Cigarette test bench error correction method, equipment, medium and program product

Abstract

The invention discloses a cigarette test bench error correction method and device, a medium and a program product, and relates to the technical field of measurement error correction. The cigarette test bench error correction method comprises the following steps: acquiring a repeatability index, a system bias value and a measurement error distribution characteristic of a current error to-be-compensated test bench; determining a stability index according to the measurement stability analysis experiment data, and determining a reproducibility index according to the filter stick measurement reproducibility experiment data; according to the repeatability index, the system bias value, the measurement error distribution characteristic, the stability index and the reproducibility index, determining key factors of performance degradation of the test board; and compensating the current measured value of the current error to-be-compensated testboard based on the testboard performance degradation key factors and the error compensation model. According to the technical scheme of the embodiment of the invention, the auditing standards of new and old cigarette test benches can be unified, and the error correction effect of the cigarette test bench can be effectively improved.

Description

Technical Field

[0001] This invention relates to the field of measurement error correction technology, and in particular to a method, equipment, medium and program product for error correction of a cigarette testing platform. Background Technology

[0002] In the cigarette production process, the cigarette testing station is a core metrology device used for online detection of key physical indicators such as cigarette weight, length, circumference, and draw resistance. The accuracy of its measurement results is directly related to the impartiality of product quality control and process evaluation.

[0003] The industry employs various types of test benches, with newer models generally using laser measurement principles, while some older models still in service use image measurement principles. However, in practice, test benches using image measurement principles and those using laser measurement principles often exhibit measurement data discrepancies. This leads to inconsistencies between workshop production testing data and quality inspection department assessment results, severely impacting the effectiveness of quality control and resulting in idle and wasted equipment resources. When technicians correct errors, they primarily rely on comparison results and experience to determine if the equipment is "out of alignment," inputting a fixed correction value into the test bench software and uniformly adding or subtracting from all subsequent measurement results to compensate for average bias. This approach is ineffective for deeper issues such as repeatability and reproducibility, and it heavily relies on manual labor, resulting in low correction efficiency. Summary of the Invention

[0004] This invention provides a method, device, medium, and program for correcting errors in cigarette testing stations, in order to solve the problems of measurement deviations between new and old cigarette testing stations that cannot be standardized for unified review, and the poor error correction effect of cigarette testing stations.

[0005] According to one aspect of the present invention, a method for correcting errors in a cigarette testing bench is provided, comprising:

[0006] Obtain the repeatability index, system bias value, and measurement error distribution characteristics of the current error-to-compensate test bench;

[0007] Based on the stability analysis experimental data, the stability index was determined, and based on the reproducibility experimental data of the filter rod, the reproducibility index was determined.

[0008] Based on repeatability indicators, system bias values, measurement error distribution characteristics, stability indicators, and reproducibility indicators, the key factors causing performance degradation of the test bench are determined.

[0009] Based on the key factors of test bench performance degradation and the error compensation model, the current measurement value of the test bench with the current error to be compensated is compensated.

[0010] According to another aspect of the present invention, a cigarette testing bench error correction device is provided, comprising:

[0011] The first data acquisition module is used to acquire the repeatability index, system bias value, and measurement error distribution characteristics of the current error compensation test bench.

[0012] The second data acquisition module is used to determine the stability index based on the measurement stability analysis experimental data, and to determine the reproducibility index based on the filter rod measurement reproducibility experimental data.

[0013] The performance degradation factor determination module is used to determine the key factors of test bench performance degradation based on repeatability indicators, system bias values, measurement error distribution characteristics, stability indicators, and reproducibility indicators.

[0014] The error compensation module is used to compensate the current measurement value of the test bench with the current error based on the key factors of test bench performance degradation and the error compensation model.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and a memory communicatively connected to said at least one processor;

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the cigarette testing platform error correction method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the cigarette testing platform error correction method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the cigarette testing platform error correction method according to any embodiment of the present invention.

[0020] The technical solution of this invention obtains the repeatability index, system bias value, and measurement error distribution characteristics of the current error-to-compensate test bench. Based on measurement stability analysis experimental data, it determines the stability index and the reproducibility index based on filter rod measurement reproducibility experimental data. Then, based on the repeatability index, system bias value, measurement error distribution characteristics, stability index, and reproducibility index, it identifies the key factors causing performance degradation of the test bench. Furthermore, based on these key factors and the error compensation model, it compensates for the current measurement value of the current error-to-compensate test bench. This solution, based on multi-source data fusion, performs a comprehensive diagnosis of the current error-to-compensate test bench and constructs a personalized error compensation model. This allows each cigarette test bench to have a personalized error correction strategy with low manual intervention requirements. The compensated values ​​are closer to the actual physical indicators of the measured object, enabling unification with the audit standards for new cigarette test benches. This solves the problems of measurement deviations between old and new cigarette test benches, which prevent the unification of audit standards, and the poor error correction effect of cigarette test benches. It unifies the audit standards for old and new cigarette test benches and effectively improves the error correction effect of cigarette test benches.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of an error correction method for a cigarette testing platform provided in Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of an error correction method for a cigarette testing platform provided in Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of an error correction device for a cigarette testing platform provided in Embodiment 4 of the present invention;

[0026] Figure 4 A schematic diagram of an electronic device that can be used to implement embodiments of the present invention is shown. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "current," "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a cigarette testing platform error correction method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where new and old cigarette testing platform models are subject to unified review standards. The method can be executed by a cigarette testing platform error correction device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] Step 110: Obtain the repeatability index, system bias value, and measurement error distribution characteristics of the current error compensation test bench.

[0032] The current error compensation test bench can be a cigarette testing bench based on the visual testing principle. The repeatability index can be an index evaluating the capability of the testing process. Optionally, the repeatability index may include Cg (repeatability coefficient) and / or Cgk (repeatability of the measuring equipment). The system bias value can be the deviation of the cigarette testing bench's measurement average value relative to the measurement standard value. The measurement error distribution characteristics can be used to identify and quantify the nonlinear error of the cigarette testing bench.

[0033] In this embodiment of the invention, the repeatability index and system bias value of the current error compensation test bench can be determined based on the high-frequency repeated test experiments of the current error compensation test bench, and the measurement error distribution characteristics can be analyzed by measuring different standard samples covering the measurement range of the current error compensation test bench.

[0034] Step 120: Based on the measurement stability analysis experimental data, determine the stability index, and based on the filter rod measurement reproducibility experimental data, determine the reproducibility index.

[0035] The measurement stability analysis experimental data can be experimental data used to perform stability analysis on the current error-compensating test bench. Stability indices can be indicators used to evaluate the stability of the measurement process on the current error-compensating test bench. For example, the Xbar-S control chart (mean-standard deviation chart) can be used as a stability index for the current error-compensating test bench. The filter rod measurement reproducibility experimental data can be reproducibility experimental data of the filter rod on the current error-compensating test bench. For example, reproducibility indices can be used to quantify the proportion of fluctuations in the cigarette testing bench caused by variations in the equipment itself (repeatability) and variations between different operators / equipment (reproducibility).

[0036] In this embodiment of the invention, the stability index of the current error compensation test bench can be determined by analyzing the measurement stability analysis experimental data, and the reproducibility index of the current error compensation test bench can be obtained by analyzing the filter rod measurement reproducibility experimental data.

[0037] Step 130: Based on repeatability indicators, system bias values, measurement error distribution characteristics, stability indicators, and reproducibility indicators, determine the key factors causing performance degradation of the test bench.

[0038] The key factors contributing to test bench performance degradation can be used to describe the critical factors causing measurement errors in the current test bench requiring error compensation. These key factors may include, but are not limited to, at least one of the following: insufficient calibration, component wear, and environmental interference.

[0039] In this embodiment of the invention, the repeatability index, system bias value, measurement error distribution characteristics, stability index, and reproducibility index of the current error-to-compensate test bench can be matched with the historical error correction cases of the current error-to-compensate test bench to obtain the key factors of test bench performance degradation that exist at this time.

[0040] For example, the repeatability index, system bias value, measurement error distribution characteristics, stability index, and reproducibility index of the current error-to-compensate test bench can be used as matching elements to match historical error correction cases of the current error-to-compensate test bench. The case with the highest similarity to the above elements, which ultimately identifies the key factor of performance degradation, is taken as the key factor causing the current measurement error in the test bench performance. Historical error correction cases can be collected from the operation logs of the current error-to-compensate test bench itself.

[0041] Step 140: Based on the key factors of test bench performance degradation and the error compensation model, compensate the current measurement value of the test bench with the current error to be compensated.

[0042] The error compensation model can be a pre-set model for correcting measurement errors of the current error-to-compensate test bench. For example, the error compensation model can be a model composed of an artificial intelligence model and a professional knowledge base, a neural network model, or a pre-built algorithm model for compensating for errors in all aspects of test bench performance degradation. The current measurement value can be the measurement value of the measured object by the current error-to-compensate test bench. It should be noted that during the experimental stage of error correction, the current measurement value of the current error-to-compensate test bench is the measurement value of the key physical indicators of the standard filter rod (such as weight, length, circumference, and draw resistance); during the application stage of error correction, the current measurement value of the current error-to-compensate test bench is the measurement value of the key physical indicators of the cigarette.

[0043] In this embodiment of the invention, the error compensation model can be optimized according to the key factors of test bench performance degradation. Then, the measured value of the current object to be measured (standard filter rod or cigarette) measured by the current error compensation test bench is taken as the current measured value, and the current measured value is compensated based on the optimized error compensation model.

[0044] Optionally, when the error compensation model is a model composed of an artificial intelligence model and a professional knowledge base, or a neural network model, the weights related to the key factors of test bench performance degradation in the error compensation model are increased according to the key factors of test bench performance degradation. When the error compensation model is an algorithmic model that compensates for errors in all factors of test bench performance degradation, the coefficients of terms in the error compensation model that are unrelated to the key factors of test bench performance degradation are adjusted to 0.

[0045] The technical solution of this invention obtains the repeatability index, system bias value, and measurement error distribution characteristics of the current error-to-compensate test bench. Based on measurement stability analysis experimental data, it determines the stability index and the reproducibility index based on filter rod measurement reproducibility experimental data. Then, based on the repeatability index, system bias value, measurement error distribution characteristics, stability index, and reproducibility index, it identifies the key factors causing performance degradation of the test bench. Furthermore, based on these key factors and the error compensation model, it compensates for the current measurement value of the current error-to-compensate test bench. This solution, based on multi-source data fusion, performs a comprehensive diagnosis of the current error-to-compensate test bench and constructs a personalized error compensation model. This allows each cigarette test bench to have a personalized error correction strategy with low manual intervention requirements. The compensated values ​​are closer to the actual physical indicators of the measured object, enabling unification with the audit standards for new cigarette test benches. This solves the problems of measurement deviations between old and new cigarette test benches, which prevent the unification of audit standards, and the poor error correction effect of cigarette test benches. It unifies the audit standards for old and new cigarette test benches and effectively improves the error correction effect of cigarette test benches.

[0046] Example 2

[0047] Figure 2 This is a flowchart of a cigarette testing platform error correction method provided in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and provides a specific optional implementation method for compensating the current measurement value of the testing platform with the current error to be compensated, based on the key factors of testing platform performance degradation and the error compensation model. Figure 2 As shown, the method includes:

[0048] Step 210: Obtain the repeatability index, system bias value, and measurement error distribution characteristics of the current error compensation test bench.

[0049] Step 220: Determine the stability index based on the measurement stability analysis experimental data, and determine the reproducibility index based on the filter rod measurement reproducibility experimental data.

[0050] Step 230: Based on repeatability indicators, system bias values, measurement error distribution characteristics, stability indicators, and reproducibility indicators, determine the key factors causing performance degradation of the test bench.

[0051] Step 240: Based on the key factors of test bench performance degradation and the error compensation model, compensate the current measurement value of the test bench with the current error to be compensated.

[0052] In an optional embodiment of the present invention, compensating the current measured value of the test bench with the current error to be compensated based on the key factors of test bench performance degradation and the error compensation model may include: determining a target compensation model based on the key factors of test bench performance degradation and the error compensation model; and compensating the current measured value of the test bench with the current error to be compensated based on the target compensation model.

[0053] The error compensation model can include a nonlinear compensation function and a time decay factor compensation function. The target compensation model can be an algorithmic model for error compensation targeting key factors contributing to test bench performance degradation. The nonlinear compensation function can be a function used to compensate for the nonlinear error of the test bench to be compensated for the current error. The nonlinear compensation function can include piecewise functions, polynomials, or other forms of functions for compensating for nonlinear errors during the measurement process. For example, the nonlinear compensation function can be determined through least squares fitting, neural network model training, or table lookup. The time decay factor compensation function can be a function that predicts time-varying errors using cumulative running time or the number of measurements as independent variables, used to dynamically predict / counteract time-varying errors introduced by equipment aging, wear, and state drift. Optionally, the time decay factor compensation function can be the product of a time decay factor and the cumulative running time or the number of measurements.

[0054] In this embodiment of the invention, only the data items related to the key factors of test bench performance degradation in the error compensation model can be retained to obtain the target compensation model. Then, based on the target compensation model and the relevant test data of the current error-to-compensate test bench (such as system bias value, nonlinear error, cumulative running time or number of measurements, etc.), the compensation value of the current error-to-compensate test bench can be calculated. Then, based on the aforementioned calculated compensation value, the current measurement value of the current error-to-compensate test bench can be compensated.

[0055] In an optional embodiment of the present invention, after compensating the current measurement value of the test bench with the current error to be compensated based on the key factors of test bench performance degradation and the error compensation model, the method may further include: obtaining the compensated measurement value of the current error to be compensated test bench for the standard filter rod; and generating a warning message when the error between the compensated measurement value of the current error to be compensated test bench for the standard filter rod and the standard measurement value of the filter rod is greater than the error threshold.

[0056] The compensation measurement value can be the compensation result of the current error compensation test bench's measurement of the standard filter rod. For example, the compensation measurement value can include, but is not limited to, the compensation value of the circumference measured by the current error compensation test bench for the standard filter rod. The standard measurement value of the filter rod can be the true physical index value of the standard filter rod, used to measure the error between the current error compensation test bench and the true value. The error threshold can be a pre-set upper limit for the error between the compensation measurement value and the standard measurement value of the filter rod. The warning information can be an alarm message generated when there is a measurement anomaly in the current error compensation test bench. The warning information can be used to characterize that the measurement error compensation effect of the current error compensation test bench is substandard. For example, error thresholds based on statistical analysis and process requirements are set for each key physical index: the error threshold for the weight unit is ±0.008g; the error threshold for the length unit is ±0.1mm; the error threshold for the circumference unit is ±0.03mm; and the error threshold for the suction resistance unit is ±0.02kPa.

[0057] In this embodiment of the invention, the current measurement value of the standard filter rod by the current error compensation test bench can be compensated to obtain the compensated measurement value of the standard filter rod by the current error compensation test bench. Then, the difference between the compensated measurement value of the standard filter rod by the current error compensation test bench and the standard measurement value of the filter rod is calculated to obtain the error between the compensated measurement value of the standard filter rod by the current error compensation test bench and the standard measurement value of the filter rod. Then, the calculated error is compared with the error threshold. If the calculated error is greater than the error threshold, an early warning information is generated to prompt technicians to perform maintenance.

[0058] In an optional embodiment of the present invention, when the error between the compensated measurement value of the current error compensation test bench and the standard measurement value of the filter rod is greater than an error threshold, generating a warning message may include: when the error between the compensated measurement value of the current error compensation test bench and the standard measurement value of the filter rod is greater than an error threshold, determining the risk level of the current error compensation test bench according to a risk level assessment strategy; and generating a warning message based on the risk level of the current error compensation test bench and the equipment identifier of the current error compensation test bench.

[0059] The risk level assessment strategy can be a pre-set strategy for assessing the risk level of measurement errors in the equipment. For example, the risk level assessment strategy could use all factors contributing to the overall performance degradation of the test bench as scoring items, or use only the key factors contributing to the performance degradation of the test bench as scoring items, summing the scores of each item, and further determining the risk level of the test bench whose error needs compensation based on the total score. Each risk level corresponds to a score range, and the correspondence between risk levels and score ranges can be pre-defined. The equipment identifier can be the equipment's identity identifier.

[0060] In this embodiment of the invention, when the error between the compensation measurement value of the current error compensation test bench and the standard measurement value of the filter rod is greater than the error threshold, the risk level of the current error compensation test bench can be determined based on the risk level assessment strategy and the performance degradation factors of the current error compensation test bench, and the risk level of the current error compensation test bench and the equipment identifier of the current error compensation test bench are used as early warning information.

[0061] In an optional embodiment of the present invention, after generating an early warning message when the error between the compensation measurement value of the current error compensation test bench and the standard measurement value of the filter rod is greater than the error threshold, the method may further include: determining the error verification cycle based on the risk level of the current error compensation test bench in the early warning message; obtaining error compensation verification data based on the error verification cycle; and updating the model parameters of the error compensation model based on the error compensation verification data.

[0062] The error verification period can be the calibration period for the current error-to-compensate test bench. For example, the error verification period could be before each shift, weekly, or monthly. The error compensation verification data can be the measurement experimental data of the current error-to-compensate test bench at the time the error verification period arrives.

[0063] In this embodiment of the invention, early warning information can be parsed to obtain the risk level of the current error-to-compensate test bench, and the error verification cycle corresponding to the risk level of the current error-to-compensate test bench can be determined. Then, the current error-to-compensate test bench after the early warning correction or the error correction meets the standard can be tested according to the error verification cycle to obtain error compensation verification data. Furthermore, the model parameters of the error compensation model can be updated based on the error compensation verification data. That is, when the error compensation model is a neural network or intelligent model, the model can be retrained using the error compensation verification data to update the model hyperparameters. When the error compensation model is an algorithm model that performs error compensation for all factors of test bench performance degradation, the coefficients of the functions in the algorithm model can be dynamically adjusted (the coefficients of the functions in the algorithm model can be manually adjusted and reviewed).

[0064] In an optional embodiment of the present invention, obtaining error compensation verification data according to the error verification cycle may include: determining the measurement verification value of the current error compensation test bench according to the error verification cycle; and determining the error compensation verification data according to the measurement verification value and the standard measurement value of the filter rod.

[0065] Among them, the measurement verification value can be the compensation measurement value of the current error compensation test bench collected when the error verification cycle is reached.

[0066] In this embodiment of the invention, the measurement verification value of the current error-to-compensate test bench can be obtained according to the error verification cycle through the standard filter rod test warning correction or the current error-to-compensate test bench that has met the error correction standard. The measurement verification value and the standard measurement value of the filter rod are used as error compensation verification data.

[0067] Step 250: Continuously monitor the stability index of the current error compensation test bench to obtain the cumulative stability index.

[0068] Among them, the cumulative stability index can be the stability index of the current error to be compensated test bench that is continuously collected.

[0069] In this embodiment of the invention, the stability index of the current error-to-compensate test bench can be continuously monitored to obtain the stability index of the current error-to-compensate test bench at different time periods, i.e., the cumulative stability index.

[0070] Step 260: When the cumulative stability index shows an abnormal trend, generate operation and maintenance early warning data based on the cumulative stability index.

[0071] The abnormal trend can refer to the abnormal change pattern of stability indicators. Abnormal trends can include continuous upward, continuous downward, or lateral shifts. Operational early warning data can be generated when an abnormal trend in accumulated stability indicators occurs. Operational early warning data may include, but is not limited to, abnormal equipment stability indicators, the identifier of the equipment exhibiting the abnormal stability indicator, and the duration of the abnormal stability indicator.

[0072] In this embodiment of the invention, it can be first determined whether the cumulative stability index shows an abnormal trend. If the cumulative stability index shows an abnormal trend, it indicates that the current error compensation test bench has a trend of increasing measurement error. Then, based on the relevant characteristics of the cumulative stability index and the relevant data of the current error compensation test bench, operation and maintenance early warning data is generated.

[0073] The technical solution of this invention obtains the repeatability index, system bias value, and measurement error distribution characteristics of the current error-to-compensate test bench. Based on measurement stability analysis experimental data, it determines the stability index and the reproducibility index based on filter rod measurement reproducibility experimental data. Then, based on the repeatability index, system bias value, measurement error distribution characteristics, stability index, and reproducibility index, it identifies key factors contributing to test bench performance degradation. Furthermore, based on these key factors and the error compensation model, it compensates for the current measurement value of the current error-to-compensate test bench and continuously monitors the stability index to obtain a cumulative stability index. When the cumulative stability index shows an abnormal trend, it generates maintenance early warning data based on the cumulative stability index. This solution, based on multi-source data fusion, performs a comprehensive diagnosis of the current test benches with uncompensated errors and constructs a personalized error compensation model. This enables each cigarette test bench to have a personalized error correction strategy with low manual intervention requirements, which can be unified with the audit standards of new cigarette test benches. It also has the ability to provide early warning before measurement errors escalate. This solves the problems of measurement deviations between old and new cigarette test benches, which cannot be unified with the audit standards, as well as the poor error correction effect of cigarette test benches. It can unify the audit standards of old and new cigarette test benches and effectively improve the error correction effect of cigarette test benches.

[0074] Example 3

[0075] Embodiment 3 of the present invention provides an optional embodiment of a method for correcting errors on a cigarette testing platform, the specific implementation of which can be found in the following embodiments. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0076] The error correction method for cigarette testing benches deeply integrates measurement system analysis, equipment operation data, and error compensation models. Its core process includes four sequential stages:

[0077] Phase 1: Multidimensional Measurement System Analysis

[0078] This phase aims to conduct a comprehensive "performance check-up" on the current error-compensating test bench, quantitatively assessing its performance across five key dimensions, specifically: 1) Repeatability and System Bias Analysis: Through high-frequency repeated measurements, calculate system bias values ​​and evaluate repeatability indicators to quantify the equipment's accuracy and short-term precision. 2) Through long-term measurements across different time periods, utilize statistical process control tools to evaluate stability indicators and identify periods or trends of performance instability. 3) By conducting cross-measurements across different equipment and operators, perform gauge repeatability and reproducibility analysis, calculating the GR&R (Gaugerepeatability & Reproducibility) percentage, i.e., the reproducibility indicator, to separate and quantify the impact of inter-equipment differences (reproducibility) on total variation. 4) By measuring different standard samples covering the measurement range of the current error-compensating test bench, analyze the measurement error distribution characteristics across the entire operating range, identifying and quantifying potential nonlinear errors.

[0079] Phase Two: Error Source Correlation and Diagnosis

[0080] The repeatability indicators, system bias values, nonlinear errors, stability indicators, and reproducibility indicators generated in the first stage are correlated with the operating logs of the test bench itself to trace the root causes of errors. Optionally, the temporal and statistical correlations between the logs of automatic calibration events (such as trigger time, frequency, and result codes) and the drift of measurement performance (such as bias and control chart trends) are analyzed. Through this correlation analysis, key factors contributing to test bench performance degradation, such as insufficient calibration, component wear, or environmental interference, are diagnosed.

[0081] Phase 3: Construction of Personalized Error Compensation Model

[0082] For each test bench to be corrected, a unique, dynamic error compensation model is constructed. The dynamic error compensation model can take the following form:

[0083] Y_corrected = Y_original + f(Bias,Linearity,Time); where Y_corrected is the final corrected compensated measurement value; Y_original is the original measurement value output by the test bench to be compensated for the current error; f(Bias,Linearity,Time) is the compensation function that integrates the three compensation components. Fixed bias compensation (Bias) is the system bias value used to eliminate the system's reference error. The nonlinear compensation function (Linearity), whose input is the original measurement value itself, is used to correct nonlinear errors caused by range changes. The time decay factor compensation function (Time) takes the cumulative running time or number of measurements since the last effective calibration as its independent variable, and is used to dynamically predict and offset time-varying errors introduced by equipment aging, wear, or state drift.

[0084] All parameters of the error compensation model are individually calibrated and configured based on the measurement system analysis results and diagnostic conclusions of specific equipment, achieving "one policy for each device".

[0085] Phase 4: Implementation and Closed-Loop Verification

[0086] This stage integrates the error compensation model built in the third stage into the data processing unit (such as host computer software or embedded system) of the current error-to-compensate test bench. It performs online, automatic correction calculations on the real-time acquired raw measurements and outputs the final results. Simultaneously, a closed-loop quality control mechanism is established: the corrected measurement system is periodically (or based on trigger conditions) validated using a standard filter rod, and the validation results (the deviation between the measured value and the standard value) are fed back to the error compensation model. Based on this feedback data, model parameters (such as the time decay factor coefficient) can be adaptively adjusted and optimized, thereby enabling the correction system to continuously learn and self-improve.

[0087] After the current error compensation test bench completes automatic calibration, the built-in automatic drive mechanism delivers the verification standard filter rod to the workstation for measurement and immediately determines the calibration validity. If the error exceeds the tolerance (greater than the error threshold), an alarm is triggered to ensure the reliability of each calibration.

[0088] For example, the risk level (e.g., high, medium, low) of the current error-to-compensate test bench can be classified based on Cgk, GR&R%, and stability indicators, and differentiated maintenance and inspection cycles can be established. By continuously monitoring the mean-standard deviation plot, early warnings can be issued when abnormal trends appear, transforming passive maintenance into predictive maintenance.

[0089] In a specific example, the C2 model integrated test bench based on the visual measurement principle is used as the test bench on the R102, Y401, and Y402 machines in the cigarette packaging workshop, and is the main target for correction. The Quantum Neo model integrated test bench based on the laser measurement principle is used as the test bench on the R203 and Y304 machines in the packaging workshop, and serves as an important component of performance comparison benchmarks and reproducibility analysis.

[0090] The following are the specific steps for performing error correction on the C2 test bench circumferential unit of the R102 machine:

[0091] On the C2 test bench of the R102 machine, five standard filter rods with a circumferential standard value of 24.04 mm were taken and measured 50 times consecutively. The average value of the 50 measurements was calculated to be 24.000 mm, so the initial bias was -0.04 mm. At the same time, the Cgk value of this unit was calculated to be less than 1.67, indicating that both repeatability and bias did not meet the requirements.

[0092] On three C2 test benches (R102, Y401, and Y402), measurements were performed on five standard filter rods for five consecutive days, with each day divided into morning and afternoon shifts. An Xbar-S control chart for the circumferential measurements was plotted. Assuming that the Y401 test bench experienced 8 out-of-control points, the Y402 test bench experienced 4, and the R102 test bench experienced 3, this indicates that the overall stability of the C2 test bench's circumferential unit is poor.

[0093] Ten filter rods were taken and measured on four test benches: R102(C2), Y304 (Quantum Neo type), Y401(C2), and Y402(C2). GR&R analysis results showed that the GR&R% of the circumferential unit exceeded 50%, and the reproducibility variance component was much larger than the repeatability component, indicating significant systematic differences between the test benches.

[0094] When circumferential standard filter rods of different specifications (such as 22.0mm, 24.0mm, 26.0mm) were measured on the C2 test bench of the R102 machine, it was found that the measurement error was not constant and there was a non-linear error.

[0095] Retrieving the automatic calibration log of the C2 test bench on the R102 machine revealed that it automatically performs calibration after measuring 100 filter rods. Comparing the calibration time points with the Xbar-S control chart showed that the measured values ​​experienced a brief period of stability after calibration, followed by a slow positive drift. This confirmed the existence of "undercalibration" and "performance drift" issues in the automatic calibration process.

[0096] The following error compensation model is established for the circular element of the C2 test bench of the R102 test bench: Circumferential correction value = Original circular measurement value + (-0.04) + Linearity (Original circular measurement value) + 0.00001 × N. Where -0.04 is the system bias value. Linearity (Original circular measurement value) is a miniature lookup table or function based on linear analysis, used to compensate for the nonlinear errors of filter rods of different specifications. The time decay factor compensation function Time is 0.00001 × N, where N is the cumulative number of measured rods since the last calibration. In the model constructed for the Y401 test bench, which has worse stability, its time decay factor compensation function is adjusted to 0.00002 × N to cope with its faster drift speed.

[0097] The model customized for the R102 test bench was integrated into the host computer of the test bench as a software plugin. All raw measurement values ​​were processed by this model before being displayed and output.

[0098] At the start of each shift, the operator is required to verify the filter rod on the R102 machine. The corrected measurement value is compared with the standard value. If the error is within ±0.03mm, it can be used normally; if it exceeds the tolerance, a forced manual calibration is required, and the verification data is recorded for subsequent optimization of model parameters.

[0099] Through the implementation of this embodiment, the measurement system of the circumferential unit of the R102 machine tool was improved from "unacceptable" to "acceptable with concessions" or even "acceptable", and the measurement consistency with the Quantum Neo model of the Y304 machine tool was greatly improved.

[0100] A standard rod compartment with a small robotic arm is installed inside the C2 test station of the Y401 machine. When the system log records that automatic calibration is complete, the robotic arm delivers a built-in standard filter rod to the measurement station for a measurement. The measurement result is automatically compared with the standard value in the database: if the error is within the error threshold, the calibration is considered valid, and the system records the success event; if the error exceeds the limit, the calibration is considered invalid, an audible and visual alarm is immediately triggered, and a recalibration can be automatically performed or the equipment can be locked for manual intervention. This process achieves transparent, automated monitoring and verification of "black box" calibration.

[0101] For example, according to the measurement system analysis report, the C2 test bench of the Y401 machine has the worst circumferential stability (8 overshoots) and a high GR&R%, so it is classified as Grade A (high risk). The C2 test bench of the R102 machine has acceptable stability but large bias, so it is classified as Grade B (medium risk). The C2 test bench of the Y402 machine is relatively the best, so it is classified as Grade C (low risk).

[0102] The system backend automatically generates tasks for Class A equipment Y401: weekly verification using standard filter rods and monthly simplified measurement system analysis. For Class C equipment Y402, only quarterly verification is required.

[0103] The Xbar-S control chart continuously monitors key indicators (such as the circumference) and performs automatic diagnosis when abnormal patterns such as "7 consecutive points showing an upward trend" appear. For example, when the control chart of Y401 shows an upward trend of 7 consecutive points, maintenance warning data will be sent to maintenance personnel in advance. For example, the circumference unit of Y401 C2 test bench may have slow drift, and it is recommended to pay attention and prepare for pre-maintenance, thereby realizing the transformation from "reactive maintenance" to "prevention".

[0104] The error correction method for the cigarette testing platform in this embodiment breaks through the limitations of traditional single-point calibration. It comprehensively addresses complex error problems from five dimensions: bias, repeatability, reproducibility, stability, and nonlinearity, improving overall measurement capabilities. Through a "one platform, one model" strategy, it achieves precise compensation for the unique error characteristics of each device, significantly improving measurement accuracy. Based on the time decay factor compensation function in the error compensation model, it can dynamically track and compensate for equipment performance drift, and through closed-loop verification, it can continuously self-optimize, maintaining long-term effectiveness. Specifically for devices with different measurement principles, a principle difference compensation sub-model effectively reduces data discrepancies, resolving data conflicts between production and quality inspection departments. Linking data analysis, model correction, and maintenance strategies enables early warning of equipment degradation trends, guides predictive maintenance, improves equipment management and operational efficiency, and allows for self-optimization and continuous reliable governance of the measurement system, ultimately creating significant value in multiple key dimensions such as accuracy, consistency, cost, efficiency, and asset utilization.

[0105] Example 4

[0106] Figure 3 This is a schematic diagram of the structure of an error correction device for a cigarette testing platform provided in Embodiment 4 of the present invention. Figure 3 As shown, the device includes:

[0107] The first data acquisition module 310 is used to acquire the repeatability index, system bias value and measurement error distribution characteristics of the current error compensation test bench;

[0108] The second data acquisition module 320 is used to determine the stability index based on the measurement stability analysis experimental data, and to determine the reproducibility index based on the filter rod measurement reproducibility experimental data.

[0109] The performance degradation factor determination module 330 is used to determine the key factors of test bench performance degradation based on repeatability index, system bias value, measurement error distribution characteristics, stability index and reproducibility index.

[0110] The error compensation module 340 is used to compensate the current measurement value of the test bench with the current error based on the key factors of test bench performance degradation and the error compensation model.

[0111] The technical solution of this invention obtains the repeatability index, system bias value, and measurement error distribution characteristics of the current error-to-compensate test bench. Based on measurement stability analysis experimental data, it determines the stability index and the reproducibility index based on filter rod measurement reproducibility experimental data. Then, based on the repeatability index, system bias value, measurement error distribution characteristics, stability index, and reproducibility index, it identifies the key factors causing performance degradation of the test bench. Furthermore, based on these key factors and the error compensation model, it compensates for the current measurement value of the current error-to-compensate test bench. This solution, based on multi-source data fusion, performs a comprehensive diagnosis of the current error-to-compensate test bench and constructs a personalized error compensation model. This allows each cigarette test bench to have a personalized error correction strategy with low manual intervention requirements. The compensated values ​​are closer to the actual physical indicators of the measured object, enabling unification with the audit standards for new cigarette test benches. This solves the problems of measurement deviations between old and new cigarette test benches, which prevent the unification of audit standards, and the poor error correction effect of cigarette test benches. It unifies the audit standards for old and new cigarette test benches and effectively improves the error correction effect of cigarette test benches.

[0112] Optionally, the error compensation module 340 is used to determine a target compensation model based on the key factors of performance degradation of the test bench and the error compensation model; wherein, the error compensation model includes a nonlinear compensation function and a time decay factor compensation function; and to compensate the current measurement value of the test bench with the current error to be compensated according to the target compensation model.

[0113] Optionally, the cigarette testing platform error correction device further includes an early warning module, used to obtain the compensation measurement value of the current error compensation testing platform for the standard filter rod; when the error between the compensation measurement value of the current error compensation testing platform for the standard filter rod and the standard measurement value of the filter rod is greater than the error threshold, an early warning message is generated.

[0114] Optionally, the early warning module is used to determine the risk level of the current error compensation test bench when the error between the compensated measurement value of the standard filter rod and the standard measurement value of the filter rod is greater than the error threshold, according to the risk level assessment strategy; and to generate the early warning information based on the risk level of the current error compensation test bench and the device identifier of the current error compensation test bench.

[0115] Optionally, the cigarette testing platform error correction device further includes a model optimization module, used to determine the error verification cycle based on the risk level of the current error-to-compensate testing platform in the early warning information; to obtain error compensation verification data based on the error verification cycle; and to update the model parameters of the error compensation model based on the error compensation verification data.

[0116] Optionally, the model optimization module is used to determine the measurement verification value of the current error-to-compensate test bench according to the error verification cycle; and to determine the error compensation verification data according to the measurement verification value and the standard measurement value of the filter rod.

[0117] Optionally, the cigarette test bench error correction device also includes a trend anomaly detection module, which is used to continuously monitor the stability index of the current error-to-compensate test bench and obtain a cumulative stability index; when the cumulative stability index shows an abnormal change trend, maintenance early warning data is generated based on the cumulative stability index.

[0118] The cigarette testing platform error correction device provided in this embodiment of the invention can execute the cigarette testing platform error correction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0119] Example 5

[0120] Figure 4 A schematic diagram of an electronic device that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0121] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as ROM 12, RAM 13, etc., communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An I / O interface 15 is also connected to the bus 14. The ROM 12 is a read-only memory, the RAM 13 is a random access memory, and the I / O interface 15 is an input / output interface.

[0122] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0123] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the cigarette testing bench error correction method.

[0124] In some embodiments, the cigarette testing bench error correction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the cigarette testing bench error correction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the cigarette testing bench error correction method by any other suitable means (e.g., by means of firmware).

[0125] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0127] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0128] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0129] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0130] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS servers, such as high management difficulty and weak business scalability.

[0131] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the cigarette testing platform error correction method provided in any embodiment of this application. This program product shares the same inventive concept as the cigarette testing platform error correction methods disclosed in the embodiments of this application, and therefore will not be described in detail here.

[0132] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0133] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for correcting errors on a cigarette testing platform, characterized in that, include: Obtain the repeatability index, system bias value, and measurement error distribution characteristics of the current error-to-compensate test bench; Based on the stability analysis experimental data, the stability index was determined, and based on the reproducibility experimental data of the filter rod, the reproducibility index was determined. Based on the repeatability index, the system bias value, the measurement error distribution characteristics, the stability index, and the reproducibility index, the key factors causing the performance degradation of the test bench are determined. Based on the key factors of test bench performance degradation and the error compensation model, the current measurement value of the test bench with the current error to be compensated is compensated.

2. The method according to claim 1, characterized in that, Based on the key factors of test bench performance degradation and the error compensation model, the current measured value of the test bench with the current error to be compensated is compensated, including: Based on the key factors of test bench performance degradation and the error compensation model, a target compensation model is determined; wherein, the error compensation model includes a nonlinear compensation function and a time decay factor compensation function. The current measurement value of the current error compensation test bench is compensated according to the target compensation model.

3. The method according to claim 1, characterized in that, After compensating the current measured value of the test bench with the current error to be compensated based on the key factors of test bench performance degradation and the error compensation model, the following steps are also included: Obtain the compensation measurement value of the standard filter rod by the current error compensation test bench; When the error between the compensated measurement value of the standard filter rod on the current error compensation test bench and the standard measurement value of the filter rod exceeds the error threshold, an early warning message is generated.

4. The method according to claim 3, characterized in that, When the error between the compensated measurement value of the standard filter rod on the current error compensation test bench and the standard measurement value of the filter rod exceeds the error threshold, an early warning message is generated, including: When the error between the compensation measurement value of the standard filter rod and the standard measurement value of the filter rod on the current error compensation test bench is greater than the error threshold, the risk level of the current error compensation test bench is determined according to the risk level assessment strategy. The warning information is generated based on the risk level of the current error compensation test bench and the equipment identifier of the current error compensation test bench.

5. The method according to claim 4, characterized in that, After generating a warning message when the error between the compensated measurement value of the standard filter rod on the current error compensation test bench and the standard measurement value of the filter rod exceeds the error threshold, the following further steps are included: The error verification cycle is determined based on the risk level of the current error-to-compensate test bench in the warning information. Based on the error verification cycle, obtain error compensation verification data, and update the model parameters of the error compensation model based on the error compensation verification data.

6. The method according to claim 5, characterized in that, Based on the aforementioned error verification cycle, obtain error compensation verification data, including: Based on the error verification cycle, determine the measurement verification value of the current error-to-compensate test bench; The error compensation verification data is determined based on the measured verification value and the standard measurement value of the filter rod.

7. The method according to claim 1, characterized in that, After compensating the current measured value of the test bench with the current error to be compensated based on the key factors of test bench performance degradation and the error compensation model, the following steps are also included: Continuously monitor the stability index of the current error-to-compensate test bench to obtain the cumulative stability index; When the cumulative stability index shows an abnormal trend, operation and maintenance early warning data is generated based on the cumulative stability index.

8. An electronic device, characterized in that, The electronic device includes: At least one processor, and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the cigarette test bench error correction method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the cigarette testing bench error correction method according to any one of claims 1-7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the error correction method for the cigarette testing bench according to any one of claims 1-7.

Images