Plastic particle batching method and system based on MCGS

Abstract

The present invention discloses a plastic particle batching method and system based on MCGS, which relates to the field of plastic particle processing, including: obtaining plastic particle physical property characteristic data and batching environment parameter data, and constructing a batching physical property correction model, using the batching physical property correction model to perform calculations to obtain an initial corrected batching target value; based on the initial corrected batching target value, obtaining historical batching deviation data and performing preprocessing to obtain processed batching deviation trend data; using the batching deviation trend data to optimize the batching physical property correction model and construct a comprehensive batching prediction model; based on the comprehensive batching prediction model, predicting batching values to obtain final corrected batching values, executing batching operations, and realizing intelligent monitoring and precise batching control of plastic particles. The present invention greatly improves batching stability, significantly outperforming traditional fixed feedback correction, and improves batching accuracy in scenarios with high moisture absorption or strong disturbance.

Description

Technical Field

[0001] The present invention relates to the technical field of plastic particle processing, and in particular to a plastic particle batching method and system based on MCGS. Background Art

[0002] Plastic particle batching technology is an important part of the plastics processing industry. It is widely used in production processes such as injection molding and extrusion to ensure product quality and production efficiency. The batching process requires precise control of the amount of plastic particles to be fed to meet the requirements of different processes for physical properties (such as density, bulk density, and moisture absorption rate), while also responding to interference from environmental factors (such as air flow rate and vibration). Traditional batching methods mostly use control systems based on PLC or DCS, which collect physical parameters and environmental data through sensors and implement batching with simple proportional or PID control algorithms. In recent years, with the improvement of industrial automation levels, batching systems based on MCGS (Monitor and Control Generated System) have gradually been applied to the field of plastic particle processing due to their flexible configuration functions and data processing capabilities.

[0003] Existing plastic particle batching technology has certain limitations in practical applications. Traditional methods mostly rely on linear control models with fixed parameters, which makes it difficult to effectively capture the physical properties of plastic particles (such as the nonlinear interaction between bulk density and moisture absorption rate) and the complex influence of environmental disturbances, resulting in a decrease in batching accuracy under high moisture absorption or strong disturbance scenarios. In addition, existing technologies are usually limited to simple feedback corrections for handling historical batching deviations, and lack dynamic analysis and adaptive optimization of deviation trends (deviation value, change rate, duration). It is difficult to adapt to the diverse needs of different plastic types and process conditions, which limits the intelligence and stability of the batching process. Summary of the Invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing MCGS-based plastic particle batching method and system, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a plastic particle batching method and system based on MCGS, which is suitable for solving the problem that the existing technology for handling historical batching deviations is usually limited to simple feedback correction, is difficult to adapt to the diverse needs of different plastic types and process conditions, and limits the intelligence and stability of the batching process.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a plastic particle batching method based on MCGS, comprising:

[0009] Obtaining plastic particle physical property characteristic data and batching environmental parameter data, and constructing a batching physical property correction model, and using the batching physical property correction model to perform calculations to obtain an initial corrected batching target value;

[0010] Based on the initial corrected batching target value, historical batching deviation data is acquired and pre-processed to obtain processed batching deviation trend data;

[0011] Utilizing the batching deviation trend data to optimize the batching property correction model, a comprehensive batching prediction model is constructed;

[0012] The batching value is predicted based on the comprehensive batching prediction model to obtain the final corrected batching value, and the batching operation is executed to realize intelligent monitoring and precise batching control of plastic particles.

[0013] As a preferred embodiment of the MCGS-based plastic particle batching method of the present invention, obtaining the physical property characteristic data of the plastic particles refers to collecting the density, bulk density, moisture absorption rate and particle size parameters of the plastic particles through sensors;

[0014] Acquiring the plastic particle batching environmental parameter data refers to collecting the ambient temperature, ambient humidity, air flow rate and vibration amplitude parameters at the batching site through sensors.

[0015] As a preferred embodiment of the MCGS-based plastic particle batching method of the present invention, the construction of the batching physical property correction model includes the following steps:

[0016] By introducing a logarithmic function to process the combined effect of bulk density and moisture absorption rate, the physical property correction value is obtained, thereby enhancing the responsiveness of the physical property correction model to high moisture absorption rate or high bulk density scenarios. The specific formula is as follows:

[0017] ;

[0018] in, is the correction value of physical properties, which represents the nonlinear interaction between the bulk density and moisture absorption rate of plastic particles. is the bulk density, is the moisture absorption rate; by introducing a fractional structure to quantify the composite effect of air velocity and vibration amplitude, the environmental disturbance suppression value is obtained, thereby reducing the interference of dynamic disturbances in the batching environment on the batching accuracy. The specific formula is as follows:

[0019] ;

[0020] in, is the environmental disturbance suppression value, which indicates the inhibitory effect of environmental parameters on ingredient correction. is the mean air velocity, is the mean vibration amplitude, is the denominator adjustment coefficient, which is used to control the impact of environmental disturbance on the batching correction. By introducing a linear correction term to process the density difference of plastic particles, the density adjustment value is obtained, thereby improving the adaptability of the batching physical property correction model under different density conditions. The specific formula is as follows:

[0021] ;

[0022] in, is the density adjustment value, which indicates the linear adjustment effect of the density of plastic particles on the target value of the ingredients. is the density of plastic particles, is the density adjustment coefficient, which is used to control the weight of density on ingredient correction;

[0023] Based on the obtained physical property correction values, environmental disturbance suppression values and density adjustment values, a material property correction model is constructed to comprehensively evaluate the impact of plastic particle properties and environmental parameters on the material target values.

[0024] As a preferred embodiment of the MCGS-based plastic particle batching method of the present invention, wherein:

[0025] The specific formula of the ingredient physical property correction model is as follows:

[0026] ;

[0027] in, It is the initial corrected batching target value, which indicates the corrected batching amount calculated based on the physical properties of the plastic particles and environmental parameters.

[0028] As a preferred embodiment of the MCGS-based plastic particle batching method of the present invention, the historical deviation data includes the deviation value between the actual batching amount and the initial corrected batching target value, the deviation change rate and the deviation duration;

[0029] Acquiring historical batching deviation data based on the initial corrected batching target value includes the following steps:

[0030] Based on the initial corrected batching target value, if the deviation between the actual batching amount and the initial corrected batching target value is less than or equal to the first deviation threshold, it is determined to be a low deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data;

[0031] If the deviation between the actual batching amount and the initial corrected batching target value is greater than the first deviation threshold and less than the second deviation threshold, it is determined to be in the medium deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data;

[0032] If the deviation between the actual batching amount and the initial corrected batching target value is greater than or equal to the second deviation threshold,

[0033] It is determined to be a high deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data.

[0034] As a preferred embodiment of the MCGS-based plastic particle batching method of the present invention, the construction of the comprehensive batching prediction model includes the following steps:

[0035] By introducing the deviation trend correction term, the dynamic interaction between the deviation value and the deviation change rate in the historical batching deviation trend is processed to obtain the deviation trend correction value. The specific formula is as follows:

[0036] ;

[0037] in, It is the deviation trend correction value, indicating the intensity and dynamic trend of the ingredient deviation at the current moment. is the deviation value at the tth moment, which represents the difference between the actual batching amount and the initial corrected batching target value. is the deviation change rate at time t, indicating the speed at which the deviation value changes over time. is the deviation influence coefficient, which is used to adjust the influence of the deviation trend on the batching correction. By introducing a comprehensive inhibition value to process the combined influence of the deviation duration and the air flow rate and physical parameters in the batching environment, a comprehensive inhibition value is obtained, thereby reducing the interference of long-term deviation and environmental disturbance on the batching accuracy. The specific formula is as follows:

[0038] ;

[0039] in, is the comprehensive inhibition value, which indicates the inhibitory effect of deviation duration and environmental / physical parameters on ingredient correction. is the deviation duration at time t, indicating the length of time the deviation exceeds the threshold. is the duration adjustment coefficient, which is used to control the effect of duration on the inhibition factor. is the flow rate adjustment coefficient, which is used to adjust the effect of air flow rate. is the physical property interaction coefficient, which is used to adjust the interaction between bulk density and moisture absorption rate;

[0040] Based on the initial corrected batching target value and combined with the optimized deviation trend correction value and comprehensive inhibition value, a comprehensive batching prediction model is constructed to comprehensively evaluate the dynamic impact of historical batching deviation trends, batching environmental parameters and physical property parameters on the batching target value. The specific formula of the comprehensive batching prediction model is as follows:

[0041] ;

[0042] in, The final revised batch value represents the optimized batch amount based on historical deviation trends and environmental / physical parameters.

[0043] As a preferred embodiment of the MCGS-based plastic particle batching method of the present invention, the batching value is predicted based on the comprehensive batching prediction model to obtain the final corrected batching value, and the batching operation is performed, including the following steps:

[0044] The batching status is judged based on the relative deviation between the final corrected batching value and the initial corrected batching target value and the cumulative effect value of the historical deviation. The following judgment is performed:

[0045] If the relative deviation is less than or equal to the first deviation threshold, and the historical deviation cumulative effect value is less than or equal to the cumulative threshold, the current batching state is determined to be normal, the batching operation is continued, and the batching data is continuously monitored;

[0046] If the relative deviation is less than or equal to the first deviation threshold, but the historical deviation cumulative effect value is greater than the cumulative threshold, it is preliminarily determined that the current batching state is a mild deviation state, and the next step is executed;

[0047] When the current batching state is initially determined to be a slightly abnormal state, an upgraded judgment is further performed based on the deviation value, deviation change rate, and deviation duration. If the deviation value is less than or equal to the deviation threshold, the deviation change rate is less than or equal to the rate threshold, and the deviation duration is less than or equal to the time threshold, the current batching state is determined to be a slightly abnormal state. The current batching parameters are recorded and the deviation influence coefficient of the comprehensive batching prediction model is adjusted. It is recommended to check the equipment operation status.

[0048] If any one of the deviation value, deviation change rate and deviation duration is greater than the corresponding threshold, the current batching state is determined to be a severe deviation state;

[0049] If the relative deviation is greater than the first deviation threshold and the cumulative effect value is greater than the cumulative threshold, the current batching state is determined to be a serious deviation state, the batching operation is suspended, and an alarm message is sent to the operator to notify equipment calibration or maintenance.

[0050] In the second aspect, the present invention further solves the problem that the existing technology is difficult to adapt to the diverse needs of different plastic types and process conditions, which limits the intelligence and stability of the batching process. The embodiment provides a plastic particle batching system based on MCGS, including:

[0051] Physical property environment acquisition module: used to obtain the physical property characteristic data of plastic particles and the batching environment parameter data, and to build a batching physical property correction model. The batching physical property correction model is used to perform calculations to obtain the initial correction batching target value.

[0052] Deviation processing module: based on the initial corrected batching target value, obtains historical batching deviation data and performs preprocessing to obtain processed batching deviation trend data;

[0053] Model optimization module: optimizes the ingredient property correction model using the ingredient deviation trend data to construct a comprehensive ingredient prediction model;

[0054] Batching execution module: Based on the comprehensive batching prediction model, the batching value is predicted, the final corrected batching value is obtained, and the batching operation is executed to realize intelligent monitoring and precise batching control of plastic particles.

[0055] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the MCGS-based plastic particle batching method as described in the first aspect of the present invention is implemented.

[0056] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the MCGS-based plastic particle batching method as described in the first aspect of the present invention is implemented.

[0057] The present invention has the following beneficial effects: The present invention introduces a logarithmic function into the batching property correction model to address the combined effects of bulk density and moisture absorption rate. The fractional structure quantifies the dynamic disturbances of air flow rate and vibration amplitude, and a linear correction term is used to adapt to density differences. This multidimensional nonlinear modeling approach significantly improves batching accuracy in scenarios with high moisture absorption rates or strong disturbances.

[0058] By collecting deviation data in a hierarchical manner and introducing deviation trend correction items and comprehensive inhibition values using a comprehensive batching prediction model, the interaction between deviation trends and environmental / physical properties is dynamically analyzed. Furthermore, adaptive adjustments are triggered through state judgments based on relative deviations and cumulative effects. This dynamic optimization mechanism effectively reduces the cumulative effects of long-term deviations and greatly improves batching stability, significantly outperforming traditional fixed feedback correction. It integrates multi-source data, dynamically adjusts prediction model parameters, and enables a hierarchical response in the batching execution module. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0060] Figure 1 This is a schematic diagram of the overall process of the MCGS-based plastic particle batching method proposed in the present invention;

[0061] Figure 2 This is a logic diagram for determining historical batching deviation data for the MCGS-based plastic particle batching method proposed in the present invention;

[0062] Figure 3 This is a schematic diagram of the state judgment logic of the MCGS-based plastic particle batching method proposed in the present invention. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0065] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0066] Furthermore, the present invention is described in detail with reference to schematic diagrams. For ease of illustration, when describing the embodiments of the present invention, cross-sectional views illustrating device structures may be partially enlarged and not to scale. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of protection of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0067] Example 1

[0068] Reference Figure 1-Figure 3 , as an embodiment of the present invention, provides a plastic particle batching method based on MCGS.

[0069] Existing plastic particle batching technology has certain limitations in practical applications. Traditional methods mostly rely on linear control models with fixed parameters, which makes it difficult to effectively capture the physical properties of plastic particles and the complex influence of environmental disturbances, resulting in a decrease in batching accuracy under high moisture absorption or strong disturbance scenarios. In addition, existing technologies for handling historical batching deviations are usually limited to simple feedback corrections, lacking dynamic analysis and adaptive optimization of deviation trends, making it difficult to adapt to the diverse needs of different plastic types and process conditions, limiting the intelligence and stability of the batching process.

[0070] This application provides a method that can effectively solve the above-mentioned problems. Next, we will use multiple embodiments to explain in detail how to implement the MCGS-based plastic particle batching method.

[0071] In this embodiment, MCGS is an industrial automation configuration software platform with good visual interface configuration capabilities, rich communication interface protocol support and real-time data processing capabilities. The present invention is based on the MCGS platform to realize the collection, display, analysis and control logic execution of the physical characteristic parameters of plastic particles (including density, bulk density, moisture absorption rate) and ingredient environment parameters (including air flow rate and vibration amplitude).

[0072] Figure 1 The overall flow chart of the MCGS-based plastic pellet batching method is shown, including:

[0073] S1: Obtain the physical property characteristic data of plastic particles and the batching environmental parameter data, and build a batching physical property correction model. Use the batching physical property correction model to perform calculations to obtain the initial corrected batching target value;

[0074] Obtaining the physical property characteristic data of plastic particles means collecting the density, bulk density, moisture absorption rate and particle size parameters of plastic particles through sensors;

[0075] Obtaining environmental parameter data for plastic particle batching refers to collecting ambient temperature, ambient humidity, air flow rate, and vibration amplitude parameters at the batching site through sensors.

[0076] The construction of the ingredient property correction model includes the following steps:

[0077] By introducing a logarithmic function to process the combined effect of bulk density and moisture absorption rate, the physical property correction value is obtained, thereby enhancing the responsiveness of the physical property correction model to high moisture absorption rate or high bulk density scenarios. The specific formula is as follows:

[0078] ;

[0079] in, is the correction value of physical properties, which represents the nonlinear interaction between the bulk density and moisture absorption rate of plastic particles. is the bulk density, is the moisture absorption rate;

[0080] By introducing a fractional structure to quantify the combined effect of air velocity and vibration amplitude, the environmental disturbance suppression value is obtained, thereby reducing the interference of dynamic disturbances in the batching environment on batching accuracy. The specific formula is as follows:

[0081] ;

[0082] in, is the environmental disturbance suppression value, which indicates the inhibitory effect of environmental parameters on ingredient correction. is the mean air velocity, is the mean vibration amplitude, is the denominator adjustment coefficient, which is used to control the impact of environmental disturbance on ingredient correction;

[0083] By introducing a linear correction term to process the density difference of plastic particles, the density adjustment value is obtained, thereby improving the adaptability of the material property correction model under different density conditions. The specific formula is as follows:

[0084] ;

[0085] in, is the density adjustment value, which indicates the linear adjustment effect of the density of plastic particles on the target value of the ingredients. is the density of plastic particles, is the density adjustment coefficient, which is used to control the weight of density on ingredient correction;

[0086] Based on the obtained physical property correction values, environmental disturbance suppression values and density adjustment values, a material property correction model is constructed to comprehensively evaluate the impact of plastic particle properties and environmental parameters on the material target values.

[0087] The specific formula of the ingredient property correction model is as follows:

[0088] ;

[0089] in, It is the initial corrected batching target value, which indicates the corrected batching amount calculated based on the physical properties of the plastic particles and environmental parameters.

[0090] In the embodiment of the present application, the denominator adjustment coefficient and density adjustment factor The coefficient value that best suits the current batching scenario can be determined by minimizing the batching error using historical batching data, or it can be adaptively adjusted through data training or optimization algorithms (such as gradient descent). Specifically, the denominator adjustment coefficient The density adjustment coefficient can be determined by experimentally calibrating the disturbance characteristics of air flow rate and vibration amplitude; The batching accuracy of the model under diverse physical property conditions can be ensured by optimizing the batching experiments of plastic particles with different densities. The above coefficients can also be initially set in combination with expert experience, which is not specifically limited in this embodiment.

[0091] Preferably, in the process of constructing the material property correction model, the nonlinear influence of the physical properties of plastic particles and environmental parameters is comprehensively considered to improve the material accuracy and physical property characteristic correction value, and the logarithmic function is used to capture the nonlinear interaction between bulk density and moisture absorption rate, adapt to high moisture absorption rate scenarios, and avoid numerical instability; the environmental disturbance suppression value quantifies the disturbance effect of air flow rate and vibration with a fractional structure, dynamically reducing the precision interference; the density adjustment value linearly adjusts the density difference to ensure the accuracy of the material of plastics with different densities; the total formula integrates three corrections to optimize the material quantity. Compared with the traditional linear model, it significantly improves the accuracy and stability of the material and adapts to complex physical properties and environmental conditions.

[0092] S2: Based on the initial corrected batching target value, historical batching deviation data is obtained and preprocessed to obtain processed batching deviation trend data;

[0093] Preferably, the historical deviation data includes the deviation value between the actual batching amount and the initial revised batching target value, the deviation change rate and the deviation duration;

[0094] Further, such as Figure 2 As shown, obtaining historical batching deviation data based on the initial corrected batching target value includes:

[0095] Based on the initial corrected batching target value, if the deviation between the actual batching amount and the initial corrected batching target value is less than or equal to the first deviation threshold, it is determined to be a low deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data;

[0096] If the deviation between the actual batching amount and the initial corrected batching target value is greater than the first deviation threshold and less than the second deviation threshold, it is determined to be in the medium deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data;

[0097] If the deviation between the actual batching amount and the initial corrected batching target value is greater than or equal to the second deviation threshold, it is determined to be a high deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data.

[0098] It should be noted that for each threshold value of deviation value judgment, firstly, based on the actual deviation characteristics of plastic particle batching, by collecting data in a typical batching scenario, statistical analysis is performed, and the deviation size is classified in combination with the batching accuracy requirements, and finally the best first deviation threshold and second deviation threshold are optimized; secondly, for the setting of the time interval of historical data collection, the batching accuracy and data processing efficiency are comprehensively evaluated, the deviation trend accuracy and calculation cost under different intervals are calculated, and the best 、 and Time interval.

[0099] Specifically, preprocessing refers to smoothing and filtering the deviation value, deviation change rate and deviation duration to obtain processed ingredient deviation trend data, improve data stability and reliability, and provide more accurate input for subsequent comprehensive ingredient prediction models.

[0100] Preferably, the present invention proposes a three-level time interval adaptive acquisition strategy based on the deviation value, using a longer interval in the low deviation area. , use moderate intervals in the medium deviation area , use shorter intervals in high deviation areas While ensuring the accuracy of capturing deviation trends, it significantly improves data collection efficiency, ensuring the dynamic response capability of high-deviation scenarios and avoiding resource waste in low-deviation scenarios.

[0101] S3: Utilize the processed batch deviation trend data to optimize the batch property correction model and construct a comprehensive batch prediction model;

[0102] Building a comprehensive batching prediction model involves the following steps:

[0103] By introducing the deviation trend correction term, the dynamic interaction between the deviation value and the deviation change rate in the historical batching deviation trend is processed to obtain the deviation trend correction value. The specific formula is as follows:

[0104] ;

[0105] in, It is the deviation trend correction value, indicating the intensity and dynamic trend of the ingredient deviation at the current moment. is the deviation value at the tth moment, which represents the difference between the actual batching amount and the initial corrected batching target value. is the deviation change rate at time t, indicating the speed at which the deviation value changes over time. is the deviation influence coefficient, which is used to adjust the influence of the deviation trend on the ingredient correction;

[0106] By introducing a comprehensive inhibition value to process the combined effects of deviation duration and air velocity and physical parameters in the batching environment, a comprehensive inhibition value is obtained, thereby reducing the interference of long-term deviation and environmental disturbance on batching accuracy. The specific formula is as follows:

[0107] ;

[0108] in, is the comprehensive inhibition value, which indicates the inhibitory effect of deviation duration and environmental / physical parameters on ingredient correction. is the deviation duration at time t, indicating the length of time the deviation exceeds the threshold. is the duration adjustment coefficient, which is used to control the effect of duration on the inhibition factor. is the flow rate adjustment coefficient, which is used to adjust the effect of air flow rate. is the physical property interaction coefficient, which is used to adjust the interaction between bulk density and moisture absorption rate;

[0109] Based on the initial corrected batching target value and combined with the optimized deviation trend correction value and comprehensive inhibition value, a comprehensive batching prediction model is constructed to comprehensively evaluate the dynamic impact of historical batching deviation trends, batching environmental parameters and physical property parameters on the batching target value. The specific formula of the comprehensive batching prediction model is as follows:

[0110] ;

[0111] in, The final revised batch value indicates the batch quantity after optimization based on historical deviation trends and environmental / physical parameters.

[0112] In the embodiment of the present application, the deviation influence coefficient , duration adjustment coefficient , flow rate adjustment coefficient and physical property interaction coefficient By minimizing the prediction error by using historical batching deviation data, the coefficient value that best suits the current batching scenario can be determined. The above coefficients can also be initially set in combination with expert experience, which is not specifically limited in this embodiment.

[0113] Preferably, the present invention significantly improves the accuracy of batching prediction through a comprehensive batching prediction model, combining historical deviation trends and the dynamic influence of environmental / physical parameters; the deviation trend correction value introduces a nonlinear combination to capture the interactive effect of the deviation value and the rate of change, and enhances the response capability to instantaneous fluctuations; the comprehensive inhibition value quantifies the combined influence of deviation duration, air flow rate, bulk density and moisture absorption rate in a fractional structure, reducing long-term deviation and environmental disturbance interference; the final formula integrates the deviation trend and inhibition factor to optimize the final batching value, which is more in line with the actual batching dynamic law than the traditional fixed feedback model, and improves the prediction accuracy and stability.

[0114] S4: Based on the comprehensive batching prediction model, the batching value is predicted to obtain the final corrected batching value, and the batching operation is executed to achieve intelligent monitoring and precise batching control of plastic particles.

[0115] Figure 3 This is a schematic diagram of the state judgment logic of the plastic particle batching method based on MCGS proposed in the present invention;

[0116] The batching value is predicted based on the comprehensive batching prediction model to obtain the final corrected batching value and perform the batching operation, including the following steps:

[0117] The batching status is judged based on the relative deviation between the final corrected batching value and the initial corrected batching target value and the cumulative effect value of the historical deviation. The following judgment is performed:

[0118] If the relative deviation is less than or equal to the first deviation threshold, and the historical deviation cumulative effect value is less than or equal to the cumulative threshold, the current batching state is determined to be normal, the batching operation is continued, and the batching data is continuously monitored;

[0119] If the relative deviation is less than or equal to the first deviation threshold, but the historical deviation cumulative effect value is greater than the cumulative threshold, it is preliminarily determined that the current batching state is a mild deviation state, and the next step is executed;

[0120] When the current batching state is initially determined to be a slightly abnormal state, an upgraded judgment is further performed based on the deviation value, deviation change rate, and deviation duration. If the deviation value is less than or equal to the deviation threshold, the deviation change rate is less than or equal to the rate threshold, and the deviation duration is less than or equal to the time threshold, the current batching state is determined to be a slightly abnormal state. The current batching parameters are recorded and the deviation influence coefficient of the comprehensive batching prediction model is adjusted. It is recommended to check the equipment operation status.

[0121] If any one of the deviation value, deviation change rate and deviation duration is greater than the corresponding threshold, the current batching state is determined to be a severe deviation state;

[0122] If the relative deviation is greater than the first deviation threshold and the cumulative effect value is greater than the cumulative threshold, the current batching state is determined to be a serious deviation state, the batching operation is suspended, and an alarm message is sent to the operator to notify equipment calibration or maintenance.

[0123] It should be noted that for the relative deviation and cumulative effect thresholds for judging the state of ingredients, firstly, based on the deviation characteristics of plastic particle ingredients, by collecting data in typical ingredient scenarios, statistical analysis is performed, and the degree of deviation is classified in combination with the ingredient accuracy requirements, and finally the best first deviation threshold and cumulative threshold are optimized; secondly, for the threshold settings of deviation value, change rate and duration, the stability and timeliness of ingredients are comprehensively evaluated, the accuracy of state judgment and operating cost under different thresholds are calculated, and the optimal threshold is determined.

[0124] For example, suppose that in a plastic particle processing plant, after a MCGS-based batching equipment has been running continuously for two hours, the intelligent monitoring system detects a slight but continuous deviation trend in the batching amount; although the relative deviation of a single measurement does not exceed the first deviation threshold, the system finds that the deviation is gradually accumulating by calculating the cumulative effect value of historical deviations; when the deviation lasts for 30 minutes and the rate of change increases slightly, the system automatically determines it as a mild deviation state, records the current batching parameters and adjusts the deviation influence coefficient of the comprehensive batching prediction model, and recommends the operator to check the equipment operation status; the operator immediately finds that the feeding valve is slightly blocked, and cleans it in time to restore normal batching, avoiding the serious deviation state caused by further expansion of the deviation, and ensuring batching accuracy and production efficiency.

[0125] It should be noted that the status monitoring of traditional batching systems usually adopts a single deviation threshold judgment, which is difficult to adapt to the complex changes of physical properties and environmental disturbances, resulting in response lag or misjudgment; this embodiment establishes a refined control system for normal, mild deviation and severe deviation by designing a three-level status judgment mechanism based on relative deviation and historical deviation cumulative effect value, and realizes dynamic evaluation of batching status by comprehensively considering current deviation and historical trend; this multi-level judgment mechanism overcomes the limitations of traditional binary control, and adopts graded response measures through multi-dimensional analysis of deviation value, change rate and duration; it significantly improves the accuracy and intelligence level of the batching process, reduces batching inaccuracy caused by failure to correct deviation in time, avoids waste of resources caused by excessive intervention, and optimizes the operating efficiency and maintenance cost of batching equipment.

[0126] In summary, the compounding accuracy in scenarios with high moisture absorption or strong disturbance is significantly improved by introducing the logarithmic function into the batching physical property correction model to deal with the combined effect of bulk density and moisture absorption rate. The dynamic disturbance of air velocity and vibration amplitude is quantified by the fractional structure, and the density difference is adapted by the linear correction term. The deviation data is collected in stages, and the deviation trend correction term and the comprehensive inhibition value are introduced by using the comprehensive batching prediction model. The interaction between the deviation trend and the environment / physical property is dynamically analyzed. The state judgment of relative deviation and cumulative effect is further used to trigger adaptive adjustment. This dynamic optimization mechanism effectively reduces the cumulative effect of long-term deviation, greatly improves the stability of batching, and is significantly better than the traditional fixed feedback correction. It integrates multi-source data, dynamically adjusts the prediction model parameters, and realizes graded response in the batching execution module.

[0127] Example 2

[0128] In one embodiment of the present invention, a plastic particle batching system based on MCGS is provided, comprising:

[0129] Physical property environment acquisition module: used to obtain the physical property characteristic data of plastic particles and the batching environment parameter data, and to build a batching physical property correction model. The batching physical property correction model is used for calculation to obtain the initial correction batching target value;

[0130] Deviation processing module: based on the initial revised batching target value, it obtains historical batching deviation data and performs preprocessing to obtain processed batching deviation trend data;

[0131] Model optimization module: Utilizes processed batch deviation trend data to optimize the batch property correction model and build a comprehensive batch prediction model;

[0132] Batching execution module: Based on the comprehensive batching prediction model, the batching value is predicted, the final corrected batching value is obtained, and the batching operation is executed to realize intelligent monitoring and precise batching control of plastic particles.

[0133] Example 3

[0134] This is an embodiment of the present invention, which is different from the previous embodiment in that:

[0135] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0136] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0137] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0138] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0139] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A plastic particle batching method based on MCGS, characterized in that: include: Obtaining plastic particle physical property characteristic data and batching environmental parameter data, and constructing a batching physical property correction model, and using the batching physical property correction model to perform calculations to obtain an initial corrected batching target value; The specific formula of the ingredient physical property correction model is as follows: ； in, is the initial correction batching target value, is the correction value of physical property characteristics, is the environmental disturbance suppression value, is the density adjustment value; Based on the initial corrected batching target value, historical batching deviation data is acquired and pre-processed to obtain processed batching deviation trend data; Utilizing the batching deviation trend data to optimize the batching property correction model, a comprehensive batching prediction model is constructed; The construction of the comprehensive batching prediction model comprises the following steps: By introducing the deviation trend correction term, the dynamic interaction between the deviation value and the deviation change rate in the historical batching deviation trend is processed to obtain the deviation trend correction value; By introducing a comprehensive inhibition value to process the combined effects of deviation duration and air velocity and physical parameters in the batching environment, a comprehensive inhibition value is obtained, thereby reducing the interference of long-term deviation and environmental disturbance on batching accuracy; Based on the initial corrected batching target value and combined with the optimized deviation trend correction value and comprehensive inhibition value, a comprehensive batching prediction model is constructed to comprehensively evaluate the dynamic impact of historical batching deviation trends, batching environmental parameters and physical property parameters on the batching target value; The batching value is predicted based on the comprehensive batching prediction model to obtain the final corrected batching value, and the batching operation is executed to realize intelligent monitoring and precise batching control of plastic particles.

2. The plastic particle batching method based on MCGS according to claim 1, characterized in that: Acquiring the physical property characteristic data of the plastic particles refers to collecting the density, bulk density and moisture absorption rate of the plastic particles through sensors; Acquiring the plastic particle batching environmental parameter data refers to collecting the air flow rate and vibration amplitude parameters at the batching site through sensors.

3. The plastic particle batching method based on MCGS according to claim 2, characterized in that: The construction of the ingredient physical property correction model comprises the following steps: By introducing a logarithmic function to process the combined effect of bulk density and moisture absorption rate, a correction value for physical property characteristics is obtained, thereby enhancing the responsiveness of the physical property correction model to scenarios with high moisture absorption rate or high bulk density. By introducing a fractional structure to quantify the combined effect of air velocity and vibration amplitude, the environmental disturbance suppression value is obtained, thereby reducing the interference of dynamic disturbances in the batching environment on batching accuracy. By introducing a linear correction term to process the density difference of plastic particles, a density adjustment value is obtained, thereby improving the adaptability of the material property correction model under different density conditions; Based on the obtained physical property correction values, environmental disturbance suppression values and density adjustment values, a material property correction model is constructed to comprehensively evaluate the impact of plastic particle properties and environmental parameters on the material target values.

4. The plastic particle batching method based on MCGS according to claim 1, characterized in that: The historical deviation data includes the deviation value between the actual batching amount and the initial revised batching target value, the deviation change rate and the deviation duration; Acquiring historical batching deviation data based on the initial corrected batching target value includes the following steps: Based on the initial corrected batching target value, if the deviation between the actual batching amount and the initial corrected batching target value is less than or equal to the first deviation threshold, it is determined to be a low deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data; If the deviation between the actual batching amount and the initial corrected batching target value is greater than the first deviation threshold and less than the second deviation threshold, it is determined to be in the medium deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data; If the deviation between the actual batching amount and the initial corrected batching target value is greater than or equal to the second deviation threshold, it is determined to be a high deviation area, and the time interval for historical data collection is set to , and obtain historical ingredient deviation data.

5. The plastic particle batching method based on MCGS according to claim 1, characterized in that: The batching value is predicted based on the comprehensive batching prediction model to obtain the final corrected batching value, and the batching operation is performed, including the following steps: The batching status is judged based on the relative deviation between the final corrected batching value and the initial corrected batching target value and the cumulative effect value of the historical deviation. The following judgment is performed: If the relative deviation is less than or equal to the first deviation threshold, and the historical deviation cumulative effect value is less than or equal to the cumulative threshold, the current batching state is determined to be normal, the batching operation is continued, and the batching data is continuously monitored; If the relative deviation is less than or equal to the first deviation threshold, but the historical deviation cumulative effect value is greater than the cumulative threshold, it is preliminarily determined that the current batching state is a mild deviation state, and the next step is executed; When the current batching state is initially determined to be a slightly abnormal state, an upgraded judgment is further performed based on the deviation value, deviation change rate, and deviation duration. If the deviation value is less than or equal to the deviation threshold, the deviation change rate is less than or equal to the rate threshold, and the deviation duration is less than or equal to the time threshold, the current batching state is determined to be a slightly abnormal state. The current batching parameters are recorded and the deviation influence coefficient of the comprehensive batching prediction model is adjusted. It is recommended to check the equipment operation status. If any one of the deviation value, deviation change rate and deviation duration is greater than the corresponding threshold, the current batching state is determined to be a severe deviation state; If the relative deviation is greater than the first deviation threshold and the cumulative effect value is greater than the cumulative threshold, the current batching state is determined to be a serious deviation state, the batching operation is suspended, and an alarm message is sent to the operator to notify equipment calibration or maintenance.

6. A plastic particle batching system based on MCGS, based on the batching method according to any one of claims 1 to 5, characterized in that: include: Physical property environment acquisition module: used to obtain the physical property characteristic data of plastic particles and the batching environment parameter data, and to build a batching physical property correction model. The batching physical property correction model is used to perform calculations to obtain the initial correction batching target value. Deviation processing module: based on the initial corrected batching target value, obtains historical batching deviation data and performs preprocessing to obtain processed batching deviation trend data; Model optimization module: optimizes the ingredient property correction model using the ingredient deviation trend data to construct a comprehensive ingredient prediction model; Batching execution module: Based on the comprehensive batching prediction model, the batching value is predicted, the final corrected batching value is obtained, and the batching operation is executed to realize intelligent monitoring and precise batching control of plastic particles.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the MCGS-based plastic particle batching method described in any one of claims 1-5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the MCGS-based plastic particle batching method described in any one of claims 1 to 5 are implemented.

Images