Intelligent management method and system for whole life cycle of weighing and batching equipment

Abstract

This application relates to the field of weighing and batching equipment technology, and in particular to a method and system for intelligent management of the entire lifecycle of weighing and batching equipment. The method includes: acquiring the operating information set of a loss-in-weight color masterbatch machine; based on the operating information set of the loss-in-weight color masterbatch machine, analyzing the synergistic impact characteristics of service host consumption fluctuations and material characteristic changes on batching information to obtain a dynamic consumption information set; based on the dynamic consumption information set, analyzing the mapping relationship between the required color changes of plastic products and batching information to obtain a lifecycle adaptation information set; and generating a collaborative control strategy based on the lifecycle adaptation information set, and outputting a lifecycle intelligent management log for the weighing and batching equipment. This achieves adaptive adjustment throughout the entire lifecycle, effectively overcoming the color drift problem. Through a dynamic compensation strategy combining feedforward and feedback, it reduces over-adjustment and repeated trial and error, significantly reducing material waste and improving production efficiency.

Description

Technical Field

[0001] This application relates to the field of weighing and batching equipment technology, and in particular to intelligent management methods and systems for the entire life cycle of weighing and batching equipment. Background Technology

[0002] In the plastics processing industry, loss-in-weight masterbatch machines are key equipment for achieving precise addition of masterbatch. They are widely used in injection molding, extrusion and other production processes. Existing weighing and batching control technologies are usually based on preset fixed formula ratios. They use loss-in-weight scales to monitor the weight of the material in real time and adjust the screw speed or vibration frequency to maintain the set addition rate. This technical solution collects equipment operating parameters and material weight data to build a closed-loop control system, ensuring that the supply of masterbatch and the consumption of the main machine are dynamically balanced during the production process, thereby meeting the basic color matching process requirements.

[0003] However, in existing technologies, during long-term continuous production, the phased fluctuations in the main machine consumption rate, the drift of material physical properties with environmental changes, and the time-varying nature of product color requirements make it difficult to maintain stable actual batching accuracy throughout the entire life cycle. This can easily lead to the accumulation of color deviations and a lack of adaptive compensation mechanisms. Summary of the Invention

[0004] This application provides a method and system for intelligent management of the entire life cycle of weighing and batching equipment to solve the above problems.

[0005] In a first aspect, this application provides a method for intelligent management of the entire lifecycle of weighing and batching equipment. The method includes: acquiring a set of working information of a loss-in-weight color masterbatch machine; based on the set of working information of the loss-in-weight color masterbatch machine, analyzing the synergistic influence characteristics of service host consumption fluctuations and material characteristic changes on batching information to obtain a dynamic consumption information set; based on the dynamic consumption information set, analyzing the mapping relationship between the color change required by the plastic product and the batching information to obtain a lifecycle adaptation information set; and generating a collaborative control strategy according to the lifecycle adaptation information set, and outputting a smart management log of the entire lifecycle of the weighing and batching equipment.

[0006] Through the above technical solution, the working information set of the loss-in-weight color masterbatch machine is obtained. A deep analysis of the synergistic impact of service host consumption fluctuations and material characteristic changes on batching information is conducted to obtain a dynamic consumption information set. Based on this, the mapping relationship between the color changes required by the plastic product and the batching information is further analyzed to obtain a full lifecycle adaptation information set. Finally, based on this adaptation information set, a collaborative control strategy including adaptive feedforward compensation and feedback correction is generated, and an intelligent management log is output. Through the time-series coupling analysis of host consumption fluctuation information and material characteristic fluctuation information, the blind spot of single-factor compensation is eliminated, making the amount of color masterbatch added closer to actual needs. Through the correlation analysis of time-varying color demand information and material lag compensation demand, adaptive adjustment throughout the entire lifecycle is achieved. With the help of a dynamic compensation strategy combining feedforward and feedback, over-adjustment and repeated trial and error are reduced, significantly reducing material waste and improving production efficiency.

[0007] Optionally, the step of analyzing the synergistic impact of service host consumption fluctuations and material characteristic changes on batching information based on the loss-in-weight color masterbatch machine's operating information set to obtain a dynamic consumption information set includes: the loss-in-weight color masterbatch machine's operating information set includes equipment operating conditions and color masterbatch material information; based on the equipment operating conditions, analyzing the impact of changes in the host's consumption rate at different production stages on the amount of color masterbatch added to obtain host consumption fluctuation information; based on the color masterbatch material information, analyzing the impact of changes in material flowability, density, and moisture content on batching accuracy to obtain material characteristic fluctuation information; and based on the host consumption fluctuation information, combined with the material characteristic fluctuation information, analyzing the synergistic impact of the interaction between the two in the batching process on batching information to obtain a dynamic consumption information set.

[0008] Through the above technical solution, a refined construction of a dynamic consumption information set from multi-dimensional data sources is achieved. By decoupling the working information set of the loss-in-weight color masterbatch machine into equipment operating conditions and color masterbatch material information, the main machine consumption fluctuation information and material characteristic fluctuation information are extracted independently, avoiding mutual interference between different variables and improving the accuracy of feature extraction. On this basis, the temporal coupling relationship between the two on the time axis is further analyzed, clarifying the interaction mechanism between the change of the main machine consumption rate and the fluctuation of the material feed rate. In particular, the matching problem between the sudden change of consumption rate and the lag of material flowability is quantified. This analysis strategy of separation and combination not only clearly defines the respective influence paths of the equipment side and the material side, but also effectively makes up for the defects of existing methods that only consider single factors or simple linear superposition by introducing synergistic influence features. The final dynamic consumption information set can comprehensively cover the complex disturbances caused by equipment wear, operating condition switching and environmental changes throughout the entire production life cycle.

[0009] Optionally, the process of constructing the host consumption fluctuation information includes: based on the operating conditions of the equipment, analyzing the dynamic deviation information between the real-time consumption rate of the service host and the target value, and identifying the current production stage; according to the current production stage, analyzing the dynamic impact of the stage-by-stage changes in the host consumption rate throughout the entire production cycle on the real-time addition ratio of color masterbatch, to obtain the host consumption fluctuation information.

[0010] The above technical solution realizes the transformation from raw operating data to structured fluctuation information. First, by monitoring the dynamic deviation between the consumption rate and the target value in real time, the changes in the operating cycle of the host are accurately captured, solving the problem that existing methods cannot detect the switching of production stages in a timely manner. On this basis, by further combining the physical characteristics of different stages, the dynamic influence mechanism of the consumption rate change on the color masterbatch addition ratio is analyzed in depth, upgrading simple rate monitoring to the construction of fluctuation information with predictive properties. This processing method not only quantifies the disturbance characteristics on the host side, but also provides a standardized time axis benchmark for subsequent integration of material characteristic fluctuation information, ensuring that the color masterbatch addition ratio can always maintain dynamic matching with the host consumption state under complex operating conditions with frequent fluctuations in host load.

[0011] Optionally, the process of constructing the material characteristic fluctuation information includes: based on the color masterbatch material information, analyzing the influence of material moisture content changes on the particle agglomeration state and surface adhesion of the color masterbatch to obtain material cohesion-adhesion state information; based on the material cohesion-adhesion state information, analyzing the characteristic information of changes in material apparent flowability and bulk density caused by changes in moisture content state to obtain the material characteristic fluctuation information.

[0012] Through the above technical solution, a deep correlation analysis from microscopic physical properties to macroscopic flow behavior is achieved. By first analyzing the influence of moisture content on the agglomeration state and surface adhesion of masterbatch, information on the cohesive-adhesive state of the material is obtained. On this basis, the specific changes in apparent flowability and bulk density caused by the state change are further deduced. Finally, material characteristic fluctuation information containing multi-dimensional physical indicators is constructed. This step-by-step analysis method not only transforms the internal state of the material, which was originally difficult to observe directly, into quantifiable control parameters, but also reveals the complete transmission mechanism of moisture content → agglomeration / adhesion → flowability / density → feeding deviation. With the help of this mechanism, it is possible to identify material performance degradation caused by changes in environmental humidity or excessive storage time in advance during the batching process, and to conduct collaborative analysis with the main unit consumption fluctuation information.

[0013] Optionally, the step of analyzing the synergistic impact of the interaction between the host machine consumption fluctuation information and the material characteristic fluctuation information on the batching information during the batching process to obtain a dynamic consumption information set includes: analyzing the overlap and misalignment relationship between the host machine consumption rate change and the material feed rate fluctuation on the time axis based on the host machine consumption fluctuation information and the material characteristic fluctuation information to obtain time-series coupling information; and analyzing the lag compensation requirement of the material flowability change on the actual addition amount of color masterbatch when the consumption rate changes, based on the time-series coupling information to obtain the dynamic consumption information set.

[0014] The above technical solution enables in-depth collaborative analysis of fluctuations in main unit consumption and material characteristics. By first constructing time-series coupled information, the overlapping risks of high-load main unit operation and low material flowability on the time axis are accurately captured, avoiding misjudgments caused by simple linear superposition. On this basis, the time-series coupling relationship is further used to derive the lag compensation requirement, enabling the control to predict and offset the material feeding delay caused by the deterioration of material characteristics at the instant of consumption rate change. This closed-loop mechanism from feedforward prediction to feedback correction effectively solves the compensation lag or overshoot problem caused by ignoring the time dimension coupling in existing methods, ensuring that the actual amount of color masterbatch added closely follows the dynamically changing production needs throughout the entire life cycle, significantly improving color matching accuracy and production stability.

[0015] Optionally, the step of analyzing the mapping relationship between the color changes required by the plastic product and the ingredient information based on the dynamic consumption information set to obtain a full life cycle adaptation information set includes: based on the dynamic consumption information set, analyzing the variation law of hue, saturation and brightness deviation of the color required by the plastic product at each production stage with production time to obtain time-varying color demand information; and based on the time-varying color demand information, analyzing the dynamic adjustment requirements of the color demand fluctuation on the real-time addition ratio of color masterbatch and the compensation amount caused by the lag of material characteristics to obtain the full life cycle adaptation information set.

[0016] The above technical solution transforms dynamic consumption information into a lifecycle-wide adaptive information set to guide batching actions. By analyzing the changes in hue, saturation, and brightness deviations over time based on the dynamic consumption information set, time-varying color demand information is constructed, enabling the perception of product quality evolution trends. Furthermore, based on this time-varying color demand information, in-depth analysis is conducted to understand the dynamic adjustment requirements of color fluctuations on the addition ratio and the compensation amount caused by material lag. This achieves an organic integration of feedforward prediction and feedback correction. This approach not only establishes the information link between equipment operation, material characteristics, and product quality but also precisely solves the control problems caused by material response lag by dynamically adjusting the superposition ratio of feedforward and feedback. This ensures that the weighing and batching equipment maintains high-precision color matching throughout its entire lifecycle, significantly improving product qualification rates and the level of intelligence in the production process.

[0017] Optionally, the process of constructing the time-varying color demand information includes: based on the dynamic consumption information set, analyzing the inertial trend of the deviation between the actual amount of color masterbatch added and the preset ratio over continuous production time to obtain deviation inertial information; and based on the deviation inertial information, analyzing the time-series correction requirements for hue, saturation, and brightness deviations caused by the lag in material characteristics to obtain the time-varying color demand information.

[0018] By analyzing the synergistic effect of deviation inertia information and material characteristic lag through the above technical solution, high-precision time-varying color demand information is constructed. Deviation inertia information provides trend prediction of color deviation evolution, solving the problem that existing control only focuses on the current instantaneous error and ignores the future trend. Meanwhile, the time-series correction demand based on material characteristic lag analysis provides time dimension calibration, ensuring that the predicted compensation amount can take effect at the accurate time point. The combination of the two makes the generated time-varying color demand information not only include how much adjustment (amplitude) is needed, but also when to adjust (phase), thereby realizing precise closed-loop control of hue, saturation and lightness deviation. This synergistic mechanism effectively avoids the oscillation phenomenon caused by simply relying on feedback adjustment. Especially in long-cycle operation scenarios where the production environment changes slowly or the material characteristics gradually deteriorate, it can maintain the consistency of product color and significantly reduce the scrap rate caused by color drift.

[0019] Optionally, the step of analyzing the dynamic adjustment requirements of the real-time addition ratio of color masterbatch due to color demand fluctuations and the compensation amount caused by material characteristic lag based on the time-varying color demand information to obtain the full life cycle adaptation information set includes: based on the time-varying color demand information, analyzing the temporal correlation between the time-varying trend of color deviation and the material characteristic lag compensation requirements in each production stage to obtain deviation-lag coupling information; and based on the deviation-lag coupling information, analyzing the superposition ratio of the feedforward adjustment amount and the feedback compensation amount of the real-time addition ratio of color masterbatch to obtain the full life cycle adaptation information set.

[0020] Through the above technical solution, the organic synergy between feedforward control and feedback control is achieved. Specifically, by analyzing the temporal correlation between the time-varying trend of color deviation and the lag compensation requirements of material characteristics, deviation-lag coupling information is constructed. This information serves as a bridge connecting environmental changes and control strategies, quantitatively describing the changes in dynamic characteristics. Based on this, the superposition ratio of feedforward adjustment and feedback compensation is dynamically adjusted according to the deviation-lag coupling information, enabling flexible switching of the control focus at different production stages: when lag is significant, feedforward is the primary method for proactive planning; when disturbances are severe, feedback is the primary method for immediate correction. This dynamic weight allocation mechanism overcomes the poor adaptability of existing fixed-ratio control strategies, significantly improving the robustness and accuracy of weighing and batching equipment in complex working conditions, and ensuring the consistency of plastic product color throughout its entire life cycle.

[0021] Optionally, the step of generating a collaborative control strategy based on the full lifecycle adaptation information set and outputting the intelligent management log of the weighing and batching equipment throughout its entire lifecycle includes: analyzing the changing trend of the superposition ratio of feedforward adjustment and feedback compensation in each production stage based on the full lifecycle adaptation information set to obtain dynamic compensation information; generating the collaborative control strategy including adaptive feedforward compensation and feedback correction based on the dynamic compensation information and the time-varying color requirement information, and outputting the intelligent management log of the weighing and batching equipment throughout its entire lifecycle.

[0022] Through the above technical solution, a seamless transformation from high-level data analysis to low-level execution instructions is achieved. Specifically, by analyzing the changing trend of the superposition ratio of feedforward adjustment and feedback compensation, the relationship between predictive control and real-time correction can be adaptively balanced, avoiding the lag or overshoot problems of a single control mode under complex operating conditions. On this basis, the collaborative control strategy generated by combining the time-varying characteristics of color demand ensures that the amount of color masterbatch added can accurately match the color drift pattern of plastic products throughout their entire life cycle. Furthermore, the output full life cycle intelligent management log fully records the decision logic and execution effect of each dynamic compensation, which not only provides real-time basis for current production quality control, but also accumulates valuable data assets for long-term equipment performance evaluation and process parameter iteration, thereby significantly improving the intelligence level, batching accuracy and maintainability of the weighing and batching equipment.

[0023] Secondly, this application provides an intelligent management system for the entire lifecycle of weighing and batching equipment. The system includes: a dynamic consumption module, used to acquire the working information set of the loss-in-weight color masterbatch machine, and based on the working information set of the loss-in-weight color masterbatch machine, analyze the synergistic influence characteristics of the service host consumption fluctuation and material characteristic changes on the batching information to obtain a dynamic consumption information set; a mapping relationship module, used to analyze the mapping relationship between the color change required by the plastic product and the batching information based on the dynamic consumption information set to obtain a lifecycle adaptation information set; and a strategy generation module, used to generate a collaborative control strategy based on the lifecycle adaptation information set and output the intelligent management log for the entire lifecycle of the weighing and batching equipment. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of an application scenario provided in an embodiment of this application; Figure 2 A flowchart illustrating an embodiment of the intelligent management method for the entire lifecycle of weighing and batching equipment provided in this application; Figure 3 A schematic diagram of the structure of an intelligent management system for the entire life cycle of a weighing and batching equipment provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0027] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0028] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0029] In the field of plastic product processing, loss-in-weight color masterbatch machines are commonly used equipment for precise addition of color masterbatch. In existing technologies, the batching of color masterbatch is usually based on a fixed formula ratio. The amount of material fed in real time is monitored by a loss-in-weight weigher and adjusted accordingly. However, in actual production, there are problems such as large fluctuations in the main machine consumption rate at different production stages, changes in the material properties of color masterbatch due to environmental influences, and drift in the color requirements of plastic products over production time. Existing control methods often fail to comprehensively analyze the synergistic effect between the fluctuation of main machine consumption and changes in material properties, resulting in lag or overshoot in the compensation strategy, making it difficult to achieve precise and adaptive control of the weighing and batching equipment throughout its entire life cycle.

[0030] Based on this, this application provides a method and system for intelligent management of the entire life cycle of weighing and batching equipment. It collects working data of loss-in-weight color masterbatch machine, couples and analyzes main unit consumption and material characteristic fluctuations, combines the mapping relationship between product color changes and batching, constructs a full-cycle adaptation system, builds a feedforward feedback collaborative control strategy, accurately controls the amount of color masterbatch added, reduces losses and improves efficiency, generates logs, and enhances the intelligent and high-precision operation capability of the equipment.

[0031] Figure 1 This application provides an illustration of an application scenario. In the plastics processing industry, during the weighing and batching process of a loss-in-weight color masterbatch machine, the method provided in this application is applied. Based on the operating data of the loss-in-weight color masterbatch machine, the fluctuation of the main machine's material usage, changes in material properties, and the correlation rules of color matching are analyzed in conjunction. A full production cycle adaptation model is established, and feedforward compensation and feedback correction algorithms are integrated to accurately and stably batch materials, reduce material loss, optimize production efficiency, retain data logs, and comprehensively enhance the high-precision intelligent operation level of the equipment.

[0032] Specifically, the method provided in this application can be applied to any server. The server interacts with the weighing sensor to obtain the working information set of the loss-in-weight color masterbatch machine provided by the weighing sensor. Through the time-series coupling analysis of the host consumption fluctuation information and the material characteristic fluctuation information, the blind spot of single-factor compensation is eliminated, and the intelligent management log of the weighing and batching equipment throughout its entire life cycle is output to the weighing and batching equipment maintenance personnel. Overall, the weighing and batching equipment has achieved a comprehensive improvement in high precision, high stability and intelligence.

[0033] The specific implementation method can be referred to in the following embodiments. The data mentioned in the embodiments are only for reference and examples, so that relevant personnel can better understand them.

[0034] Figure 2 This is a flowchart illustrating a method for intelligent management of the entire lifecycle of weighing and batching equipment according to an embodiment of this application. The method of this embodiment can be applied to servers in the above scenarios. For example... Figure 2 As shown, the method includes: S201. Obtain the working information set of the loss-in-weight color masterbatch machine. Based on the working information set of the loss-in-weight color masterbatch machine, analyze the synergistic impact characteristics of the service host consumption fluctuation and material characteristic changes on the batching information to obtain the dynamic consumption information set.

[0035] The working information set of the loss-in-weight color masterbatch machine refers to a data set used to characterize the operating status and material properties of the machine, with a weighing sensor as the data source. This information set specifically includes equipment operating conditions and color masterbatch material information. Equipment operating conditions include real-time consumption rate of the main unit (e.g., injection molding machine screw speed, extrusion volume), production stage indicators (start-up, stable, shutdown), temperature, and pressure parameters; color masterbatch material information includes material type, batch, humidity, flowability index, bulk density, and moisture content. Fluctuations in main unit consumption refer to the phenomenon where the material consumption rate of the injection molding machine or extruder deviates from the target value due to load changes at different production stages. Changes in material properties refer to fluctuations in the flowability, density, and moisture content of the color masterbatch due to factors such as environmental humidity and storage time. The process of analyzing synergistic impact characteristics involves aligning the main unit consumption fluctuation information and material property fluctuation information along the time axis, identifying the overlap and misalignment relationships between the two during the batching process, and then calculating the time-series coupling information and lag compensation requirements. The dynamic consumption information set is a data set based on the above analysis, which includes actual consumption rate, moisture content, flowability index, lag time, synergistic effect coefficient and compensation suggestions. Its function is to quantify the combined interference of the main unit and materials on the batching accuracy, and to provide basic data for subsequent control.

[0036] For example, in the continuous production of a certain ABS black hopper, the measured consumption rate of the injection molding machine during the stable phase fluctuated periodically between 0.45 and 0.53 kg / min. At the same time, the moisture content of the masterbatch measured by the moisture meter increased from the standard 0.3% to 0.52%, resulting in an increase in the angle of repose and a decrease in fluidity of about 6%. Through analysis, it was found that there was some overlap between the period of increased consumption rate and the period of decreased material fluidity. The synergistic influence coefficient was calculated, and a dynamic consumption information set containing normalized data at each moment was generated. Through this multi-dimensional synergistic analysis, the blind spots of single-factor compensation can be eliminated, and the dynamic interference sources in the batching process can be accurately captured.

[0037] This step aims to fully perceive the real-time changes in equipment operation and material status through multi-source data fusion, thereby obtaining a dynamic consumption information set that reflects the actual batching environment, laying a data foundation for subsequent precise mapping and control strategy generation.

[0038] S202. Based on the dynamic consumption information set, analyze the mapping relationship between the color changes required by plastic products and the ingredient information to obtain the full life cycle adaptation information set.

[0039] The color change required for plastic products can refer to the shifts in hue, saturation, and brightness caused by changes in process parameters such as mold temperature, screw speed, and cooling conditions during long-term production. Ingredient information refers to control parameters such as the real-time addition ratio of color masterbatch and the feeding speed. The process of analyzing the mapping relationship is based on a dynamic consumption information set, tracking the changing pattern of color deviation over production time, identifying color response delays caused by material characteristic lags, and inertia in addition deviations caused by fluctuations in host machine consumption, thereby establishing a correlation model between time-varying color demand information and ingredient adjustment amounts. The full lifecycle adaptation information set can be a data set generated based on this mapping relationship, including feedforward adjustment amounts, feedback compensation amounts, and their superposition ratios. Its function is to guide the system on how to dynamically allocate the proportion of predictive compensation and real-time correction throughout the entire production cycle to cope with the time-varying nature of color demand.

[0040] For example, online color detection collects product color difference data every 10 minutes. It finds that from the start to the 120th minute, the product hue gradually shifts towards blue while the brightness slightly decreases, with the total color difference showing an approximately linear increase. Combined with the material lag time (e.g., 0.8 seconds) in the dynamic consumption information set, it predicts that without intervention, the color difference will exceed the limit in the next 30 minutes. This allows for the calculation of the required feedforward adjustment, which, combined with real-time feedback correction, forms a full lifecycle adaptation information set including weighted allocation (e.g., 70% feedforward, 30% feedback). Through this mapping relationship, color drift trends can be predicted in advance, and compensation space can be reserved, effectively overcoming the control challenges caused by material response lag.

[0041] This step, by linking dynamic consumption information with color quality requirements, enables a shift from passive correction to proactive adaptation, and the batching strategy can cover various operating conditions throughout the entire equipment lifecycle.

[0042] S203. Based on the full lifecycle adaptation information set, generate a collaborative control strategy and output the full lifecycle intelligent management log of the weighing and batching equipment.

[0043] The collaborative control strategy refers to a set of execution instructions that includes adaptive feedforward compensation and feedback correction. Its generation method is based on the changing trend of the superposition ratio of feedforward adjustment and feedback compensation in the full lifecycle adaptation information set, combined with the time-varying information of current color demand, to calculate specific actuator action parameters (such as the screw speed increment of the loss-in-weight color masterbatch machine, vibration frequency adjustment value, etc.). The role of this strategy is to drive the loss-in-weight color masterbatch machine to adjust its feeding parameters in real time to offset the negative impacts of fluctuations in main unit consumption and changes in material characteristics. The intelligent management log for the weighing and batching equipment's full lifecycle is a text or data file that records the equipment's operating status, adjustment records, deviation analysis, and expected results. Its output format can include timestamps, production stages, key parameter values, and cumulative adjustment counts, used for tracing the production process and optimizing operation and maintenance decisions.

[0044] For example, based on the full lifecycle adaptation information set, a collaborative control strategy is generated to increase the proportion of color masterbatch addition by 0.106%, which is then converted into an instruction to increase the screw speed from 50 rpm to 50.2 rpm and sent to the actuator. Simultaneously, a management log is automatically generated, recording the current production stage (stable), main unit consumption rate deviation, material moisture content, color deviation value, specific adjustments for feedforward and feedback, and expected effects. This strategy generation and log output mechanism not only achieves automated execution of closed-loop control but also provides detailed data support for subsequent quality traceability and process optimization.

[0045] This step ultimately completes the closed loop from data analysis to decision execution, significantly improving the accuracy and stability of ingredient mixing through adaptive collaborative control, and enhancing the system's intelligence level through log-based management.

[0046] Example 2: In another optional embodiment, the method of analyzing the synergistic impact characteristics of service host consumption fluctuations and material characteristic changes on batching information based on the working information set of the loss-in-weight color masterbatch machine to obtain a dynamic consumption information set further includes the following steps: Step 1: The working information set of the loss-in-weight color masterbatch machine includes equipment operating conditions and color masterbatch material information; The equipment operating conditions can include parameters such as the real-time consumption rate of the main unit, production stage indicators, screw speed, back pressure, and barrel temperature. These parameters reflect the main unit's demand for material throughput at different times. The masterbatch material information can include physicochemical properties such as the type of masterbatch in the current batch, moisture content, bulk density, flowability index, and angle of repose. This information comes from periodic sampling by online moisture meters, weighing sensors, and material characteristic detection modules. For example, the production stage indicators in the equipment operating conditions can be divided into the start-up preheating period, the stable production period, and the shutdown transition period. The moisture content in the masterbatch material information can be obtained in real time through an infrared moisture meter at a frequency of once per minute. When the detected moisture content increases from the standard 0.3% to 0.5%, this value is included in the working information set. By constructing a complete information set that includes dynamic data from the equipment side and static / quasi-static data from the material side, a comprehensive data foundation is provided for subsequent decoupled analysis of main unit fluctuations and material characteristics, avoiding analytical biases caused by missing input dimensions.

[0047] Step 2: Based on the equipment operating conditions, analyze the impact of the main unit's consumption rate changes at different production stages on the amount of masterbatch added, and obtain the main unit consumption fluctuation information; The main machine consumption fluctuation information refers to dynamic deviation data reflecting the changes in the main machine's material demand over time. This is obtained by comparing the real-time collected main machine consumption rate with a preset target consumption rate and performing a weighted analysis based on the current production stage. Specifically, the current production stage is first identified. If it is in a stable production period, the focus is on analyzing the periodic small fluctuations in the consumption rate around the target value; if it is in the start-up or shutdown phase, the focus is on analyzing the step change trend of the consumption rate. This information quantifies the immediate disturbance of the main machine's addition of masterbatch. Its determination includes calculating the percentage dynamic deviation between the real-time rate and the target value, and identifying periods of accelerated consumption where multiple consecutive sampling points exceed a threshold. For example, when the injection molding machine is in a stable operating phase, and the measured consumption rate fluctuates between 0.45 kg / min and 0.53 kg / min in a 3-minute period, with the average value slightly higher than the target value of 0.48 kg / min, this fluctuation amplitude and phase are recorded as main machine consumption fluctuation information, and the peak consumption interval is marked. By independently analyzing the fluctuations in main unit consumption, we can accurately capture the direct impact of equipment-side factors on batching accuracy, providing a basis for distinguishing between equipment interference and material interference.

[0048] Step 3: Based on the material information of the masterbatch, analyze the influence characteristics of changes in material flowability, density and moisture content on the batching accuracy, and obtain material characteristic fluctuation information; The material characteristic fluctuation information refers to a set of data characterizing changes in the physical properties of masterbatch that lead to changes in feeding behavior. This information is obtained by analyzing the changes in the material's cohesive-adhesive state caused by changes in moisture content, and then deriving the characteristics of changes in apparent flowability and bulk density. Specifically, an increase in moisture content leads to increased surface viscosity of the masterbatch, resulting in agglomeration, which reduces the material's flowability index and changes its bulk density. This change directly affects the feeding response speed and actual output of the loss-in-weight scale. The generation process of this information includes: first, calculating the degree of material cohesion based on moisture content data, and then mapping the percentage decrease in flowability and the increment of feeding lag time using historical experimental models. For example, when the moisture content of the masterbatch is monitored to increase from 0.3% to 0.52%, its angle of repose is calculated to increase from 38° to 42.3°, and the flowability index decreases from 1.0 to 0.93 accordingly. This means that the amount of material fed at the same opening is reduced by about 3%, and the lag time between the feeding command and the actual discharge increases from 0.5 seconds to 0.8 seconds. These quantitative indicators constitute the material characteristic fluctuation information. By deeply analyzing the influence mechanism of the material's micro-characteristics on the macro-feeding behavior, it is possible to effectively identify the material performance drift caused by environmental humidity or storage time, and ensure that the batching control can respond to the nonlinear changes of the material itself.

[0049] Step 4: Based on the main unit consumption fluctuation information and the material characteristic fluctuation information, analyze the synergistic impact characteristics of the interaction between the two in the batching process on the batching information, and obtain the dynamic consumption information set; The dynamic consumption information set refers to a comprehensive control basis that integrates equipment-side fluctuations and material-side fluctuations and their coupling effects. It is obtained by aligning the main unit's consumption fluctuation information and material characteristic fluctuation information on the time axis, analyzing their temporal overlap and misalignment, and calculating the lag compensation requirement. Specifically, it analyzes the relative positions of the moments when the main unit's consumption rate changes and the material's flowability changes to determine whether there is a superposition effect of simultaneous consumption peaks and flowability troughs, or whether there is a lag compensation requirement due to a phase difference between the two. This information set not only includes their independent fluctuation data but also includes a synergistic impact coefficient characterizing their interaction and compensation suggestions. For example, if the main unit is detected to be in a period of accelerated consumption (high demand), while the material's flowability decreases due to high moisture content (difficulty in feeding), the two overlap on the time axis, resulting in a high synergistic impact coefficient, indicating that a significant feedforward compensation is needed to offset the double negative impact. Conversely, if the two are misaligned, the synergistic impact is smaller. By comprehensively analyzing the synergistic effects between the host and materials, the blind spots of single-factor compensation are eliminated, enabling the generated dynamic consumption information set to accurately reflect the real material requirements under complex working conditions, providing a reliable input for the subsequent generation of a high-precision full life cycle adaptation information set.

[0050] Example 3: In one embodiment, the process of constructing the host consumes fluctuation information further includes the following steps: Step 1: Based on the equipment operating conditions, analyze the dynamic deviation information between the real-time consumption rate of the service host and the target value to identify the current stage of production; The equipment operating conditions refer to the real-time status data generated during the operation of the injection molding machine or extruder served by the loss-in-weight color masterbatch machine. This data includes parameters such as screw speed, injection rate, back pressure, melt temperature, and material extrusion rate per unit time. The real-time consumption rate of the service host is the instantaneous flow rate value obtained by collecting material extrusion data from the above equipment operating conditions and performing differential calculations based on timestamps. Its function is to characterize the actual demand intensity of the host for raw materials at the current moment. The target value is the theoretical consumption rate set according to the preset production process formula and is used as a benchmark reference. Dynamic deviation information refers to the difference between the real-time consumption rate and the target value, and its rate of change. This information reflects the degree of deviation of the host load from the standard operating conditions.

[0051] Specifically, a sliding window algorithm is used to smooth the real-time consumption rate and calculate its dynamic deviation from the target value. When the dynamic deviation is within a preset positive threshold range for multiple consecutive sampling periods, the host is determined to be in a high-load acceleration phase; when the dynamic deviation fluctuates slightly near zero and the variance is lower than a set threshold, the host is determined to be in a stable production phase; when the dynamic deviation shows a continuous negative increasing trend and the rate is lower than the minimum operating threshold, the host is determined to be in a shutdown or deceleration phase. For example, in an ABS hopper production scenario, the target consumption rate is set to 0.48 kg / min. If the rate of 10 consecutive data points (sampling interval of 0.5 seconds) exceeds 0.50 kg / min, the current production stage is identified as the consumption acceleration period; if the rate fluctuates between 0.47 and 0.49 kg / min, it is identified as the stable operation period.

[0052] This dynamic deviation-based stage identification mechanism enables contextual awareness of host load changes, providing an accurate time-dimensional benchmark for formulating differentiated ingredient strategies for different stages.

[0053] Step 2: Based on the current production stage, analyze the dynamic impact of the phased changes in the main unit's consumption rate throughout the entire production cycle on the real-time addition ratio of color masterbatch, and obtain the main unit consumption fluctuation information. The production cycle can refer to the complete operational period from equipment startup and stable operation to shutdown and cleaning. Phased changes can refer to the specific time-varying patterns of the main unit's consumption rate during different production stages (such as the warm-up period, stable production period, and shutdown transition period). For example, the rate rapidly rises from zero to the set value during startup, fluctuates slightly around the set value during the stable phase, and gradually decreases to zero during shutdown. The real-time masterbatch addition ratio refers to the mass ratio of masterbatch addition to main material consumption per unit time, which directly determines the color concentration of the final product. Dynamic influences refer to the fact that due to the phased fluctuations in the main unit's consumption rate, the masterbatch addition ratio required to maintain a constant color is not fixed but needs to be dynamically adjusted in the opposite or same direction as changes in the main unit's load to offset the uneven mixing or metering lag effects caused by changes in flow rate.

[0054] Specifically, based on the identified current production stage, a pre-stored stage characteristic model is invoked to analyze its dynamic impact on the addition ratio. During stable production, the dynamic impact is mainly manifested as periodic fluctuation compensation, i.e., the addition ratio is fine-tuned in advance according to the peaks and troughs of the consumption rate. During transitional stages such as start-up or shutdown, the dynamic impact is mainly manifested as large inertia compensation, i.e., considering material residue during screw pressurization or depressurization, a significant feedforward correction of the addition ratio is required. For example, when the main unit is identified as being in an accelerated consumption phase, analysis shows that the increased material filling degree in the screw channel and the resulting rise in shear heat may lead to changes in the dispersibility of the masterbatch. Therefore, the real-time addition ratio of the masterbatch needs to be dynamically increased by 0.05%~0.1% from the theoretical value to compensate for the shortened mixing time effect caused by the increased flow rate; conversely, it is adjusted downwards accordingly during deceleration. The resulting main unit consumption fluctuation information not only includes the current consumption rate value but also encapsulates the correction instructions for the masterbatch addition ratio over a future period based on this rate change trend.

[0055] Through the above analysis, the abstract production stages are transformed into specific proportional adjustment factors, enabling the quantification of the extent to which the host machine's consumption fluctuations affect the batching accuracy under different operating conditions. This step is closely linked to the above, using the identified stage labels as contextual indexes to accurately extract the corresponding dynamic influence patterns. This eliminates the problem of insufficient adaptability of a single fixed proportional control when facing drastic changes in host machine load, significantly improving the response speed and tracking accuracy of masterbatch addition.

[0056] Example 4: In one optional embodiment, the process of constructing the material characteristic fluctuation information further includes: Step 1: Based on the material information of the color masterbatch, analyze the influence of the change in material moisture content on the agglomeration state and surface adhesion of the color masterbatch, and obtain the material cohesion-adhesion state information; The material information for color masterbatch refers to a set of data on the physicochemical properties of the color masterbatch obtained through online detection modules or offline laboratory analysis. This includes parameters such as real-time moisture content, batch number, and storage time. Moisture content is a key variable affecting the microstructure of the color masterbatch. It can be data collected in real-time by an infrared moisture meter installed at the hopper outlet, or the difference between a preset standard reference value and the actual measured value. This step aims to reveal how moisture content alters the interparticle interaction forces, thereby quantifying the material's micro-aggregation tendency. Specifically, when the moisture content increases, water molecules form liquid bridges on the surface of the color masterbatch particles, significantly increasing capillary and van der Waals forces between particles, making them more prone to aggregation. Simultaneously, the surface adhesion of the particles increases, making them more likely to adhere to the silo wall or the inner wall of the discharge pipe. The material cohesion-adhesion state information is calculated based on a comparison of the real-time moisture content with a preset critical moisture content threshold, combined with historical experimental data models. It includes an aggregation level index and a surface adhesion coefficient. For example, when the moisture content of the masterbatch is detected to increase from the standard 0.3% to 0.52%, based on the preset physical property mapping table, the agglomeration level is determined to change from a discrete state to a slightly agglomerated state, and the surface adhesion coefficient is calculated to increase from 1.0 to 1.15. This means that the cohesion between particles has increased by 15%, and the risk of adhesion to the metal wall has increased significantly. Through this analysis from moisture content to microscopic state, the invisible internal physical property changes can be transformed into calculable intermediate state parameters, laying the foundation for the derivation of subsequent macroscopic flow characteristics.

[0057] Step 2: Based on the material's cohesive-attachment state information, analyze the changes in the material's apparent flowability and bulk density caused by changes in moisture content to obtain material property fluctuation information.

[0058] In this step, the material's cohesive-attachment state information serves as the input condition and directly determines the evolution trend of the material's macroscopic flow behavior. Apparent flowability refers to the ease with which masterbatch passes through the feed inlet under gravity or external force, typically characterized by the angle of repose or flow index. Bulk density refers to the mass of masterbatch per unit volume, influenced by the density of particle arrangement. This step aims to establish a causal chain between the microscopic state and macroscopic batching accuracy, identifying the root causes of feed deviations due to changes in physical properties. The executing entity analyzes how increased cohesion hinders relative particle sliding, thereby deriving a decrease in flowability and a loosening of the packing structure. Specifically, as the agglomeration level in the material's cohesive-attachment state information increases, the frictional resistance between particles increases, leading to a larger angle of repose and a decrease in the flow index; simultaneously, the formation of agglomerates increases the porosity between particles, resulting in a decrease in overall bulk density. For example, based on the surface adhesion coefficient of 1.15 obtained in the previous step, it is calculated that the angle of repose of the material will increase from the standard 38° to 42.3°, and the flow index will decrease from 1.0 to 0.93, indicating that the amount of material fed through a fixed orifice in the same time period will decrease by about 3%; at the same time, the bulk density will decrease from 0.85 g / cm³. 3 Reduced to 0.82 g / cm³ 3 These quantified changes in apparent flowability and bulk density collectively constitute the material property fluctuation information. Therefore, the system can accurately predict material feeding delays and insufficient feeding caused by material moisture, providing a precise physical basis for generating dynamic compensation strategies and effectively avoiding color deviations caused by material property drift.

[0059] Example 5: In another embodiment, the method further includes the following steps: Based on the host consumption fluctuation information and combined with the material characteristic fluctuation information, the method analyzes the synergistic impact characteristics of their interaction during the batching process on the batching information to obtain a dynamic consumption information set. Step 1: Based on the main unit consumption fluctuation information and the material characteristic fluctuation information, analyze the overlap and misalignment relationship between the main unit consumption rate change and the material feed rate fluctuation on the time axis to obtain time-series coupling information; The main unit consumption fluctuation information refers to the dynamic deviation sequence of the real-time consumption rate of the main unit relative to the target value at different production stages. This is derived from continuous acquisition and sliding window analysis of operating data such as screw speed and injection rate of the injection molding machine or extruder. The material characteristic fluctuation information refers to the set of characteristics showing changes in the flowability index, bulk density, and feeding lag time of the masterbatch due to changes in environmental factors such as moisture content and temperature. Analyzing the overlap and misalignment of these two types of information on the time axis involves aligning the timestamps of both types of information and calculating the intersection ratio and phase difference between the time periods when the main unit consumption rate is in the peak range (e.g., exceeding the target value by 5%) and the time periods when the material flowability is in the trough range (e.g., the angle of repose is greater than a preset threshold). This time alignment mechanism can identify dangerous overlap moments of high consumption and low flowability, as well as misalignment moments where the consumption peak precedes the deterioration of flowability. For example, when the host load consumption rate is consistently above 0.50 kg / min between the 90th and 93rd minutes, while the material moisture content increases during the same period, causing the flowability index to drop from 1.0 to 0.93 and the material feeding lag time to increase by 0.3 seconds, a significant temporal overlap is determined, and temporal coupling information is generated to mark the overlapping period and the degree of overlap. This step aims to quantify the synchronicity of host load changes and material physical property changes over time, thereby providing a basis for subsequent judgments on whether to initiate collaborative compensation, effectively avoiding the one-sidedness of making decisions based solely on the magnitude of a single factor.

[0060] Step 2: Based on the time-series coupling information, analyze the lag compensation requirement of material flowability changes on the actual addition amount of color masterbatch when the consumption rate changes, and obtain the dynamic consumption information set.

[0061] In this context, the lag compensation requirement refers to the feedforward adjustment that needs to be applied in advance to offset the delay in feeding response caused by increased internal friction or adhesion of the material, in scenarios where the main machine's consumption rate changes rapidly and is accompanied by fluctuations in material flowability. The analysis process specifically includes: based on the degree of overlap and misalignment phase identified in the timing coupling information, calculating the nonlinear hindrance effect of the instantaneous change in material flowability on the actual feeding quantity at the rising or falling edge of the consumption rate. When a sharp increase in the consumption rate is detected while the material flowability decreases simultaneously, the actual feeding quantity response will lag significantly behind the control command. At this time, the system calculates the additional compensation coefficient needed to fill the material gap caused by this time difference. For example, if the timing coupling information shows that the main machine's consumption rate will increase by 10% in the next 30 seconds, and the feeding lag time caused by the current material moisture content is 0.8 seconds, then it is calculated that a command to increase the screw speed needs to be issued 0.8 seconds in advance, and the compensation amount is set to 1.05 times the theoretical requirement to overcome the resistance caused by the decrease in flowability. This step, based on the timing coupling information obtained in the previous step, transforms static material parameters into a dynamic compensation strategy. The host machine consumption fluctuation information and material characteristic fluctuation information are used in conjunction here to jointly determine the timing and magnitude of compensation, thus realizing the transformation from passive feedback to active feedforward control. The resulting dynamic consumption information set not only includes the current consumption rate and material status but also embeds hysteresis compensation predictions for future short-term windows, significantly improving the response speed and accuracy of the batching system under complex operating conditions.

[0062] Example 6: In another optional embodiment, the method of analyzing the mapping relationship between the required color changes of plastic products and the ingredient information based on the dynamic consumption information set to obtain a full life cycle adaptation information set further includes the following steps: Step 1: Based on the dynamic consumption information set, analyze the variation of hue, saturation, and brightness deviations of the colors required for plastic products at each production stage with production time, and obtain time-varying information on color demand. Among them, time-varying color demand information refers to a set of quantitative data reflecting the evolution of finished product color parameters (hue H, saturation S, lightness L, or Lab value) over time due to equipment operating condition drift, material characteristic fluctuations, and the cumulative effects of environmental factors during continuous production of plastic products. This information is obtained by collecting finished product color data measured in real time by an online spectrophotometer or visual inspection system, and combining it with the dynamic consumption information set obtained in the aforementioned steps (including main machine consumption rate deviation, material flowability index, and lag time, etc.) for time-series correlation analysis. Its function is to reverse-map the quality performance of the end product back to the batching control link, and identify the inertial trend and response delay characteristics of color deviation. Specifically, firstly, the main machine consumption fluctuation characteristics and material characteristic fluctuation characteristics of the current production stage are extracted from the dynamic consumption information set and used as input variables to construct a color deviation prediction model; then, the deviations of hue, saturation, and lightness actually measured in historical time periods relative to the standard target values ​​are statistically analyzed, and the slope and curvature of these deviations as production time extends are analyzed. For example, in continuous production of ABS black hoppers, if the dynamic consumption information set shows that the material moisture content increases from 0.3% to 0.52%, causing a 0.3-second increase in feeding lag time, and the main unit is in a high consumption rate phase, the color difference data over the past 60 minutes will be analyzed. This will reveal a negative linear increase in the hue (b) value (i.e., gradually becoming more bluish), and a slow decrease in the lightness (L) value. The average hourly color difference (ΔE) will increase by approximately 0.6, and it will be predicted that without intervention, the color difference will exceed the acceptable threshold after 30 minutes. This time-based pattern analysis allows for early detection of color drift, providing forward-looking data support for subsequent dynamic adjustments and effectively preventing quality defects caused by delayed feedback.

[0063] Step 2: Based on the time-varying information of color demand, analyze the dynamic adjustment requirements of the real-time addition ratio of color masterbatch due to the fluctuation of color demand and the compensation amount caused by the lag of material characteristics, and obtain the full life cycle adaptation information set. The full lifecycle adaptation information set refers to a set of color masterbatch addition ratio correction schemes generated by comprehensively considering the immediate adjustment needs and historical lag effects for color quality requirements at different time points throughout the entire production cycle. This information set is based on the aforementioned time-varying color demand information. By decoupling the immediate driving factors of color fluctuations from the lag factors of material response, it calculates the feedforward adjustment amount and the feedback compensation amount separately, and then superimposes them according to dynamic weights. Its function is to generate a set of collaborative control instructions that can both cope with current color deviations and offset future trend drifts, ensuring the stability of batching accuracy throughout the entire lifecycle. Specifically, firstly, the temporal correlation between the time-varying trend of color deviation (such as the rate of deviation increase) and the lag compensation needs of material characteristics (such as material feeding delay time) in each production stage is analyzed to determine the degree of coupling between deviation and lag; then, the superposition ratio of the feedforward adjustment amount (used to offset predicted future deviations) and the feedback compensation amount (used to correct current measured deviations) is dynamically set according to the degree of coupling. For example, when analysis reveals a strong inertial growth trend in color deviation and a long material lag time, the weight of the feedforward adjustment will be automatically increased (e.g., set to 70%). Based on the predicted color difference after 30 minutes, a feedforward adjustment of 0.12% to increase the proportion of color masterbatch needs to be calculated. Simultaneously, this is combined with the PID feedback compensation of 0.012% calculated based on the current real-time color difference. The two are then combined to form the final adjustment command. Conversely, if the color fluctuation is highly random and has a small lag, the feedforward weight is reduced, relying primarily on feedback correction. This result provides precise quantitative basis for the subsequent generation of collaborative control strategies, thereby significantly improving the adaptive capability under complex operating conditions. It realizes a shift from passive correction to proactive prevention in the control mode, effectively reducing the risk of downtime and material waste caused by color non-compliance.

[0064] Example 7: In another embodiment, the process of constructing the time-varying information of color demand further includes the following steps: Step 1: Based on the dynamic consumption information set, analyze the inertial trend of the deviation between the actual amount of color masterbatch added and the preset ratio over continuous production time to obtain deviation inertia information; The dynamic consumption information set is a dataset containing time-series coupling characteristics generated after considering the fluctuations in the main unit's consumption and the fluctuations in material characteristics. Deviation inertia information refers to the continuity of the trend of the actual amount of color masterbatch added deviating from the preset theoretical ratio over time. It reflects the magnitude of the deviation that the batching system might reach in the future under the current control strategy without intervention. This deviation inertia information is obtained by performing difference calculations between the actual addition data and the preset ratio data collected during a continuous production period, and then extracting the trend term of the deviation sequence using a sliding window algorithm or time series prediction model (such as the ARIMA model or exponential smoothing). Its function is to quantify the memory effect and drift speed of color deviation, providing a predictive benchmark for subsequent feedforward compensation. For example, in the production process of ABS black hoppers, if it is detected that the actual amount of masterbatch added has been consistently lower than the preset ratio by 0.05% to 0.08% over the past 60 minutes, and this negative deviation shows a linear increasing trend, then by calculating the slope of this trend, it can be predicted that the cumulative deviation will reach a critical value that causes the product color difference ΔE to exceed 1.5 after the next 30 minutes, thereby generating deviation inertia information containing this predicted trajectory. Through this quantitative analysis of deviation inertia trends, potential quality risks can be identified in advance, transforming passive post-event correction into proactive pre-event prediction.

[0065] Step 2: Based on the deviation inertia information, analyze the time-series correction requirements for hue, saturation, and brightness deviations caused by the lag in material characteristics, and obtain time-varying information on color requirements; Among them, the time-varying information of color demand is a comprehensive control basis that integrates deviation prediction trends and physical lag effects. Material characteristic lag can refer to the time delay required for the color masterbatch to actually reach the melting and mixing zone and display a color effect after the control command is issued, due to factors such as changes in the moisture content of the color masterbatch, reduced fluidity, or mechanical transmission gaps in the equipment. Hue, saturation, and lightness deviations correspond to the degree of deviation of the a / b value, chroma, and L value in the CIELAB color space, respectively. Timing correction requirements refer to the control quantity and its timing advance that need to be applied in advance at the current moment to offset the above-mentioned lag effects. This timing correction requirement is calculated by using a phase lead compensation algorithm based on the future deviation curve predicted by deviation inertia information, combined with the measured or estimated material lag time (e.g., 0.8 seconds to 1.2 seconds). Specifically, when the deviation inertia information shows that the color will drift towards a bluer direction, if there is also a 1-minute color response delay due to material moisture, it is necessary to calculate the proportion of color masterbatch that should be added at the current moment to ensure that the compensation amount that takes effect 1 minute later can exactly offset the prediction deviation at that time. For example, for a batch of masterbatch with high moisture content leading to decreased flowability, a 0.9-second feeding lag was identified. Based on this, the +0.1% ratio adjustment command, originally scheduled to be executed at time T, was advanced to time T-0.9 seconds, and the hue correction coefficient was adjusted simultaneously to match the expected change in brightness. Thus, by introducing a timing correction mechanism, the problem of control overshoot or insufficient response caused by physical lag was effectively solved, significantly improving the dynamic stability of color control throughout its entire lifecycle.

[0066] Example 8: In another embodiment, the method further includes the following steps: based on the time-varying color demand information, analyzing the dynamic adjustment requirements of color demand fluctuations on the real-time addition ratio of color masterbatch and the compensation amount caused by material characteristic lags, to obtain the full life cycle adaptation information set. Step 1: Based on the time-varying information of color demand, analyze the temporal correlation between the time-varying trend of color deviation and the lag compensation demand of material characteristics in each production stage to obtain deviation-lag coupling information; Among them, time-varying color demand information refers to a data set recording the changes in hue, saturation, and brightness deviations of plastic products at different production moments. This data originates from trend fitting and inertial prediction of online color detection data during continuous production. Material characteristic lag compensation demand is a correction calculated based on the material feeding response delay time caused by changes in physical parameters such as masterbatch moisture content and flowability index. Deviation-lag coupling information is obtained by aligning the time-varying trend curve of color deviation with the time axis of material characteristic lag compensation demand. It characterizes the degree of overlap and mutual influence between color drift speed and material feeding delay effect in the time dimension. Specifically, the product or weighted integral of the color deviation change rate and the lag time length is calculated to quantify the coupling strength between the two at a specific production stage. For example, when a linear and rapid increase in color deviation is detected, and the material feeding lag time increases significantly due to high moisture content, the temporal overlap of the two will cause the actual addition action to lag far behind the demand change. In this case, the calculated deviation-lag coupling information will show a high-strength positive correlation coupling value. This time-series correlation analysis can accurately identify the sources of dynamic errors that cannot be resolved by relying solely on the current color difference feedback, providing a basis for the weight allocation of subsequent control strategies.

[0067] Step 2: Based on the deviation-hysteresis coupling information, analyze the superposition ratio of the feedforward adjustment and feedback compensation of the real-time addition ratio of color masterbatch to obtain the full life cycle adaptation information set; The feedforward adjustment is a compensation value pre-calculated based on the predicted future color deviation trend, used to offset known systematic drift. The feedback compensation is a correction value calculated by a closed-loop controller (such as a PID algorithm) based on the real-time measured current color deviation, used to eliminate random disturbances. The superposition ratio refers to the weighting coefficients of the feedforward adjustment and feedback compensation when they together constitute the total adjustment. This superposition ratio is dynamically determined based on the strength of the deviation-hysteresis coupling information: when the deviation-hysteresis coupling information shows high coupling strength (i.e., significant hysteresis effect and stable color trend), the weighting ratio of the feedforward adjustment is automatically increased, and the weighting ratio of the feedback compensation is decreased, to utilize predictive information to intervene in control in advance and overcome the response delay caused by hysteresis; conversely, when the coupling strength is low but random disturbances are large, the weighting ratio of the feedback compensation is increased to enhance the system's anti-interference capability. For example, in a certain production stage, if the analysis shows that the deviation-hysteresis coupling coefficient exceeds the preset threshold of 0.8, it indicates that material hysteresis has a significant impact on color control. The feedforward weight is then adjusted to 75%, and the feedback weight to 25%. In another stage, if the coupling coefficient is only 0.2, the feedforward weight is reduced to 40%, and the feedback weight is increased to 60%. The final generated full lifecycle adaptation information set not only includes specific adjustment values ​​but also fully records the applicable feedforward and feedback superposition ratio at the current moment, ensuring that the control strategy adapts and evolves with the production state. This achieves dynamic shift of the control center of gravity, effectively avoiding overshoot or slow response problems caused by fixed ratios.

[0068] Example 9: In one embodiment, the method of generating a collaborative control strategy based on the full lifecycle adaptation information set and outputting a full lifecycle intelligent management log for the weighing and batching equipment further includes the following steps: Step 1: Based on the full lifecycle adaptation information set, analyze the changing trend of the superposition ratio of feedforward adjustment and feedback compensation in each production stage to obtain dynamic compensation information; The full lifecycle adaptation information set is the data set defined above, which includes the superposition ratio of feedforward adjustment and feedback compensation for the real-time addition ratio of masterbatch. Dynamic compensation information refers to a data sequence formed by further extracting the evolutionary pattern over time based on the aforementioned superposition ratio. It is used to characterize the changes in the control system's dependence on predictive compensation and real-time correction at different production stages. Specifically, this dynamic compensation information is obtained by continuously monitoring the numerical fluctuations of feedforward and feedback weights in each production stage. For example, in the stable operation stage of injection molding production, if the color response delay caused by material characteristic lag is detected to gradually increase, the proportion of feedforward adjustment will be automatically increased, causing the feedforward weight to gradually rise from the initial 60% to 71%, while the variance of the feedback weight will decrease accordingly. This trajectory of weight changes over time constitutes the core content of the dynamic compensation information. Through this detailed analysis of the trend of superposition ratio changes, the key factors dominating color deviation in the current production environment can be accurately identified, thus providing a dynamic basis for generating precise control strategies.

[0069] Step 2: Based on the dynamic compensation information and the time-varying information of color requirements, generate a collaborative control strategy that includes adaptive feedforward compensation and feedback correction, and output the intelligent management log of the weighing and batching equipment throughout its entire life cycle.

[0070] The collaborative control strategy is a set of specific execution instructions generated based on a weight allocation scheme determined by dynamic compensation information and combined with the time-varying color demand information regarding the timing correction requirements for hue, saturation, and brightness deviations. Adaptive feedforward compensation refers to the action of adjusting the proportion of color masterbatch added in advance based on the predicted future color deviation trend, while feedback correction refers to the action of fine-tuning based on the color difference data detected in real time. The intelligent management log of the weighing and batching equipment throughout its entire life cycle is an audit file that records key data of the entire control process. Its contents include fields such as timestamp, production stage identifier, host consumption rate, material characteristic parameters, color deviation value, specific adjustment amounts of feedforward and feedback, final actuator actions, and expected effects. Specifically, the process of generating the collaborative control strategy involves applying the feedforward weights from the dynamic compensation information to the predicted deviation value in the time-varying color demand information to calculate the feedforward adjustment amount, and simultaneously applying the feedback weights to the real-time color difference value to calculate the feedback correction amount. The two are then superimposed and converted into the execution parameters of the loss-in-weight color masterbatch machine (such as screw speed increment or vibration frequency). For example, when dynamic compensation information shows a feedforward weight of 71% and time-varying color demand information predicts that the color difference will exceed the standard in 30 minutes, a feedforward instruction to increase the color masterbatch ratio by 0.094% is generated. Combined with a feedback instruction of 0.012% based on the current real-time color difference calculation, the final output is a control strategy that increases the screw speed from 50 rpm to 50.2 rpm. Simultaneously, all the above-mentioned intermediate values, decision-making basis, and final execution results are packaged and written into the management log, forming a complete and traceable record. This strategy generation mechanism, which combines dynamic trend analysis with real-time demand mapping, not only achieves end-to-end closed-loop control of color deviation but also constructs a transparent operational audit trajectory, facilitating subsequent equipment maintenance and process optimization.

[0071] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0072] Figure 3 This is a schematic diagram of the structure of an intelligent management system for the entire lifecycle of a weighing and batching equipment provided in an embodiment of this application, as shown below. Figure 3 As shown, the intelligent management system 300 for the entire life cycle of weighing and batching equipment in this embodiment includes: a dynamic consumption module 301, a mapping relationship module 302, and a strategy generation module 303.

[0073] The dynamic consumption module 301 is used to acquire the working information set of the loss-in-weight color masterbatch machine, and based on the working information set of the loss-in-weight color masterbatch machine, analyze the synergistic influence characteristics of the service host consumption fluctuation and material characteristic changes on the batching information to obtain the dynamic consumption information set; the mapping relationship module 302 is used to analyze the mapping relationship between the color change required by the plastic product and the batching information based on the dynamic consumption information set to obtain the full life cycle adaptation information set; the strategy generation module 303 is used to generate a collaborative control strategy according to the full life cycle adaptation information set, and output the full life cycle intelligent management log of the weighing and batching equipment.

[0074] Optionally, when the dynamic consumption module 301 analyzes the synergistic impact characteristics of the service host consumption fluctuation and material characteristic changes on the batching information based on the loss-in-weight color masterbatch machine's operating information set to obtain the dynamic consumption information set, it is specifically used for: the loss-in-weight color masterbatch machine's operating information set including equipment operating conditions and color masterbatch material information; based on the equipment operating conditions, analyzing the impact characteristics of the change in the host's consumption rate at different production stages on the amount of color masterbatch added to obtain host consumption fluctuation information; based on the color masterbatch material information, analyzing the impact characteristics of changes in material flowability, density, and moisture content on batching accuracy to obtain material characteristic fluctuation information; based on the host consumption fluctuation information, combined with the material characteristic fluctuation information, analyzing the synergistic impact characteristics of the interaction between the two in the batching process on the batching information to obtain the dynamic consumption information set.

[0075] Optionally, the dynamic consumption module 301, during the process of constructing the host consumption fluctuation information, is specifically used to: analyze the dynamic deviation information between the real-time consumption rate of the service host and the target value based on the operating conditions of the equipment, and identify the current production stage; and, based on the current production stage, analyze the dynamic impact of the stage-by-stage changes in the host's consumption rate throughout the entire production cycle on the real-time addition ratio of color masterbatch, thereby obtaining the host consumption fluctuation information.

[0076] Optionally, the dynamic consumption module 301, during the construction process of the material characteristic fluctuation information, is specifically used to: analyze the influence of material moisture content changes on the agglomeration state and surface adhesion of the color masterbatch based on the color masterbatch material information, and obtain material cohesion-adhesion state information; based on the material cohesion-adhesion state information, analyze the change characteristics of material apparent flowability and bulk density caused by changes in moisture content state, and obtain the material characteristic fluctuation information.

[0077] Optionally, when the dynamic consumption module 301 analyzes the synergistic impact characteristics of the interaction between the host consumption fluctuation information and the material characteristic fluctuation information on the batching information during the batching process to obtain a dynamic consumption information set, it is specifically used to: analyze the overlap and misalignment relationship between the host consumption rate change and the material feed amount fluctuation on the time axis based on the host consumption fluctuation information and the material characteristic fluctuation information to obtain time-series coupling information; and analyze the lag compensation requirement of the material flowability change on the actual addition amount of color masterbatch when the consumption rate changes, based on the time-series coupling information, to obtain the dynamic consumption information set.

[0078] Optionally, when the mapping relationship module 302 analyzes the mapping relationship between the color changes required by the plastic product and the ingredient information based on the dynamic consumption information set to obtain the full life cycle adaptation information set, it is specifically used to: analyze the variation law of hue, saturation and brightness deviation of the color required by the plastic product at each production stage with the production time based on the dynamic consumption information set to obtain the time-varying information of color demand; and analyze the dynamic adjustment requirements of the color demand fluctuation on the real-time addition ratio of color masterbatch and the compensation amount caused by the lag of material characteristics, based on the time-varying information of color demand to obtain the full life cycle adaptation information set.

[0079] Optionally, the mapping module 302, during the construction process of the time-varying color demand information, is specifically used to: analyze the inertial trend of the deviation between the actual amount of color masterbatch added and the preset ratio over continuous production time based on the dynamic consumption information set, and obtain deviation inertial information; based on the deviation inertial information, analyze the time-series correction requirements for hue, saturation, and brightness deviations caused by the lag in material characteristics for color response delay, and obtain the time-varying color demand information.

[0080] Optionally, when the mapping relationship module 302 analyzes the dynamic adjustment requirements of the color demand fluctuation on the real-time addition ratio of color masterbatch and the compensation amount caused by the lag in material characteristics based on the time-varying color demand information to obtain the full life cycle adaptation information set, it is specifically used to: analyze the temporal correlation between the time-varying trend of color deviation and the compensation requirements for lag in material characteristics in each production stage based on the time-varying color demand information to obtain deviation-lag coupling information; and analyze the superposition ratio of the feedforward adjustment amount and the feedback compensation amount of the real-time addition ratio of color masterbatch based on the deviation-lag coupling information to obtain the full life cycle adaptation information set.

[0081] Optionally, when the strategy generation module 303 generates a collaborative control strategy based on the full lifecycle adaptation information set and outputs the intelligent management log of the weighing and batching equipment's full lifecycle, it is specifically used to: analyze the changing trend of the superposition ratio of feedforward adjustment and feedback compensation in each production stage based on the full lifecycle adaptation information set to obtain dynamic compensation information; generate the collaborative control strategy including adaptive feedforward compensation and feedback correction based on the dynamic compensation information and combined with the time-varying color requirement information, and output the intelligent management log of the weighing and batching equipment's full lifecycle.

[0082] The system in this embodiment can be used to execute the methods of any of the above embodiments, and its implementation principle and technical effect are similar, so they will not be described again here.

Claims

1. A method for intelligent management of the entire lifecycle of weighing and batching equipment, characterized in that, include: Obtain the working information set of the loss-in-weight color masterbatch machine; based on the working information set of the loss-in-weight color masterbatch machine, analyze the synergistic influence characteristics of the service host consumption fluctuation and material characteristic changes on the batching information to obtain the dynamic consumption information set. Based on the dynamic consumption information set, the mapping relationship between the color changes required by plastic products and the ingredient information is analyzed to obtain a full life cycle adaptation information set. Based on the full lifecycle adaptation information set, a collaborative control strategy is generated, and a full lifecycle intelligent management log of the weighing and batching equipment is output.

2. The method according to claim 1, characterized in that, Based on the working information set of the weightless color masterbatch machine, the synergistic impact characteristics of the service host consumption fluctuation and material characteristic changes on the batching information are analyzed to obtain a dynamic consumption information set, including: The loss-in-weight color masterbatch working information set includes equipment operating conditions and color masterbatch material information; Based on the operating conditions of the equipment, the influence of the main unit's consumption rate changes at different production stages on the amount of masterbatch added is analyzed to obtain the main unit consumption fluctuation information. Based on the information of the masterbatch material, the influence characteristics of changes in material flowability, density and moisture content on the batching accuracy are analyzed to obtain material characteristic fluctuation information. Based on the host consumption fluctuation information and the material characteristic fluctuation information, the interaction between the two in the batching process is analyzed to determine the synergistic impact characteristics on the batching information, thereby obtaining a dynamic consumption information set.

3. The method according to claim 2, characterized in that, The process of constructing the host consumption fluctuation information includes: Based on the operating conditions of the equipment, analyze the dynamic deviation information between the real-time consumption rate of the service host and the target value to identify the current stage of production. Based on the current production stage, the dynamic impact of the phased changes in the main unit's consumption rate throughout the entire production cycle on the real-time addition ratio of color masterbatch is analyzed to obtain main unit consumption fluctuation information.

4. The method according to claim 2, characterized in that, The process of constructing the material property fluctuation information includes: Based on the material information of the masterbatch, the influence of the change in material moisture content on the agglomeration state and surface adhesion of the masterbatch is analyzed to obtain the material cohesion-adhesion state information. Based on the cohesive-attachment state information of the material, the changes in the apparent flowability and bulk density of the material caused by the change in moisture content are analyzed to obtain the fluctuation information of the material properties.

5. The method according to claim 2, characterized in that, The dynamic consumption information set is obtained by analyzing the interaction between the host consumption fluctuation information and the material characteristic fluctuation information during the batching process, and combining the latter with the former. Based on the host consumption fluctuation information and the material characteristic fluctuation information, the overlap and misalignment relationship between the host consumption rate change and the material feed rate fluctuation on the time axis is analyzed to obtain time-series coupling information. Based on the time-series coupling information, the lag compensation requirement of material flowability changes on the actual addition amount of color masterbatch when the consumption rate changes is analyzed, and the dynamic consumption information set is obtained.

6. The method according to claim 5, characterized in that, Based on the dynamic consumption information set, the mapping relationship between the required color changes of plastic products and the ingredient information is analyzed to obtain a full life cycle adaptation information set, including: Based on the dynamic consumption information set, the variation of hue, saturation and brightness deviations of the colors required for plastic products at each production stage with production time is analyzed to obtain time-varying information on color demand. Based on the time-varying information of color demand, the dynamic adjustment requirements of the real-time addition ratio of color masterbatch due to the fluctuation of color demand and the compensation amount caused by the lag of material characteristics are analyzed to obtain the full life cycle adaptation information set.

7. The method according to claim 6, characterized in that, The process of constructing the time-varying information of color requirements includes: Based on the dynamic consumption information set, the inertial trend of the deviation of the actual amount of color masterbatch added relative to the preset ratio over continuous production time is analyzed to obtain deviation inertial information. Based on the aforementioned deviation inertia information, the time-series correction requirements for hue, saturation, and brightness deviations caused by the lag in material characteristics are analyzed to obtain the time-varying information of the color requirements.

8. The method according to claim 6, characterized in that, Based on the time-varying color demand information, the dynamic adjustment requirements of the real-time addition ratio of color masterbatch due to color demand fluctuations and the compensation amount caused by material characteristic lags are analyzed to obtain the full life cycle adaptation information set, including: Based on the time-varying information of color demand, the temporal correlation between the time-varying trend of color deviation and the lag compensation demand of material characteristics in each production stage is analyzed to obtain deviation-lag coupling information. Based on the aforementioned deviation-hysteresis coupling information, the superposition ratio of the feedforward adjustment and feedback compensation of the real-time addition ratio of color masterbatch is analyzed to obtain the full life cycle adaptation information set.

9. The method according to claim 8, characterized in that, The process of generating a collaborative control strategy based on the full lifecycle adaptation information set and outputting a full lifecycle intelligent management log for the weighing and batching equipment includes: Based on the full lifecycle adaptation information set, the trend of the superposition ratio of feedforward adjustment and feedback compensation in each production stage is analyzed to obtain dynamic compensation information. Based on the dynamic compensation information and combined with the time-varying color requirement information, a collaborative control strategy including adaptive feedforward compensation and feedback correction is generated, and the intelligent management log of the weighing and batching equipment throughout its entire lifecycle is output.

10. A full lifecycle intelligent management system for weighing and batching equipment, characterized in that, The method applied to any one of claims 1-9 includes: The dynamic consumption module is used to acquire the working information set of the loss-in-weight color masterbatch machine, and based on the working information set of the loss-in-weight color masterbatch machine, analyze the synergistic influence characteristics of the service host consumption fluctuation and material characteristic changes on the batching information to obtain the dynamic consumption information set. The mapping relationship module is used to analyze the mapping relationship between the required color change of plastic products and the ingredient information based on the dynamic consumption information set, so as to obtain the full life cycle adaptation information set. The strategy generation module is used to generate collaborative control strategies based on the full lifecycle adaptation information set and output the intelligent management log of the weighing and batching equipment throughout its entire lifecycle.

Images