Intelligent Evaluation Method for VOC Recovery Effect in Diaphragm Printing and Electronic Device Diaphragm

Abstract

The present invention relates to the technical fields of artificial intelligence, intelligent processing of printing data, electronic device diaphragms, etc., and provides an intelligent evaluation method for the VOC recovery effect in diaphragm printing and an electronic device diaphragm. By collecting the inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates in the operation records of the VOC recovery device of the diaphragm printing, and based on these collected printing data, the VOC recovery rate of the VOC recovery device is predicted using a trained neural network model. According to the prediction result obtained by predicting the VOC recovery rate of the VOC recovery device using the neural network model, an intelligent evaluation and optimization suggestions for the recovery effect of the VOC recovery device are provided, so as to effectively evaluate the VOC recovery effect during the printing process of the electronic device diaphragm, perform refined management on VOC recovery, and ensure printing safety.

Description

Technical Field

[0001] The present invention relates to the technical fields of artificial intelligence, intelligent processing of printing data, electronic device diaphragms, etc., and particularly relates to an intelligent evaluation method for the VOC recovery effect in diaphragm printing and an electronic device diaphragm. Background Art

[0002] In printing practice, solvent-based printing inks are often used to print electronic device diaphragms. Due to the characteristics of solvent-based printing inks, during the printing process of electronic device diaphragms, the printing machine will generate VOC emissions. High concentrations of VOCs pose significant hazards to the health of operators, such as causing headaches, respiratory irritation, and even chronic poisoning. Long-term exposure to a high-VOC environment may lead to serious occupational diseases. To solve this technical problem in printing, a solvent recovery device is usually installed on the printing machine using solvent-based printing inks to recover VOCs. However, during the long-term printing use process, the recovery effect of the solvent recovery device on VOCs has not been evaluated, the management of VOC recovery is not fine enough, and printing safety needs to be further improved.

[0003] In summary, in the prior art, there are technical problems such as the recovery effect of VOCs not being evaluated during the printing process of electronic device diaphragms, the management of VOC recovery not being fine enough, and printing safety needing to be improved. Summary of the Invention

[0004] Aiming at the deficiencies of the above-mentioned prior art, the present invention provides an intelligent evaluation method for the VOC recovery effect in diaphragm printing and an electronic device diaphragm to effectively evaluate the recovery effect of VOCs during the printing process of electronic device diaphragms, conduct refined management of VOC recovery, and ensure printing safety.

[0005] In the first aspect, the present invention provides an intelligent evaluation method for the VOC recovery effect in diaphragm printing, including:

[0006] Collecting the inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates in the operation records of the VOC recovery device during diaphragm printing;

[0007] According to the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rates, using the trained neural network model to predict the VOC recovery rate of the VOC recovery device;

[0008] Based on the prediction result obtained by predicting the VOC recovery rate of the VOC recovery device according to the neural network model, provide an intelligent evaluation of the recovery effect of the VOC recovery device and optimization suggestions.

[0009] In a second aspect, the present invention provides an electronic device diaphragm. When printing the electronic device diaphragm, the intelligent evaluation method for the VOC recovery effect in the above diaphragm printing is used to evaluate the VOC recovery effect of the VOC recovery device.

[0010] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0011] The present invention provides an intelligent evaluation method for the VOC recovery effect in diaphragm printing and an electronic device diaphragm. By collecting the inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates in the operation record of the VOC recovery device, according to the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rates, use the trained neural network model to predict the VOC recovery rate of the VOC recovery device. Based on the prediction result obtained by predicting the VOC recovery rate of the VOC recovery device according to the neural network model, provide an intelligent evaluation of the recovery effect of the VOC recovery device and optimization suggestions, so as to effectively evaluate the recovery effect of VOC during the printing process of the electronic device diaphragm, perform refined management of VOC recovery, and ensure printing safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention.

[0013] Figure 1 is a schematic flow chart of an intelligent evaluation method for the VOC recovery effect in diaphragm printing according to an embodiment of the present invention;

[0014] Figure 2 is a schematic flow chart when training the neural network model in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0016] Embodiment 1

[0017] This embodiment provides an intelligent evaluation method for the VOC recovery effect in diaphragm printing. By collecting the inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates in the operation record of the VOC recovery device, and based on the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rates, the VOC recovery rate of the VOC recovery device is predicted using a trained neural network model. According to the prediction result obtained by predicting the VOC recovery rate of the VOC recovery device using the neural network model, an intelligent evaluation and optimization suggestions for the recovery effect of the VOC recovery device are provided, so as to effectively evaluate the VOC recovery effect during the printing process of electronic device diaphragms, conduct refined management of VOC recovery, and ensure printing safety.

[0018] See Figure 1 - Figure 2 , the intelligent evaluation method for the VOC recovery effect in diaphragm printing provided in this embodiment may include the following steps:

[0019] S101. Collect the inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates in the operation record of the VOC recovery device;

[0020] S102. Based on the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rates, use a trained neural network model to predict the VOC recovery rate of the VOC recovery device;

[0021] S103. According to the prediction result obtained by predicting the VOC recovery rate of the VOC recovery device using the neural network model, provide an intelligent evaluation and optimization suggestions for the recovery effect of the VOC recovery device.

[0022] It should be noted that in step S101, printing data related to VOC recovery evaluation in diaphragm printing is collected. These data include the inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates in the operation records of the VOC recovery device. Among them, the inlet VOC concentration detection data and outlet VOC concentration detection data directly reflect the change of VOC concentration and can be used to calculate the treatment effect of the recovery device. The operating parameters of the VOC recovery device (such as air volume, temperature, adsorption material state, etc.) reflect the working state of the recovery device and determine the recovery efficiency. The environmental parameters during the operation of the VOC recovery device (such as humidity, air pressure, etc.) are the external conditions affecting the process of the VOC recovery device adsorbing VOC. The historical recovery rate can provide a benchmark for model training and trend analysis. In step S101, by collecting the inlet and outlet VOC concentrations, operating parameters, and environmental parameters, the key factors affecting the VOC recovery effect are comprehensively covered, ensuring the comprehensiveness and accuracy of model prediction. The operation records of the VOC recovery device reflect the long-term operation trend of the equipment and can provide a reliable data source for the training of the neural network model. The multi-dimensionality of the data can provide a data basis for subsequent intelligent evaluation and optimization. In step S102, a neural network model is used to predict the VOC recovery rate. The neural network model can learn the complex non-linear relationships between input features and the prediction results are more accurate compared with traditional methods (such as simple linear regression). Through high-precision model prediction, the current VOC recovery efficiency can be quickly obtained, providing a core basis for subsequent intelligent evaluation. In step S103, by comparing the predicted VOC recovery rate with the target recovery rate, the current working effect of the VOC recovery device can be evaluated, specific problems (such as abnormal operating parameters or equipment aging) can be located, and targeted optimization suggestions (such as adjusting the air volume, controlling the temperature and humidity, replacing the adsorption material) can be put forward to achieve refined management of VOC recovery. Moreover, by timely identifying the situation of poor recovery effect, the risk of excessive VOC emissions can be reduced, ensuring printing safety.

[0023] In some preferred embodiments, according to the prediction result obtained by predicting the VOC recovery rate of the VOC recovery device using the neural network model, an intelligent evaluation and optimization suggestions for the recovery effect of the VOC recovery device are provided, including: comparing the VOC recovery rate predicted by the neural network model with the target recovery rate to determine whether the current working state of the VOC recovery device meets the expectation, so as to provide an intelligent evaluation and optimization suggestions for the recovery effect of the VOC recovery device. It should be noted that in this embodiment, through the benchmark value of the target recovery rate, it can be quickly determined whether the actual operation effect of the VOC recovery device reaches the expected level. If the actually predicted VOC recovery rate is lower than the target value, it indicates that the recovery effect is not good and corresponding optimization measures are urgently needed; if it is higher than or close to the target value, it means that the device is working normally and the recovery effect is ideal.

[0024] In some further embodiments, when the actually predicted VOC recovery rate is lower than the target recovery rate, using the feature weights of the neural network model, analyze the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rate to obtain the key parameters that have a greater impact on the VOC recovery rate, and get the negative key parameters that lead to poor recovery effect; provide optimization suggestions according to the negative key parameters. It should be noted that when the actual recovery rate is lower than the target recovery rate, the reasons need to be checked in time. By extracting the feature weights of the neural network model, the influence degree of each feature (such as inlet VOC concentration, environmental temperature and humidity, air volume, etc.) on the recovery efficiency can be intuitively quantified, so as to quickly locate the negative key parameters that lead to the decline of the recovery efficiency. After finding the negative key parameters, more targeted improvement measures can be given. For example, if the humidity is too high, it is recommended to reduce the humidity; if the state of the adsorption material is aging, it is recommended to replace the material; if the air volume is insufficient, it is recommended to increase the air volume.

[0025] In some further embodiments, when analyzing the key parameters that have a greater impact on the VOC recovery rate by using the feature weights of the neural network model, it includes: based on the trained neural network model, extracting the weights corresponding to each input feature, and the weights corresponding to each input feature include the feature weights corresponding to the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rate respectively; sorting the extracted feature weights from largest to smallest, and identifying the features within the set threshold range as high-impact features; analyzing the high-impact features according to the current operating state of the VOC recovery device to obtain the negative key parameters that result in poor recovery effect. It should be noted that although the neural network model can accurately predict the VOC recovery rate, it is difficult to directly explain why the recovery rate is low or which factors lead to the decline in the recovery efficiency. In this embodiment, through the process of extracting feature weights + sorting, the importance of each feature (such as the inlet VOC concentration, temperature and humidity, air volume, historical recovery rate trend, etc.) in the model prediction process can be clearly quantified, so that managers can quickly judge which features have a key impact on the current recovery efficiency. When the actual recovery rate is lower than the expected value, if the specific reason is not clear, it may be necessary to comprehensively check all input features (including equipment parameters and environmental parameters, etc.), resulting in high costs and time consumption. In this embodiment, by sorting the feature weights and screening out the high-impact features, it is possible to quickly focus on a few parameters that are most likely to cause poor recovery (such as aging adsorption materials, high-humidity environment, abnormal air volume, etc.), greatly improving the diagnosis and rectification efficiency. It should be noted that even if some features have high weights globally, if the actual operating parameters of the current VOC recovery device are within the normal range, they will not trigger a significant decrease in the recovery rate; on the contrary, if the current parameters of some features with high weights exceed the normal range, they are more likely to become negative key parameters. In this embodiment, by combining the actual operating state of the current VOC recovery device (for example: the temperature rises abnormally, the air volume is significantly lower than the standard value), it is possible to accurately screen out the real negative key parameters that result in the current low recovery efficiency, thereby avoiding unnecessary adjustments to the high-weight features that are not malfunctioning.

[0026] In some further embodiments, when providing optimization suggestions according to the negative key parameters, it includes: based on the historical operation data of the VOC recovery device, setting corresponding safety thresholds for allowing fluctuations for each negative key parameter (such as air volume, temperature, humidity, or adsorption material usage duration, etc.) in the negative key parameters; obtaining the actual operation parameters of the current VOC recovery device, comparing them one by one with the set safety thresholds of each negative key parameter, and calculating the deviation degrees of each negative key parameter from the actual operation parameters of the current VOC recovery device; according to the deviation degrees of each negative key parameter from the actual operation parameters of the current VOC recovery device, proposing corresponding optimization measures (for example: increasing or decreasing the air volume, temperature; replacing the adsorption material; controlling the environmental humidity or air pressure; adjusting the intake and exhaust ratio, etc.). It should be noted that in this embodiment, by mining the historical operation data of the VOC recovery device, the numerical range or critical values at which each parameter is in normal and efficient operation can be determined. Compared with setting fixed values based on experience, the safety thresholds formed by using historical data are more scientific and applicable, and can truly reflect the actual situation of the device under different environments and loads. In addition, comparing the current actual operation parameters with the safety thresholds one by one can quickly identify which parameters have large deviation degrees. Compared with the traditional comprehensive inspection, this method is more targeted, can significantly improve the diagnosis efficiency, and avoid wasting time and resources on irrelevant or normal parameters. When the specific deviations of each negative key parameter (such as air volume, temperature, humidity, adsorption material usage duration, etc.) from the safety threshold are clear, differential optimization measures can be proposed, for example: increasing the air volume when the air volume is too low, moderately decreasing the air volume when the air volume is too high; enabling dehumidification or cooling means when the temperature and humidity exceed the standard; replacing the adsorption material in time when the adsorption material is aged; adjusting the ratio scheme when the intake and exhaust ratio is abnormal, etc.

[0027] In some preferred embodiments, when predicting the VOC recovery rate of the VOC recovery device using the trained neural network model, it includes: performing standardization processing on the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rate to obtain standardized multi-dimensional feature data with a unified scale, reduced relative weights of outliers, and consistent numerical ranges; integrating the standardized multi-dimensional feature data into a multi-dimensional input feature vector for input into the model; and inputting the multi-dimensional input feature vector into the trained neural network model to predict the VOC recovery rate of the VOC recovery device. It should be noted that the numerical ranges of the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters, the environmental parameters, and the historical VOC recovery rate may vary greatly. Without standardization processing, features with larger numerical ranges will dominate during model training, resulting in unstable training or slow convergence speed. In this embodiment, through standardization (such as converting to a form with a mean of 0 and a standard deviation of 1), all features can be within a relatively unified scale range, ensuring that the model pays more balanced attention to each feature. In addition, there may be sudden peaks or outliers in the above model input data. If these outliers are directly input into the model without any processing, it is easy to cause problems such as gradient explosion and prediction deviation during training. Standardization can, to a certain extent, reduce the impact of outliers on the overall distribution and make the model more robust during the learning process.

[0028] In some preferred embodiments, when integrating the standardized multi-dimensional feature data into a multi-dimensional input feature vector for input into a model, it includes: classifying the standardized multi-dimensional feature data to obtain continuous feature data, categorical feature data, and time series feature data; sorting the continuous feature data to obtain continuous feature data arranged in a fixed order; sorting the categorical feature data to obtain numerically encoded categorical feature data; sorting the time series feature data to obtain complete time series feature data; combining all the sorted continuous feature data, categorical feature data, and time series feature data in a fixed order to form a feature set with a unified scale and no redundancy between features; converting the combined multi-dimensional feature data into a vector form to form the multi-dimensional input feature vector input into the neural network model, where each feature corresponds to a component of the feature vector. It should be noted that in this embodiment, by first classifying and sorting the standardized multi-dimensional feature data (continuous, categorical, time series), and then combining them in a fixed order and converting them into the input feature vector of the neural network model, the attributes and processing requirements of different features can be maximally matched, ensuring that the data structure input into the final model is orderly, redundant-free, and easy to expand, thereby improving the model training efficiency and prediction stability, and providing a solid data foundation for the subsequent accurate evaluation of the VOC recovery effect. Among them, continuous features (such as VOC concentration, temperature and humidity, air volume, pressure, etc.), categorical features (such as the state of the adsorption material), and time series features (such as historical recovery rates) have different data forms and processing requirements. By first classifying and sorting the standardized features, processing methods that best match their feature attributes can be used respectively (such as arranging continuous features in order, numerically encoding categorical features, and retaining the time order or extracting statistical values for time series features), avoiding data conflicts or redundancy caused by mixed processing in the same process. In this embodiment, the integration of the three types of features (continuous, categorical, time series features) in a segmented manner means that if new features (such as new sensor data, more types of categorical information, or additional time series) are to be added in the future, they only need to be added in the corresponding feature category and keep the overall data structure and model input specifications consistent, thereby reducing repetitive labor and the risk of errors. In this embodiment, by classifying first and then sorting, features of different natures (numerical, categorical, time series) can each maintain their correct positions and data forms, avoiding being wrongly regarded as the same type of data in the model (for example, time series features being treated as ordinary continuous features).

[0029] In some preferred embodiments, after forming the multi-dimensional input feature vector of the input neural network model, it is checked whether the formed multi-dimensional input feature vector contains all the standardized feature data, and the feature order is ensured to be consistent with the input requirements of the neural network model to ensure the integrity of the multi-dimensional input feature vector. It should be noted that during the process of separately sorting and combining continuous features, categorical features, and time series features, if there are omissions or repetitions, it may result in some features not being included in the final vector, or erroneously including additional irrelevant data. In this embodiment, through the explicit checking step, it is ensured that all the standardized features (such as inlet VOC concentration, outlet VOC concentration, environmental parameters, operating parameters, historical VOC recovery rate, etc.) are correctly included in the feature vector without omission or repetition. Additionally, the input layer of the neural network model usually requires features to correspond one by one in a specific order. Any swapping of the order will cause confusion during model training and inference, resulting in inaccurate prediction results or the model being unable to work properly. In this embodiment, by ensuring that the feature order is consistent with the input requirements of the neural network model, misalignment in the feature integration link can be avoided, and the model's correct understanding of the feature meaning can be guaranteed.

[0030] In some preferred embodiments, the continuous feature data includes the inlet VOC concentration detection data, the outlet VOC concentration detection data, the air volume, temperature, and adsorption material usage duration in the operating parameters, and the humidity and air pressure in the environmental parameters; the categorical feature data includes the adsorption material status in the operating parameters; the time series feature data includes the historical VOC recovery rate. It should be noted that different types of feature data usually require different preprocessing or encoding methods before being input into the model. Among them, continuous feature data (such as VOC concentration, temperature, air volume, etc.) usually can be directly normalized or standardized and then used as model input; categorical feature data (such as adsorption material status) needs to be One-Hot encoded or numerically mapped; time series feature data (such as historical VOC recovery rate) needs to retain the time order or extract statistical features. In this embodiment, by classifying these features, it helps with subsequent targeted processing, reduces confusion, and ensures the accuracy and consistency of data integration. Additionally, during the VOC recovery process of diaphragm printing, the inlet / outlet VOC concentration, temperature, humidity, air pressure, etc. all show continuous distributions, the adsorption material status is often a discrete category, and the historical recovery rate accumulates and changes over time. The essential attributes of the three are not the same. Clearly classifying these features can be more in line with the logic of the actual production conditions, facilitating understanding and use by managers and technicians. Additionally, by distinguishing different types of features and implementing differential processing, the model can more fully learn the feature distributions of various features and their impacts on the VOC recovery rate, thereby improving the prediction accuracy.

[0031] In some preferred embodiments, when training the neural network model, it includes: collecting data samples containing inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates; performing standardization processing on the collected data samples to obtain standardized multi-dimensional feature data with a unified scale, reduced relative weight of outliers, and consistent numerical range; using the standardized multi-dimensional feature data after standardization processing as the input features of the training set to train the neural network model, and using the corresponding actual VOC recovery rate as the label value to supervise the training of the neural network model. It should be noted that in this embodiment, by collecting real operation data, performing standardization processing, and using supervised training to construct and optimize the neural network model, the accuracy and reliability of subsequent prediction results are ensured, thereby providing solid technical support for the intelligent evaluation of the VOC recovery effect in the diaphragm printing process. Before predicting and evaluating the VOC recovery rate in the actual industrial scenario, a large amount of real and diverse operation data is required as the learning material for the model. In this embodiment, by collecting inlet / outlet VOC concentrations, operating parameters (air volume, temperature, adsorption material status / usage duration, etc.), environmental parameters (humidity, air pressure, etc.), and historical VOC recovery rates, sufficient multi-dimensional information can be provided for the model, enabling it to better learn and capture the key factors affecting the VOC recovery rate and their internal relationships. Using the corresponding actual VOC recovery rate as the label value allows the neural network model to continuously adjust its own parameters (weights, biases) during the training process to minimize the error between the predicted value and the true value. This supervised learning process can ensure that the model makes full use of the large number of data samples collected, gradually improves the prediction accuracy, and also has good generalization ability when facing new data.

[0032] In some preferred embodiments, the neural network model includes an input layer, a hidden layer, and an output layer; the number of nodes in the input layer is consistent with the dimension of the multi-dimensional input feature vector; the hidden layer is provided with a plurality of neurons for learning the complex relationships between the input features; the output layer is provided with one node for outputting the predicted VOC recovery rate. It should be noted that setting the number of nodes in the input layer to be consistent with the dimension of the multi-dimensional input feature vector ensures that each feature has a corresponding neuron at the network input end to receive data, thereby avoiding feature loss or duplicate input and ensuring that the model can completely obtain all the feature information that has been standardized (such as the inlet VOC concentration, the outlet VOC concentration, operating parameters, environmental parameters, and historical VOC recovery rates, etc.). During the diaphragm printing process, the factors affecting the VOC recovery rate are often not simple linear relationships (such as the interaction effects of temperature and humidity, air volume, and VOC concentration). Setting a plurality of hidden layer neurons can automatically extract high-order features or implicit patterns during the non-linear mapping process, learn these complex relationships, and effectively improve the prediction accuracy. The number of neurons in the hidden layer can be adjusted according to the data scale, model complexity requirements, etc. to seek a balance between the fitting ability and the risk of overfitting. In addition, setting the output layer to one node directly corresponds to a continuous numerical prediction (i.e., the VOC recovery rate), which conforms to the attribute that the target variable of the recovery rate is a real value. The output form matching the regression task can simplify the interpretation of the model results. During model training, only the error between this single output and the true recovery rate needs to be minimized to complete the learning process, which is convenient for connecting with subsequent processes in practical applications, such as comparing the predicted recovery rate with the target recovery rate, determining the operating state of the device, and generating optimization suggestions.

[0033] In some preferred embodiments, the standardized multi-dimensional feature data after standardization processing is used as the input features of the training set to train a neural network model, including: using the mean square error as the loss function to calculate the error between the predicted VOC recovery rate and the actual VOC recovery rate; using the gradient descent method to minimize the loss function and adjust the parameters of the neural network model; optimizing the model weights through multiple iterations until the loss function converges; using an independent validation data set to evaluate the prediction accuracy of the model to ensure that the model has good generalization ability on unseen data; testing the performance of the model to obtain the trained neural network model. It should be noted that the mean square error (MSE) is a commonly used loss function for regression tasks, which can quantify the error between the predicted value and the true value (i.e., the predicted VOC recovery rate and the actual VOC recovery rate). MSE is more sensitive to large deviations, which can urge the model to minimize large error situations, thereby improving the prediction accuracy of the VOC recovery rate. The gradient descent method is an efficient and general optimization algorithm, which is suitable for the large-scale parameter update requirements in neural network training. By calculating the gradient through backpropagation and then using the gradient information to iteratively update the model weights, it can quickly converge to a better solution in the high-dimensional feature space. In addition, neural networks usually have many weight and bias parameters and require multiple rounds of iteration to gradually approach the global or local optimum. Through repeated training and error feedback, it is ensured that the neural network learns sufficient information, so as to have stronger generalization ability and stability when predicting the VOC recovery rate. During the training process of the neural network model, good performance only on the training set does not guarantee the prediction ability of the model for new data. The validation data set (the part not participating in the training) can help to detect overfitting or underfitting in a timely manner and evaluate the performance of the model on unseen data. After training and validation are completed, it is also necessary to use the test set (or new data in the actual production environment) to conduct a final performance evaluation of the model to obtain objective evaluation indicators, and finally obtain the trained neural network model. Among them, the neural network model can select a multi-layer perceptron.

[0034] Embodiment 2

[0035] See Figure 1, this embodiment provides an electronic device diaphragm. When printing the electronic device diaphragm, the intelligent evaluation method for the VOC recovery effect in diaphragm printing described in any of the above embodiments is used to evaluate the VOC recovery effect of the VOC recovery device. By collecting the inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates in the operation record of the VOC recovery device, and based on the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rates, the trained neural network model is used to predict the VOC recovery rate of the VOC recovery device. According to the prediction result obtained by predicting the VOC recovery rate of the VOC recovery device using the neural network model, an intelligent evaluation and optimization suggestion for the recovery effect of the VOC recovery device are provided, so as to effectively evaluate the VOC recovery effect during the printing process of the electronic device diaphragm, conduct refined management of VOC recovery, and ensure printing safety.

[0036] It should be noted that the above embodiments are only preferred specific embodiments of the present invention, and the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. The protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An intelligent evaluation method for VOC recovery effect in film printing, characterized in that: include: Collect the inlet VOC concentration detection data of the VOC recovery device during film printing, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters when the VOC recovery device is running, and the historical VOC recovery rate in the VOC recovery device operation record; According to the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters when the VOC recovery device is running, and the historical VOC recovery rate, the VOC recovery rate of the VOC recovery device is predicted using the trained neural network model; Providing intelligent evaluation and optimization suggestions on the recovery effect of the VOC recovery device based on the prediction results obtained by predicting the VOC recovery rate of the VOC recovery device according to the neural network model; When the VOC recovery rate of the VOC recovery device is predicted by using the trained neural network model, the method includes: standardizing the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rate to obtain standardized multidimensional feature data with a unified scale, reduced relative weights of abnormal values, and consistent numerical ranges; integrating the standardized multidimensional feature data into a multidimensional input feature vector for inputting a model; and inputting the multidimensional input feature vector into the trained neural network model to predict the VOC recovery rate of the VOC recovery device; Providing intelligent evaluation and optimization suggestions for the recovery effect of the VOC recovery device according to the prediction results obtained by predicting the VOC recovery rate of the VOC recovery device by the neural network model, including: comparing the VOC recovery rate predicted by the neural network model with the target recovery rate, judging whether the current working state of the VOC recovery device meets expectations, so as to provide intelligent evaluation and optimization suggestions for the recovery effect of the VOC recovery device; When the actual predicted VOC recovery rate is lower than the target recovery rate, the feature weights of the neural network model are used to analyze the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the key parameters in the historical VOC recovery rate that have a greater impact on the VOC recovery rate, to obtain negative key parameters that lead to poor recovery effect; optimization suggestions are provided based on the negative key parameters; when the feature weights of the neural network model are used to analyze the key parameters that have a greater impact on the VOC recovery rate, the method includes: based on the trained neural network model, extracting the weights corresponding to each input feature, the weights corresponding to each input feature include the feature weights corresponding to the inlet VOC concentration detection data, the outlet VOC concentration detection data, the operating parameters of the VOC recovery device, the environmental parameters during the operation of the VOC recovery device, and the historical VOC recovery rate; sorting the extracted feature weights from large to small, and identifying the features within the set threshold range as high-impact features; analyzing the high-impact features according to the current operating status of the VOC recovery device to obtain the negative key parameters that lead to poor recovery effect.

2. The intelligent evaluation method for VOC recovery effect in film printing according to claim 1, characterized in that: When the standardized multidimensional feature data is integrated into a multidimensional input feature vector for inputting a model, it includes: classifying the standardized multidimensional feature data to obtain continuous feature data, classified feature data and time series feature data; sorting the continuous feature data to obtain continuous feature data arranged in a fixed order; sorting the classified feature data to obtain numerically encoded classified feature data; sorting the time series feature data to obtain complete time series feature data; combining all the sorted continuous feature data, classified feature data and time series feature data in a fixed order to form a feature set with a unified scale and no redundancy between features; converting the combined multidimensional feature data into a vector form to form the multidimensional input feature vector for inputting a neural network model, wherein each feature corresponds to a component of the feature vector.

3. The intelligent evaluation method for VOC recovery effect in film printing according to claim 2, characterized in that: After forming the multidimensional input feature vector for input into the neural network model, check whether the formed multidimensional input feature vector contains all the standardized feature data, and ensure that the feature order is consistent with the input requirements of the neural network model to ensure the integrity of the multidimensional input feature vector.

4. The intelligent evaluation method for VOC recovery effect in film printing according to claim 2, characterized in that: The continuous characteristic data includes the inlet VOC concentration detection data, the outlet VOC concentration detection data, the air volume, temperature and adsorption material usage time in the operating parameters, and the humidity and air pressure in the environmental parameters; the classified characteristic data includes the adsorption material state in the operating parameters; the time series characteristic data includes the historical VOC recovery rate.

5. The intelligent evaluation method for VOC recovery effect in film printing according to claim 1, characterized in that: When training the neural network model, it includes: collecting data samples including inlet VOC concentration detection data, outlet VOC concentration detection data, operating parameters of the VOC recovery device, environmental parameters during the operation of the VOC recovery device, and historical VOC recovery rates; standardizing the collected data samples to obtain standardized multidimensional feature data with a unified scale, reduced relative weights of abnormal values, and consistent numerical ranges; using the standardized multidimensional feature data after standardization as training set input features to train the neural network model, and using the corresponding actual VOC recovery rate as a label value to supervise the training of the neural network model.

6. The intelligent evaluation method for VOC recovery effect in film printing according to claim 5, characterized in that: The neural network model includes an input layer, a hidden layer and an output layer; the number of nodes in the input layer is consistent with the dimension of the multi-dimensional input feature vector; the hidden layer is provided with a number of neurons for learning the complex relationship between the input features; the output layer is provided with a node for outputting the predicted VOC recovery rate.

7. The intelligent evaluation method for VOC recovery effect in film printing according to claim 5, characterized in that: The standardized multidimensional feature data after standardization is used as the input feature of the training set to train the neural network model, including: using the mean square error as the loss function to calculate the error between the predicted VOC recovery rate and the actual VOC recovery rate; using the gradient descent method to minimize the loss function and adjust the parameters of the neural network model; optimizing the model weights through multiple iterations until the loss function converges; using an independent validation data set to evaluate the prediction accuracy of the model to ensure that the model has good generalization ability on unseen data; and testing the performance of the model to obtain the trained neural network model.

8. An electronic device film, characterized in that: When printing the electronic device film, the VOC recovery effect of the VOC recovery device is evaluated using the intelligent evaluation method for VOC recovery effect in film printing as described in any one of claims 1 to 7.

Images