Adhesive mixing reaction equipment design method based on industrial big data

Abstract

The present invention relates to the technical field of product design methods, and specifically to a method for designing adhesive mixing reaction equipment based on industrial big data, including: dividing the mixing reaction process into stages according to the set stage, determining the target state characteristics of each stage; performing numerical simulation analysis on the rationality of the target state characteristics of each stage; obtaining discrete state process control quantities based on each target state characteristic; designing the distribution scheme of equipment sensors based on each state process control quantity, and designing the structural characteristics of the equipment based on each target state characteristic. The present invention can foresee the performance of the equipment in the early stage of design, avoiding waste of time and resources; by establishing standardized target state characteristics, each module can be more efficient in the later equipment integration, reducing the debugging time and complexity of the overall equipment; through the design of the sensor system and the state process control quantity, the equipment can monitor key parameters in real time and provide instant feedback.

Description

Technical Field

[0001] The present invention relates to the technical field of product design methods, and in particular to a method for designing adhesive mixing reaction equipment based on industrial big data. Background Art

[0002] At present, the design of adhesive mixing reaction equipment is often based on the existing equipment solution, which is improved through appropriate calculations and product design experience to obtain a new equipment solution, and the final equipment form is obtained through trial production and adjustment.

[0003] In the design process of the above scheme, the following problems exist:

[0004] After obtaining equipment for actual use through trial production and debugging, it is often accompanied by waste of equipment size, power, etc., and it is impossible to achieve optimal equipment cost control; the raw material supply system, mixing system, reaction system, homogenization and discharge system, and sensor system in the adhesive mixing reaction equipment often need to be improved independently, and the complete set of equipment formed after the improvement is adapted to the required adhesive mixing reaction process, which often requires multiple adjustments. In particular, the design of the sensor system is often added based on the problems that occur, and it often takes a longer time to achieve a better layout result.

[0005] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides a method for designing adhesive mixing reaction equipment based on industrial big data, thereby effectively solving the problems pointed out in the background technology.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is:

[0008] An adhesive mixing reaction equipment design method based on industrial big data, wherein the adhesive mixing reaction equipment includes a raw material supply system, a mixing system, a reaction system, a homogenization and discharge system, and a sensor system;

[0009] Design methods include:

[0010] Divide the stage according to the set mixing reaction process of the adhesive, and determine the target state characteristics of each stage, wherein the stage at least includes a raw material feeding stage, a mixing stage, a reaction stage, and a homogenization and discharge stage;

[0011] Through historical production data and experimental data, the rationality of the target state characteristics of each stage is numerically simulated and analyzed, and the target state characteristics are adjusted according to the analysis results until the set standards are met;

[0012] Obtaining discrete state process control quantities based on each of the target state characteristics;

[0013] Based on the process control quantities of each state, a distribution plan of equipment sensors is designed, and based on the characteristics of each target state, the structural characteristics of the equipment are designed.

[0014] Furthermore, based on each of the target state characteristics, a discrete state process control quantity is obtained, including:

[0015] Extracting measurable parameter types and target values ​​from the target state characteristics;

[0016] Identifying a change curve of each of the measurable parameters in a corresponding stage based on historical production data, wherein the change curve passes through the target value;

[0017] The variation curve is discretized in a piecewise linear manner, and the continuous variation trend is converted into discrete data points, and the data points are used as state process control quantities.

[0018] Furthermore, identifying the change curve of each measurable parameter in the corresponding stage based on the historical production data includes:

[0019] Determine the historical production data within the corresponding time range according to the stage that needs to be analyzed;

[0020] By analyzing the time series of historical production data within the time range, the data points of each measurable parameter within the time range are plotted into a curve;

[0021] The curve trend is mapped within the corresponding stage and passes through the target value.

[0022] Furthermore, the curve trend is smoothed using a linear regression or moving average method.

[0023] Furthermore, in the piecewise linear process, the number of segments of each of the measurable parameters is proportional to the following weights:

[0024] ;

[0025] W i is the weight of the measurable parameter i;

[0026] R i The reliability score of measurable parameter i is determined by comprehensive judgment of data source, data integrity and historical stability;

[0027] I i is the importance score of measurable parameter i, which is determined by combining expert evaluation and historical importance;

[0028] j represents the total number of all measurable parameters.

[0029] Furthermore, measurable parameter types and target values ​​are extracted from the target state characteristics, including:

[0030] List multiple parameters, evaluate the correlation between each parameter and the target state feature, and select the set ratio parameter with the highest correlation with the target state feature;

[0031] Selecting a measurable parameter from among the set proportional parameters;

[0032] According to the correlation evaluation results of the measurable parameters, a deviation range of the target value is set for the measurable parameter, the deviation range is negatively correlated with the correlation evaluation result, and the deviation range is positively correlated with the measurement error of the sensor.

[0033] Furthermore, through historical production data and experimental data, numerical simulation analysis is performed on the rationality of the target state characteristics of each stage, including:

[0034] Collecting the historical production data and experimental data and cleaning them;

[0035] Determine the numerical simulation tools according to the different forms of target state characteristics;

[0036] Execute a numerical simulation process and obtain numerical simulation results;

[0037] The numerical simulation results are compared with the set target standards to analyze the rationality of the target state characteristics.

[0038] Furthermore, based on each state process control quantity, a distribution scheme of equipment sensors is designed, including:

[0039] Divide the physical space of the equipment into different sections according to the process, and mark the boundaries of each section on the number axis;

[0040] marking the physical location on the device by specific coordinates on the number axis in each of the segments;

[0041] Construct a sensor matrix, where the rows of the matrix represent the types of sensors and the columns represent the positions of the sensors on the numerical axis;

[0042] An index relationship between a number axis and a sensor matrix is ​​established, and the number axis, the matrix and the index relationship together serve as the distribution scheme.

[0043] Furthermore, the index relationship includes an index relationship between a numerical axis coordinate and a matrix column, and an index relationship between a sensor type and a state process control quantity.

[0044] Furthermore, based on the target state characteristics, the structural characteristics of the device are designed, including:

[0045] According to the target state characteristics of each stage, clarify the functional requirements of each system of the equipment;

[0046] Design the size and shape of each system according to the functional requirements;

[0047] According to the size and shape, material selection and strength calculation, and / or heat transfer design, and / or fluid flow design are performed to obtain preliminary design results;

[0048] Based on the preliminary design results, CAE tools are used to simulate the equipment as a whole.

[0049] The technical solution of the present invention can achieve the following technical effects:

[0050] The present invention reduces human randomness and errors through a design method based on industrial big data. Through the target state characteristics of the numerical simulation analysis stage, it can predict the performance of the equipment in the early design stage, avoiding the waste of time and resources caused by a large number of trial production and debugging in the later stage. This method can identify potential problems earlier and make optimization adjustments, thereby achieving high efficiency of the design.

[0051] Through systematic design, we ensure the best fit and performance of each component in the overall equipment, reduce waste in equipment size and power, and clarify the target state characteristics of each system in the design, which will help achieve higher resource utilization in the production process and thus reduce costs. By establishing standardized target state characteristics, modular design can be carried out more flexibly. This design method not only simplifies the improvement process, but also makes each module more efficient in later equipment integration, reducing the debugging time and complexity of the overall equipment. Through the design of sensor systems and state process control quantities, the equipment can monitor key parameters in real time and provide instant feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1Flowchart of the method for designing adhesive mixing reaction equipment based on industrial big data;

[0054] Figure 2 A flow chart for obtaining discrete state process control quantities based on the characteristics of each target state;

[0055] Figure 3 A flow chart for identifying the change curve of each measurable parameter in the corresponding stage based on historical production data;

[0056] Figure 4 A flowchart for extracting the types of measurable parameters and target values ​​from target state characteristics;

[0057] Figure 5 A flowchart for numerical simulation analysis of the rationality of target state characteristics at each stage using historical production data and experimental data;

[0058] Figure 6 A flow chart for designing a distribution scheme for equipment sensors based on the process control quantities of each state;

[0059] Figure 7 A flow chart for designing the structural characteristics of the equipment based on the characteristics of each target state. DETAILED DESCRIPTION

[0060] The technical solutions in the embodiments of the present invention will be described clearly and completely 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, rather than all the embodiments.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0062] like Figure 1 As shown in the figure, the adhesive mixing reaction equipment design method based on industrial big data, the adhesive mixing reaction equipment includes a raw material supply system, a mixing system, a reaction system, a homogenization and discharge system and a sensor system; the design method includes:

[0063] A1: Divide the stages according to the set mixing reaction process of the adhesive and determine the target state characteristics of each stage. The stages at least include the raw material feeding stage, mixing stage, reaction stage, homogenization and discharge stage;

[0064] A2: Through historical production data and experimental data, numerical simulation analysis is performed on the rationality of the target state characteristics at each stage, and the target state characteristics are adjusted according to the analysis results until the set standards are met;

[0065] A3: Based on the characteristics of each target state, obtain the discrete state process control quantity;

[0066] A4: Design the distribution plan of equipment sensors based on the process control quantity of each state, and design the structural characteristics of the equipment based on the characteristics of each target state.

[0067] In this embodiment, the raw material feeding stage is mainly responsible for feeding each component raw material into the mixer according to the set ratio, and the target state characteristics may include the precise ratio of the raw materials, the feeding rate, etc.; in the mixing stage, the component raw materials are fully mixed through the mixer, and the target state characteristics may include mixing uniformity, mixing time, stirring speed, etc.; in the reaction stage, the chemical reaction of the adhesive begins to occur, and the target state characteristics may include reaction temperature, reaction time, reaction rate, reaction completion, etc.; in the final stage, the mixture is homogenized to ensure the consistency of the product and discharged from the equipment. The target state characteristics of the homogenization and discharge stage may include homogenization effect, discharge speed, product viscosity, etc.

[0068] During the implementation process, numerical simulation tools (such as CFD, FEM, etc.) can be used to analyze the target state characteristics of each stage. During the simulation process, calculations in fluid mechanics, thermodynamics, chemical reaction kinetics, etc. are often involved. In the simulation, it is verified whether the set target state of each stage is reasonable and whether the expected mixed reaction effect can be achieved. If the simulation results deviate from expectations, the target state characteristics can be adjusted according to the simulation feedback, and the simulation can be re-iterated until the set standards are met. Based on the reasonable target state characteristics, the target state characteristics of each stage are converted into measurable and controllable state process quantities, such as temperature, pressure, flow, viscosity, etc.; these state quantities usually change continuously, but in order to facilitate control and detection, they need to be discretized and decomposed into discrete data points that can be monitored in actual equipment. These discrete data points will be used in the process control system of the actual equipment to provide real-time feedback and adjustment basis for the operation of each stage.

[0069] In view of the final design goal, sensors are arranged according to the discrete points of the state process control quantity to ensure that each key parameter can be monitored in real time during the operation of the equipment. The distribution of sensors needs to consider their respective response speed, accuracy and matching degree with the mixing reaction process; based on the target state characteristics of each stage, the specific structure of the equipment is designed, such as the shape and size of the mixer, the type of stirring blades, the volume of the reactor, the layout of the heat transfer device, etc. The structural design should ensure that the equipment can operate efficiently in actual production and is easy to maintain and operate.

[0070] In this embodiment, a design method based on industrial big data is used to reduce human randomness and errors. Through the target state characteristics of the numerical simulation analysis stage, the performance of the equipment can be predicted in the early stage of design, avoiding the waste of time and resources caused by a large number of trial production and debugging in the later stage. This method can identify potential problems earlier and make optimization adjustments, thereby achieving high efficiency of the design.

[0071] Through systematic design, we ensure the best fit and performance of each component in the overall equipment, reduce waste in equipment size and power, and clarify the target state characteristics of each system in the design, which will help achieve higher resource utilization in the production process and thus reduce costs. By establishing standardized target state characteristics, modular design can be carried out more flexibly. This design method not only simplifies the improvement process, but also makes each module more efficient in later equipment integration, reducing the debugging time and complexity of the overall equipment. Through the design of sensor systems and state process control quantities, the equipment can monitor key parameters in real time and provide instant feedback.

[0072] As a preferred embodiment of the above, Figure 2 As shown, based on the characteristics of each target state, discrete state process control quantities are obtained, including:

[0073] B1: Extract the types of measurable parameters and target values ​​from the target state characteristics; ensure that key parameters can be monitored in real time during the adhesive mixing reaction process, and through clear target values, operators can accurately understand the expected value of each parameter; for example, in the raw material feeding stage, the measurable parameters include raw material ratio, feeding rate, raw material temperature, etc. The target value is the specific ratio of each component (such as the ratio of A to B), feeding rate (such as how many grams per minute), and raw material feeding temperature (such as 20°C);

[0074] B2: Based on historical production data, the change curve of each measurable parameter in the corresponding stage is identified, where the change curve passes through the target value; the analysis based on historical production data enhances the reliability of decision-making and reduces the risk caused by lack of experience. During the processing, it is ensured that the change curve matches the preset target value, and that the key parameters are monitored and controlled to the target value in real time during the production process. During the control process, deviations can be quickly identified and corrected to keep the production process in the best state;

[0075] B3: The change curve is discretized by piecewise linear method, and the continuous change trend is converted into discrete data points, which are used as state process control quantities.

[0076] This preferred solution can effectively monitor key parameters during the adhesive mixing reaction process, thereby ensuring the high efficiency and stability of the production process.

[0077] As a preferred embodiment of the above, Figure 3 As shown, based on historical production data, the change curves of each measurable parameter in the corresponding stage are identified, including:

[0078] B21: Determine the historical production data within the corresponding time range according to the stage to be analyzed;

[0079] B22: Through time series analysis of historical production data within a time range, the data points of each measurable parameter within the time range are plotted into a curve;

[0080] B23: Map the curve trend within the corresponding stage and pass through the target value.

[0081] In this preferred solution, by mapping the curve trend obtained by drawing the actual historical data to the corresponding production stage and making the curve trend pass through the set target value, it is ensured that each parameter can move closer to the expected target according to the trend of historical data during the production process, and the relationship between the historical data and the set target state characteristics is coordinated. This goal-oriented design enables the production process to have clear control standards.

[0082] Among them, the curve trend is smoothed using linear regression or moving average method to eliminate short-term fluctuations, reduce the impact of noise, improve the interpretability of data, and enhance goal-oriented trends.

[0083] As a preference of the above embodiment, in the piecewise linear process, the number of segments of each measurable parameter is proportional to the following weight:

[0084] ;

[0085] W i is the weight of the measurable parameter i;

[0086] R i The reliability score of measurable parameter i is determined by data source, data integrity and historical stability. The data source may include whether the data comes from reliable sensors, experimental results or other sources. Generally speaking, the more reliable the source, the higher the score. Data integrity refers to whether the data set is complete and whether there are missing values ​​or outliers. Parameters with high data integrity will often receive higher scores. Historical stability indicates whether the performance of the parameter in past production was stable. Parameters with stable historical performance usually receive higher reliability scores.

[0087] I iis the importance score of measurable parameter i, which is judged by expert evaluation and historical importance. Domain experts give scores based on the impact of parameters on product quality, reaction efficiency, etc. By analyzing historical data, they identify which parameters have the greatest impact on the final result in actual production, and thus give these parameters higher scores.

[0088] j represents the total number of all measurable parameters.

[0089] When the weight of a measurable parameter is higher, the number of its segments will increase accordingly, which means that more sensors are needed to monitor the different states of the parameter. This method ensures detailed monitoring of key parameters and can capture changes in a timely manner. Detailed monitoring of high-weight parameters can ensure that the system can quickly feedback and adjust the control strategy. For example, if inhomogeneity is detected in a segment of the mixing stage, the system can take immediate measures to adjust the stirring speed or time.

[0090] In summary, by setting the number of segments of each parameter in positive correlation with the weight, the monitoring capability of key parameters can be effectively improved. This setting not only improves the efficiency of sensor layout and the accuracy of data acquisition, but also enhances the flexibility and scientificity of process control, and ultimately promotes the stability of the adhesive mixing reaction process and the consistency of product quality.

[0091] As a preferred embodiment of the above, Figure 4 As shown, measurable parameter types and target values ​​are extracted from target state characteristics, including:

[0092] C1: List multiple parameters, evaluate the correlation between each parameter and the target state characteristics, and select the set proportion parameters with the highest correlation with the target state characteristics; this correlation can be achieved by calculating the Pearson correlation coefficient;

[0093] C2: Select the measurable parameter in the set ratio parameter;

[0094] C3: According to the correlation evaluation results of each measurable parameter, a deviation range of the target value is set for the measurable parameter. The deviation range is negatively correlated with the correlation evaluation result, and positively correlated with the measurement error of the sensor.

[0095] In this preferred embodiment, the correlation assessment not only helps to screen out the parameters that have a greater impact on the target state characteristics, ensuring that the most important parameters are controlled and monitored first, thereby optimizing the design of the equipment and process control, but also can further set a reasonable deviation range for the target value of each parameter. The deviation range is not a simple fixed range, but is determined based on the correlation between the parameter and the target state characteristics. That is, parameters with high correlation may require stricter deviation ranges, while parameters with low correlation allow for a wider range. This differentiated setting ensures the flexibility and accuracy of the production process.

[0096] The correlation evaluation results can directly guide the measurement error setting of the sensor. For high-correlation parameters, lower measurement error requirements can ensure accurate monitoring and prevent deviations of key parameters due to excessive sensor errors, which can affect production quality and efficiency. For low-correlation parameters, a higher error range can be allowed to reduce the requirements for unnecessary accuracy, thereby reducing the sensor configuration cost and ensuring that the system achieves the best balance between accuracy and cost.

[0097] In summary, for key parameters that have a greater impact on target state characteristics, the correlation evaluation results can help set more precise target values ​​and deviation ranges, and achieve accurate monitoring through precision-optimized sensors, which can effectively improve the stability of the production process and reduce product quality fluctuations.

[0098] As a preferred embodiment of the above, Figure 5 As shown, through historical production data and experimental data, the rationality of the target state characteristics of each stage is numerically simulated and analyzed, including:

[0099] D1: Collect historical production data and experimental data, and clean them;

[0100] D2: Determine the numerical simulation tools according to the different forms of target state characteristics;

[0101] D3: Execute the numerical simulation process and obtain the numerical simulation results;

[0102] D4: Compare the numerical simulation results with the set target standards to analyze the rationality of the target state characteristics.

[0103] During the implementation of this preferred solution, data is the basis of numerical simulation analysis. Ensuring the quality of data is the key to the success of simulation analysis. Historical production data can reflect the operation of equipment in a real environment, while experimental data can be used to supplement the deficiencies of historical data. Cleaning data can remove noise and outliers to ensure the accuracy and consistency of data. Invalid, erroneous or incomplete data will affect the accuracy of simulation results. Different process stages and target state characteristics require different simulation tools. For example, fluid mechanics problems may require the use of CFD (computational fluid dynamics) tools, while FEM (finite element analysis) tools may be selected when it comes to structural and stress analysis. Choosing the right simulation tool is the key to ensuring accurate simulation results. In this preferred solution, the target standard can be set according to demand.

[0104] As a preferred embodiment of the above, Figure 6 As shown, based on the process control quantity of each state, the distribution scheme of equipment sensors is designed, including:

[0105] A41: Divide the physical space of the equipment into different sections according to the process, and mark the boundaries of each section on the number axis;

[0106] A42: Mark the physical location on the device with specific coordinates on the number axis in each section;

[0107] A43: Construct a sensor matrix, where the rows represent the types of sensors and the columns represent the positions of the sensors on the axis;

[0108] A44: Establish an index relationship between the number axis and the sensor matrix. The number axis, matrix and index relationship together serve as a distribution scheme.

[0109] During the implementation process, the boundaries of each section can be marked on the number axis to clarify the start and end positions of each process stage. For example, positions 0 to 1 on the number axis represent raw material delivery, 1 to 2 represent mixing, 2 to 3 represent reaction, and so on; in each section, the specific physical position of the equipment is marked, for example, a certain position can be the center point of the mixing tank, the entrance, exit, discharge port and other key parts of the reaction chamber. These coordinates on the number axis represent the actual physical space of each position in the equipment, which is convenient for locating the installation position of the sensor. These position marks can help accurately determine the physical points where the sensors are installed, ensuring that the layout of each sensor is consistent with the actual requirements of the production process. In this preferred solution, the sensor matrix can intuitively display the type of sensor and its function at each position; the index relationship makes the distribution plan of the sensor more systematic, easy to query and adjust, and any changes in physical position or process requirements can be quickly reflected in the sensor layout through the index relationship.

[0110] The use of the number axis combines the physical space of the equipment with the production process stage, clearly expressing the location of each section, making the planning of sensor layout clearer, and displaying the layout of different types of sensors at each location through the matrix, making the management and query of sensor distribution information more systematic. Through this combination of the number axis and matrix based on the process flow, the distribution of sensors can be better optimized, ensuring that the monitoring points of the key process stages are reasonably laid out, avoiding sensor redundancy or monitoring blind spots, improving the utilization of sensor resources, and having good scalability.

[0111] Among them, the index relationship includes the index relationship between the axis coordinates and the matrix columns, and the index relationship between the sensor type and the state process control quantity. Specifically, each coordinate point on the axis, such as 0, 1, 2, etc., is mapped to the column in the matrix through the index relationship to indicate which sensors should be installed at that position; for example, the position coordinate 0 on the axis represents the raw material delivery port, then the first column in the matrix represents the "raw material delivery port", and all sensors installed at the raw material delivery port will be listed in this column; the position coordinate 2 on the axis represents the reaction chamber entrance of the reaction stage, then the third column in the matrix represents the sensor layout at the reaction chamber entrance.

[0112] A direct index relationship is established between the sensor type and the monitored state process control quantity, that is, the physical location where each sensor is installed and the specific process control quantity monitored are also indicated in the matrix, so as to clearly show the role of the sensor. For example, the temperature sensor is at the entrance of the reaction chamber at the numerical axis coordinate 2 (the third column of the matrix), and its indexed state process control quantity is "temperature monitoring"; the pressure sensor is at the mixing tank at the numerical axis coordinate 1 (the second column of the matrix), and its indexed state process control quantity is "pressure monitoring".

[0113] As a preferred embodiment of the above, Figure 7 As shown, based on the characteristics of each target state, the structural characteristics of the design equipment include:

[0114] A45: According to the target state characteristics of each stage, clarify the functional requirements of each system of the equipment;

[0115] A46: Design the size and shape of each system based on functional requirements;

[0116] A47: Carry out material selection and strength calculation, and / or heat transfer design, and / or fluid flow design for size and shape to obtain preliminary design results;

[0117] A48: Based on the preliminary design results, use CAE tools to simulate the equipment as a whole.

[0118] The target state characteristics of each stage (such as temperature, pressure, flow, mixing uniformity, reaction time, etc.) define the functions that the equipment in this stage needs to have. For example, in the raw material feeding stage, the raw materials need to be accurately fed and automatically proportioned to ensure the quantitative input and flow control of the raw materials; according to the specific functional requirements, the preliminary design of the equipment structure is carried out for each system, and its key parameters such as size and shape are determined to ensure that it meets the target state characteristics. For example, the size of the feed port and the diameter of the feed pipe are determined to ensure that the material can be transported on demand and prevent blockage, the size and shape of the mixing tank are designed to ensure that the mixing blades can effectively cover the mixing area and ensure mixing uniformity, the type and number of mixing blades are determined, and the volume and shape of the reactor are designed to ensure that the materials in the reaction process have enough space for sufficient chemical reactions.

[0119] Select equipment materials, perform structural strength analysis, heat transfer design and fluid dynamics design to ensure that the equipment can withstand the expected process conditions and operate efficiently. Specifically:

[0120] Material selection: Select appropriate materials based on the process conditions of each system, such as temperature, pressure, corrosiveness, etc. For example, the mixing tank may require stainless steel material to prevent corrosion, while the reactor may require high temperature resistant material.

[0121] Strength calculation: Structural mechanics calculations are performed to ensure that the equipment can operate under high temperature and pressure conditions without structural failure. For example, by calculating the reactor wall thickness, it is ensured that it will not break under high pressure.

[0122] Heat transfer design: Design heat transfer systems, such as external heating jackets or internal cooling pipes, to control the temperature during the reaction stage, ensuring that the reaction temperature can be maintained within the set range.

[0123] Fluid dynamics design: Conduct fluid dynamics analysis (such as CFD calculation) for stages involving flow (such as raw material supply, discharge, etc.) to ensure that the flow rate and flow rate of the fluid meet the process requirements and avoid blockage or uneven flow.

[0124] During the implementation process, specific simulation content may include verifying whether the equipment will deform or rupture under production conditions, ensuring the safety and reliability of the equipment, checking the efficiency of the heating or cooling system, ensuring that the temperature can be stably controlled within a predetermined range, simulating the flow of fluid in the equipment, ensuring that the flow rate and flow rate meet the design expectations, and optimizing the flow path to reduce energy loss or blockage risks. According to the simulation results, adjust the unreasonable aspects of the equipment design and re-simulate until the design meets all process and safety requirements.

[0125] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. The design method of adhesive mixing reaction equipment based on industrial big data is characterized by: The adhesive mixing reaction equipment includes a raw material supply system, a mixing system, a reaction system, a homogenization and discharge system and a sensor system; Design methods include: Divide the stage according to the set mixing reaction process of the adhesive, and determine the target state characteristics of each stage, wherein the stages at least include a raw material feeding stage, a mixing stage, a reaction stage, and a homogenization and discharge stage; Through historical production data and experimental data, the rationality of the target state characteristics of each stage is numerically simulated and analyzed, and the target state characteristics are adjusted according to the analysis results until the set standards are met; Based on each of the target state characteristics, a discrete state process control quantity is obtained, including: Extracting measurable parameter types and target values ​​from the target state characteristics; Identifying a change curve of each of the measurable parameters in a corresponding stage based on historical production data, wherein the change curve passes through the target value; The change curve is discretized in a piecewise linear manner, and the continuous change trend is converted into discrete data points. The data points are used as state process control quantities. In the piecewise linear process, the number of segments of each measurable parameter is proportional to the following weight: ； W i is the weight of the measurable parameter i; R i The reliability score of measurable parameter i is determined by comprehensive judgment of data source, data integrity and historical stability; I i is the importance score of measurable parameter i, which is determined by combining expert evaluation and historical importance; j represents the total number of all measurable parameters; Based on the state process control quantity, the distribution scheme of the equipment sensors is designed, including: Divide the physical space of the equipment into different sections according to the process, and mark the boundaries of each section on the number axis; marking the physical location on the device by specific coordinates on the number axis in each of the segments; Construct a sensor matrix, where the rows of the matrix represent the types of sensors and the columns represent the positions of the sensors on the numerical axis; Establishing an index relationship between a number axis and a sensor matrix, wherein the number axis, the matrix and the index relationship together serve as the distribution scheme; And based on the characteristics of each target state, the structural characteristics of the equipment are designed.

2. The adhesive mixing reaction equipment design method based on industrial big data according to claim 1 is characterized in that: Based on the historical production data, the change curve of each measurable parameter in the corresponding stage is identified, including: Determine the historical production data within the corresponding time range according to the stage that needs to be analyzed; By analyzing the time series of historical production data within the time range, the data points of each measurable parameter within the time range are plotted into a curve; The curve trend is mapped within the corresponding stage and passes through the target value.

3. The adhesive mixing reaction equipment design method based on industrial big data according to claim 2 is characterized in that: The curve trend is smoothed using linear regression or moving average method.

4. The adhesive mixing reaction equipment design method based on industrial big data according to claim 1 is characterized in that: Extracting measurable parameter types and target values ​​from the target state characteristics includes: List multiple parameters, evaluate the correlation between each parameter and the target state feature, and select the set ratio parameter with the highest correlation with the target state feature; Selecting a measurable parameter from among the set proportional parameters; According to the correlation evaluation result of each of the measurable parameters, a deviation range of the target value is set for the measurable parameter, the deviation range is negatively correlated with the correlation evaluation result, and the deviation range is positively correlated with the measurement error of the sensor.

5. The adhesive mixing reaction equipment design method based on industrial big data according to claim 1 is characterized in that: Through historical production data and experimental data, the rationality of the target state characteristics of each stage is numerically simulated and analyzed, including: Collecting the historical production data and experimental data and cleaning them; Determine the numerical simulation tools according to the different forms of target state characteristics; Execute a numerical simulation process and obtain numerical simulation results; The numerical simulation results are compared with the set target standards to analyze the rationality of the target state characteristics.

6. The adhesive mixing reaction equipment design method based on industrial big data according to claim 1 is characterized in that: The index relationship includes the index relationship between the axis coordinates and the matrix columns, and the index relationship between the sensor type and the state process control quantity.

7. The adhesive mixing reaction equipment design method based on industrial big data according to claim 1 is characterized in that: Based on the characteristics of each target state, the structural characteristics of the device are designed, including: According to the target state characteristics of each stage, clarify the functional requirements of each system of the equipment; Design the size and shape of each system according to the functional requirements; According to the size and shape, material selection and strength calculation, and / or heat transfer design, and / or fluid flow design are performed to obtain preliminary design results; Based on the preliminary design results, CAE tools are used to simulate the equipment as a whole.

Images