Method and system for collecting and monitoring production data of automotive trim injection molding equipment

Abstract

The invention relates to the technical field of equipment monitoring, in particular to a method and a system for collecting and monitoring production data of automotive trim injection molding equipment. Comprising the following steps: firstly, acquiring real-time operation state data from injection molding equipment through a communication node, generating an equipment state data set, and constructing a parameter coupling model through a time sequence analysis method; when the temperature parameter fluctuation exceeds a preset threshold value, fusing the pressure data to generate optimal configuration, transmitting the optimal configuration to related equipment through an interactive network, and determining a linkage parameter set; thirdly, the linkage parameter set is processed through a classification method, a deviation index is obtained, a synchronization instruction is generated according to deviation, it is ensured that beats between the devices are consistent, and a unified production cycle is formed; and finally, through the prediction model, extracting production cycle data, predicting parameter fluctuation, adjusting equipment parameters, and determining final process configuration. The problems of beat deviation and parameter fluctuation between injection molding equipment in production are solved, the production process is optimized, and the production efficiency and the product quality are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of equipment monitoring, and in particular to a production data acquisition and monitoring method and system for automotive interior injection molding equipment. BACKGROUND

[0002] In the production process of automotive interior parts, the production efficiency and product quality stability are highly dependent on the coordinated operation of multiple devices such as injection molding machines, mold temperature machines, and drying machines. However, there is a complex dynamic coupling relationship between key process parameters such as barrel temperature, mold temperature, and injection pressure. Small fluctuations in these parameters often lead to abnormal changes in injection pressure, which in turn causes production cycle to be extended or shortened, resulting in decreased product size precision, increased surface defects, or even increased scrap rate. For example, when the barrel temperature fluctuates slightly around the set value, it may cause the injection pressure to be unstable, thereby directly affecting the molding consistency of the product.

[0003] At the same time, the beat deviation between different devices in the production line also destroys the overall production synchronization. If there is a difference in the running rhythm of the injection molding machine, the mold temperature machine, and the robot, it is easy to form inconsistent production cycles, increase the difficulty of scheduling and control, and thus reduce the overall production efficiency. The existing technology usually relies on static control of single machine parameters, and it is difficult to cope with the complexity brought by real-time interaction of multiple devices and multiple parameters in actual production. Especially in the manufacturing scene of high-precision automotive interior parts, the existing scheme cannot accurately model the dynamic relationship between barrel temperature fluctuations and injection pressure, nor can it quantitatively identify and correct the beat deviation and synchronize the production cycles of multiple devices, which leads to poor production consistency, difficult quality control, and high scrap rate.

[0004] Therefore, how to effectively acquire and monitor key process parameters in automotive interior injection molding production, establish a model that can reflect the coupling relationship between temperature and pressure, and real-time identify and correct the beat deviation to achieve dynamic synchronization of multiple device production cycles, has become a core technical problem that needs to be solved in the field of injection molding intelligent manufacturing. SUMMARY

[0005] The production data acquisition and monitoring method and system for automotive interior injection molding equipment proposed by the present application can realize dynamic acquisition, fusion analysis, and collaborative control of multi-source data of injection molding machines, mold temperature machines, barrels, and related devices, thereby significantly improving the stability of the production process and the quality of the products.

[0006] In a first aspect, the present application provides a production data acquisition and monitoring method for automotive interior injection molding equipment, mainly comprising: Step S1: obtaining device state data set from injection molding equipment through communication node by acquiring real-time running state data, and processing the device state data set by using time series analysis method to construct parameter coupling model; Step S2: Input the real-time collected barrel temperature sequence and injection pressure sequence into the parameter coupling model to determine whether the temperature parameter fluctuation exceeds the preset threshold. If it does, the injection pressure data is fused to generate mold temperature controller control instructions and temperature optimization configuration. The barrel temperature optimization configuration is obtained through the barrel fluctuation amplitude and transmitted to relevant devices through the interactive network to determine the linkage parameter set. Step S3: The set of linkage parameters is processed using a classification method to obtain a deviation index. If the deviation index exceeds the allowable range, a synchronization instruction sequence is generated and transmitted to the relevant equipment to obtain a unified production cycle. Step S4: Extract data from the unified production cycle using the prediction model to predict parameter fluctuations, adjust equipment parameters, and determine the final process configuration.

[0007] As a preferred embodiment of the present invention, in step S1, obtaining equipment status dataset by acquiring real-time operating status data from the injection molding equipment through a communication node includes: By collecting barrel temperature, mold temperature, and injection pressure data through communication nodes deployed in the injection molding machine, mold temperature controller, and dryer, an equipment status dataset containing the barrel temperature, mold temperature, and injection pressure is generated. Feature extraction is performed on the small fluctuation data of the barrel temperature to determine the influence characteristics of the small fluctuations of the barrel temperature on the injection pressure, and an equipment status dataset for subsequent analysis is generated.

[0008] As a preferred embodiment of the present invention, step S1 involves processing the equipment status dataset using a time series analysis method to determine the parameter coupling model, including: The dynamic change characteristics are obtained by performing time series decomposition on the equipment status dataset. The time series correlation between the micro-fluctuation of the barrel temperature and the injection pressure is analyzed. A coupling effect model including the micro-fluctuation of the barrel temperature and the instability of the injection pressure is constructed. Based on the coupling effect model, the correspondence between the barrel temperature fluctuation and the injection pressure is obtained. Based on the correspondence, a parameter coupling model is constructed. The barrel temperature micro-fluctuation data and the injection pressure data are used as training data, and the parameter coupling model is trained.

[0009] As a preferred embodiment of the present invention, in step S2, it is determined whether the temperature parameter fluctuation exceeds a preset threshold based on the parameter coupling model. If it does, the pressure data is fused to adjust the control command and generate an optimized configuration, including: The real-time obtained barrel temperature sequence and injection pressure sequence are input into the parameter coupling model, and it is judged whether the barrel temperature fluctuation amplitude exceeds a preset threshold value, if yes, a mold temperature machine control factor is generated by fusing the injection pressure data, a mold temperature machine control instruction is obtained according to the control factor, the barrel temperature configuration is optimized through the barrel fluctuation amplitude and the temperature of the mold temperature machine, a barrel temperature optimization configuration containing an optimized temperature value is generated, and the step is repeated to obtain the mold temperature machine control instruction and the temperature optimization configuration in real time and transmit them to the mold temperature machine to realize real-time adjustment cycle.

[0010] As a preferred technical solution of the present application, in step S2, the optimization configuration is transmitted to the related equipment through the interactive network to determine the linkage parameter set, including: The adjusted mold temperature value is extracted from the temperature optimization configuration, transmitted to the injection molding machine and the mold temperature machine through the interactive network, and a linkage parameter set containing the mold temperature and the beat time sequence is generated. The beat difference between the devices in the linkage parameter set is quantified by using the parameter vector representation method, and the linkage parameter set for subsequent classification is determined.

[0011] As a preferred technical solution of the present application, in step S3, the classification method is used to process the linkage parameter set to obtain a deviation index, including: The support vector classification method is used to classify and process the linkage parameter set, and a classification result representing the degree of beat difference is generated. The beat deviation index is calculated according to the classification result, the range of the beat deviation index is defined by a preset classification boundary, the deviation index for evaluating the synchronization of the linkage equipment is determined, and a real-time judgment mechanism is generated.

[0012] As a preferred technical solution of the present application, in step S3, if the deviation index exceeds the allowed range, a synchronization instruction sequence is generated and transmitted to the related equipment to obtain a unified production cycle, including: It is judged whether the deviation index exceeds the preset allowed range, if yes, a synchronization instruction sequence is generated according to the deviation index, the synchronization instruction sequence is transmitted to the injection molding machine and the manipulator, the device running beat is adjusted to generate a unified production cycle, and the beat difference is quantified by an optimization algorithm to correct the slight deviation.

[0013] As a preferred technical solution of the present application, step S4 includes: The cycle matching data is extracted from the unified production cycle, the neural network model is used to process the cycle matching data, a predicted parameter fluctuation sequence is generated, the historical data and the real-time adjustment cycle data are fused to adjust the dryer parameters, and the final process configuration is generated by integrating the predicted parameter fluctuation sequence and the adjusted parameters.

[0014] In a second aspect, the present application further provides a production data acquisition and monitoring system for an automotive interior injection molding device, which is used to implement the above method, and the system comprises: a model construction unit configured to obtain a device state data set by acquiring real-time running state data of the injection molding device through a communication node, and to construct a parameter coupling model by processing the device state data set using a time series analysis method; a parameter determination unit configured to input a real-time acquired barrel temperature sequence and injection pressure sequence into the parameter coupling model, to determine whether the temperature parameter fluctuation exceeds a preset threshold, to generate a mold temperature controller instruction and a temperature optimization configuration by fusing injection pressure data if the temperature parameter fluctuation exceeds the preset threshold, to acquire the barrel temperature optimization configuration by a barrel fluctuation amplitude, and to transmit the temperature optimization configuration to related devices through an interactive network to determine a linkage parameter set; a calculation unit configured to obtain a deviation index by processing the linkage parameter set using a classification method, and to generate a synchronization instruction sequence and transmit the synchronization instruction sequence to related devices to obtain a unified production cycle if the deviation index exceeds an allowable range; a device adjustment unit configured to extract data from the unified production cycle to predict a parameter fluctuation by using a prediction model, to adjust a device parameter to determine a final process configuration, and to output the final process configuration to a device.

[0015] In a third aspect, the present application further provides a computer readable storage medium, and the computer readable storage medium stores instructions, and the instructions are executed by a processor to implement the above method.

[0016] The technical scheme provided by the embodiments of the present application can have the following beneficial effects: The application can effectively capture the dynamic relationship between the barrel temperature micro-fluctuation and the injection pressure instability by the time series analysis and the parameter coupling model construction of step S1, avoid the limitation of single parameter control, provide a scientific basis for subsequent judgment, step S2 judges whether the temperature fluctuation exceeds the threshold based on the coupling model, if it exceeds the threshold, the injection pressure data is fused to generate an adjustment factor, and then an optimized mold temperature machine control instruction is formed to realize the dynamic correction of the barrel temperature configuration and reduce the pressure instability caused by temperature fluctuation; in step S3, the beat inconsistency problem between devices can be found in time by classifying the linkage parameter set and calculating the deviation index; when the deviation exceeds the allowed range, a synchronization instruction is automatically generated to make the injection molding machine, mold temperature machine and manipulator maintain a unified production cycle, thereby ensuring the time coordination of multi-device operation; further, step S4 extracts feature data in the unified production cycle through a prediction model, generates a predicted fluctuation sequence by combining historical and real-time data, and adjusts the process configuration in advance to realize predictive control of future working conditions; through the mutual cooperation of the above technical solutions, both abnormal fluctuations of barrel temperature and injection pressure can be suppressed in real time, and the consistency of multi-device production cycle can be ensured, and the forward-looking prediction function is also provided, thereby effectively solving the problems of unstable production process, large beat deviation and difficult product quality guarantee in the prior art, and finally realizing the intelligentization, refinement and high efficiency of the automobile interior injection molding production. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The application is an embodiment of a method for monitoring production data acquisition of an automobile interior injection molding device.

[0018] Figure 2 The application is an embodiment of a method for monitoring production data acquisition of an automobile interior injection molding device. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the application will be described clearly and in detail below with reference to the drawings in the embodiments of the application. The described embodiments are only a part of the embodiments of the application.

[0020] As Figure 1 , the embodiment of the application is a method for monitoring production data acquisition of an automobile interior injection molding device, which can specifically include: Step S1: obtaining device state data set from injection molding equipment through communication node by real-time running state data, adopting time series analysis method to process the device state data set to determine parameter coupling model; In step S1, the device state data set is obtained from the injection molding equipment through the communication node by real-time running state data, which includes: The injection pressure, mold temperature and barrel temperature data are collected through the communication nodes arranged in the injection molding machine, mold temperature controller and barrel, an equipment state data set containing the barrel temperature, mold temperature and injection pressure is generated, the feature extraction is performed on the slight fluctuation data of the barrel temperature, the influence feature of the barrel temperature fluctuation on the injection pressure is determined, and the equipment state data set is generated.

[0021] Specifically, in the production process of automotive interior injection molding, the fluctuation and synchronism of equipment parameters often lead to low production efficiency and unstable product quality, especially in the production of high-precision interior parts, any slight parameter fluctuation will affect the dimensional accuracy and surface quality of the injection molded product. The injection molding machine is the core execution equipment of production, and the barrel is located in the heating and injection unit, which is the key part of plastic particle melting and storage, and its temperature directly determines the stability of the melt viscosity and injection pressure. The mold temperature controller adjusts the mold temperature to affect the cooling rate and thermal equilibrium of the melt in the cavity, and the heat exchange between the mold and the melt in turn affects the stability of the barrel temperature. Specifically, there is a complex mutual coupling relationship between key parameters such as barrel temperature, mold temperature and injection pressure, and the fluctuation of these parameters will directly affect the synchronism of the equipment and the production cycle. Therefore, real-time running state data including barrel temperature, mold temperature and injection pressure and other parameters are collected through the communication nodes arranged in the injection molding machine, mold temperature controller and barrel to generate an equipment state data set. To ensure the real-time of the data, the communication nodes collect data once per second through wireless sensors, store these data in time series format, and include time stamp and corresponding parameter value to form an initial equipment state data set. Next, for the slight fluctuation data of the barrel temperature, wavelet transform technology is used to extract its features, the signal is decomposed into different frequency components, and the appropriate wavelet base such as Daubechies wavelet is selected to calculate the coefficients, from which the features representing the slight fluctuation are extracted, such as the standard deviation of the detail coefficient. This processing method can identify the slight change of the barrel temperature fluctuation less than 1 degree Celsius, i.e. the above-mentioned slight fluctuation data, and further analyze the influence feature of the temperature fluctuation on the injection pressure. Specifically, the Pearson correlation coefficient method is used to calculate the linear relationship between the temperature fluctuation and the injection pressure. If the correlation coefficient is greater than 0.8, it means that the temperature fluctuation will cause the pressure fluctuation to be unstable, and further affect the molding precision and product quality in the injection molding process. By integrating the extracted fluctuation features and influence features into the initial data set, an extended data set is formed, which provides data support for subsequent parameter coupling analysis.

[0022] In the implementation process, such as in the scenario of ABS plastic injection molding, if the barrel temperature is set to 220 degrees Celsius, the fluctuation is less than 0.3 degrees Celsius, and the average value of the detail coefficients extracted by wavelet transform is 0.1, indicating low-frequency fluctuation, which helps to identify potential deviations early, improves the consistency of automotive interior parts forming, and reduces the scrap rate; further, in the PC material injection molding process, a temperature fluctuation of 0.4 degrees Celsius may cause an injection pressure deviation of 1.5 megapascals, with a correlation coefficient of 0.85, indicating a strong influence of temperature fluctuation on pressure; the above data support optimizing production efficiency by adjusting control parameters in real time, and reducing small tact deviations to ensure equipment synchronization and improve overall production stability; in addition, the present embodiment also extends to other scenarios, such as automotive precision gear injection molding, with a temperature fluctuation threshold of 0.2 degrees Celsius, further reducing small tact deviations and ensuring the coordinated operation of production equipment. Through comprehensive analysis of equipment state data sets, wavelet transform to extract fluctuation characteristics, Pearson correlation coefficient analysis to analyze influence characteristics, and real-time data processing, the final realization of precise control of small deviations in the injection molding process improves product quality and production efficiency.

[0023] Further, in step S1, a parameter coupling model is determined by processing the equipment state data set using a time series analysis method, comprising: The time series decomposition of the barrel temperature sequence and the injection pressure sequence in the equipment state data set obtains dynamic change characteristics, analyzes the time series correlation between the barrel temperature micro-fluctuation and the injection pressure, constructs a coupling effect model containing the barrel temperature micro-fluctuation and the injection pressure instability, obtains the corresponding relationship between the barrel temperature fluctuation and the injection pressure based on the coupling effect model, and constructs a parameter coupling model based on the corresponding relationship. The barrel temperature micro-fluctuation data, the barrel temperature sequence data and the injection pressure data are used as training data, and the parameter coupling model is trained.

[0024] Specifically, in the production process of automotive interior injection molding equipment, the cooperation between injection molding machines, mold temperature machines, barrels and other devices plays a crucial role in production efficiency and product quality. However, due to the dynamic fluctuation and complex coupling relationship of device parameters such as barrel temperature and injection pressure, it often leads to unstable production cycle, tact deviation between devices and quality problems of final products; therefore, by decomposing the barrel temperature sequence and injection pressure sequence in the equipment state data set using time series analysis method, the data is divided into trend component, seasonal component and residual component, wherein the trend component captures long-term changes, the seasonal component reflects periodic patterns, and the residual component represents random fluctuations; further, according to the decomposition result, the contribution of each component is quantified to extract dynamic change characteristics, especially the influence of barrel temperature micro-fluctuation on injection pressure, effectively avoiding the interference of original data noise.

[0025] Next, the time series correlation between the barrel temperature fluctuations and the injection pressure is analyzed. The correlation between the barrel temperature fluctuation sequence and the injection pressure sequence is calculated by the cross-correlation function, the linear correlation strength between the temperature fluctuations and the pressure instability is quantified by the Pearson correlation coefficient, and finally the Granger causality test is used to determine whether a time series can be used to predict another sequence. When the three analysis results are consistent, i.e., the temperature change precedes the pressure change in time, there is a significant correlation between the two, and the temperature has Granger causality to the pressure, it is determined that the barrel temperature fluctuations will directly cause the instability of the injection pressure and quantify the impact. Conversely, it will not; the above analysis provides key data support for the subsequent steps, helping to accurately identify the impact of temperature changes on pressure instability, and ensuring the robustness of the model under different materials such as ABS plastic or POM material.

[0026] On this basis, a vector autoregression algorithm is used to construct a coupling effect model of barrel temperature fluctuations and injection pressure instability. The barrel temperature sequence and the injection pressure sequence are used as endogenous variables, and the coefficient matrix is used to capture the dynamic interaction between them, for example, the temperature fluctuation term as a lag predictor of pressure instability, by introducing a coupling coefficient, the sensitivity of the barrel temperature change rate to the injection pressure deviation is quantified. The above coupling effect model is fitted by the least squares method to simulate the coupling effect, for example, a 1% increase in temperature fluctuations leads to a 1.5-fold increase in the amplitude of pressure instability, ensuring accurate capture of the impact of small deviations on production control. At the same time, the parameter coupling effect model can be adjusted according to the load of different devices in actual production, ensuring the consistency of production under different working conditions.

[0027] In addition, the Kalman filter is used to fuse the barrel temperature data and the injection pressure data, and the state equation and the observation equation are used to iteratively update the data, reduce the measurement noise, and generate a smooth joint sequence. By assigning appropriate weights to the temperature and pressure data, accurate data fusion is achieved, and the adaptability of the parameter coupling model in complex production scenarios is improved, thereby training and optimizing the coupling effect model. That is, the barrel temperature sequence and the injection pressure sequence are used as data inputs, and the corresponding relationship between the predicted future period of barrel temperature and the above injection pressure, i.e., the coupling coefficient between the two and the predicted injection pressure deviation, is used as the output. Finally, based on the results of the previous steps, the final parameter coupling model is generated to provide support for the optimization of the injection molding production process. This model not only ensures the coordination between temperature, pressure and other parameters, but also optimizes the production cycle by adjusting the device parameters in real time, improves the production efficiency and the stability of product quality, effectively solves the technical problems of beat deviation and parameter fluctuation among multiple devices, and realizes the intelligentization and high efficiency of the injection molding production process.

[0028] Step S2: input the real-time collected barrel temperature sequence and injection pressure sequence into the parameter coupling model, determine whether the temperature parameter fluctuation exceeds the preset threshold, if it exceeds, if it exceeds, then generate mold temperature controller instruction and temperature optimization configuration by fusing injection pressure data, and obtain mold temperature optimization configuration through barrel fluctuation amplitude, and transmit the temperature optimization configuration to related equipment through interactive network to determine the linkage parameter set; In step S2, according to the parameter coupling model, determine whether the temperature parameter fluctuation exceeds the preset threshold, if it exceeds, if it exceeds, then generate mold temperature controller instruction and temperature optimization configuration by fusing injection pressure data, and obtain mold temperature optimization configuration through barrel fluctuation amplitude, including: Input the real-time obtained barrel temperature sequence and injection pressure sequence into the parameter coupling model, and determine whether the barrel temperature micro-fluctuation amplitude exceeds the preset threshold, if it exceeds, then generate mold temperature controller instruction by fusing the injection pressure data, obtain the mold temperature controller instruction according to the control factor, and also generate the barrel temperature optimization configuration containing the optimized temperature value through the barrel fluctuation amplitude and the temperature optimization barrel temperature configuration of the mold temperature controller, and repeat the step to obtain the mold temperature controller instruction and the temperature optimization configuration in real time, and transmit them to the mold temperature controller to realize real-time adjustment cycle.

[0029] Specifically, in the present embodiment, first, real-time running state data is obtained from the automotive interior injection molding equipment through the communication node to form an equipment state data set. This data set includes time series data of key parameters such as barrel temperature, mold temperature and injection pressure. Then, the equipment state data set is processed using time series analysis method to build a parameter coupling model; specifically, for the barrel temperature data, its micro fluctuation amplitude is calculated, for example, by calculating the temperature difference value sequence of adjacent time points, and taking the standard deviation as the amplitude index; if the calculated amplitude exceeds the preset threshold (for example, 0.5 degrees Celsius), the subsequent fusion step is triggered, in which the injection pressure data sequence is extracted, and the micro fluctuation data of the barrel temperature is fused with the injection pressure data; for this purpose, the parameter coupling model is used to predict the influence of temperature fluctuation on pressure change, and the coupling coefficient, i.e. the influence intensity of the above-mentioned barrel temperature change on the injection pressure change, is generated through data fusion, and the corresponding predicted injection pressure deviation is also obtained. The mold temperature is controlled by the mold temperature machine, and when the mold temperature machine temperature changes, the mold surface temperature changes will change the heat dissipation rate of the melt, thereby affecting the overall temperature balance of the melt in the barrel. The mold temperature machine does not directly intervene in the barrel heating, but plays the role of a "thermal buffer" in the injection heating process, for example: when different kinds or batches of plastic particles are replaced, such as ABS to POM, due to the different heat sensitivity of the materials, the control difficulty of the barrel temperature increases, and the fluctuation amplitude is also larger. By adjusting the mold temperature machine, the heat balance of the barrel and the melt is indirectly changed. Therefore, by using the above-mentioned coupling coefficient and the above-mentioned predicted injection pressure deviation, the adjustment factor of the above-mentioned mold temperature machine temperature, i.e. the additional injection pressure influence intensity caused by the barrel temperature exceeding the threshold, is generated, and based on the corresponding relationship between the above-mentioned adjustment factor and the mold temperature machine temperature, the mold temperature machine control instruction is generated, for example, if the temperature fluctuation causes the injection pressure to increase by 5 bar, the mold temperature machine temperature can be adjusted by the above-mentioned control instruction, for example, the mold temperature machine temperature is reduced by 1 degree Celsius to compensate for the influence of the barrel temperature fluctuation. After the mold temperature machine executes, the barrel temperature sensor and the injection pressure sensor will feed back new data to judge whether the barrel temperature fluctuation has fallen within the threshold, and the temperature optimization configuration for adjusting the above-mentioned barrel temperature is generated based on the real-time obtained barrel fluctuation amplitude and the above-mentioned mold temperature machine temperature to reduce the temperature fluctuation of the barrel temperature, and the real-time temperature of the above-mentioned mold temperature machine is repeatedly adjusted in real time to optimize the configuration. The optimized configuration verifies the change of the fluctuation amplitude by simulating the adjusted temperature value, such as 199.5 degrees Celsius, to ensure that it falls below the threshold, thereby ensuring temperature stability and the stability of melt viscosity and injection pressure, thereby improving production efficiency and reducing the accumulation of small deviations, ensuring product consistency and precision, especially when producing high-precision automotive interior parts, ensuring accurate control of various parameters, reducing part defects caused by barrel temperature fluctuation and unstable injection pressure, and optimizing production cycle and process configuration.

[0030] Further, in step S2, the optimized configuration is transmitted to the relevant devices through the interactive network to determine the linkage parameter set, including: The adjusted mold temperature value is extracted from the temperature optimization configuration and transmitted to the injection molding machine and the mold temperature machine through the interactive network to generate a linkage parameter set containing mold temperature and beat time sequence. The beat difference between devices in the linkage parameter set is quantified by parameter vector representation method, and the linkage parameter set for subsequent classification is determined.

[0031] Specifically, in order to improve the efficiency and product quality stability of injection molding production, first, the running state data is obtained from the injection molding equipment in real time through the communication node to generate the device state data set, and the time series analysis method is used to process the data set to build the parameter coupling model. On this basis, when the temperature parameter fluctuation exceeds the preset threshold, the optimization control instruction is generated by fusing the pressure data, and the optimized configuration is transmitted to the relevant devices through the interactive network to determine the linkage parameter set.

[0032] In the specific implementation process, the adjusted mold temperature value is extracted from the above-mentioned temperature optimization configuration, wherein the temperature optimization configuration includes barrel temperature optimization configuration and mold temperature machine temperature optimization configuration, and the value is transmitted to the injection molding machine and the mold temperature machine through the interactive network to generate a linkage parameter set containing mold temperature and beat time sequence, wherein the beat time sequence is the duration data of the injection molding equipment, i.e. the barrel, the mold temperature machine and the injection molding machine, in each production cycle, which is used to describe the time rhythm of the injection molding equipment in each production cycle. At this time, the mold temperature and the beat time sequence are converted into vector form by parameter vector representation method, the beat difference between different devices is quantified into numerical form, and the difference degree is calculated. Taking the injection molding machine and the mold temperature machine as an example, the mold temperature and the beat time sequence correspond to the vector component and the time sequence respectively, the difference is quantified by calculating the Euclidean distance, for example, when the beat of the injection molding machine is [2.5, 2.6] seconds, and the beat of the mold temperature machine is [2.4, 2.5] seconds, the calculated difference is 0.1 seconds. This difference value can effectively reflect the beat deviation between devices, so as to identify the influence of small fluctuations in the process of precision production in time.

[0033] Further, according to the calculated beat difference degree, the weight is adjusted and weighted average is carried out to more accurately quantify the beat deviation and ensure parameter fusion in real-time adjustment; finally, the quantized linkage parameter set will be used for support vector classification to judge the deviation degree and generate real-time synchronization instruction sequence, which will be transmitted to the relevant devices to adjust the running beat of the devices to ensure that multiple devices operate synchronously in the production process, forming a unified production cycle, thereby effectively reducing the instability in the molding of precision parts and improving the production consistency and product quality.

[0034] The technical scheme can automatically adjust the equipment running state based on the data collected by the sensor, in combination with time series analysis and classification methods, optimize the temperature, pressure and beat control in the injection molding production process, and thus improve the overall production efficiency and the size precision of the parts.

[0035] Step S3: processing the linkage parameter set by using a classification method to obtain a deviation index, and if the deviation index exceeds an allowable range, generating a synchronization instruction sequence and transmitting the synchronization instruction sequence to related equipment to obtain a unified production cycle; In step S3, the linkage parameter set is processed by using a classification method to obtain a deviation index, including: The linkage parameter set is classified and processed by using a support vector classification method to generate a classification result representing the degree of beat difference, the beat deviation is calculated according to the classification result, the range of the beat deviation is defined by a preset classification boundary, the deviation index for evaluating the synchronization of the linkage equipment is determined, and a real-time judgment mechanism is generated.

[0036] Specifically, the linkage parameter set is classified and processed by using a support vector classification method to generate a classification result representing the degree of beat difference. The classification method maps data points to a high-dimensional feature space and uses a kernel function, i.e., a radial basis function, to process nonlinear relationships, optimizes a hyperplane to maximize the interval between class data points, and thus ensures effective separation between different classes. The classification result is in the form of a numerical score, such as 1 for slight difference, 2 for moderate difference, and 3 for serious difference. The deviation index is calculated by weighted average, and thus the overall synchronization state is reflected.

[0037] According to the preset classification boundary range, the deviation index is defined in the range of 0 to 5, wherein 0 to 2 represents an acceptable range, and 3 or more triggers an alarm. If the deviation index exceeds the allowed range, a synchronization instruction sequence is automatically generated and transmitted to the device to adjust the device beat to achieve a unified production cycle. The real-time performance of this process is fully guaranteed. Especially when the barrel temperature fluctuates by 0.5 degrees Celsius, the beat time sequence in the linkage parameter set shows that the injection molding machine cycle is 10 seconds, the manipulator cycle is 10.2 seconds, the classification result is moderate difference, and the deviation index is 2.5. Through the preset range judgment mechanism, a synchronization instruction is generated in real time to adjust to a unified 10-second cycle. Among them, the manipulator undertakes the functions of automatic part picking, transferring and other operations during the injection molding process, and is also the core node of production beat and cycle division, used to identify the production cycle boundary and participate in the construction of the linkage parameter set, and through the synchronization instruction adjustment, the coordination of the entire injection molding production line is ensured, thereby supporting the efficient collaborative operation of the automotive interior injection molding equipment. In addition, by combining historical data and real-time fluctuation data, the deviation is further corrected through a prediction model, and the processing of small beat deviations is strengthened to ensure the coordinated operation of the devices, especially on the production line with high precision requirements. When the barrel temperature exceeds the threshold of 0.3 degrees Celsius, the real-time adjustment mechanism will automatically correct it to ensure the efficiency and stability of the production process.

[0038] The above technical solution solves the problems of beat difference and parameter fluctuation among devices in injection molding production by combining time series analysis, classification algorithm, prediction model and other technical means, improves the synchronization and precision of production, and ensures the efficiency of automotive interior injection molding production process and the stability of product quality.

[0039] Further, in step S3, if the deviation index exceeds the allowed range, a synchronization instruction sequence is generated and transmitted to the related devices to obtain a unified production cycle, including: determining whether the deviation index exceeds the preset allowed range, if it exceeds, generating a synchronization instruction sequence according to the deviation index, transmitting the synchronization instruction sequence to the injection molding machine and the manipulator, adjusting the device running beat to generate a unified production cycle, and quantifying the beat difference by an optimization algorithm to correct small deviations.

[0040] Specifically, in one specific embodiment, when the beat deviation generated after the linkage parameter set is processed via the classification method exceeds the preset allowed range, a synchronization instruction sequence is triggered to achieve uniform production beat between injection molding equipment; Specifically, first, it is judged whether the deviation index exceeds the beat threshold range such as 0.1 to 0.5 seconds; If the judgment result is out of limit, the specific value of the deviation index (such as 0.3 seconds delay of the injection molding machine) is extracted, and the synchronization instruction sequence containing the injection molding machine waiting time compensation and the mechanical hand pre-action instruction is generated according to the difference ratio between the value and the mechanical hand beat. The sequence is transmitted to the injection molding machine and mechanical hand control system via the interaction network to realize the beat adjustment between the equipment.

[0041] After receiving the synchronization instruction sequence, the injection molding machine control unit adjusts the running rhythm by modifying the injection cycle parameters, and at the same time the mechanical hand controller adjusts the starting time of its grabbing action according to the instruction sequence, so as to unify to the standardized 15-second production cycle. Thereafter, through setting the beat monitoring mechanism, the equipment running rhythm is tracked in real time to ensure that all participating equipment runs under the same clock reference, eliminating the problem of inconsistent beats caused by parameter fluctuations.

[0042] To further optimize the above synchronization adjustment process, the system introduces a particle swarm optimization algorithm to quantify and correct the beat difference. The algorithm initializes a particle swarm containing different beat adjustment schemes, sets the "position" and "speed" of each particle to represent the delay adjustment value and its change rate respectively, and iteratively updates the position of each particle to approach the minimum beat difference solution. The fitness function takes the sum of the squares of the beat difference as the evaluation index, and updates the local optimal and global optimal solutions in each iteration, finally controls the beat difference within 0.05 seconds, and realizes precise beat synchronization.

[0043] For example, in the high-precision injection molding production process of automotive interior parts, if it is detected that the injection molding machine cycle is delayed by 0.3 seconds, the system will generate a synchronization instruction sequence containing an injection molding machine delay of 0.2 seconds and a mechanical hand advance of 0.2 seconds, and through particle swarm optimization, the beat difference between the equipment will be compressed from 0.3 seconds to 0.02 seconds after 50 iterations, ensuring the coordination of equipment operation and the consistency of product size. At the same time, in order to deal with different deviation causes, the synchronization instruction can adapt different compensation mechanisms according to the deviation type, such as automatically introducing temperature adjustment instructions for beat delay caused by slight fluctuations in barrel temperature, and introducing corresponding injection parameter compensation logic for deviations caused by pressure fluctuations. The whole process is controlled by data-driven decision-making, realizing high-precision collaborative control of small deviations in the production process, effectively improving the stability and yield of the automotive interior injection molding production line.

[0044] Step S4: extracting data prediction parameters from the unified production cycle through the prediction model to determine the final process configuration; specifically including: Cycle matching data is extracted from the unified production cycle, the cycle matching data is processed by a neural network model to generate a predicted parameter fluctuation sequence, historical data and real-time adjustment cycle data are fused to adjust the barrel parameters, and a final process configuration is generated by integrating the predicted parameter fluctuation sequence and the adjusted parameters.

[0045] Specifically, on the basis of forming a unified production cycle by injection molding machines, mechanical hands and other equipment, first, cycle matching data is extracted from the unified production cycle, the cycle matching data is the starting point and the end point of each production cycle identified according to the synchronous control time sequence of the injection molding machine and the mechanical hand, and the time sequence data formed by combining the temperature data and the pressure data corresponding to these key nodes is further vectorized to provide a standardized input format for subsequent intelligent prediction; then, the above cycle matching data is input into a neural network model with time sequence learning ability, i.e. long short-term memory network (LSTM); the network structure dynamically adjusts the historical information retention degree and the current state update logic through the gating mechanism, which can effectively capture the potential influence of the slight fluctuation of the barrel temperature on the injection pressure; during the model processing, first, the input data is normalized to ensure the scale consistency of each parameter data and improve the network training stability and convergence speed; then, the historical temperature and pressure information to be retained is determined by the forgetting gate, the new time step information is introduced by the input gate, and the current prediction output is generated by the output gate, thereby generating a predicted parameter fluctuation sequence including the timestamp and the fluctuation amplitude, which can be used to estimate the possible deviation of the barrel temperature or the injection pressure in the future several production cycles in actual injection molding production.

[0046] After the prediction data is obtained, the barrel operating parameters recorded in the historical database, such as the humidity control value and the temperature set value, are further fused, and the real-time adjustment data obtained in the current cycle optimization process are combined, and a weighted average method is used for fusion calculation to form a barrel adjustment parameter with prediction and real-time response capability; wherein the weight distribution of the historical data and the real-time data is pre-set according to the device response delay characteristics and the production stability requirements, for example, it can be set to a ratio of 0.6 and 0.4 to ensure that the barrel can still realize stable feeding under different material moisture fluctuations.

[0047] Finally, the predicted parameter fluctuation sequence is further integrated with the adjusted barrel parameters to generate a final process configuration applicable to the current injection molding production cycle; this configuration not only includes control parameter values for all key equipment, including injection molding machine temperature upper limit, injection pressure threshold, barrel temperature and humidity set value, but also organizes time series information to form a stable equipment coordinated operation configuration table, and ensures that the process configuration has sustainable execution and multi-device coordination stability in future multiple unified production cycles. Through the above data acquisition, processing, prediction and optimization configuration process, the dynamic prediction control and process configuration closed-loop optimization of injection molding equipment parameters are effectively realized, and the intelligent degree and product consistency quality level of the injection molding process of automotive interior parts are improved.

[0048] The application also provides an automotive interior injection molding equipment production data acquisition and monitoring system for realizing the above method, the system comprising: a model construction unit for obtaining equipment state data set by acquiring real-time running state data from the injection molding equipment through the communication node, and constructing a parameter coupling model by processing the equipment state data set using a time series analysis method; a parameter determination unit for inputting the real-time collected barrel temperature sequence and injection pressure sequence into the parameter coupling model, determining whether the temperature parameter fluctuation exceeds the preset threshold, and if it exceeds, fusing the injection pressure data to generate a temperature optimization configuration and a temperature optimization configuration of the barrel temperature fluctuation amplitude, and transmitting the temperature optimization configuration to the related equipment through the interactive network to determine the linkage parameter set; a calculation unit for processing the linkage parameter set using a classification method to obtain a deviation index, and if the deviation index exceeds the allowed range, generating a synchronization instruction sequence and transmitting it to the related equipment to obtain a unified production cycle; a device adjustment unit for extracting data from the unified production cycle through the prediction model to predict parameter fluctuation and adjust the equipment parameters to determine the final process configuration.

[0049] The application also provides a computer readable storage medium having instructions stored thereon, which are executed by a processor to realize the above method.

[0050] In summary, the application collects the real-time running state data of the barrel temperature, injection pressure and mold temperature through the communication node, extracts dynamic change characteristics by using the time series decomposition method, and further establishes a parameter coupling model. The model can reveal the coupling relationship between the barrel temperature micro-fluctuation and the injection pressure instability, and provide a data basis for subsequent judgment and control. According to the parameter coupling model, the real-time temperature fluctuation is monitored. If the amplitude exceeds the threshold value, the injection pressure data is automatically fused and the coupling coefficient is calculated to generate an adjustment factor, thereby forming an optimized mold temperature machine control instruction. This control instruction not only realizes the optimization of the barrel temperature configuration, but also is issued in real time through the interaction network, ensuring the parameter consistency of multiple devices under the same production condition. Through classification and deviation index calculation of the linkage parameter set, if the beats of the devices are found to be out of sync, the system automatically generates a synchronization instruction sequence to realize the unified production cycle of the injection molding machine, mold temperature machine and manipulator. This link ensures the time consistency between devices, effectively reduces the negative impact of beat deviation on product size and process stability. Finally, the prediction model is used to analyze the parameters under the unified production cycle, predict possible temperature and pressure fluctuations in advance, and adjust the device configuration based on historical data and real-time cycle results to generate the final process parameter table. This not only improves the predictability of future conditions, but also realizes the adaptive regulation and control of the whole process. Through the mutual cooperation of the above technical solutions, the precise monitoring and dynamic adjustment of the multi-source data of the automotive interior injection molding equipment are realized, and each step forms a closed loop that supports each other, effectively solving the problems of parameter fluctuation amplification, beat inconsistency and unstable product quality in the prior art, and realizing the intelligent, fine and efficient production process.

[0051] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the application. It should be understood that the above description is only a specific embodiment of the application and is not intended to limit the protection scope of the application. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the application should be included in the protection scope of the application.

Claims

1. A method for collecting and monitoring production data of an automotive interior injection molding device, characterized in that, The method comprises the following steps: Step S1: obtaining a device state data set by acquiring real-time running state data of an injection molding device through a communication node, and processing the device state data set by using a time series analysis method to construct a parameter coupling model; Step S2: inputting a real-time collected barrel temperature sequence and injection pressure sequence into the parameter coupling model, and judging whether the temperature parameter fluctuation exceeds a preset threshold value, if yes, fusing injection pressure data to generate a mold temperature controller instruction and a temperature optimization configuration, and obtaining a barrel temperature optimization configuration through a barrel fluctuation amplitude, and transmitting the temperature optimization configuration to related devices through an interactive network to determine a linkage parameter set; Step S3: processing the linkage parameter set by using a classification method to obtain a deviation index, if the deviation index exceeds an allowable range, generating a synchronization instruction sequence and transmitting it to related devices to obtain a unified production cycle; Step S4: extracting data from the unified production cycle by using a prediction model to predict parameter fluctuation and adjust device parameters to determine a final process configuration.

2. The method of claim 1, wherein, In step S1, a device state data set is obtained by acquiring real-time running state data of an injection molding device through a communication node, which comprises the following steps: Barrel temperature, mold temperature and injection pressure data are collected through communication nodes arranged on an injection molding machine, a mold temperature controller and a dryer to generate a device state data set containing the barrel temperature, mold temperature and injection pressure, feature extraction is performed on the small fluctuation data of the barrel temperature, the influence feature of the barrel temperature micro-fluctuation on the injection pressure is determined, and a device state data set for subsequent analysis is generated.

3. The method of claim 2, wherein, In step S1, the device state data set is processed by using a time series analysis method to determine a parameter coupling model, which comprises the following steps: The device state data set is decomposed by time series to obtain dynamic change characteristics, the time series correlation between the barrel temperature micro-fluctuation and the injection pressure is analyzed, a coupling effect model containing the barrel temperature micro-fluctuation and the injection pressure instability is constructed, the corresponding relationship between the barrel temperature fluctuation and the injection pressure is obtained based on the coupling effect model, and the barrel temperature micro-fluctuation data and the injection pressure data are used as training data, and the parameter coupling model is trained.

4. The method of claim 1, wherein, In step S2, whether the temperature parameter fluctuation exceeds the preset threshold value is judged according to the parameter coupling model, if yes, the pressure data is fused to adjust the control instruction to generate an optimization configuration, which comprises the following steps: The real-time acquired barrel temperature sequence and injection pressure sequence are input into the parameter coupling model, and whether the barrel temperature micro-fluctuation amplitude exceeds the preset threshold value is judged, if yes, the injection pressure data is fused to generate a mold temperature controller factor, the mold temperature controller instruction is obtained according to the factor, the barrel temperature configuration is optimized through the mold temperature controller, a barrel temperature optimization configuration containing an optimized temperature value is generated, and the step is repeated to obtain the mold temperature controller instruction and the temperature optimization configuration in real time, which are transmitted to the mold temperature controller to realize real-time adjustment cycle.

5. The method of claim 4, wherein, In step S2, the optimization configuration is transmitted to related devices through an interactive network to determine a linkage parameter set, which comprises the following steps: Extract the adjusted mold temperature value from the temperature optimization configuration, transmit it to the injection molding machine and mold temperature machine through the interactive network, generate a linkage parameter set containing the mold temperature and beat time sequence, quantify the beat difference between devices in the linkage parameter set using parameter vector representation method, and determine the linkage parameter set for subsequent classification.

6. The method of claim 1, wherein, In step S3, the linkage parameter set is processed using a classification method to obtain a deviation index, including: The linkage parameter set is classified and processed using a support vector classification method to generate a classification result representing the degree of beat difference, the beat deviation index is calculated according to the classification result, the range of the beat deviation index is defined by a pre-set classification boundary, the deviation index is determined for evaluating the synchronization of the linkage equipment, and a real-time judgment mechanism is generated.

7. The method of claim 6, wherein, In step S3, if the deviation index exceeds the allowed range, a synchronization instruction sequence is generated and transmitted to the related equipment to obtain a uniform production cycle, including: Determine whether the deviation index exceeds the pre-set allowed range, if it does, generate a synchronization instruction sequence according to the deviation index, transmit the synchronization instruction sequence to the injection molding machine and robot, adjust the device running beat to generate a uniform production cycle, and quantify the beat difference to correct minor deviations through an optimization algorithm.

8. The method of claim 1, wherein, Step S4, including: Extract cycle matching data from the uniform production cycle, process the cycle matching data using a neural network model to generate a predicted parameter fluctuation sequence, fuse historical data and real-time adjustment cycle data to adjust the dryer parameters, and generate a final process configuration by integrating the predicted parameter fluctuation sequence and the adjusted parameters.

9. A production data acquisition and monitoring system for an automotive interior injection molding apparatus, for implementing the method according to any one of claims 1 to 8, characterized in that The system comprises: A model construction unit for obtaining device state data set from real-time running state data of injection molding equipment through a communication node, processing the device state data set using a time series analysis method to construct a parameter coupling model; A parameter determination unit for inputting the real-time collected barrel temperature sequence and injection pressure sequence into the parameter coupling model, determining whether the temperature parameter fluctuation exceeds the pre-set threshold, if it does, fusing the injection pressure data to generate mold temperature machine control instructions and temperature optimization configuration, obtaining the barrel temperature optimization configuration through barrel fluctuation amplitude, and transmitting the temperature optimization configuration to related equipment through an interactive network to determine a linkage parameter set; A calculation unit for processing the linkage parameter set using a classification method to obtain a deviation index, and generating a synchronization instruction sequence if the deviation index exceeds the allowed range to transmit to related equipment to obtain a uniform production cycle; A device adjustment unit for extracting data from the uniform production cycle through a prediction model to predict parameter fluctuations and adjust device parameters to determine a final process configuration.

10. A computer-readable storage medium having stored thereon instructions, the computer-readable storage medium comprising: The instructions are executed by the processor to implement the method of any one of claims 1-8.

Images