time point t. The lateral temperature rate change of the mold is obtained based on the temperature difference between the inside and outside at adjacent time points. ; Extract the lateral temperature rate change of the mold and compare it with a preset threshold range. If the lateral temperature rate change of the mold is within the preset threshold range, then the lateral temperature rate change of the mold is normal; if the lateral temperature rate change of the mold is not within the preset threshold range, then the lateral temperature rate change of the mold has a level one anomaly.

3. The method for detecting defects in automotive parts based on the Internet of Things according to claim 1, characterized in that, Based on the first and second temperature change sequences, the longitudinal temperature rate change of the mold is analyzed, and a secondary abnormal temperature is identified. The specific steps are as follows: Obtain the first temperature change sequence at monitoring point i. and the second temperature change sequence at monitoring point j Obtain the first temperature change sequence at monitoring point i-1. and the second temperature change sequence at monitoring point j-1 ; Extract the first temperature distribution parameters of the mold at the same time point t and monitoring point i. and the first temperature distribution parameters of monitoring point i-1 The difference in the first temperature distribution parameter between adjacent monitoring points is calculated as the first longitudinal temperature rate change. ; Extract the second temperature distribution parameters of the mold at the same time point t and monitoring point j. and the second temperature distribution parameters of monitoring point j-1 The difference in the second temperature distribution parameter between adjacent monitoring points is calculated as the second longitudinal temperature rate change. ; The longitudinal temperature rate change is obtained by averaging the first and second longitudinal temperature rate changes. ; Extract the longitudinal temperature rate change of the mold and compare it with a preset threshold range. If the longitudinal temperature rate change of the mold is within the preset threshold range, then the longitudinal temperature rate change of the mold is normal; if the longitudinal temperature rate change of the mold is not within the preset threshold range, then the longitudinal temperature rate change of the mold has a secondary abnormality.

4. The method for detecting defects in automotive parts based on the Internet of Things according to claim 3, characterized in that, The first rate change sequence is: The second rate change sequence is ,in, The position at time p is The final value of the rate of temperature change. for The time position is The final value of the rate of temperature change. For casting time, for The time position is The final value of the rate of temperature change. for The time position is The final value of the rate of temperature change. This refers to the cooling time.

5. The method for detecting defects in automotive parts based on the Internet of Things according to claim 4, characterized in that, Based on the joint analysis of the first and second rate change sequences, the mold temperature change is analyzed to determine whether the first flow velocity needs to be adjusted. The specific steps are as follows: Extracting the first rate change sequence Calculate the first temperature deviation value and compare it with a preset threshold. If the first temperature deviation value is greater than the preset threshold, the first flow rate needs to be adjusted. Second rate change sequence Calculate the second temperature deviation value and compare it with a preset threshold. If the second temperature deviation value is greater than the preset threshold, the first flow rate needs to be adjusted.

6. The method for detecting defects in automotive parts based on the Internet of Things according to claim 5, characterized in that, The first rate change sequence is the temperature rate change sequence of the mold during the casting process, and the second rate change sequence is the temperature rate change sequence of the mold during the cooling process. .

7. An Internet of Things (IoT)-based automotive parts defect detection system, applied to the IoT-based automotive parts defect detection method as described in any one of claims 1-6, characterized in that, The system includes: a parameter acquisition module, a temperature rate change detection module, and a parameter linkage control module; The parameter acquisition module is used to acquire the first temperature distribution parameters of the mold by uniformly arranging multiple thermocouples from top to bottom along the casting direction inside the mold to construct a multi-dimensional temperature acquisition network, and to acquire the second temperature distribution parameters of the mold by arranging an infrared thermal imaging camera on the outside of the mold. It also monitors the first working parameters of the solution during the casting process based on a flow meter. The first working parameters include the flow rate and the casting time. The temperature rate change detection module is used to construct a temperature change recognition model based on the first temperature distribution parameter and the second temperature distribution parameter, to identify anomalies in the longitudinal and transverse temperature rate changes of the mold, and to output the final value of the mold temperature rate change based on the identification result. The parameter linkage control module is used to build a linkage control strategy based on the final value of the mold temperature rate change and the historical first working parameters, so as to dynamically balance the quality and production capacity of automotive parts.

Images