Plastic foam particle coating drying state monitoring method based on intelligent sensor

Abstract

The invention provides a method for monitoring the drying state of a plastic foam particle coating based on an intelligent sensor, and relates to the technical field of sensor monitoring, and the method comprises the steps: carrying out the drying fitting through constructing a twin model, and building a deep balance drying constraint; calling a temperature and humidity sensor to obtain environment data; performing surface layer monitoring based on a surface layer sensor, and establishing a first drying monitoring result; performing depth node monitoring based on a twinborn model, and establishing a second dry monitoring result; performing drying monitoring and early warning by using the deep balance drying constraint and the first and second drying monitoring results, and establishing a first monitoring and early warning result; performing surface layer dryness analysis by using the environmental data and the first dryness monitoring result, and establishing a second monitoring and early warning result; and carrying out combined early warning report on the first and second monitoring early warning results. The technical problem of insufficient monitoring accuracy and reliability caused by lack of monitoring means for the deep dry state of the foam in the prior art is solved, and the monitoring accuracy and reliability are improved.

Description

Technical Field

[0001] The present application relates to the field of sensor monitoring technology, and in particular to a method for monitoring the coating and drying state of plastic foam particles based on intelligent sensors. Background Art

[0002] Plastic foam particle coating is a common production process, widely used in packaging, insulation and other fields. During the coating process, plastic foam particles need to be dried to ensure the quality and stability of the coating. The drying effect directly affects the quality of the product. At present, the drying state monitoring method of plastic foam particle coating mainly relies on traditional temperature and humidity sensors and manual monitoring. Although these methods can provide real-time data of the drying process to a certain extent, they usually ignore the difference between the surface and deep state of the particles during the drying process, and cannot fully reflect the drying state of the particles, resulting in uneven drying or unstable product quality, and also waste of resources. Summary of the invention

[0003] The present application provides a method for monitoring the coating and drying state of plastic foam particles based on intelligent sensors, which solves the technical problem that the prior art lacks effective means to monitor the deep drying state of plastic foam, resulting in insufficient monitoring accuracy and reliability, thereby affecting product quality, and achieves the technical effect of improving the monitoring accuracy and reliability of the coating and drying process of plastic foam particles.

[0004] In view of the above problems, the present application provides a method for monitoring the drying state of plastic foam particle coating based on intelligent sensors, the method comprising: performing three-dimensional modeling of the plastic foam particle coating to construct a twin model, the twin model being constructed by reading the data of the plastic foam particle coating; performing drying fitting of the plastic foam particle coating based on the twin model, and establishing a deep balanced drying constraint; after the plastic foam particle coating performs drying monitoring, calling the temperature and humidity sensor to monitor the temperature and humidity of the drying space, and establishing environmental data; performing surface monitoring of the plastic foam particle coating based on the surface sensor, and establishing a first drying monitoring result; configuring deep nodes based on the twin model, deploying a wireless sensor network at the deep nodes, and establishing a second drying monitoring result; performing drying monitoring warning using the deep balanced drying constraint and the first drying monitoring result and the second drying monitoring result, and establishing a first monitoring warning result; performing surface drying analysis using the environmental data and the first drying monitoring result, and establishing a second monitoring warning result; and issuing a joint early warning of the first monitoring warning result and the second monitoring warning result.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages: By reading the data of plastic foam particle coating, a twin model is constructed. This model can dynamically simulate the drying process and make real-time adjustments according to actual data, thereby improving the visualization and monitoring accuracy of the drying process. Based on the twin model, the drying fitting of plastic foam particle coating is performed, and the deep balanced drying constraint is established to ensure the balance of heat and humidity during the drying process and avoid excessive or insufficient drying. After the plastic foam particle coating performs drying monitoring, the temperature and humidity sensor is called to monitor the temperature and humidity of the drying space to establish environmental data; the surface layer of the plastic foam particle coating is monitored based on the surface sensor to establish the first drying monitoring result; the deep node is configured based on the twin model, and the wireless sensor network is deployed at the deep node to establish the second drying monitoring result. By monitoring the drying process in real time from multiple levels and collecting sensor data, the different stages of the drying process can be fully understood, and the monitoring accuracy can be further improved. The various sensor data are analyzed, combined with the deep balanced drying constraint, and the drying monitoring warning is generated in real time, including the first monitoring warning result and the second monitoring warning result, which provides important auxiliary decision-making for process control and reduces the quality problems caused by unsatisfactory drying conditions. The first monitoring and early warning result and the second monitoring and early warning result are jointly issued as an early warning, and the reliability of the monitoring result is enhanced through a multiple early warning mechanism.

[0006] To summarize, the present application utilizes intelligent sensors and wireless sensor networks to realize real-time monitoring of the drying process. Through multi-sensor data fusion and joint early warning mechanism, it can more accurately monitor the drying state of the plastic foam particle coating, improve the accuracy and reliability of the monitoring results, and promptly detect abnormal conditions in the drying process to avoid product quality problems caused by insufficient or excessive drying.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic flow chart of a method for monitoring the coating and drying status of plastic foam particles based on an intelligent sensor provided in an embodiment of the present application.

[0009] Figure 2 A schematic flow chart of establishing a deep equilibrium drying constraint in a method for monitoring the drying state of plastic foam particles coated with an intelligent sensor based on an embodiment of the present application.

[0010] Figure 3A schematic diagram of a process for establishing a second monitoring and early warning result in a method for monitoring the coating and drying state of plastic foam particles based on an intelligent sensor provided in an embodiment of the present application. DETAILED DESCRIPTION

[0011] The embodiment of the present application provides a method for monitoring the coating and drying state of plastic foam particles based on intelligent sensors, thereby solving the technical problem that the prior art lacks effective means to monitor the deep drying state of plastic foam, resulting in insufficient monitoring accuracy and reliability, thereby affecting product quality, and achieves the technical effect of improving the monitoring accuracy and reliability of the coating and drying process of plastic foam particles.

[0012] like Figure 1 As shown, the embodiment of the present application provides a method for monitoring the drying state of plastic foam particles based on an intelligent sensor, the method comprising: Step S1: Perform three-dimensional modeling on the plastic foam particle coating to construct a twin model, wherein the twin model is constructed by reading data of the plastic foam particle coating.

[0013] Specifically, use 3D modeling software (such as AutoCAD, SolidWorks, etc.) to model the coated plastic foam particles and determine the 3D model of the plastic foam particles. These 3D models can reflect the geometric shape of the plastic foam particles, as well as the surface and internal properties of the plastic foam particles, such as the density of the foam, surface roughness, etc. Read the data of the plastic foam particle coating, including the thickness, shape, material properties, etc. of the coating, as well as the temperature, humidity, pressure and other data in the actual production process. Associate the 3D model with the data of the plastic foam particle coating to construct a twin model corresponding to the plastic foam particle coating. This twin model can accurately reflect the appearance, internal structure and other characteristics of the coating, and provide a digital research object that corresponds to the actual object for subsequent operations such as drying analysis of the plastic foam particle coating.

[0014] Step S2: performing drying fitting of plastic foam particle coating based on the twin model and establishing depth balance drying constraints.

[0015] Specifically, the depth balance drying constraint defines the relationship that various parameters (such as the distribution of humidity and temperature at different depths) should satisfy when the ideal depth balance state is achieved during the drying process. The data collected during the actual drying process is used to simulate the drying process in the twin model to find the humidity variation law at different depths inside the plastic foam particles during normal drying, and the depth balance drying constraint is established as an important judgment criterion for subsequent drying monitoring and early warning.

[0016] Step S3: After the plastic foam particles are coated and dry, the temperature and humidity sensors are called to monitor the temperature and humidity of the drying space to establish environmental data.

[0017] Specifically, the temperature and humidity sensor can convert the physical quantities of temperature and humidity in the environment into electrical signals, and then convert them into digital signals that can be read. The temperature and humidity sensor is installed in a suitable position in the drying space, such as in the corner or center of the drying box. When the plastic foam particle coating begins to be dried, the temperature and humidity sensor is called to continuously collect the temperature and humidity information in the drying space, for example, collecting data every 5 minutes. Then the collected temperature and humidity data are sorted in a certain format (such as a table of time-temperature-humidity) to establish environmental data, which can be used to analyze the impact of environmental factors on the drying process of plastic foam particle coating.

[0018] Step S4: Perform surface monitoring of the plastic foam particle coating based on the surface sensor to establish a first drying monitoring result.

[0019] Specifically, the surface sensor is a sensor specially used to detect the surface dryness of the plastic foam particle coating. The sensor reflects the dryness state by detecting the temperature, humidity and other characteristics of the surface. It can be a temperature sensor (such as a K-type thermocouple) and a humidity sensor (such as an RH sensor). The surface sensor is placed on the surface of the plastic foam particle coating or close to the surface. For example, if it is a sensor for detecting surface humidity, the humidity information of the coating surface can be obtained by contact or non-contact (such as a capacitive humidity sensor). The surface sensor converts the detected signal into corresponding dryness information. For example, if the surface humidity is detected to be 30%, this value can be used as the first dryness monitoring result. This result provides basic data on the dryness of the coating surface for subsequent analysis and early warning.

[0020] Step S5: Configure deep nodes based on the twin model, deploy wireless sensor networks at the deep nodes, and establish a second drying monitoring result.

[0021] Specifically, depth nodes refer to some pre-set internal points in the twin model, which simulate different depth positions inside the plastic foam particles. Based on the twin model in step S1, the position of the depth node is determined inside the model according to the distribution of the plastic foam particles and the needs of drying analysis. For example, if the depth of the plastic foam particles is 50 cm, depth nodes may be set at depths of 10 cm, 20 cm, and 40 cm. A wireless sensor network is deployed at the depth nodes to collect the inner layer humidity and temperature of the plastic foam particles, and establish a second drying monitoring result to help determine whether the drying is uniform.

[0022] Step S6: Perform dryness monitoring and early warning using the depth balance dryness constraint and the first dryness monitoring result and the second dryness monitoring result to establish a first monitoring and early warning result.

[0023] Specifically, the depth balance drying constraint is compared and analyzed with the first drying monitoring result (such as the surface humidity value) and the second drying monitoring result (such as the humidity at different depths inside). For example, if the depth balance drying constraint requires that the surface humidity is less than 30% and the humidity at a specific depth inside is less than 40%, it is considered a normal drying state, and the actual first drying monitoring result is that the surface humidity is 35%, and the second drying monitoring result shows that the humidity at a specific depth inside is 45%, then it can be determined that the drying process deviates from the normal state. Based on the results of this comparative analysis, the first monitoring warning result is obtained.

[0024] Step S7: Utilize the environmental data and the first drying monitoring result to perform surface drying analysis and establish a second monitoring and early warning result.

[0025] Specifically, the environmental data and the first drying monitoring results are comprehensively analyzed to further analyze the uniformity of surface drying. The second monitoring and early warning results are established based on the analysis results. For example, if it is known that the normal surface humidity should be lower than 30% in an environment with a temperature of 50°C and a humidity of 30%, but the first drying monitoring results show that the surface humidity is 35%, the corresponding early warning information is matched according to the humidity deviation, and the second monitoring and early warning results are established. If the surface humidity deviates from the normal range by a small amount, a mild early warning information is generated, and if the deviation is large, a higher level of early warning information is generated.

[0026] Step S8: Combine the first monitoring and early warning result and the second monitoring and early warning result to issue an early warning.

[0027] Specifically, the first monitoring and early warning results (based on the data of depth and surface sensors) are combined with the second monitoring and early warning results (based on the data of environmental and surface analysis) to form a comprehensive early warning report. This joint early warning can more accurately identify potential problems in the drying process and provide operators with comprehensive and accurate information on the drying status of plastic foam particles so that they can take appropriate measures to reduce quality problems in production.

[0028] Further, such as Figure 2 As shown, step S2 of the embodiment of the present application also includes: Step S21: Acquire depth data based on the twin model, input the depth data into the grid density distribution channel, and establish a calibration grid density.

[0029] Step S22: Use the calibrated grid density to perform finite element meshing of the twin model and establish a finite element unit set.

[0030] Step S23: Establishing the surface-deep direction for the finite element unit set, and setting the heat conduction parameters and humidity diffusion parameters based on the data of the plastic foam particle coating.

[0031] Step S24: fitting the heat conduction and humidity diffusion of each unit in the finite element unit set using the surface-deep direction, the heat conduction parameters, and the humidity diffusion parameters, establishing a temperature and humidity gradient based on the fitting results, and creating a deep balanced drying constraint based on the temperature and humidity gradient and the surface-deep direction.

[0032] Specifically, the data of different levels of plastic foam particles from the surface to the bottom layer, that is, the depth data, are obtained from the twin model. These depth data include the specific distribution information of different depth layers of plastic foam particles. These depth data are input into the grid density distribution channel. The grid density distribution channel analyzes the depth data, determines the appropriate grid density, and outputs the calibrated grid density. The calibrated grid density represents the calculation granularity within each grid unit. If the plastic foam particles are relatively large, the grid division may be coarse; for smaller or more complex plastic foam particles, the grid density will be higher to ensure that the characteristics of the area can be accurately represented in the subsequent finite element mesh division.

[0033] According to the calibrated grid density, the plastic foam particle coated twin model is decomposed into multiple finite element units using finite element analysis software (such as ANSYS, etc.). The collection of these finite element units is the finite element unit set. Each unit in the set represents a small part of the plastic foam particle, and the subsequent calculation of physical processes such as heat conduction and humidity diffusion will be performed in each unit.

[0034] In the established finite element unit set, a direction from the surface of the plastic foam particle to the deep inside is clearly defined, that is, the surface-deep direction, which is the direction for subsequent heat conduction and humidity diffusion analysis. Then, the heat conduction parameters and humidity diffusion parameters are set according to the actual material properties of the plastic foam particle coating and related test data. The heat conduction parameters are used to describe the speed and difficulty of heat conduction of plastic foam particles during the heat conduction process. The humidity diffusion parameters reflect the humidity diffusion characteristics in plastic foam particles.

[0035] For each unit in the finite element unit set, the heat conduction and humidity diffusion are simulated and calculated by the finite element analysis method (such as based on the energy conservation and mass conservation equations) using the set surface-deep direction, heat conduction parameters and humidity diffusion parameters. By fitting and simulating the heat conduction and humidity diffusion of all finite element units, the changes in temperature and humidity in the surface-deep direction are obtained, thereby establishing a temperature and humidity gradient, that is, the rate of change of temperature and humidity in the surface-deep direction. Based on the temperature and humidity gradient and the surface-deep direction, a deep equilibrium drying constraint is created. This constraint is a mathematical expression of the relationship between the temperature and humidity gradient and the surface-deep direction, which is used to subsequently determine whether the drying state has reached equilibrium.

[0036] Furthermore, step S5 further includes: Step S51: Obtain the set monitoring accuracy of the plastic foam particle coating, and generate a first configuration constraint according to the set monitoring accuracy, wherein the first configuration constraint is a distribution quantity constraint.

[0037] Step S52: performing constraint gradient analysis on the depth balanced drying constraint, and establishing a second configuration constraint based on the constraint gradient analysis result, wherein the second configuration constraint is a density distribution constraint.

[0038] Step S53: configuring the depth node based on the first configuration constraint and the second configuration constraint.

[0039] Specifically, the set monitoring accuracy is a predetermined indicator used to measure the accuracy of plastic foam particle coating monitoring, which determines the required level of detail and error range in the monitoring process. The first configuration constraint is a constraint condition generated according to the set monitoring accuracy, which is used to limit the number of depth nodes distributed. The second configuration constraint is a constraint condition established based on the constraint gradient analysis results, which is used to limit the density distribution of depth nodes at different depths to better adapt to the characteristic changes at different depths during the drying process.

[0040] Get a preset monitoring accuracy value. This value can be determined based on product quality requirements and production process standards. According to the monitoring accuracy, match the appropriate depth node distribution number range and set the first configuration constraint. For example, at least 3 depth nodes are required for each cubic centimeter of film.

[0041] The deep balanced drying constraint is subjected to constraint gradient analysis to determine the gradient of temperature and humidity changes at different depths. Then, based on the results of these constraint gradient analysis, the second configuration constraint is established. For example, in the depth range of 0 to 1 cm, the temperature and humidity change gradient is large, while in the range of 10 to 20 cm, the temperature and humidity change gradient is small. In areas with large humidity change gradients, more dense depth nodes are required to accurately monitor the drying situation. Therefore, it is stipulated that in the depth range of 0 to 10 cm where the humidity change gradient is large, the density of the depth node is one node per 2 cm; and in the depth range of 10 to 20 cm where the humidity change gradient is small, the density of the depth node is one node per 5 cm.

[0042] The depth nodes are configured based on the first configuration constraint and the second configuration constraint. For example, the first configuration constraint stipulates that the total number of depth nodes cannot exceed 20, and the second configuration constraint stipulates that the density of depth nodes in the first half of the plastic foam particles is larger, and the density in the second half is smaller. Then, in actual configuration, according to the specific shape and size of the plastic foam particles, a certain number of depth nodes (such as 12) will be reasonably allocated in the first half at a higher density, and the remaining depth nodes (such as 8) will be allocated in the second half at a lower density, thereby completing the configuration of the depth nodes.

[0043] Through the above node configuration method, it can be ensured that each key area in the drying process can be fully monitored, making the temperature and humidity data collection of the entire drying process more accurate and comprehensive.

[0044] Further, such as Figure 3 As shown, step S7 of the embodiment of the present application also includes: Step S71: Perform environmental drying fitting based on the twin model to establish an environmental adaptation model.

[0045] Step S72: input the environmental data and the first drying monitoring result into an environmental adaptation model to establish an adaptation recognition result.

[0046] Step S73: performing drying rate identification on the first drying monitoring result to establish a rate identification result.

[0047] Step S74: establishing a second monitoring and early warning result according to the adaptation identification result and the rate identification result.

[0048] Specifically, the twin model is used to simulate the coating and drying process of plastic foam particles under different environments, and the influence of environmental factors on the drying process is analyzed, so as to establish an environmental adaptation model. The environmental adaptation model can describe the adaptation relationship between environmental factors (such as temperature and humidity) and the coating and drying process of plastic foam particles.

[0049] The environmental data obtained in step S3 and the first drying monitoring result obtained in step S4 are input into the environmental adaptation model, and the environmental adaptation model calculates the drying state of the plastic foam particles under the current conditions according to its internal algorithm and parameter relationship, and generates an adaptation identification result.

[0050] The relevant data in the first drying monitoring result is analyzed, the ratio of the humidity change to time is calculated, and the drying rate is obtained as the rate identification result.

[0051] A second monitoring and early warning result is established based on the adaptation recognition result and the rate recognition result. If the adaptation recognition result shows that the environment and the surface drying condition are not well adapted, and the rate recognition result shows that the drying rate is slow, then considering these two results comprehensively, a more serious second monitoring and early warning result (such as a moderate warning) can be established. If the adaptation recognition result shows that the adaptation is good, and the rate recognition result shows that the drying rate is normal, then a normal second monitoring and early warning result can be established, indicating that the surface drying process is in a normal state.

[0052] Furthermore, step S6 of the embodiment of the present application also includes: Step S61: establishing deep drying data using the first drying monitoring result and the second drying monitoring result.

[0053] Step S62: performing drying constraint trigger identification of the depth drying data based on the depth balance drying constraint, and establishing a trigger identification result.

[0054] Step S63: Establish a first monitoring and early warning result according to the trigger identification result.

[0055] Specifically, the first drying monitoring result obtained in step S4, such as the humidity value, temperature value or drying state of the surface layer, is obtained, and then the second drying monitoring result obtained in step S5, such as the humidity and temperature at different depth nodes inside, is obtained. These data are then combined, for example, a data matrix can be constructed, in which rows represent different monitoring positions (surface layer and different depth nodes), and columns represent drying-related data such as humidity and temperature. This combined data matrix is ​​the deep drying data. The deep drying data can fully reflect the drying conditions of the plastic foam particles from the surface layer to the inside.

[0056] The deep drying data is analyzed based on the deep balanced drying constraint. The deep balanced drying constraint limits the temperature and humidity range at different depths inside. If the temperature and humidity values ​​at this location in the deep drying data exceed this range, it means that the constraint condition is not met. Each relevant data in the deep drying data is compared and analyzed with each condition of the deep balanced drying constraint one by one to determine the degree of deviation between the deep drying data and the deep balanced drying constraint, and obtain the trigger identification result. The trigger identification result is used as the first monitoring and early warning result.

[0057] Furthermore, step S8 of the embodiment of the present application also includes: Step S81: If the first monitoring warning result is a non-warning result and the second monitoring warning result is a warning result, temperature control compensation and air circulation compensation are generated.

[0058] Step S82: Outputting the temperature control compensation and the air circulation compensation as a joint early warning alarm.

[0059] Specifically, when the first monitoring warning result is a non-warning result, and the second monitoring warning result is a warning result, it means that from the perspective of deep drying monitoring, the drying process of the plastic foam particle coating is in a normal state, but there are problems in the surface drying process. At this time, it is necessary to generate temperature control compensation and air circulation compensation. Temperature control compensation is a compensatory adjustment measure for temperature in order to improve the drying process. It is used to optimize the temperature according to the warning results to make the drying process go better. Air circulation compensation is an adjustment measure for air circulation conditions, which improves the drying effect by changing the flow state of air (such as flow rate, flow direction, etc.).

[0060] For example, for temperature compensation, if the ambient temperature is too high or too low, resulting in an abnormal drying rate, the temperature control setting of the drying equipment needs to be adjusted. For example, if it is detected that the surface temperature rises too quickly, the temperature needs to be lowered to avoid over-drying. If the temperature and humidity gradient is too large, resulting in the ineffective removal of the inner layer moisture, it is necessary to promote the discharge of the inner layer moisture by adjusting the wind speed or increasing air circulation to ensure the uniformity of the drying process.

[0061] The generated temperature control compensation and air circulation compensation are issued as a joint early warning. For example, if the drying process is abnormal, it is recommended to perform temperature control compensation to increase the temperature by 5°C; at the same time, perform air circulation compensation to increase the fan speed to 1200 rpm. This joint early warning can provide operators with clear adjustment directions so that they can take corresponding measures to improve the drying process of plastic foam particle coating.

[0062] Furthermore, the method described in the embodiment of the present application also includes: Step S83: If the first monitoring warning result and the second monitoring warning result are both warning results, the warning abnormality level is matched according to the warning values ​​of the first monitoring warning result and the second monitoring warning result.

[0063] Step S84: The matched warning abnormality level is issued as a joint early warning alarm.

[0064] Specifically, when the first monitoring and early warning result and the second monitoring and early warning result are both early warning results, it is first necessary to obtain the early warning values ​​in the two results. The early warning value in the first monitoring and early warning result is calculated based on the degree of deviation between the deep drying data and the deep balanced drying constraint. For example, the degree of deviation is 30%, and the corresponding early warning value is 0.3; the early warning value in the second monitoring and early warning result is obtained based on a comprehensive evaluation of the adaptation recognition result and the rate recognition result. Then, according to the pre-set matching rules, the two early warning values ​​are comprehensively considered to match the early warning abnormality level. Exemplarily, the set rule can be that when the sum of the two warning values ​​is less than 0.5, it is a mild warning, between 0.5 and 0.8, it is a moderate warning, and when it is greater than 0.8, it is a severe warning.

[0065] The matched warning abnormality levels are issued as a joint early warning alarm so that operators can quickly understand the severity of the problems in the drying process and take appropriate countermeasures.

[0066] Furthermore, the method described in the embodiment of the present application also includes: Step S91: Record the joint warning and establish a warning database.

[0067] Step S92: Perform bias analysis of warning triggering through the warning database and establish bias feedback.

[0068] Step S93: Perform control correction management of plastic foam particle coating and drying based on the bias feedback.

[0069] Specifically, each time a joint warning is generated, the detailed information of the joint warning is recorded, including the time when the warning occurred, the warning abnormality level, the specific values ​​or states in the first monitoring warning result and the second monitoring warning result, etc. This information is stored in a relational database (such as MySQL) to establish an early warning database.

[0070] Extract data from the early warning database and analyze the relationship between early warning triggers and different factors. Data mining techniques (such as association rule mining) or simple statistical analysis methods can be used to count the frequency of occurrence of different factors (temperature, humidity, air circulation, etc.) when early warnings occur, and calculate the probability of early warnings under different combinations of factors. Based on the analysis results, identify long-standing operational bias problems and establish bias feedback to remind operators to adjust the settings of the drying process in similar situations. For example, the early warning database shows that during multiple drying processes, the temperature is set to 85°C and the "surface layer dries too quickly" warning is repeatedly triggered. Then, bias feedback can be obtained: a temperature of 85°C may cause drying to be too fast, and it is recommended to lower the temperature.

[0071] According to the historical warning data and bias analysis results, the control parameters of the drying equipment (such as temperature, humidity, wind speed, etc.) are adjusted accordingly. For example, if the bias feedback indicates that the problem of uneven drying occurs frequently at certain temperatures, the temperature setting will be automatically adjusted to avoid triggering the same warning again. If the bias feedback indicates that a certain environmental condition (such as high humidity and low wind speed) always leads to incomplete removal of deep moisture, it can be compensated by increasing air circulation or adjusting the temperature and humidity settings. Through targeted control and correction management, the efficiency and quality of plastic foam particle coating drying can be improved and the frequency of warnings can be reduced.

[0072] In summary, the method for monitoring the coating and drying state of plastic foam particles based on intelligent sensors provided in the embodiments of the present application has the following technical effects: By reading the data of plastic foam particle coating, a twin model is constructed. This model can accurately reflect the various characteristics of plastic foam particle coating and provide an accurate data basis for subsequent drying fitting and other operations. The twin model is used for drying fitting to obtain the deep balanced drying constraint, which provides a theoretical basis for drying monitoring and avoids over-drying or insufficient drying. The temperature and humidity sensors are called to monitor the temperature and humidity of the drying space, establish environmental data, and provide real-time basic information for the analysis and optimization of the drying process. The surface monitoring of plastic foam particle coating is carried out based on the surface sensor, and the drying information of the coating surface is directly obtained to establish the first drying monitoring result; the deep node is configured based on the twin model, and the wireless sensor network is deployed at the deep node to establish the second drying monitoring result. Complementing with the surface monitoring, it can more comprehensively understand the overall drying situation and further improve the accuracy of monitoring. Analyze the data of various sensors, combine the deep balanced drying constraint, and generate drying monitoring warnings in real time, including the first monitoring warning results and the second monitoring warning results, which provide important auxiliary decision-making for process control and reduce the quality problems caused by unsatisfactory drying conditions. The first monitoring and early warning result and the second monitoring and early warning result are jointly issued as an early warning, and the reliability of the monitoring result is enhanced through a multiple early warning mechanism.

[0073] Overall, the embodiment of the present application realizes comprehensive, accurate and real-time monitoring and early warning of the drying state of plastic foam particles by constructing a twin model, deep balanced drying constraints, multi-level sensor monitoring and real-time early warning mechanism. It not only improves the accuracy and reliability of monitoring the drying process, but also can timely discover abnormal conditions in the drying process, provide data support for drying strategy optimization, avoid quality fluctuations in the drying process, and help reduce energy waste and resource consumption.

[0074] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring the drying state of plastic foam particles based on intelligent sensors, characterized in that: The method comprises: Performing three-dimensional modeling on the plastic foam particle coating to construct a twin model, wherein the twin model is constructed by reading data of the plastic foam particle coating; Based on the twin model, dry fitting of plastic foam particle coating is performed to establish deep balanced drying constraints; After the plastic foam particles are coated and dried, the temperature and humidity sensors are called to monitor the temperature and humidity of the drying space and establish environmental data; The surface layer of the plastic foam particles is monitored based on the surface sensor to establish the first drying monitoring result; Based on the twin model, deep nodes are configured, wireless sensor networks are deployed at the deep nodes, and the second drying monitoring results are established; Perform dryness monitoring and early warning using the depth balance dryness constraint and the first dryness monitoring result and the second dryness monitoring result to establish a first monitoring and early warning result; Performing surface drying analysis using the environmental data and the first drying monitoring result to establish a second monitoring and early warning result; The first monitoring and early warning result and the second monitoring and early warning result are combined for early warning output.

2. The method for monitoring the drying state of plastic foam particles based on intelligent sensors according to claim 1, characterized in that: The method of performing dry fitting of plastic foam particle coating based on the twin model and establishing deep balanced dry constraints includes: Obtain depth data based on the twin model, input the depth data into the grid density distribution channel, and establish a calibrated grid density; Use the calibrated mesh density to perform finite element meshing of the twin model and establish a finite element unit set; Establish the surface-deep direction for the finite element unit set, and set the heat conduction parameters and humidity diffusion parameters based on the data of the plastic foam particle coating; The surface-deep direction, the heat conduction parameters, and the humidity diffusion parameters are used to fit the heat conduction and humidity diffusion of each unit in the finite element unit set, a temperature and humidity gradient is established according to the fitting results, and a deep balanced drying constraint is created based on the temperature and humidity gradient and the surface-deep direction.

3. The method for monitoring the drying state of plastic foam particles based on intelligent sensors according to claim 1, characterized in that: The configuration of the deep node based on the twin model includes: Acquire a set monitoring accuracy of the plastic foam particle coating, and generate a first configuration constraint according to the set monitoring accuracy, wherein the first configuration constraint is a distribution quantity constraint; Performing constraint gradient analysis on the depth balanced drying constraint, and establishing a second configuration constraint based on the constraint gradient analysis result, wherein the second configuration constraint is a density distribution constraint; The depth node is configured based on the first configuration constraint and the second configuration constraint.

4. The method for monitoring the drying state of plastic foam particles based on intelligent sensors according to claim 1, characterized in that: The using the environmental data and the first drying monitoring result to perform surface drying analysis and establish a second monitoring and early warning result includes: Performing environmental drying fitting based on the twin model to establish an environmental adaptation model; Inputting the environmental data and the first drying monitoring result into an environmental adaptation model to establish an adaptation identification result; Performing drying rate identification on the first drying monitoring result to establish a rate identification result; A second monitoring and early warning result is established according to the adaptation identification result and the rate identification result.

5. The method for monitoring the drying state of plastic foam particles based on intelligent sensors according to claim 1, characterized in that: The step of performing dryness monitoring and early warning using the deep balanced dryness constraint and the first dryness monitoring result and the second dryness monitoring result to establish a first monitoring and early warning result includes: Establishing deep drying data using the first drying monitoring result and the second drying monitoring result; Perform drying constraint trigger identification of the deep drying data based on the deep balanced drying constraint, and establish a trigger identification result; A first monitoring and early warning result is established based on the trigger identification result.

6. The method for monitoring the drying state of plastic foam particles based on intelligent sensors according to claim 1, characterized in that: The step of performing a joint early warning output of the first monitoring and early warning result and the second monitoring and early warning result comprises: If the first monitoring and early warning result is a no-warning result and the second monitoring and early warning result is a warning result, then generating temperature control compensation and air circulation compensation; The temperature control compensation and the air circulation compensation are output as a joint early warning alarm.

7. The method for monitoring the drying state of plastic foam particles based on intelligent sensors according to claim 6, characterized in that: The method further comprises: If the first monitoring warning result and the second monitoring warning result are both warning results, matching the warning abnormality level according to the warning values ​​of the first monitoring warning result and the second monitoring warning result; The matched warning anomaly levels are issued as joint early warning alarms.

8. The method for monitoring the drying state of plastic foam particles based on intelligent sensors according to claim 1, characterized in that: The method further comprises: Keep early warning records for joint early warning and establish an early warning database; Perform bias analysis of warning triggering through the warning database and establish bias feedback; Based on the bias feedback, control correction management of plastic foam particle coating and drying is performed.

Images