A method and system for detecting filling flow rate in a filling production line.

Abstract

This invention relates to the field of electronic digital data processing technology, specifically to a method and system for detecting filling flow rate in a filling production line. The method includes: acquiring filling flow rate data at various times during the current filling process; inputting the filling flow rate data at each time point during the current filling process into an improved machine learning model; outputting the liquid volume on the inner wall of the pipe after the current filling process stops; and determining that an anomaly exists in the current filling process if the liquid volume on the inner wall of the pipe after the current filling process stops is greater than a set threshold. This invention solves the problem of low detection accuracy in existing models.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology. More specifically, this invention relates to a method and system for detecting filling flow rate in a filling production line. Background Technology

[0002] Currently, in bottling production lines for beverages, condiments, and chemical liquids, real-time detection and anomaly identification of filling flow rate are crucial for ensuring product quality, reducing raw material waste, and maintaining production stability. Traditional filling flow rate detection methods mostly rely on hardware devices such as flow meters and pressure sensors to collect flow data, combined with fixed threshold judgments and simple statistical analysis to determine if there are any anomalies in the filling process. While these methods are relatively simple to implement, they have several shortcomings. First, the fixed threshold judgment method has poor adaptability to different batches and operating conditions. When liquid viscosity, temperature, or filling pressure changes, the threshold often needs to be manually reset; otherwise, misjudgments or missed judgments are likely to occur. Second, simple statistical analysis methods cannot effectively handle the inherent random noise in the collected data, especially when the production line is running at high speed. The flow signal will contain a large number of instantaneous anomalies caused by equipment vibration, liquid fluctuations, and sensor drift. These interference signals will seriously affect the accuracy of the judgment results.

[0003] In recent years, with the rapid development of intelligent manufacturing and industrial big data technologies, machine learning methods have been increasingly applied to flow detection in the filling process. By deeply analyzing and modeling the large amount of historical flow data accumulated on the production line, machine learning models can automatically uncover the potential nonlinear mapping relationship between flow changes and abnormal states. This, to a certain extent, eliminates the reliance on human experience and fixed thresholds in traditional methods, enabling more adaptive and predictive anomaly detection. Compared to simply relying on manual rules or simple statistical methods, these data-driven models can not only comprehensively consider multi-dimensional features such as instantaneous flow values, fluctuation amplitudes, and trend changes, but also continuously improve their ability to identify complex working conditions through continuous training and optimization. They exhibit higher flexibility and intelligence, especially in filling production environments with multiple batches, multiple varieties, and changing equipment conditions.

[0004] However, existing machine learning-based models still have some limitations that cannot be ignored. First, most models have fixed values ​​for kernel function parameters (such as length scale) or other hyperparameters, lacking the ability to adaptively adjust to dynamic changes in the filling process. This makes the models prone to being overly sensitive to noise or undersensitive to subtle anomalies when facing filling processes with different stability levels, resulting in low detection accuracy. Summary of the Invention

[0005] To address the problem of low detection accuracy mentioned in the background art, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a filling flow detection method for a filling production line, comprising: acquiring filling flow data at each moment during the current filling process; inputting the filling flow data at each moment during the current filling process into an improved machine learning model, outputting the liquid volume on the inner wall of the pipe after the current filling stops; if the liquid volume on the inner wall of the pipe after the current filling stops is greater than a set threshold, then determining that there is an anomaly in the current filling; wherein, the improved machine learning model includes a length scale in a Gaussian kernel function, the length scale being positively correlated with the initial value and negatively correlated with the update factor of the current filling, the update factor representing the stability of the current filling process.

[0007] The aforementioned technical solution inputs the flow data from the filling process into an improved machine learning model with adaptive adjustment capabilities. During the analysis, it dynamically balances the model's sensitivity to abnormal fluctuations with its adaptability to stable trends, thereby more accurately estimating the amount of residual liquid on the inner wall of the pipeline after filling and enabling rapid anomaly detection. By introducing a length scaling design in the Gaussian kernel function that is positively correlated with the initial value and inversely correlated with the stability index, the model can automatically adjust the smoothness of the feature space for different operating conditions. This maintains prediction accuracy in stable conditions while improving response speed and recognition capabilities when anomalies occur, effectively enhancing the reliability, adaptability, and real-time performance of filling flow detection.

[0008] Furthermore, the length scale for, In the formula, To find the maximum value function, The minimum value of the preset length scale. As the initial value, For the natural constant An exponential function with base 0. For the first The update factor for the next filling process.

[0009] The aforementioned technical solution introduces a maximum value function and an exponential decay mechanism into the calculation of the length scale, enabling the model to adaptively adjust its sensitivity to feature differences under different filling batches. When the update factor is large, the length scale decreases accordingly, thereby enhancing the model's responsiveness to abnormal changes; while when the update factor is small or close to normal, the length scale remains above a preset minimum to avoid overfitting and feature distortion. This design ensures both the model's prediction accuracy under stable operating conditions and improves its detection sensitivity under abnormal operating conditions, thus significantly enhancing the robustness and adaptability of filling flow detection.

[0010] Furthermore, the update factor is, , For the first The first level of abnormality in the filling process For the first The second level of abnormality in the filling process.

[0011] The above technical solution achieves a comprehensive characterization of abnormal states in the filling process by multiplying the first degree of anomaly by the second degree of anomaly to obtain the update factor. The first degree of anomaly reflects the deviation between the flow fluctuation and the historical average during a single filling process, indicating the difference between the current operating conditions and the normal state. The second degree of anomaly describes the directionality and persistence of abnormal changes during multiple filling processes, reflecting the stable characteristics of the abnormal trend. The combination of these two factors not only captures instantaneous abnormal fluctuations but also identifies long-term abnormal trends, enabling the update factor to more comprehensively and accurately characterize the stability of the filling process. This provides a more reliable basis for subsequent adaptive adjustment of model parameters and precise anomaly detection.

[0012] Furthermore, the first degree of anomaly for, , For the first The first level of abnormality in the filling process To preset hyperparameters, For the first Dynamic flow resistance during the filling process This is the average of the dynamic flow resistance over multiple historical filling processes.

[0013] The above technical solution calculates the degree of anomaly by using a weighted recursive update method, combining the relative deviation between the dynamic flow resistance of the current filling process and the historical average level with the degree of the previous anomaly, effectively balancing the response speed and stability of anomaly detection.

[0014] Furthermore, the dynamic flow resistance for, , For the first Flow variance in each filling process For the first Average flow rate per filling process To preset hyperparameters, For the natural constant An exponential function with base 0. For the first Flow deviation during the filling process.

[0015] The aforementioned technical solution constructs a dynamic flow resistance index by integrating three key statistical characteristics of the flow rate: variance, mean, and skewness. It uses the ratio of variance to mean flow rate to reflect the relative intensity of flow rate fluctuations, and simultaneously amplifies the asymmetric impact of flow rate distribution through an exponential function, effectively capturing the instability and abnormal fluctuations in flow rate during the filling process. This multi-dimensional feature fusion method not only improves the sensitivity to flow rate fluctuation patterns but also enhances the ability to identify abnormal states. This allows the dynamic flow resistance to more accurately reflect the actual stability of the filling process, thereby providing more scientific and comprehensive data support for anomaly detection and model parameter adjustment.

[0016] Furthermore, the second degree of abnormality , , For symbolic functions, , The first sequence The first level of abnormality in the filling process This represents the total number of filling processes throughout history.

[0017] The aforementioned technical solution quantifies the overall upward or downward trend of abnormal indicators by statistically analyzing the sign trend of changes in the degree of abnormality during multiple filling processes, thereby reflecting the persistence and development direction of the abnormal state. By averaging the direction of continuous changes in the degree of abnormality in historical data, this method can effectively distinguish between short-term fluctuations and long-term trends, enhance the ability to perceive the evolution of abnormalities, avoid misjudgments caused by single fluctuations, improve the stability and accuracy of abnormality detection, and provide a more reliable trend judgment basis for intelligent monitoring of the filling process.

[0018] Furthermore, it also includes denoising the filling flow data.

[0019] Furthermore, the machine learning model is a support vector machine model.

[0020] Furthermore, it also includes training the machine learning model, specifically: inputting the training set into the pre-built machine learning model for training; during the training process, calculating the loss between the output predicted value and the label; adjusting the model parameters using gradient descent to minimize the prediction error; iteratively adjusting the parameters of the machine learning model until the loss is less than a set value or the set number of training iterations is reached, and finally obtaining the trained machine learning model.

[0021] In a second aspect, the present invention provides a filling flow detection system for a filling production line, comprising a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a filling flow detection method for a filling production line as described above is implemented.

[0022] The beneficial effects of this invention are as follows:

[0023] This invention utilizes an improved machine learning model to intelligently analyze flow data at various points during the filling process, enabling accurate prediction of the amount of residual liquid on the inner wall of the pipeline after filling, and effectively identifying filling anomalies based on this prediction. The employed length-scale adaptive adjustment mechanism dynamically optimizes the model's sensing range according to the stability of the filling process, improving the ability to capture flow change characteristics under different operating conditions, thereby enhancing the sensitivity and accuracy of anomaly detection. The multi-dimensional characterization of anomaly severity and the update factor formed by their fusion not only comprehensively reflect instantaneous fluctuations and long-term trends but also effectively suppress noise interference, improving the model's robustness. Through denoising of the flow data and optimization of the support vector machine model training, this solution significantly improves the ability to identify and respond in real-time to abnormal states in complex filling environments, achieving efficient, stable, and adaptive filling flow detection, greatly promoting the automation monitoring level of the production line and product quality assurance. Attached Figure Description

[0024] Figure 1 This is a flowchart schematically illustrating a filling flow detection method for a filling production line according to an embodiment of the present invention;

[0025] Figure 2 This is a schematic block diagram illustrating the structure of a filling flow detection system for a filling production line according to an embodiment of the present invention. Detailed Implementation

[0026] An embodiment of a filling flow detection method for a filling production line.

[0027] like Figure 1 As shown, a flowchart of a filling flow detection method for a filling production line according to an embodiment of the present invention includes the following steps:

[0028] S1: Obtain the filling flow rate data at each moment during the current filling process.

[0029] In a preferred embodiment, in order to accurately obtain the filling flow rate data at each moment during the current filling process, a high-precision flow sensor is installed on the liquid conveying pipeline of the filling production line. The sensor is preferably an electromagnetic flow meter or a mass flow meter to ensure that high measurement accuracy can be maintained under different liquid physical properties (such as viscosity, density, and temperature).

[0030] In practical applications, when the filling equipment begins to execute a batch of filling tasks, it first sends a start command to the flow sensor, causing it to enter real-time monitoring mode. At this time, the flow sensor continuously collects the instantaneous flow rate of the liquid in the pipeline at a preset sampling frequency. Each sampling cycle generates a flow data point, along with a timestamp accurate to the millisecond level, to ensure that the complete flow change curve can be reconstructed in subsequent analysis.

[0031] It also includes denoising the filling flow data. In order to further improve the accuracy and usability of the filling flow data acquired at each moment during the current filling process, after the data acquisition is completed, the filling flow data is subjected to denoising. The denoising can be achieved by mean filtering to eliminate high-frequency noise and abnormal fluctuations introduced by measurement errors, environmental interference and equipment mechanical fluctuations, thereby obtaining a smoother, more stable and more accurate flow curve that reflects the liquid flow state.

[0032] S2: Input the filling flow data at each moment during the current filling process into the improved machine learning model, and output the amount of liquid on the inner wall of the pipe after the current filling stops.

[0033] In a preferred embodiment, the machine learning model is a support vector machine (SVM) model. Further, taking the SVM model as an example, training the SVM model specifically involves: inputting the training set into a pre-built SVM model for training; calculating the loss between the output predicted value and the label during training; adjusting the model parameters using gradient descent to minimize the prediction error; iteratively adjusting the parameters of the SVM model until the loss is less than a set value or a set number of training iterations are reached, ultimately obtaining a trained SVM.

[0034] The improved machine learning model includes a length scale in the Gaussian kernel function, wherein the length scale... for, In the formula, To find the maximum value function, The minimum value of the preset length scale. As the initial value, For the natural constant An exponential function with base 0. For the first The update factor for the filling process is determined by employing a dynamic adjustment strategy based on an exponential function in the length scaling design of the Gaussian kernel function, while setting a minimum threshold for the length scale to ensure it does not fall below a preset lower limit. Specifically, the length scale adaptively adjusts as the update factor changes during the filling process, flexibly shrinking or expanding according to fluctuations in flow data, thereby achieving accurate capture of data characteristics under different filling states. This mechanism effectively avoids the overfitting or underfitting problems that may arise from traditional fixed-length scaling, improving the kernel function's adaptability to local data structures.

[0035] Furthermore, by limiting the lower bound of the length scale, this scheme prevents the model from becoming sensitive to noise and the prediction results from being unstable due to an excessively small length scale, thus enhancing the overall robustness and generalization ability of the algorithm. In summary, this technical solution improves the stability and accuracy of machine learning models in filling flow data processing, enabling them to more reliably reflect the changing characteristics of the actual filling process. This provides a solid data foundation for subsequent filling volume prediction and anomaly detection, significantly optimizing the control effect and production efficiency of the filling process.

[0036] The update factor is, , For the first The first level of abnormality in the filling process For the first The second level of abnormality in the filling process.

[0037] First degree of abnormality for, , For the first The first level of abnormality in the filling process To preset hyperparameters, For the first Dynamic flow resistance during the filling process This is the average dynamic flow resistance over multiple historical filling processes. The dynamic flow resistance... for, , For the first Flow variance in each filling process For the first Average flow rate per filling process To preset hyperparameters, For the natural constant An exponential function with base 0. For the first Flow deviation during the filling process.

[0038] By constructing an update factor composed of two types of anomaly levels, and incorporating a combination of historical weight smoothing and current flow resistance deviation in the calculation of the first anomaly level, the system can balance sensitivity to short-term fluctuations in the filling process with stability to long-term trends. The calculation of dynamic flow resistance integrates multi-dimensional features such as flow variance, average flow rate, and flow distribution skewness, and utilizes an exponential function to amplify asymmetric features, thus providing a more comprehensive reflection of liquid flow stability and anomaly levels. This approach not only captures subtle anomalies in the filling process in a timely manner but also suppresses the interference of occasional fluctuations on the overall assessment, helping to improve the model's discrimination accuracy and robustness under complex operating conditions. It provides high-quality input for subsequent model parameter adjustments based on the update factor, thereby significantly optimizing the prediction and control performance of the filling process.

[0039] Second degree of abnormality , , For symbolic functions, , The first sequence The first level of abnormality in the filling process This represents the total number of filling processes throughout history.

[0040] By introducing a sign function into the calculation of the second degree of anomaly to statistically analyze the changing direction of the first degree of anomaly in the continuous filling process, and averaging the results over multiple historical data points, this method effectively reflects the persistence and trend of the anomaly degree over time. Compared to assessment methods that rely solely on the magnitude of a single anomaly, this method can identify the frequency and directional consistency of anomaly changes, thus distinguishing between occasional fluctuations under a stable trend and truly persistent, evolving anomalies. This approach provides a more robust ability to identify anomaly trends in dynamic monitoring, reduces interference from short-term random noise, provides a more accurate trend reference for the predictive control of the filling process, and enhances stability and early warning capabilities under complex operating conditions.

[0041] S3: If the amount of liquid on the inner wall of the pipe is greater than the set threshold after the current filling stops, it is determined that there is an abnormality in the current filling.

[0042] In a preferred embodiment, by detecting the amount of residual liquid on the inner wall of the pipeline after filling and comparing it with a preset threshold, anomalies in the filling process can be directly determined. Since the residual liquid in the pipeline should normally remain at a stable and low level after filling stops, exceeding the threshold often indicates anomalies in filling pressure, flow control, or liquid recovery. This method can quickly locate potential problems without relying on complex signal analysis. This judgment mechanism based on physical residual amount has the advantages of being intuitive, reliable, and easy to implement. It can achieve timely anomaly identification in actual production, reduce liquid waste and production efficiency decline caused by equipment failure or control deviations, and provide a clear basis for subsequent maintenance and parameter optimization.

[0043] This invention introduces a machine learning model based on an improved support vector machine, combined with dynamically adjusted Gaussian kernel length scaling and multidimensional anomaly indexes, to achieve accurate analysis and anomaly detection of filling flow data. Through denoising of the flow data and optimization of model training, the solution effectively improves the accuracy and real-time response capability of identifying anomalies in the filling process, enhances the stability and robustness of detection, and thus improves the quality control level and production efficiency of the filling production line.

[0044] An embodiment of a filling flow detection system for a filling production line:

[0045] like Figure 2 As shown in the figure, a structural block diagram of a filling flow detection system for a filling production line according to an embodiment of the present invention includes a processor and a memory.

[0046] This invention also provides a filling flow detection system for a filling production line. For example... Figure 2 As shown, the system includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement a filling flow detection method for a filling production line according to the present invention.

[0047] The filling flow detection system for a filling production line also includes other components well known to those skilled in the art, such as communication interfaces. Their settings and functions are known in the art and will not be described in detail here.

[0048] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0049] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise explicitly specified.

[0050] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. A method for detecting the filling flow rate of a filling line, characterized in that, The method comprises: obtaining filling flow data at each time point in the current filling process; inputting the filling flow data at each time point in the current filling process into an improved machine learning model to output the liquid amount on the inner wall of the pipeline after the current filling stops, and determining that the current filling is abnormal if the liquid amount on the inner wall of the pipeline after the current filling stops is greater than a set threshold; wherein the improved machine learning model comprises a length scale in a Gaussian kernel function, the length scale being positively correlated with an initial value and inversely correlated with an update factor of the current filling, the update factor representing the stability degree in the current filling process; length scale is , wherein is a maximum function, is a minimum value of the preset length scale, is an initial value, is an exponential function with a natural constant as a base, is the first update factor of the filling process. The update factor is ; First level of abnormality for , For the first The first level of abnormality in the filling process To preset hyperparameters, For the first Dynamic flow resistance during the filling process This is the average of the dynamic flow resistance over multiple historical filling processes; Second abnormality degree , , is a symbol function, is the total number of historical multiple filling processes.

2. The filling flow rate detection method for a filling production line according to claim 1, characterized by, the dynamic flow resistance is , is the flow variance for the filling process, is the average flow for the filling process, is a preset hyperparameter, is an exponential function with the natural constant as base, is the skewness of the flow during the filling process.

3. The method for detecting the filling flow rate of a filling production line according to claim 1, characterized in that, further comprising denoising the filling flow data.

4. The method for detecting the filling flow rate of a filling production line according to claim 1, characterized in that, The machine learning model is a support vector machine model.

5. The method for detecting the filling flow rate of a filling production line according to claim 1, characterized in that, Further comprising training the machine learning model, specifically: inputting a training set into a pre-constructed machine learning model for training, calculating the loss between the predicted value and the label during the training process; adjusting the model parameters using the gradient descent method to minimize the prediction error; iteratively adjusting the parameters of the machine learning model until the loss is less than a set value or the set number of training times is reached, and finally obtaining the trained machine learning model.

6. A filling flow detection system for a filling line, characterized in that The method comprises a memory and a processor, and the memory stores computer program instructions, which, when executed by the processor, implement the filling flow detection method for the filling production line according to any one of claims 1-5.

Images