Real-time monitoring and control method and system for VOCs emission of printing equipment

Through the VOCs emission monitoring and collaborative control technology combined with neural network model and wireless sensor network, the problems of low efficiency and difficulty in controlling traditional VOCs governance methods are solved, and the refined management and efficient removal of VOCs emissions in the printing workshop are achieved.

CN119044403APending Publication Date: 2024-11-29ZHEJIANG MEIGE MACHINERY CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411079396.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The traditional VOCs governance method has low governance efficiency, high energy consumption, large operating costs, and is difficult to achieve precise control and optimized management of VOCs emissions, especially in the printing workshop where VOCs emissions have large concentration changes and uneven temporal and spatial distribution. Down.

Method used

Using a multi-factor VOCs emission mathematical model based on neural networks for real-time monitoring and control, combining real-time operating parameters and VOCs concentration data, the model is dynamically updated to achieve accurate prediction of VOCs emissions and emission rates, and through wireless sensor networks and Krigin Spatial interpolation recognizes local high-concentration areas and coordinates the control of various VOCs processing devices such as adsorption, photocatalysis and biological scrubber for customized processing in different regions and levels.

Benefits of technology

It has improved the pertinence and effectiveness of VOCs governance, achieved refined management of VOCs emissions, significantly improved the efficiency of VOCs removal, and reduced the harm to the environment and human health.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119044403A_ABST
    Figure CN119044403A_ABST
Patent Text Reader

Abstract

The invention provides a printing equipment VOCs emission real-time monitoring and control method and system, and relates to the technical field of printing machines, and the method comprises the steps: obtaining real-time operation parameters of printing equipment; on the basis of the real-time operation parameters, in combination with a preset multi-factor VOCs emission mathematical model, the VOCs real-time emission amount and emission rate of the current printing equipment are calculated; vOCs concentrations of multiple areas in the printing workshop are detected in real time, spatial characteristics of concentration distribution are identified, and a local high-concentration area where VOCs are discharged is judged; the VOCs concentration detected in each area is compared with a preset multi-stage VOCs concentration threshold value; if the VOCs concentration of any area exceeds the VOCs concentration threshold value of the corresponding level, a preset treatment efficiency curve of multiple VOCs treatment processes is matched, multiple VOCs treatment devices are cooperatively controlled, the VOCs treatment devices comprise at least one of an adsorption device, a photocatalysis device, a low-temperature plasma device and a biological washing tower, and regional and graded customized VOCs treatment is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to printing press technology, and in particular to a real-time monitoring and control method and system for VOCs emissions from printing equipment. Background Art

[0002] VOCs (volatile organic compounds) are one of the main air pollutants emitted by the printing industry, causing serious harm to the environment and human health. Traditional VOCs treatment methods mainly use end-of-pipe treatment methods, such as activated carbon adsorption and catalytic combustion, which have problems such as low treatment efficiency, high energy consumption, and high operating costs. At the same time, due to the characteristics of VOCs emissions in printing workshops, such as large concentration changes and uneven temporal and spatial distribution, traditional treatment methods are difficult to achieve precise control and optimized management of VOCs emissions.

[0003] In order to improve the pertinence and effectiveness of VOCs treatment and realize the refined management of VOCs emissions, it is urgent to develop a real-time monitoring and control system for VOCs emissions from printing equipment. At present, in terms of VOCs emission monitoring, some studies have used portable VOCs detectors to conduct fixed-point and timed monitoring of VOCs concentrations in printing workshops, but it is difficult to achieve comprehensive and continuous monitoring of VOCs emissions. In terms of control, most of the existing VOCs treatment equipment adopts a single control strategy, such as timed switches, constant air volume, etc., and lacks the ability to adaptively control VOCs emission characteristics. Summary of the invention

[0004] The embodiments of the present invention provide a real-time monitoring and control method and system for VOCs emissions from printing equipment, which can solve the problems in the prior art.

[0005] According to a first aspect of the embodiments of the present invention,

[0006] Provide real-time monitoring and control methods for VOCs emissions from printing equipment, including:

[0007] Acquire real-time operating parameters of the printing equipment, including at least one of printing speed, type and amount of printing materials, type of substrate, type and amount of ink, temperature, humidity, and workshop air flow rate; based on the real-time operating parameters, combined with a preset multi-factor VOCs emission mathematical model, calculate the real-time VOCs emission amount and emission rate of the current printing equipment;

[0008] Real-time detection of VOCs concentrations in multiple areas of the printing workshop, identification of the spatial characteristics of concentration distribution, and determination of local high-concentration areas of VOCs emissions; comparison of the VOCs concentrations detected in each area with the preset multi-level VOCs concentration thresholds;

[0009] If the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, the preset treatment efficiency curves of multiple VOCs treatment processes are matched, and multiple VOCs treatment devices are coordinated and controlled. The VOCs treatment devices include at least one of an adsorption device, a photocatalytic device, a low-temperature plasma device and a biological washing tower, to achieve customized VOCs treatment by region and level.

[0010] In an optional embodiment,

[0011] Based on the real-time operating parameters and in combination with a preset multi-factor VOCs emission mathematical model, before calculating the real-time VOCs emission amount and emission rate of the current printing device, the method further includes constructing a multi-factor VOCs emission mathematical model:

[0012] The multi-factor VOCs emission mathematical model is constructed based on a neural network;

[0013] The real-time operating parameters are used as inputs of the multi-factor VOCs emission mathematical model; wherein the multi-factor VOCs emission mathematical model includes a three-layer feedforward neural network model, wherein the number of input layer nodes is the same as the number of real-time operating parameters, the number of hidden layer nodes is determined by grid search, and the number of output layer nodes is the number of VOCs emissions and emission rates;

[0014] The ReLU activation function is used to perform nonlinear transformation on the input of the hidden layer and the output layer, and the weighted mean square error is used as the loss function. The Adam optimization algorithm is used to train the neural network model to obtain the initial multi-factor VOCs emission mathematical model.

[0015] Obtain the latest real-time operating parameters and VOCs emission monitoring data online, add them to the training data set, trigger the retraining of the multi-factor VOCs emission mathematical model, and realize the dynamic update of model parameters;

[0016] In the process of retraining the multi-factor VOCs emission mathematical model, the forgetting factor is introduced to decay the weight of the historical samples. For each historical data sample, the forgetting factor is calculated according to the timestamp of its generation. The forgetting factor decays exponentially with the increase of the time difference, and the time constant controls the forgetting rate.

[0017] The calculated forgetting factor is introduced into the weighted mean square error loss function, and the VOCs emission amount and emission rate of printing equipment are predicted in real time using the retrained multi-factor VOCs emission mathematical model.

[0018] In an optional embodiment,

[0019] The calculated forgetting factor is introduced into the weighted mean square error loss function as shown in the following formula:

[0020]

[0021]

[0022] Among them, λ i is the forgetting factor of the i-th historical sample, t is the current timestamp, t i is the timestamp of the i-th sample, τ is the time constant, which controls the forgetting rate; m is the number of training samples, y i is the actual VOCs emission or emission rate of the i-th sample, is the model's predicted value.

[0023] In an optional embodiment,

[0024] Real-time detection of VOCs concentrations in multiple areas of the printing workshop, identification of the spatial characteristics of concentration distribution, and determination of local high-concentration areas of VOCs emissions include:

[0025] Multiple wireless VOCs sensor nodes are deployed in different areas of the printing workshop. Each sensor node integrates a VOCs concentration sensor, a temperature and humidity sensor, a wireless communication module and a microprocessor. The collected VOCs concentration and environmental parameters are transmitted to the data aggregation node in real time through the wireless network.

[0026] The data aggregation node receives the data uploaded by each sensor node, pre-processes and stores it, and transmits the received data to the host computer in real time via wired Ethernet;

[0027] The host computer performs Kriging spatial interpolation on the received VOCs concentration and environmental parameters, constructs a semivariogram to describe the spatial correlation between data points, performs weighted sum estimation on the VOCs concentration at unknown locations, and generates a continuous VOCs concentration distribution map;

[0028] According to the preset VOCs concentration warning threshold and alarm threshold, the concentration distribution map is scanned point by point, the grid points exceeding the threshold are marked, and the adjacent high-concentration grid points are merged into local high-concentration areas using the region growing algorithm.

[0029] In an optional embodiment,

[0030] The host computer performs Kriging spatial interpolation on the received VOCs concentration and environmental parameters, constructs a semivariogram to describe the spatial correlation between data points, performs weighted summation estimation on the VOCs concentration at unknown locations, and generates a continuous VOCs concentration distribution map including:

[0031] The semivariogram function is shown in the following formula:

[0032]

[0033] Where h is the distance between data points, C0 is the nugget value, C is the sill value, and a is the range;

[0034] The Kriging spatial interpolation formula is as follows:

[0035]

[0036] Where n is the number of known data points involved in the estimation, Q j is the weight coefficient of the jth data point, μ is the Lagrange multiplier, and h kj is the distance between the kth data point and the jth data point, h k0 is the distance between the kth data point and the position to be estimated.

[0037] In an optional embodiment,

[0038] If the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, the processing efficiency curves of the preset multiple VOCs treatment processes are matched, and multiple VOCs treatment devices are collaboratively controlled, including:

[0039] Establish a dynamic model to describe the dynamic operating characteristics of each VOCs treatment device;

[0040] Each VOCs treatment device is regarded as a subsystem in a distributed control system, and a collaborative control framework for multiple VOCs treatment devices is constructed. Each subsystem independently optimizes and controls operating parameters based on its own dynamic model and optimization objectives while satisfying global constraints.

[0041] For each subsystem, a predictive controller based on a dynamic model is designed to predict the optimal control sequence in the future according to the current state and future reference trajectory, and the first element of the optimal control sequence is output as the control quantity at the current moment;

[0042] Based on the iterative negotiation algorithm with weight distribution, each subsystem sends the optimization results to other subsystems, and adjusts its own weight coefficient according to the feedback information received, and repeats the iteration until a consensus solution or a preset number of times is reached.

[0043] In the second aspect of the embodiments of the present application,

[0044] Provide real-time monitoring and control system for VOCs emissions from printing equipment, including:

[0045] The first unit is used to obtain the real-time operating parameters of the printing equipment, including at least one of the printing speed, the type and amount of printing materials, the type of substrate, the type and amount of ink, the temperature, the humidity, and the air flow rate of the workshop; based on the real-time operating parameters, combined with the preset multi-factor VOCs emission mathematical model, calculate the real-time VOCs emission amount and emission rate of the current printing equipment;

[0046] The second unit is used to detect the VOCs concentration in multiple areas of the printing workshop in real time, identify the spatial characteristics of the concentration distribution, and determine the local high-concentration areas of VOCs emissions; compare the VOCs concentration detected in each area with the preset multi-level VOCs concentration threshold;

[0047] The third unit is used to match the preset treatment efficiency curves of multiple VOCs treatment processes if the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, and coordinately control multiple VOCs treatment devices, wherein the VOCs treatment devices include at least one of an adsorption device, a photocatalytic device, a low-temperature plasma device and a biological washing tower, to achieve customized VOCs treatment by region and level.

[0048] According to a third aspect of the embodiments of the present invention,

[0049] An electronic device is provided, comprising:

[0050] processor;

[0051] a memory for storing processor-executable instructions;

[0052] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0053] A fourth aspect of the embodiments of the present invention is:

[0054] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0055] By obtaining the real-time operating parameters of the printing equipment and combining it with the preset multi-factor VOCs emission mathematical model, the real-time VOCs emission amount and emission rate of the printing equipment can be accurately calculated, providing precise data support for subsequent VOCs treatment, which helps to improve the pertinence and effectiveness of VOCs treatment.

[0056] By real-time detection of VOCs concentrations in multiple areas within the printing workshop and identifying the spatial characteristics of the concentration distribution, local high-concentration areas of VOCs emissions can be discovered in a timely manner, laying the foundation for customized VOCs treatment based on regions and levels.

[0057] By comparing the VOCs concentration detected in each area with the preset multi-level VOCs concentration threshold, the VOCs treatment strategy can be dynamically adjusted according to the VOCs concentration levels in different areas, achieving more refined and differentiated VOCs control, avoiding a "one-size-fits-all" approach, and improving the overall efficiency of VOCs governance.

[0058] When the VOCs concentration in a certain area exceeds the threshold of the corresponding level, by matching the preset treatment efficiency curves of multiple VOCs treatment processes and collaboratively controlling multiple VOCs treatment devices of different types, the optimal treatment process combination can be selected for VOCs with different concentration levels and composition characteristics, giving full play to the synergistic effect of different treatment technologies and significantly improving the VOCs removal efficiency.

[0059] By using a variety of VOCs treatment devices such as adsorption devices, photocatalytic devices, low-temperature plasma devices and biological scrubbers to work together, we can fully utilize the advantages of different treatment technologies, achieve multi-path and deep treatment of VOCs, effectively reduce VOCs emission concentrations, and reduce harm to the environment and human health. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of a method for real-time monitoring and controlling VOCs emissions from printing equipment according to an embodiment of the present invention;

[0061] Figure 2 It is a schematic diagram of the structure of a real-time monitoring and control system for VOCs emissions from printing equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0064] Figure 1 FIG. 1 is a flow chart of a method for real-time monitoring and controlling VOCs emissions from printing equipment according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0065] S101. Obtaining real-time operating parameters of the printing equipment, including at least one of printing speed, printing material type and amount, substrate type, ink type and amount, temperature, humidity, and workshop air flow rate; based on the real-time operating parameters, combined with a preset multi-factor VOCs emission mathematical model, calculating the real-time VOCs emission amount and emission rate of the current printing equipment;

[0066] In an optional embodiment,

[0067] Based on the real-time operating parameters and in combination with a preset multi-factor VOCs emission mathematical model, before calculating the real-time VOCs emission amount and emission rate of the current printing device, the method further includes:

[0068] The multi-factor VOCs emission mathematical model is constructed based on a neural network;

[0069] The real-time operating parameters are used as inputs of the multi-factor VOCs emission mathematical model; wherein the multi-factor VOCs emission mathematical model includes a three-layer feedforward neural network model, wherein the number of input layer nodes is the same as the number of real-time operating parameters, the number of hidden layer nodes is determined by grid search, and the number of output layer nodes is the number of VOCs emissions and emission rates;

[0070] The ReLU activation function is used to perform nonlinear transformation on the input of the hidden layer and the output layer, and the weighted mean square error is used as the loss function. The Adam optimization algorithm is used to train the neural network model to obtain the initial multi-factor VOCs emission mathematical model.

[0071] Obtain the latest real-time operating parameters and VOCs emission monitoring data online, add them to the training data set, trigger the retraining of the multi-factor VOCs emission mathematical model, and realize the dynamic update of model parameters;

[0072] In the process of retraining the multi-factor VOCs emission mathematical model, the forgetting factor is introduced to decay the weight of the historical samples. For each historical data sample, the forgetting factor is calculated according to the timestamp of its generation. The forgetting factor decays exponentially with the increase of the time difference, and the time constant controls the forgetting rate.

[0073] The calculated forgetting factor is introduced into the weighted mean square error loss function, and the VOCs emission amount and emission rate of printing equipment are predicted in real time using the retrained multi-factor VOCs emission mathematical model.

[0074] In an optional embodiment,

[0075] The calculated forgetting factor is introduced into the weighted mean square error loss function as shown in the following formula:

[0076]

[0077]

[0078] Among them, λ i is the forgetting factor of the i-th historical sample, t is the current timestamp, t i is the timestamp of the i-th sample, τ is the time constant, which controls the forgetting rate; m is the number of training samples, y i is the actual VOCs emission or emission rate of the i-th sample, is the model's predicted value.

[0079] For example, accurate estimation of VOCs emissions from printing equipment is the basis for real-time monitoring and control of VOCs emissions. Traditional VOCs emission estimation methods mainly use single-factor linear models, such as the emission coefficient method based on ink usage, which ignores the influence of other factors such as printing speed, temperature and humidity, and the estimation accuracy is low. To address this problem, this paper proposes a multi-factor VOCs emission mathematical model based on machine learning.

[0080] First, through field research and historical data analysis of printing workshops, key factors affecting VOCs emissions were identified, including printing speed, printing material type and amount, substrate type, ink type and amount, temperature, humidity, workshop air flow rate, etc. On this basis, real-time operating parameters of printing equipment and VOCs emission monitoring data within a certain time range were collected to establish a multi-factor VOCs emission data set.

[0081] Considering the nonlinear relationship between each factor and VOCs emission, and the possible interaction between factors, this paper chooses to use a neural network model to fit the VOCs emission law. A three-layer feedforward neural network is designed. The number of input layer nodes is the number of influencing factors, the number of hidden layer nodes is optimized by grid search, and the number of output layer nodes is 2, representing VOCs emission and emission rate respectively. The ReLU activation function and Adam optimization algorithm are used to train the neural network with mean square error as the loss function.

[0082] In order to further improve the generalization ability and adaptability of the model, an online learning mechanism was introduced. When new printing equipment operating parameters and VOCs emission monitoring data arrive, they are added to the training set in a timely manner, and the model is retrained regularly to achieve dynamic updates of model parameters. At the same time, a forgetting factor is designed to give a smaller weight to earlier historical data, reduce its impact on the current model, and improve the model's fitting effect on the latest data.

[0083] After training and optimization, the mean absolute percentage error (MAPE) of the multi-factor VOCs emission mathematical model obtained on the test set is less than 10%, meeting the accuracy requirements of VOCs emission estimation. The model is embedded in the VOCs emission monitoring system of printing equipment, which receives the operating parameters of printing equipment in real time, dynamically predicts VOCs emissions and emission rates, and provides data support for subsequent VOCs governance.

[0084] Compared with the traditional estimation method based on emission coefficient, the multi-factor VOCs emission mathematical model based on machine learning proposed in this paper fully considers the nonlinear correlation between the influencing factors, realizes adaptive updating of the model through online learning, significantly improves the dynamics and accuracy of VOCs emission estimation, and lays the foundation for refined VOCs control.

[0085] Furthermore, in view of the nonlinear characteristics and interactive effects of the factors affecting VOCs emissions from printing equipment, this paper designs a three-layer feedforward neural network model to fit the VOCs emission law. The input of the model is the real-time operating parameters of the printing equipment, including printing speed, printing material type and amount, substrate type, ink type and amount, temperature, humidity, workshop air flow rate, etc., a total of n influencing factors, so the number of nodes in the input layer is n. The number of nodes in the output layer is set to 2, representing the VOCs emission and emission rate respectively.

[0086] The key lies in determining the number of hidden layer nodes. In order to find the optimal number of hidden layer nodes, this paper adopts the grid search method to traverse different numbers of nodes within a certain range, such as integers between 10 and 100 with a step length of 10. For each candidate number of nodes, a 5-fold cross-validation method is used to train and evaluate the model performance, and the number of nodes with the best average performance is selected as the final number of hidden layer nodes.

[0087] During the training process of the neural network, the ReLU activation function is used to perform nonlinear transformation on the input of the hidden layer and the output layer, introducing nonlinear factors and enhancing the network's expressive power.

[0088] In order to optimize the training process of the neural network, this paper uses the Adam optimization algorithm to update the network parameters. The Adam algorithm is an adaptive learning rate optimization method that can automatically adjust the learning rate for different parameters, accelerate convergence and improve training stability. The optimization goal is to minimize the mean square error loss function, that is:

[0089]

[0090] Among them, m is the number of training samples, y i is the actual VOCs emission or emission rate of the i-th sample, is the model's predicted value.

[0091] In order to make the VOCs emission model adapt to the dynamic changes of printing conditions, this paper introduces an online learning mechanism. Specifically, when new printing equipment operating parameters and VOCs emission monitoring data arrive, they are added to the training set in a timely manner, and the model retraining is triggered regularly to achieve dynamic updating of model parameters. This online learning method can enable the model to continuously learn the latest emission patterns and improve the timeliness and accuracy of predictions.

[0092] In the process of online learning, if all historical data are simply included in the training with equal weights, the early data may dominate the model, affecting the model's fitting effect on the latest data. To this end, this paper designs a weight adjustment strategy based on the forgetting factor. For each historical data sample, a forgetting factor is calculated according to the timestamp of its generation to attenuate its weight in the loss function. The calculation formula of the forgetting factor is as follows:

[0093]

[0094] Among them, λ i is the forgetting factor of the i-th historical sample, t is the current timestamp, t i is the timestamp of the i-th sample, and τ is the time constant, which controls the forgetting rate. The time constant can be adjusted according to the frequency of changes in the printing conditions. Under conditions with faster changes, a smaller time constant can be selected to speed up the forgetting of historical data.

[0095] Introducing the forgetting factor into the loss function, we get the weighted mean square error loss:

[0096]

[0097] Through this weighted loss function, the model can pay more attention to the latest data samples during the dynamic update process, reduce the influence of historical data, and improve the adaptability and robustness of the model.

[0098] Combining the above neural network model design and online learning optimization strategy, this paper constructs an intelligent modeling framework that can dynamically fit the VOCs emission law. This framework fully considers the nonlinear correlation and interaction of influencing factors, optimizes the network structure through grid search, and introduces online learning mechanism and forgetting factor to achieve continuous adaptive update of VOCs emission model. Experimental results show that the framework can accurately predict the VOCs emission and emission rate of printing equipment, and the average absolute percentage error is controlled within 10%, providing reliable data support for subsequent VOCs governance decisions.

[0099] S102. Real-time detection of VOCs concentrations in multiple areas of the printing workshop, identification of spatial characteristics of concentration distribution, and determination of local high-concentration areas of VOCs emissions; comparison of the VOCs concentrations detected in each area with preset multi-level VOCs concentration thresholds;

[0100] In an optional embodiment,

[0101] Real-time detection of VOCs concentrations in multiple areas of the printing workshop, identification of the spatial characteristics of concentration distribution, and determination of local high-concentration areas of VOCs emissions include:

[0102] Multiple wireless VOCs sensor nodes are deployed in different areas of the printing workshop. Each sensor node integrates a VOCs concentration sensor, a temperature and humidity sensor, a wireless communication module and a microprocessor. The collected VOCs concentration and environmental parameters are transmitted to the data aggregation node in real time through the wireless network.

[0103] The data aggregation node receives the data uploaded by each sensor node, pre-processes and stores it, and transmits the received data to the host computer in real time via wired Ethernet;

[0104] The host computer performs Kriging spatial interpolation on the received VOCs concentration and environmental parameters, constructs a semivariogram to describe the spatial correlation between data points, performs weighted sum estimation on the VOCs concentration at unknown locations, and generates a continuous VOCs concentration distribution map;

[0105] According to the preset VOCs concentration warning threshold and alarm threshold, the concentration distribution map is scanned point by point, the grid points exceeding the threshold are marked, and the adjacent high-concentration grid points are merged into local high-concentration areas using the region growing algorithm.

[0106] In an optional embodiment,

[0107] The host computer performs Kriging spatial interpolation on the received VOCs concentration and environmental parameters, constructs a semivariogram to describe the spatial correlation between data points, performs weighted summation estimation on the VOCs concentration at unknown locations, and generates a continuous VOCs concentration distribution map including:

[0108] The semivariogram function is shown in the following formula:

[0109]

[0110] Where h is the distance between data points, C0 is the nugget value, C is the sill value, and a is the range;

[0111] The Kriging spatial interpolation formula is as follows:

[0112]

[0113] Where n is the number of known data points involved in the estimation, Q j is the weight coefficient of the jth data point, μ is the Lagrange multiplier, and h kj is the distance between the kth data point and the jth data point, h k0 is the distance between the kth data point and the position to be estimated.

[0114] For example, in order to fully grasp the distribution of VOCs concentration in the printing workshop, this paper designs a multi-point VOCs concentration detection system. The system consists of several wireless VOCs sensor nodes and a data aggregation node, using a star network topology. VOCs sensor nodes are deployed in different areas of the workshop, such as around the printing press, ink mixing area, and waste gas treatment equipment inlet and outlet. Each sensor node integrates VOCs concentration sensors, temperature and humidity sensors, wireless communication modules, and microprocessors. It can collect VOCs concentrations and environmental parameters at its location in real time, and transmit data to the aggregation node through a wireless network.

[0115] VOCs concentration sensors use sensors based on the principle of photoionization detection (PID), such as the PID-A12 sensor. This type of sensor has the advantages of high sensitivity, fast response, and good linearity, and can meet the ppb-level VOCs detection requirements. In order to extend the service life of the sensor and ensure the detection accuracy, an automatic calibration circuit is designed on each sensor node, and the sensor is calibrated regularly using standard VOCs gas. At the same time, a filter device is installed at the front end of the sensor to prevent interfering substances such as dust from affecting the measurement results.

[0116] The data aggregation node is responsible for receiving the data uploaded by each sensor node, and preprocessing and storing it. The aggregation node uses an industrial-grade embedded computer and is equipped with a high-reliability data receiving and storage module to ensure the integrity and security of the data. The aggregation node communicates with the host computer via wired Ethernet, and transmits the received data to the host computer in real time for analysis and visualization.

[0117] The multi-point VOCs concentration detection system obtains discrete concentration data. In order to intuitively present the continuous distribution of VOCs in the printing workshop, it is necessary to perform spatial interpolation on the discrete data to generate a continuous concentration distribution map. This paper uses the Kriging interpolation method to perform spatial mapping of VOCs concentration.

[0118] Kriging interpolation is a spatial interpolation method based on geostatistical principles. It can make full use of the spatial correlation between data points to make the best linear unbiased estimate of the attribute value at the unknown location. The basic idea is to describe the spatial correlation between data points by constructing a semivariogram, and on this basis, to perform a weighted summation estimate of the attribute value at the unknown location, with the weight determined by the spatial position relationship between the semivariogram and the data points.

[0119] The establishment of the Kriging equation group requires the participation of the semi-variogram. The semi-variogram describes the relationship between the spatial correlation between data points and the distance, which can be obtained by fitting the measured data. Commonly used semi-variogram models include exponential model, Gaussian model and spherical model.

[0120] After obtaining the semivariogram and weight coefficient, the grid points inside the workshop are traversed, and the VOCs concentration value of each grid point is estimated using the above formula to generate a continuous concentration distribution map. By analyzing the contour lines and color scales in the concentration distribution map, the high and low distribution of VOCs concentrations in the workshop and the local high concentration areas can be intuitively judged.

[0121] In order to further realize the automatic identification and early warning of local high-concentration areas of VOCs, this paper designs a threshold-based region identification algorithm. First, the early warning threshold and alarm threshold of VOCs concentration are set according to industry standards and actual workshop conditions. Then, the gridded concentration distribution data generated by spatial interpolation is scanned point by point, and the grid points that exceed the early warning threshold and alarm threshold are marked.

[0122] For the marked high-concentration grid points, the region growing algorithm is used to merge the regions. Each high-concentration grid point is used as a seed point, and the adjacent high-concentration grid points are expanded to the surrounding areas to merge into the same region. During the region growing process, the area, center coordinates, average concentration and other attribute parameters of the region are calculated at the same time. When the region no longer expands, it is marked as an independent high-concentration region.

[0123] All identified high-concentration areas are screened and sorted, noise areas with too small an area are eliminated, and areas are sorted according to area size and average concentration. The identification results are presented in a list and visualization form, with the location, area, concentration and other information of each area marked, and graded according to the warning and alarm levels. When the concentration of a certain area exceeds the alarm threshold, the system automatically sends an alarm message to the management personnel, prompting them to take emergency measures.

[0124] Through the above-mentioned technical means such as real-time detection, spatial mapping and regional identification, it is possible to fully grasp the distribution characteristics of VOCs concentration in the printing workshop, timely discover local high-concentration areas, provide accurate data support for subsequent targeted governance and emergency disposal, and improve the pertinence and effectiveness of VOCs governance.

[0125] Furthermore, after obtaining the VOCs concentration and environmental parameter measurements at multiple locations in the printing workshop, it is necessary to perform spatial interpolation on these discrete data points to generate a continuous VOCs concentration distribution map. This paper uses the Kriging interpolation method for spatial interpolation, which can fully consider the spatial correlation between data points and provide the optimal linear unbiased estimate. The implementation steps of Kriging interpolation are as follows:

[0126] The acquired VOCs concentration and environmental parameter data are detected and eliminated for outliers to ensure the validity and reliability of the data. According to the spatial coordinate information of the sensor nodes, the data points are mapped onto a two-dimensional plane.

[0127] Construct a semivariogram. The semivariogram describes the relationship between the spatial correlation between data points and the distance, and is the core of Kriging interpolation. According to the measured data, calculate the semivariogram values ​​at different distance intervals, and select a suitable semivariogram model for fitting. Commonly used semivariogram models include exponential models, Gaussian models, and spherical models. Taking the spherical model as an example, their mathematical expressions are:

[0128]

[0129] Among them, h is the distance between data points, C0 is the nugget value, C is the sill value, and a is the range. The optimal semivariogram model parameters are fitted through optimization algorithms such as the least squares method.

[0130] Establish the Kriging equations. For the VOCs concentration value at the location to be estimated (x, y), establish the Kriging equations according to the spatial position relationship between the semivariogram and the known data points:

[0131]

[0132] Where n is the number of known data points involved in the estimation, Q j is the weight coefficient of the jth data point, μ is the Lagrange multiplier, and h kj is the distance between the kth data point and the jth data point, h k0 is the distance between the kth data point and the position to be estimated. By solving the Kriging equations, the weight coefficient of each data point can be obtained.

[0133] Using the weight coefficient obtained, the VOCs concentration value at the estimated position (x, y) is estimated by weighted summation:

[0134]

[0135] in, is the VOCs concentration measurement value of the jth data point.

[0136] Grid the entire space of the printing workshop, select the appropriate grid spacing, and generate grid point coordinates. Estimate the VOCs concentration value for each grid point. Map the estimated grid point concentration values ​​to colors or contour lines to generate a continuous VOCs concentration distribution map.

[0137] The accuracy of Kriging interpolation is evaluated through methods such as cross-validation. Some data points are randomly selected as validation points, and the remaining data points are used for interpolation estimation. The error between the estimated value and the measured value at the validation point is calculated. Commonly used error indicators include mean square error (MSE), mean absolute error (MAE), and coefficient of determination. The interpolation accuracy is evaluated based on the error indicators, and the semivariogram model and parameters are adjusted if necessary to optimize the interpolation effect.

[0138] Through the above steps, the VOCs concentration distribution map based on Kriging spatial interpolation is generated. Kriging interpolation makes full use of the spatial correlation between data points and can provide more accurate concentration estimation results. The generated concentration distribution map intuitively reflects the spatial distribution characteristics of VOCs in the printing workshop, providing a data basis for the subsequent identification of local high-concentration areas.

[0139] For example, in order to further study the diffusion characteristics of VOCs in the printing workshop and predict the trend of VOCs concentration changes in local high-concentration areas, this paper proposes a VOCs diffusion simulation and concentration prediction method based on computational fluid dynamics (CFD). This method uses CFD numerical simulation technology, combined with real-time monitoring of VOCs emissions, emission rates and environmental parameters in the workshop, to construct a VOCs diffusion model in the printing workshop, simulate its spatiotemporal distribution and change laws, and provide support for the formulation of targeted VOCs governance strategies. The specific implementation steps are as follows:

[0140] According to the actual layout and size of the printing workshop, the 3D geometric model of the workshop is established using CAD software. The geometric model should include key elements such as main equipment, room structure, doors, windows, vents, etc., and non-critical details should be appropriately simplified to reduce calculation complexity.

[0141] The established geometric model is imported into the CFD pre-processing software to mesh the computational domain. Unstructured meshes are used to perform local encryption in key areas such as VOCs emission sources and vents to improve the calculation accuracy. The mesh quality has an important impact on the calculation results, and the mesh quality needs to be checked and optimized to ensure that the mesh orthogonality, aspect ratio, and scale transition meet the requirements.

[0142] According to the actual situation, set the boundary conditions of the model. For the air inlet, set its velocity, temperature, humidity and other parameters; for the air outlet, set the pressure boundary condition; for the wall, set it to the no-slip wall condition; for the VOCs emission source, set it to the mass flow inlet condition, and set the VOCs mass fraction at the inlet according to the real-time monitored emission rate data.

[0143] Select appropriate turbulence model and VOCs component transport model, set solution algorithm and convergence criteria. Turbulence model is used to describe the turbulent characteristics of indoor air flow, and VOCs component transport model is used to describe the convection, diffusion and mixing process of VOCs in the air. The solution algorithm adopts SIMPLE algorithm, and selects appropriate discrete format and relaxation factor to ensure the stability and convergence of the calculation.

[0144] Import the set model into the CFD solver for numerical simulation. During the solution process, monitor the residual change and the convergence of key parameters, and adjust the relaxation factor and grid settings if necessary to accelerate convergence and improve calculation accuracy. The calculation results include the velocity field, pressure field, temperature field, humidity field, and VOCs concentration field in the workshop.

[0145] CFD post-processing software is used to visualize the calculation results and generate velocity vector diagrams, streamline diagrams, isosurface diagrams, etc., which intuitively show the air flow characteristics and VOCs concentration distribution in the workshop. For local high-concentration areas, the VOCs concentration change curve over time is extracted to analyze the rising or falling trend of the concentration and predict the concentration change in the future.

[0146] Use actual monitoring data to verify the CFD simulation results, compare the degree of agreement between the simulation values ​​and the measured values, and calculate indicators such as relative error and correlation coefficient. If the error exceeds the acceptable range, the model needs to be optimized and adjusted, such as refining the grid, adjusting the boundary conditions, and selecting a more accurate turbulence model, until the simulation results reach a satisfactory accuracy.

[0147] Based on the verified CFD model, the diffusion characteristics of VOCs in the printing workshop are analyzed, including diffusion range, diffusion rate, concentration gradient, etc. Focus on local high-concentration areas and predict their future concentration change trends to provide a basis for VOCs governance. At the same time, by changing ventilation conditions and optimizing exhaust vent layout, effective measures to reduce the diffusion range of VOCs and reduce local concentrations are studied.

[0148] Through the above steps, the CFD-based VOCs diffusion characteristics simulation and concentration prediction were realized. This method comprehensively considers the emission characteristics of VOCs, the environmental parameters of the workshop, and the spatial layout. It can accurately simulate the temporal and spatial distribution of VOCs in the printing workshop, provide a quantitative basis for identifying high-concentration areas and predicting concentration trends, and guide the VOCs control work in the printing workshop. At the same time, CFD simulation also provides a powerful tool for optimizing ventilation plans and improving the air quality in the workshop, and has good application prospects.

[0149] S103. If the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, the preset treatment efficiency curves of multiple VOCs treatment processes are matched, and multiple VOCs treatment devices are coordinated and controlled. The VOCs treatment devices include at least one of an adsorption device, a photocatalytic device, a low-temperature plasma device and a biological washing tower, so as to realize customized VOCs treatment by region and level.

[0150] In an optional embodiment,

[0151] If the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, the processing efficiency curves of the preset multiple VOCs treatment processes are matched, and multiple VOCs treatment devices are collaboratively controlled, including:

[0152] Establish a dynamic model to describe the dynamic operating characteristics of each VOCs treatment device;

[0153] Each VOCs treatment device is regarded as a subsystem in a distributed control system, and a collaborative control framework for multiple VOCs treatment devices is constructed. Each subsystem independently optimizes and controls operating parameters based on its own dynamic model and optimization objectives while satisfying global constraints.

[0154] For each subsystem, a predictive controller based on a dynamic model is designed to predict the optimal control sequence in the future according to the current state and future reference trajectory, and the first element of the optimal control sequence is output as the control quantity at the current moment;

[0155] Based on the iterative negotiation algorithm with weight distribution, each subsystem sends the optimization results to other subsystems, and adjusts its own weight coefficient according to the feedback information received, and repeats the iteration until a consensus solution or a preset number of times is reached.

[0156] For example, in order to achieve efficient coordinated control of multiple VOCs treatment devices and improve the efficiency and stability of the entire treatment system, this paper proposes a coordinated control strategy based on distributed model predictive control (DMPC). This strategy comprehensively considers the operating status, energy consumption level and processing capacity of each treatment device, and realizes load balancing and coordinated control between treatment devices by optimizing the operating parameters of each device in real time. The specific implementation steps are as follows:

[0157] Establish a dynamic model of a single VOCs treatment device. For each VOCs treatment device, according to the principles and characteristics of its treatment process, establish mathematical models of reaction kinetics, mass transfer and heat transfer to describe the dynamic operation characteristics of the device. Taking the activated carbon adsorption device as an example, the linear driving force (LDF) model can be used to describe the adsorption process:

[0158]

[0159] Where, t represents time, q represents the adsorption amount of activated carbon, and q * is the equilibrium adsorption capacity, k L is the overall mass transfer coefficient.

[0160] Construct a collaborative control framework for multiple VOCs treatment devices. Treat each treatment device as a subsystem in a distributed control system. Each subsystem independently optimizes and controls operating parameters based on its own dynamic model and optimization objectives while satisfying global constraints. The subsystems achieve collaborative optimization of the entire system through information exchange and negotiation.

[0161] Design a subsystem-level model predictive controller. For each subsystem (i.e., a single processing device), design a predictive controller based on a dynamic model. The controller predicts the optimal control sequence for a period of time in the future based on the current state and future reference trajectory, and outputs the first element of the sequence as the control quantity at the current moment. The objective function of the predictive controller can be set as:

[0162]

[0163] Among them, P and M are the prediction step size and control step size respectively, r v is the reference trajectory of the vth subsystem, u v,s is the steady-state control quantity of the vth subsystem, Q and R are the weight matrices of state error and control quantity change, x v 、u v They represent the state variables and control variables of the vth subsystem respectively.

[0164] In order to achieve collaboration among subsystems, a negotiation optimization mechanism needs to be designed so that each subsystem can meet its own constraints while also considering the operating status and needs of other subsystems. This paper adopts an iterative negotiation algorithm based on weight allocation. The specific steps are as follows:

[0165] Each subsystem initializes its own optimization problem, calculates an initial solution based on local information, and sends it to other subsystems;

[0166] After receiving the solutions sent by other subsystems, each subsystem adds them to its own optimization problem as additional equality constraints and re-solves the updated optimization problem;

[0167] Each subsystem sends the updated solution to other subsystems and adjusts the weight coefficients in its own optimization problem based on the feedback information received; until the solutions of all subsystems converge to a consensus solution or the preset number of iterations is reached.

[0168] On the basis of distributed collaborative control, an upper-level centralized monitoring and scheduling system is designed to monitor the operating status, energy consumption level and treatment effect of each treatment device, and coordinate and schedule each subsystem according to the global optimization goal. The centralized monitoring system can also dynamically adjust the start and stop status and operating parameters of each treatment device according to the changes in VOCs concentration distribution, so as to realize flexible scheduling and optimized control of the entire system.

[0169] Through the above steps, the design of a distributed collaborative control model for multiple VOCs treatment devices was realized. The model fully considers the dynamic characteristics and operating constraints of each treatment device, and realizes load balancing and collaborative optimization between treatment devices through subsystem-level predictive control and iterative negotiation between subsystems. At the same time, the upper-level centralized monitoring and scheduling system can flexibly schedule each subsystem based on global information, further improving the overall efficiency and intelligence level of the VOCs treatment system.

[0170] Figure 2 Schematic diagram of the structure of the real-time monitoring and control system for VOCs emissions from printing equipment according to an embodiment of the present invention. Figure 2 As shown, the system comprises:

[0171] The first unit is used to obtain the real-time operating parameters of the printing equipment, including at least one of the printing speed, the type and amount of printing materials, the type of substrate, the type and amount of ink, the temperature, the humidity, and the air flow rate of the workshop; based on the real-time operating parameters, combined with the preset multi-factor VOCs emission mathematical model, calculate the real-time VOCs emission amount and emission rate of the current printing equipment;

[0172] The second unit is used to detect the VOCs concentration in multiple areas of the printing workshop in real time, identify the spatial characteristics of the concentration distribution, and determine the local high-concentration areas of VOCs emissions; compare the VOCs concentration detected in each area with the preset multi-level VOCs concentration threshold; if the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, then based on the calculated VOCs real-time emission amount and emission rate, combined with the environmental information of the air flow rate, temperature and humidity in the area, the computational fluid dynamics method is used to simulate the diffusion characteristics of VOCs in the workshop and predict the VOCs concentration change trend in the exceeding area;

[0173] The third unit is used to match the preset treatment efficiency curves of multiple VOCs treatment processes according to the prediction results of VOCs diffusion characteristics, and coordinately control multiple VOCs treatment devices, wherein the VOCs treatment devices include at least one of an adsorption device, a photocatalytic device, a low-temperature plasma device and a biological washing tower, to achieve customized VOCs treatment by region and level.

[0174] According to a third aspect of the embodiments of the present invention,

[0175] An electronic device is provided, comprising:

[0176] processor;

[0177] a memory for storing processor-executable instructions;

[0178] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0179] A fourth aspect of the embodiments of the present invention is:

[0180] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0181] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A real-time monitoring and control method for VOCs emissions from printing equipment, characterized in that: include: Acquire real-time operating parameters of the printing equipment, including at least one of printing speed, type and amount of printing materials, type of substrate, type and amount of ink, temperature, humidity, and workshop air flow rate; based on the real-time operating parameters, combined with a preset multi-factor VOCs emission mathematical model, calculate the real-time VOCs emission amount and emission rate of the current printing equipment; Real-time detection of VOCs concentrations in multiple areas of the printing workshop, identification of the spatial characteristics of concentration distribution, and determination of local high-concentration areas of VOCs emissions; comparison of the VOCs concentrations detected in each area with the preset multi-level VOCs concentration thresholds; If the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, the preset treatment efficiency curves of multiple VOCs treatment processes are matched, and multiple VOCs treatment devices are coordinated and controlled. The VOCs treatment devices include at least one of an adsorption device, a photocatalytic device, a low-temperature plasma device and a biological washing tower, to achieve customized VOCs treatment by region and level.

2. The method according to claim 1, characterized in that Based on the real-time operating parameters and in combination with a preset multi-factor VOCs emission mathematical model, before calculating the real-time VOCs emission amount and emission rate of the current printing device, the method further includes constructing a multi-factor VOCs emission mathematical model: The multi-factor VOCs emission mathematical model is constructed based on a neural network; The real-time operating parameters are used as inputs of the multi-factor VOCs emission mathematical model; wherein the multi-factor VOCs emission mathematical model includes a three-layer feedforward neural network model, wherein the number of input layer nodes is the same as the number of real-time operating parameters, the number of hidden layer nodes is determined by grid search, and the number of output layer nodes is the number of VOCs emissions and emission rates; The ReLU activation function is used to perform nonlinear transformation on the input of the hidden layer and the output layer, and the weighted mean square error is used as the loss function. The Adam optimization algorithm is used to train the neural network model to obtain the initial multi-factor VOCs emission mathematical model. Obtain the latest real-time operating parameters and VOCs emission monitoring data online, add them to the training data set, trigger the retraining of the multi-factor VOCs emission mathematical model, and realize the dynamic update of model parameters; In the process of retraining the multi-factor VOCs emission mathematical model, the forgetting factor is introduced to decay the weight of the historical samples. For each historical data sample, the forgetting factor is calculated according to the timestamp of its generation. The forgetting factor decays exponentially with the increase of the time difference, and the time constant controls the forgetting rate. The calculated forgetting factor is introduced into the weighted mean square error loss function, and the VOCs emission amount and emission rate of printing equipment are predicted in real time using the retrained multi-factor VOCs emission mathematical model.

3. The method according to claim 2, characterized in that The calculated forgetting factor is introduced into the weighted mean square error loss function as shown in the following formula: Among them, λ i is the forgetting factor of the i-th historical sample, t is the current timestamp, t i is the timestamp of the i-th sample, τ is the time constant, which controls the forgetting rate; m is the number of training samples, y i is the actual VOCs emission or emission rate of the i-th sample, is the model's predicted value.

4. The method according to claim 1, characterized in that Real-time detection of VOCs concentrations in multiple areas of the printing workshop, identification of the spatial characteristics of concentration distribution, and determination of local high-concentration areas of VOCs emissions include: Multiple wireless VOCs sensor nodes are deployed in different areas of the printing workshop. Each sensor node integrates a VOCs concentration sensor, a temperature and humidity sensor, a wireless communication module and a microprocessor. The collected VOCs concentration and environmental parameters are transmitted to the data aggregation node in real time through the wireless network. The data aggregation node receives the data uploaded by each sensor node, pre-processes and stores it, and transmits the received data to the host computer in real time via wired Ethernet; The host computer performs Kriging spatial interpolation on the received VOCs concentration and environmental parameters, constructs a semivariogram to describe the spatial correlation between data points, performs weighted sum estimation on the VOCs concentration at unknown locations, and generates a continuous VOCs concentration distribution map; According to the preset VOCs concentration warning threshold and alarm threshold, the concentration distribution map is scanned point by point, the grid points exceeding the threshold are marked, and the adjacent high-concentration grid points are merged into local high-concentration areas using the region growing algorithm.

5. The method according to claim 4, characterized in that The host computer performs Kriging spatial interpolation on the received VOCs concentration and environmental parameters, constructs a semivariogram to describe the spatial correlation between data points, performs weighted summation estimation on the VOCs concentration at unknown locations, and generates a continuous VOCs concentration distribution map including: The semivariogram function is shown in the following formula: Where h is the distance between data points, C0 is the nugget value, C is the sill value, and a is the range; The Kriging spatial interpolation formula is as follows: Where n is the number of known data points involved in the estimation, Q j is the weight coefficient of the jth data point, μ is the Lagrange multiplier, and h kj is the distance between the kth data point and the jth data point, h k0 is the distance between the kth data point and the position to be estimated.

6. The method according to claim 1, characterized in that If the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, the processing efficiency curves of the preset multiple VOCs treatment processes are matched, and multiple VOCs treatment devices are collaboratively controlled, including: Establish a dynamic model to describe the dynamic operating characteristics of each VOCs treatment device; Each VOCs treatment device is regarded as a subsystem in a distributed control system, and a collaborative control framework for multiple VOCs treatment devices is constructed. Each subsystem independently optimizes and controls operating parameters based on its own dynamic model and optimization objectives while satisfying global constraints. For each subsystem, a predictive controller based on a dynamic model is designed to predict the optimal control sequence in the future according to the current state and future reference trajectory, and the first element of the optimal control sequence is output as the control quantity at the current moment; Based on the iterative negotiation algorithm with weight distribution, each subsystem sends the optimization results to other subsystems, and adjusts its own weight coefficient according to the feedback information received, and repeats the iteration until a consensus solution or a preset number of times is reached.

7. A real-time monitoring and control system for VOCs emissions from printing equipment, used to implement the method described in any one of claims 1 to 6, characterized in that: include: The first unit is used to obtain the real-time operating parameters of the printing equipment, including at least one of the printing speed, the type and amount of printing materials, the type of substrate, the type and amount of ink, the temperature, the humidity, and the air flow rate of the workshop; based on the real-time operating parameters, combined with the preset multi-factor VOCs emission mathematical model, calculate the real-time VOCs emission amount and emission rate of the current printing equipment; The second unit is used to detect the VOCs concentration in multiple areas of the printing workshop in real time, identify the spatial characteristics of the concentration distribution, and determine the local high-concentration areas of VOCs emissions; compare the VOCs concentration detected in each area with the preset multi-level VOCs concentration threshold; The third unit is used to match the preset treatment efficiency curves of multiple VOCs treatment processes if the VOCs concentration in any area exceeds the VOCs concentration threshold of the corresponding level, and coordinately control multiple VOCs treatment devices, wherein the VOCs treatment devices include at least one of an adsorption device, a photocatalytic device, a low-temperature plasma device and a biological washing tower, to achieve customized VOCs treatment by region and level.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Citation Information

Cited By

  • Online and offline comprehensive monitoring method and system for printing VOCs (Volatile Organic Compounds)

    CN120908114A

  • Multi-point VOCs leakage detection method and system, intelligent terminal and storage medium

    CN121364041A