Method and program product for tobacco quality treatment in a cigarette factory cut tobacco production line

Abstract

This invention discloses a method and program product for handling the quality of tobacco shreds in a cigarette manufacturing production line. The method includes: acquiring process timing data and equipment operation timing data of the target cigarette at the target production progress; determining the target process characteristics corresponding to the target production progress based on the process timing data, and determining the equipment characteristics corresponding to the target production progress based on the equipment operation timing data; inputting the target process characteristics into a pre-trained process quality detection model to determine the process quality detection results of the target cigarette at the target production progress; inputting the equipment characteristics into a pre-trained equipment status detection model to determine the equipment status detection results of the target cigarette at the target production progress; and generating a maintenance work order for the target cigarette based on the process quality detection results and the equipment status detection results. By performing multi-dimensional detection on target cigarettes at multiple production progresses, the stability and intelligence level of cigarette manufacturing are improved.

Description

Technical Field

[0001] This invention relates to the field of cigarette production technology, and in particular to a method and procedure for quality treatment of tobacco shreds in a cigarette factory's tobacco processing production line. Background Technology

[0002] Tobacco processing is the core process in cigarette production, and its quality directly affects the quality and stability of the final product.

[0003] In related technologies, the quality control of the tobacco processing process mainly relies on human experience and fixed threshold alarms. However, these technologies suffer from delayed responses to quality anomalies, making it easy to discover quality problems only after a batch of cigarettes has been produced. This results in waste of raw materials and loss of production efficiency. Furthermore, the management of cigarette production equipment is often lax, leading to either excessive or insufficient maintenance. Therefore, these technologies can easily cause instability in cigarette production quality. Summary of the Invention

[0004] This invention provides a method and procedure for quality treatment of tobacco shreds in a cigarette manufacturing production line, in order to solve the problem of insufficient quality control in cigarette production processes in related technologies.

[0005] According to one aspect of the present invention, a method for quality treatment of tobacco shreds in a cigarette manufacturing production line is provided, the method comprising:

[0006] Acquire the process timing data and equipment operation timing data of the target cigarettes when they reach the target production progress;

[0007] The target process features corresponding to the target production progress are determined based on the process timing data, and the equipment features corresponding to the target production progress are determined based on the equipment operation timing data.

[0008] The target process features are input into a pre-trained process quality detection model to determine the process quality detection results of the target cigarette at the target production progress.

[0009] The equipment features are input into a pre-trained equipment status detection model to determine the equipment status detection result of the target cigarette at the target production progress.

[0010] Based on the process quality inspection results and the equipment status inspection results, a maintenance work order for maintaining the target cigarette is generated.

[0011] According to another aspect of the present invention, a tobacco quality processing device for a cigarette manufacturing production line is provided, the device comprising:

[0012] The data acquisition module is used to acquire process timing data and equipment operation timing data of the target cigarettes when they reach the target production progress.

[0013] The feature determination module is used to determine the target process features corresponding to the target production progress based on the process timing data, and to determine the equipment features corresponding to the target production progress based on the equipment operation timing data.

[0014] The process quality inspection module is used to input the target process features into a pre-trained process quality inspection model to determine the process quality inspection results of the target cigarette at the target production progress.

[0015] The equipment status detection module is used to input the equipment features into a pre-trained equipment status detection model to determine the equipment status detection result of the target cigarette at the target production progress.

[0016] The maintenance work order generation module is used to generate a maintenance work order for the target cigarette based on the process quality inspection results and the equipment status inspection results.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] One or more processors; and a memory communicatively connected to at least one of the processors; wherein the memory stores a computer program executable by at least one of the processors, which, when executed by one or more of the processors, causes the one or more processors to implement a method for quality processing of tobacco shreds in a cigarette manufacturing production line as described in an embodiment of the present invention.

[0019] 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 a method for quality processing of tobacco shreds in a cigarette manufacturing production line as described in the embodiments of the present invention.

[0020] According to another aspect of the present invention, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements a method for quality processing of tobacco shreds in a cigarette manufacturing production line as described in the embodiments of the present invention.

[0021] The technical solution of this invention firstly acquires the process timing data and equipment operation timing data of the target cigarette when it reaches the target production progress. This ensures the timeliness and relevance of the analyzed data information at multiple production progress stages, providing a reliable data foundation for subsequent cigarette quality assessment. Secondly, the target process characteristics corresponding to the target production progress are determined based on the process timing data, and the equipment characteristics corresponding to the target production progress are determined based on the equipment operation timing data. By analyzing production timing data from different dimensions, representative process and equipment characteristics can be selected, effectively reducing the computational complexity of subsequent model processing and highlighting the core factors affecting cigarette quality and equipment operation, thus improving the reliability of feature analysis. Furthermore, the target process characteristics are input into a pre-trained process quality detection model to determine the process quality detection results of the target cigarette at the target production progress. Through intelligent analysis of the process characteristics using the trained model, the process quality detection results at that production progress can be quickly and objectively determined, allowing for timely detection of process deviations, processing of substandard cigarettes, and reducing the impact of defective cigarettes on overall cigarette quality. Furthermore, the equipment characteristics are input into a pre-trained equipment status detection model to determine the equipment status detection results for the target cigarette at the target production progress. By automatically identifying equipment characteristics through the trained equipment status detection model, the operational health status of the equipment at the current production progress can be accurately judged, avoiding production interruptions or product quality fluctuations caused by sudden equipment failures, thus improving the continuity and stability of cigarette production. Finally, based on the process quality detection results and the equipment status detection results, a maintenance work order for the target cigarette is generated. Through comprehensive analysis of multi-dimensional detection results, maintenance work orders can be generated, allowing for timely adjustment of cigarette production. This achieves collaborative management of preventative maintenance and quality optimization, ensuring reliable control over the quality of multiple batches of cigarettes. Therefore, this technical solution, by constructing a multi-dimensional data comprehensive analysis, realizes the intelligent and automated transformation of cigarette production quality control from experience-based regulation to data-driven regulation, effectively improving the stable control of cigarette manufacturing quality and ensuring high-quality cigarette production.

[0022] 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

[0023] 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.

[0024] Figure 1 This is a flowchart of a method for quality processing of tobacco shreds in a cigarette manufacturing production line, provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a method for quality processing of tobacco shreds in a cigarette manufacturing production line, provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of a tobacco quality processing device for a cigarette factory tobacco processing production line provided in Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the electronic device used in a method for processing the quality of tobacco shreds in a cigarette manufacturing production line, as provided in Embodiment 4 of the present invention. Detailed Implementation

[0028] 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.

[0029] It should be noted that the terms "first cluster," "second cluster," "first process feature," "second process feature," "primary feature," and "target feature," etc., used 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 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.

[0030] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0031] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0032] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0033] Example 1

[0034] Figure 1 This invention provides a flowchart of a method for quality processing of tobacco shreds in a cigarette factory's tobacco processing production line, as described in Embodiment 1. This embodiment is applicable to scenarios involving quality inspection of cigarettes produced on a cigarette factory production line, particularly for inspecting the quality of cigarettes produced during the tobacco processing workshop. This method can be executed by a tobacco shred quality processing device used in a cigarette factory's tobacco processing production line. This device can be implemented in hardware and / or software, optionally through electronic devices such as mobile terminals, PCs, or servers. Figure 1 As shown, the method may specifically include:

[0035] S110. Obtain the process timing data and equipment operation timing data of the target cigarette when it reaches the target production progress.

[0036] Here, "target cigarette" can be understood as any brand of cigarette. "Target production progress" can be understood as a specific completion indicator when any batch of cigarettes reaches a preset percentage in the cigarette production process. For example, in the production of a certain batch of cigarettes, if the completed quantity of cigarettes accounts for 30%, 50%, and 80% of the total quantity of that batch, then the target production progress of the target cigarette can be 30%, 50%, and 80%, respectively. "Process timing data" can be understood as data related to cigarette production process parameters collected continuously in chronological order during cigarette production. Specifically, process timing data can include at least one of the following cigarette production process parameters: temperature, humidity, wind speed, steam pressure, steam flow rate, and moisture content. "Equipment operation timing data" can be understood as data related to cigarette production equipment collected continuously in chronological order during cigarette production. Specifically, equipment operation timing data can include at least one of the following cigarette production equipment data: vibration frequency, motor power, current, voltage, and motor speed.

[0037] Specifically, data can be collected from various types of process sensors deployed in the cigarette manufacturing workshop. Based on these sensors, process parameters related to the cigarette's state can be determined. These parameters are then categorized and labeled chronologically. When the target production schedule is reached, the collected process parameter data is processed to obtain the process timeline data at that stage. Similarly, production equipment sensors with the same acquisition frequency as the process sensors can be used. These sensors, pre-installed in the cigarette processing equipment, can collect different types of equipment operating status parameters. When the target production schedule is reached, these parameters are processed to obtain the equipment operating timeline data at that stage. This technical solution, by acquiring monitoring data from different dimensions at the target production schedule, ensures the timeliness and consistency of cigarette quality analysis, thus improving the reliability of cigarette production quality assessment.

[0038] S120. Determine the target process features corresponding to the target production progress based on the process timing data, and determine the equipment features corresponding to the target production progress based on the equipment operation timing data.

[0039] The target process characteristics can be understood as key quantitative indicators extracted from process time-series data to characterize the process characteristics at the target production progress. These are typically derived quantities obtained through statistics. Target process characteristics usually include statistical values ​​of multiple process parameters at the target production progress. For example, in the temperature dimension, target process characteristics may include at least one of the statistical characteristics of the dryer outlet temperature, such as the mean, maximum, minimum, drift, fluctuation, and quantile characteristics. In the steam pressure dimension, target process characteristics may include at least one of the statistical characteristics of the dryer steam pressure, such as the mean, maximum, minimum, drift, fluctuation, and quantile characteristics. Equipment characteristics can be understood as key quantitative indicators extracted from equipment operation time-series data to characterize the health status of each cigarette production device at the target production progress. These typically include statistical values ​​of multiple equipment operation status parameters at the target production progress. For example, in the motor power dimension, target process characteristics may include at least one of the statistical characteristics of the target equipment motor power, such as the mean, fluctuation, and quantile characteristics. Equipment features can have the same statistical feature dimensions as the target process features, but equipment features can have different data type dimensions than the target process features.

[0040] Specifically, for the collected process time-series data, statistical characteristic data such as the mean, maximum and minimum values, drift values, and fluctuation values ​​of each process parameter at the target production progress are obtained according to the data type of each process parameter. Based on these statistical characteristics of multiple process parameters, target process characteristics at the target production progress are generated. Similarly, for the collected equipment operation time-series data, statistical characteristic data such as the mean, maximum and minimum values, drift values, and fluctuation values ​​of each equipment operation status parameter at the target production progress are obtained according to the data type of each equipment operation status parameter. Based on these statistical characteristics of multiple equipment operation status parameters, target process characteristics at the target production progress are generated. By performing statistical analysis on multiple types of data across different dimensions, representative process parameter characteristics and equipment operation characteristics can be selected, thereby improving the reliability of cigarette production quality analysis based on more reliable and accurate characteristic data.

[0041] In one embodiment, determining the target process feature corresponding to the target production progress based on the process timing data includes: dividing the process timing data according to production steps to determine the process timing data under at least one production step; extracting features from the process timing data under a single production step to obtain the target feature corresponding to the production step; and determining the target process feature corresponding to the target production progress based on the target feature corresponding to at least one production step.

[0042] In this context, "production process" can be understood as the operational steps involved in processing the target cigarettes during production. A production process can include at least steps such as drying, adding ingredients, cutting, rehydration, and blending / flavoring. The time-series data for a single production process can be understood as the cigarette manufacturing parameters collected sequentially over time at that specific step. Furthermore, the cigarette manufacturing parameters for different steps can be the same or different. It's understood that different steps may contain specific cigarette manufacturing parameters that need to be detected and collected at a particular step, or conventional cigarette manufacturing parameters such as temperature and humidity may be detected and collected at multiple steps. "Target characteristics" can be understood as the statistical characteristics of all cigarette manufacturing parameters at a given step.

[0043] Specifically, for target cigarettes that have reached the target production progress, the process time series data of all these target cigarettes is divided according to the cigarette production process, thereby determining the process time series data under multiple production processes. Then, by extracting features from the process time series data under each production process, statistical characteristics such as the mean, maximum, minimum, and drift values ​​of each type of process time series data are calculated, thus obtaining the target features under the target production process. Finally, the target features under multiple production processes can be processed and combined in chronological order to generate the target process features of the target cigarettes at the target production progress. By extracting features from multiple process data under multiple processes, a relatively complete and comprehensive process feature result can be obtained when the target production progress is reached, ensuring the comprehensiveness and accuracy of the process feature analysis.

[0044] In another implementation, different types of target features in different processes can be normalized to obtain target features with the same dimension. These normalized target features can then be concatenated to generate target process features. Alternatively, based on the importance of each production process, target features in different processes can be weighted, and then the weighted target features can be concatenated to ensure the authenticity of the impact of target features in different processes on cigarette production quality.

[0045] In one embodiment, the process timing data includes sub-process data of multiple data types; the step of extracting features from the process timing data under the production process to obtain target features corresponding to the production process includes: determining primary features corresponding to each sub-process data of each data type in the process timing data; and combining the primary features corresponding to the sub-process data of multiple data types to obtain target features corresponding to the production process.

[0046] Here, sub-process data can be understood as the process data corresponding to each data type. For example, sub-process data can be at least one of the following: outlet temperature of the drying machine, steam pressure before the control valve, steam pressure before the control valve, and steam pressure of the drying machine. Primary features can be understood as the statistical features obtained based on each type of sub-process data.

[0047] Specifically, within a single process, sub-process data of each data type is extracted based on the process time sequence data for that process. Then, statistical characteristics such as the mean, drift value, and fluctuation value of the sub-process data of that data type are calculated within the time range corresponding to the target process, thereby obtaining the primary features corresponding to that data type of sub-process data. Furthermore, by combining the primary features corresponding to sub-process data of multiple data types, the target features for the target process are obtained by combining multiple primary features. Extracting primary features from multiple sub-process data allows for dimensionality reduction of the original collected data, reducing the amount of data for subsequent analysis and calculation, while retaining relatively core process feature parameters, thus improving the interpretability of statistical feature analysis.

[0048] In one embodiment, determining the equipment features corresponding to the target production progress based on the equipment runtime sequence data includes: extracting runtime parameter features corresponding to each data type based on the data type of the equipment runtime sequence data; and combining multiple runtime parameter features to obtain the equipment features corresponding to the target production progress.

[0049] Among them, the operating parameter characteristics can be understood as the statistical characteristics corresponding to the operating status parameters of each type of equipment.

[0050] Specifically, various equipment operating status parameters are determined based on the acquired equipment runtime sequence data. By calculating the mean, fluctuation, quantile characteristics, and other statistical features of each equipment operating status parameter, the operating parameter characteristics corresponding to each equipment operating status parameter at the target production progress are determined. Furthermore, by combining the operating parameter characteristics corresponding to multiple operating status parameters, the equipment characteristics corresponding to the target cigarettes at the target production progress are obtained. By extracting features from multiple equipment parameters, the influence of multi-dimensional data types on equipment operation can be effectively combined, thereby obtaining more comprehensive and accurate equipment characteristics, and ensuring the accuracy of the health status analysis of production equipment.

[0051] S130. Input the target process features into the pre-trained process quality detection model to determine the process quality detection result of the target cigarette at the target production progress.

[0052] The process quality inspection model can be understood as a machine learning model or statistical model trained on historical data. This model can include multiple standard clusters, each containing multiple sample process features. Used to assess the quality of target cigarettes, the process quality inspection model can specifically include a random forest classification model. Furthermore, the process quality inspection model can also include multiple standard clusters corresponding to different types of cigarettes, with each target cigarette's corresponding standard cluster labeled with a different specific identifier. The process quality inspection result can be understood as the quality status of the cigarette product at the target production stage, output by the model. This can include at least one of the following assessment types: quality score, pass / fail, deviation amount, etc.

[0053] Specifically, target process features can be input into a pre-trained process quality inspection model. The statistical characteristics of various process parameters are then matched against multiple standard clusters within the model. Based on the matching results with these standard clusters, the process quality inspection results for the target cigarette at the target production stage can be determined. This technical solution effectively improves the efficiency of statistical feature processing by using a process quality inspection model for efficient batch processing of target process features. Furthermore, based on a unified standard cluster evaluation standard, it ensures the accuracy and reliability of the process quality inspection results.

[0054] S140. Input the equipment features into the pre-trained equipment status detection model to determine the equipment status detection result of the target cigarette at the target production progress.

[0055] The equipment status detection model can be understood as a machine learning model or statistical model trained on historical data, used to detect and determine the operating status of cigarette production equipment. The process quality detection model can specifically include anomaly detection models. The equipment status detection result can be understood as the detection result of the current status of the cigarette production equipment output by the model, which can include at least one of the following parameter types: health score, normal / abnormal, and fault type.

[0056] Specifically, equipment features can be input into a pre-trained equipment condition detection model. By clustering the acquired equipment features with the feature parameters in the equipment condition detection model and performing anomaly detection on the equipment features, the equipment condition detection results at the target production progress can be determined. This technical solution, by using an equipment condition detection model to process equipment features, can effectively improve the ability to identify the deterioration of production equipment, thereby realizing quality-driven predictive maintenance of production equipment, and thus effectively improving the production stability and service life of production equipment.

[0057] In one implementation, the step of inputting the equipment features into a pre-trained equipment state detection model to determine the equipment state detection result of the target cigarette at the target production progress includes: clustering the equipment features, determining the equipment production mode corresponding to the equipment features based on the clustering results, and determining the equipment state detection result of the target cigarette at the target production progress based on the equipment production mode.

[0058] Among them, the equipment production mode can be understood as the type of equipment operation status exhibited during the period of achieving the target production progress. The equipment production mode can correspond to different equipment feature clustering results. Different clustering results can be used to characterize different equipment production modes. Specifically, the equipment production mode can also include at least one of the following modes: normal mode, fluctuation mode, abnormal mode, standby mode, etc.

[0059] Specifically, the acquired equipment features are input into the equipment status detection model, and then clustered with multiple pre-stored clusters within the model. Based on the clustering results of the equipment features and these clusters—that is, which clusters the equipment features primarily belong to—the production mode corresponding to the equipment features is determined based on at least one cluster. Simultaneously, when determining the cluster to which the equipment features belong, the features can also be input into another anomaly detection model. This model determines the anomaly detection results for the production equipment, and based on the production mode and the anomaly detection results, the equipment status detection results for the cigarette production equipment at the target production progress are jointly determined. This technical solution, by employing a combination of multiple detection models, allows for correlation verification of different detection results, thereby effectively improving the accuracy of equipment status detection result identification.

[0060] S150. Based on the process quality inspection results and the equipment status inspection results, generate a maintenance work order for maintaining the target cigarette.

[0061] A maintenance work order can be understood as a work instruction sheet for performing maintenance tasks on a certain piece of equipment or production line. It may include at least one of the following: task type, object to be performed, execution time, maintenance materials, etc.

[0062] Specifically, process quality inspection results can be correlated and verified with equipment status inspection results. When any inspection result under different dimensions shows an abnormal state, a maintenance work order is generated to maintain the production target cigarettes. Based on the maintenance work order, the process parameters of the cigarettes or the operating parameters of the cigarette production equipment can be adjusted. This technical solution effectively improves the smooth production and quality stability of cigarettes by performing correlation analysis on inspection results under multiple dimensions and generating maintenance work orders based on the inspection results to maintain high-quality cigarette production.

[0063] In one embodiment, generating a maintenance work order for the target cigarette based on the process quality inspection results and the equipment status inspection results includes: determining the production status of the target cigarette based on the process quality inspection results and the equipment status inspection results; and generating a maintenance work order for the target cigarette when the production status is abnormal.

[0064] The production status can include at least normal status, warning status, and abnormal status. An abnormal status can be understood as any detection result of process quality inspection or equipment status inspection being below a preset threshold, unqualified, or in an abnormal mode.

[0065] Specifically, the production status corresponding to the process quality inspection results and equipment status inspection results are determined separately, and the final production status of the target cigarette is determined based on the combination of these two production statuses. Furthermore, if the final production status is normal, cigarette production can continue; if the final production status is in a warning state, enhanced sampling inspections of the target cigarette can be implemented; if the production status is abnormal, a maintenance work order for maintaining the target cigarette production process is generated. By combining the production statuses from the process quality inspection results and equipment status inspection results, a simple and clear identification of the cigarette production status can be achieved, and timely maintenance of the cigarette production process can be carried out in case of abnormalities, thereby improving the stability and intelligence level of cigarette manufacturing quality.

[0066] In another implementation, when the process quality inspection results and equipment status inspection results are numerical, a weighted calculation can be performed on both results to determine the production status. A comprehensive score is then calculated to characterize the production status, and the final production status of the target cigarette is determined based on a scoring threshold. Furthermore, if the comprehensive score is below the scoring threshold, a maintenance work order for the target cigarette can be generated. This technical solution, by analyzing and calculating inspection results of different data types, effectively improves the flexibility of analyzing the production status of the target cigarette and enhances the timeliness and reliability of the quality dimensions of cigarette manufacturing based on the degree of influence of different dimensions on cigarette production.

[0067] The technical solution of this invention firstly acquires the process timing data and equipment operation timing data of the target cigarette when it reaches the target production progress. This ensures the timeliness and relevance of the analyzed data information at multiple production progress stages, providing a reliable data foundation for subsequent cigarette quality assessment. Secondly, the target process characteristics corresponding to the target production progress are determined based on the process timing data, and the equipment characteristics corresponding to the target production progress are determined based on the equipment operation timing data. By analyzing production timing data from different dimensions, representative process and equipment characteristics can be selected, effectively reducing the computational complexity of subsequent model processing and highlighting the core factors affecting cigarette quality and equipment operation, thus improving the reliability of feature analysis. Furthermore, the target process characteristics are input into a pre-trained process quality detection model to determine the process quality detection results of the target cigarette at the target production progress. Through intelligent analysis of the process characteristics using the trained model, the process quality detection results at that production progress can be quickly and objectively determined, allowing for timely detection of process deviations, processing of substandard cigarettes, and reducing the impact of defective cigarettes on overall cigarette quality. Furthermore, the equipment characteristics are input into a pre-trained equipment status detection model to determine the equipment status detection results for the target cigarette at the target production progress. By automatically identifying equipment characteristics through the trained equipment status detection model, the operational health status of the equipment at the current production progress can be accurately judged, avoiding production interruptions or product quality fluctuations caused by sudden equipment failures, thus improving the continuity and stability of cigarette production. Finally, based on the process quality detection results and the equipment status detection results, a maintenance work order for the target cigarette is generated. Through comprehensive analysis of multi-dimensional detection results, maintenance work orders can be generated, allowing for timely adjustment of cigarette production. This achieves collaborative management of preventative maintenance and quality optimization, ensuring reliable control over the quality of multiple batches of cigarettes. Therefore, this technical solution, by constructing a multi-dimensional data comprehensive analysis, realizes the intelligent and automated transformation of cigarette production quality control from experience-based regulation to data-driven regulation, effectively improving the stable control of cigarette manufacturing quality and ensuring high-quality cigarette production.

[0068] Example 2

[0069] Figure 2 This is a flowchart of a method for processing tobacco shreds in a cigarette manufacturing production line according to Embodiment 2 of the present invention. This embodiment is a refinement of the technical solution of "inputting the target process characteristics into a pre-trained process quality detection model to determine the process quality detection result of the target cigarette at the target production progress" based on the above embodiments. Specific implementation details can be found in the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here. Figure 2 As shown, the method may specifically include:

[0070] S210. Obtain the process timing data and equipment operation timing data of the target cigarette when it reaches the target production progress.

[0071] S220. Determine the target process features corresponding to the target production progress based on the process timing data, and determine the equipment features corresponding to the target production progress based on the equipment operation timing data.

[0072] S230. For each standard cluster in the process quality detection model, determine the deviation data between the target process feature and the standard cluster based on the distance between the target process feature and the centroid of the standard cluster, and the standard deviations corresponding to multiple sample process features in the standard cluster.

[0073] The deviation data can be used to characterize the degree of difference or similarity between the target process feature and the standard cluster. The process quality inspection model may include multiple standard clusters, and each standard cluster may include multiple of the aforementioned sample process features.

[0074] Specifically, for multiple standard clusters in the process quality detection model, clustering is performed between the target process feature and multiple standard clusters. The distance between the target process feature and the centroid of each standard cluster, as well as the standard deviation corresponding to multiple sample process features within each standard cluster, are calculated to determine the deviation data between the target process feature and multiple standard clusters. By calculating the deviation with multiple standard clusters, the similarity between the target process feature and at least some of the standard clusters can be determined, thereby improving the accuracy of the assessment of the target cigarette production quality at the current stage.

[0075] S240. Determine the process quality inspection results of the target cigarette at the target production progress based on multiple deviation data.

[0076] Specifically, based on the calculated deviation data, at least one target standard cluster adjacent to the target process feature under the current target production progress is determined. The target process feature is then clustered with the target standard clusters to determine the at least one standard cluster to which the target process feature belongs. Furthermore, based on the pre-labeled process quality tags of multiple standard clusters, the process quality inspection result of the target cigarette at the target production progress is determined. This technical solution clusters the deviation data with multiple standard clusters, thereby maximizing the accuracy of process quality assessment corresponding to the target process feature based on the quality tags corresponding to the multiple standard clusters.

[0077] In one possible implementation, if there is only one standard cluster, if the target process feature can be clustered with the standard cluster, the process quality test result of the target process feature is considered to be qualified. If clustering is not possible, it can be directly considered unqualified, so as to directly output the process quality test result of the target cigarette at the target production progress.

[0078] In another implementation, each standard cluster in the process quality inspection model can also correspond to different standard quality score intervals, such as a first score interval, a second score interval, a third score interval, etc., with the process quality corresponding to each score interval decreasing sequentially. Then, the quality score corresponding to the target process feature under the current target production progress can also be calculated. By comparing it with the standard quality score interval of each standard cluster, if the quality score corresponding to the target process feature is in the first score interval, the process quality inspection result of the target cigarette under the target production progress can be considered qualified; if the quality score corresponding to the target process feature is in the second score interval, the process quality inspection result of the target cigarette under the target production progress can be considered a warning; if the quality score corresponding to the target process feature is in the third score interval, the process quality inspection result of the target cigarette under the target production progress can be considered unqualified. By classifying the process quality inspection results in a hierarchical manner, a more flexible process quality handling method can be achieved, and the accuracy of classifying the process quality inspection results can be improved, allowing for more appropriate processing methods to be adopted.

[0079] In one embodiment, after determining the process quality inspection result of the target cigarette at the target production progress based on the plurality of deviation data, the method further includes: if the process quality inspection result is the target quality inspection result, generating a target report based on the deviation data between the target process characteristics and the standard cluster.

[0080] Among them, the target quality inspection result can be understood as the quality inspection result that is below the preset threshold or is unqualified, which belongs to the abnormal state.

[0081] Specifically, when the process quality inspection result is the target quality inspection result, a structured "production process - key process parameter - deviation" list is generated based on the deviation data and the importance ranking results of each sub-process data in the process time series data based on the random forest feature importance model. This facilitates efficient location of abnormal processes or process parameters and enables more accurate and rapid root cause tracing analysis.

[0082] Furthermore, based on the deviation data, it is also possible to generate deviation radar charts, comparison tables, and other visual reports to produce different types of visual reports and improve the display effect of the report list in different scenarios.

[0083] In one embodiment, the method for obtaining the standard cluster includes: acquiring sample process time-series data and sample quality inspection data of target cigarettes in multiple batches; determining a first process feature corresponding to each sample process time-series data; clustering the first process features in multiple batches to obtain multiple first clusters; determining multiple second process features from the multiple first clusters based on the sample quality inspection data in each of the multiple batches within each first cluster; filtering the multiple second process features according to preset screening conditions to determine sample process features; clustering the multiple sample process features to determine multiple second clusters; and determining a standard cluster based on the multiple second clusters, wherein different standard clusters correspond to different quality labels.

[0084] Among them, sample process time-series data and sample quality inspection data can be understood as sample data within a historical time period, and their essential meaning is the same as that of process time-series data and quality inspection data. The first process feature can be understood as the process parameter feature obtained by directly extracting statistical features from the sample process time-series data. The second process feature can be understood as the process parameter feature obtained by filtering based on the sample quality inspection data. Preset filtering conditions can be understood as preset conditions for filtering process parameter features, such as temperature control ranges, quantile feature ranges, etc. Sample process features can be understood as process parameter features after secondary filtering.

[0085] Specifically, the process involves acquiring time-series data of the target cigarette production process and sample quality inspection data from multiple batches. First, for a single batch, a first process feature corresponding to each batch's time-series data is extracted. Then, multiple first process features from various batches are clustered to obtain multiple first clusters. Next, based on the sample quality inspection data from multiple batches within these first clusters, the clusters are filtered to determine multiple second process features. Second, statistical features within these second process features can be further filtered according to preset criteria to determine the sample process features. Finally, clustering is performed based on these multiple sample process features to determine multiple second clusters. These second clusters are then used as standard clusters, with different standard clusters corresponding to different quality labels.

[0086] In another embodiment, the method for obtaining standard clusters may further include: acquiring sample process time-series data and sample quality inspection data of target cigarettes in multiple batches; for a single batch, extracting sample process characteristic parameters based on the sample process time-series data of the batch; determining a sample quality score based on the sample quality inspection data of the batch; combining the sample process characteristic parameters of the batch with the sample quality inspection data to determine a first clustering parameter for the batch; clustering based on the first clustering parameters of multiple batches to determine multiple first clusters; for a single first cluster, determining the mean sample quality score of the first cluster based on the sample quality scores corresponding to the sample quality inspection data of multiple batches in the first cluster; determining multiple second clustering parameters from the multiple first clusters based on the mean sample quality score; filtering the sample process characteristic parameters in the multiple second clustering parameters according to preset screening conditions to determine a third clustering parameter, and clustering based on the multiple third clustering parameters to determine multiple second clusters; and determining standard clusters based on the multiple second clusters, wherein different standard clusters correspond to different quality labels. By combining sample process time-series data and sample quality inspection data for screening, the sample process time-series data can be screened and graded more thoroughly based on the sample quality inspection data, thereby improving the stability of the standard cluster construction.

[0087] S250. Input the equipment features into the pre-trained equipment status detection model to determine the equipment status detection result of the target cigarette at the target production progress.

[0088] S260. Based on the process quality inspection results and the equipment status inspection results, generate a maintenance work order for maintaining the target cigarette.

[0089] The technical solution of this invention, firstly, for each standard cluster in the process quality detection model, determines the deviation data between the target process feature and the standard cluster based on the distance between the target process feature and the centroid of the standard cluster, and the standard deviations corresponding to multiple sample process features in the standard cluster. This accurately quantifies the degree of deviation between the target process feature and different standard clusters, thereby improving the accuracy of the target process feature evaluation. Secondly, the process quality detection result of the target cigarette at the target production progress is determined based on multiple deviation data, thus maximizing the reliability of the process quality detection result determination. Therefore, this technical solution, by using data deviation calculation between the target process feature and multiple standard clusters, can effectively improve the accuracy of process quality detection result analysis and also improve the efficiency and automation level of process quality detection through the standard clusters in the model.

[0090] Example 3

[0091] Figure 3 This is a schematic diagram of a tobacco quality processing device for a cigarette manufacturing production line according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a data acquisition module 301, a feature determination module 302, a process quality detection module 303, an equipment status detection module 304, and a maintenance work order generation module 305.

[0092] The system includes: a data acquisition module 301 for acquiring process timing data and equipment operation timing data of the target cigarette when it reaches the target production progress; a feature determination module 302 for determining the target process features corresponding to the target production progress based on the process timing data, and determining the equipment features corresponding to the target production progress based on the equipment operation timing data; a process quality detection module 303 for inputting the target process features into a pre-trained process quality detection model to determine the process quality detection result of the target cigarette at the target production progress; an equipment status detection module 304 for inputting the equipment features into a pre-trained equipment status detection model to determine the equipment status detection result of the target cigarette at the target production progress; and a maintenance work order generation module 305 for generating a maintenance work order for the target cigarette based on the process quality detection result and the equipment status detection result.

[0093] The technical solution of this invention involves, firstly, the data acquisition module 301 acquiring process timing data and equipment operation timing data of the target cigarette when it reaches the target production progress. This ensures the timeliness and relevance of the analyzed data information across multiple production stages, providing a reliable data foundation for subsequent cigarette quality assessment. Secondly, the feature determination module 302 determines the target process features corresponding to the target production progress based on the process timing data, and determines the equipment features corresponding to the target production progress based on the equipment operation timing data. By analyzing production timing data from different dimensions, representative process and equipment features can be selected, effectively reducing the computational complexity of subsequent model processing, highlighting the core factors affecting cigarette quality and equipment operation, and improving the reliability of feature analysis. Furthermore, the process quality inspection module 303 inputs the target process characteristics into a pre-trained process quality inspection model to determine the process quality inspection results of the target cigarette at the target production progress. Through intelligent analysis of the process characteristics using the trained model, the process quality inspection results at this production progress can be quickly and objectively determined, allowing for timely detection of process deviations and processing of substandard cigarettes, thus reducing the impact of defective cigarettes on overall cigarette quality. In addition, the equipment status detection module 304 inputs the equipment characteristics into a pre-trained equipment status detection model to determine the equipment status inspection results of the target cigarette at the target production progress. Through automated identification of equipment characteristics using the trained equipment status detection model, the operational health status of the equipment at the current production progress can be accurately determined, avoiding production interruptions or product quality fluctuations caused by sudden equipment failures, thereby improving the continuity and stability of cigarette production. Finally, the maintenance work order generation module 305 generates a maintenance work order for the target cigarette based on the process quality inspection results and the equipment status inspection results. By comprehensively analyzing the inspection results from multiple dimensions, and generating maintenance work orders for maintenance, timely adjustments can be made to cigarette production. This achieves collaborative management of preventative maintenance and quality optimization, ensuring reliable control over the quality of multiple batches of cigarettes. Therefore, this technical solution, through the construction of multi-dimensional data comprehensive analysis, realizes the intelligent and automated transformation of cigarette production quality control from experience-based regulation to data-driven regulation, effectively improving the stable control of cigarette manufacturing quality and ensuring high-quality cigarette production.

[0094] Based on the above-mentioned optional technical solutions, the feature determination module 302 may optionally include: a process timing data determination unit, a target feature determination unit, and a target process feature determination unit. The process timing data determination unit is used to divide the process timing data according to production processes to determine the process timing data under at least one production process. The target feature determination unit is used to extract features from the process timing data under a single production process to obtain target features corresponding to that production process. The target process feature determination unit is used to determine target process features corresponding to the target production progress based on the target features corresponding to at least one of the production processes.

[0095] Based on the above-mentioned optional technical solutions, optionally, the target feature determination unit may include: a primary feature determination unit and a primary feature combination unit. The process time series data includes sub-process data of multiple data types. The primary feature determination unit is used to determine a primary feature corresponding to each type of sub-process data in the process time series data; the primary feature combination unit is used to combine the primary features corresponding to the sub-process data of multiple data types to obtain a target feature corresponding to the production process.

[0096] Based on the above-mentioned optional technical solutions, the process quality inspection module 303 may optionally include: a deviation calculation unit and a process quality determination unit. The process quality inspection model includes multiple standard clusters, each containing multiple sample process features. The deviation calculation unit is used to determine the deviation data between the target process feature and the standard cluster for each standard cluster in the process quality inspection model, based on the distance between the target process feature and the centroid of the standard cluster, and the standard deviations corresponding to the multiple sample process features in the standard cluster. The process quality determination unit is used to determine the process quality inspection result of the target cigarette at the target production progress based on the multiple deviation data.

[0097] Based on the above-mentioned optional technical solutions, optionally, the tobacco quality processing device for the cigarette factory tobacco processing production line further includes: a target report generation module. The target report generation module is used to generate a target report based on the deviation data between the target process characteristics and the standard cluster, after determining the process quality inspection result of the target cigarette at the target production progress according to multiple deviation data, provided that the process quality inspection result is the target quality inspection result.

[0098] Based on the above-mentioned optional technical solutions, optionally, the method for obtaining the standard cluster includes: acquiring sample process time-series data and sample quality inspection data of target cigarettes in multiple batches; determining a first process feature corresponding to each sample process time-series data; clustering the first process features in multiple batches to obtain multiple first clusters; determining multiple second process features from the multiple first clusters based on the sample quality inspection data in each of the multiple batches in each first cluster; filtering the multiple second process features according to preset screening conditions to determine sample process features; clustering the multiple sample process features to determine multiple second clusters; and determining a standard cluster based on the multiple second clusters, wherein different standard clusters correspond to different quality labels.

[0099] Based on the above-mentioned optional technical solutions, the feature determination module 302 may optionally include: an operation parameter extraction unit and a device feature determination unit. The operation parameter extraction unit is used to extract operation parameter features corresponding to each data type of the device runtime sequence data; the device feature determination unit is used to combine multiple operation parameter features to obtain device features corresponding to the target production progress.

[0100] Based on the above-mentioned optional technical solutions, the equipment status detection module 304 may optionally include: an equipment mode determination unit and an equipment status determination unit. The equipment mode determination unit is used to cluster the equipment features and determine the equipment production mode corresponding to the equipment features based on the clustering results; the equipment status determination unit is used to determine the equipment status detection result of the target cigarette at the target production progress based on the equipment production mode.

[0101] Based on the above-mentioned optional technical solutions, the maintenance work order generation module 305 may optionally include: a production status determination unit and a maintenance work order generation unit. The production status determination unit is used to determine the production status of the target cigarette based on the process quality inspection results and the equipment status inspection results; the maintenance work order generation unit is used to generate a maintenance work order for the target cigarette when the production status is abnormal.

[0102] The tobacco quality processing device for a cigarette factory shredding production line provided in this embodiment of the invention can execute the tobacco quality processing method for a cigarette factory shredding production line provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0103] Example 4

[0104] Figure 4A schematic diagram of an electronic device 10, which 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 processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), 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.

[0105] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, 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 from storage unit 18 into the RAM 13. 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 input / output (I / O) interface 15 is also connected to the bus 14.

[0106] 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.

[0107] 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, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a method for quality processing of tobacco shreds in a cigarette manufacturing production line.

[0108] In some embodiments, a method for quality processing of tobacco shreds in a cigarette manufacturing production line can 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 can 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 method for quality processing of tobacco shreds in a cigarette manufacturing production line described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform a method for quality processing of tobacco shreds in a cigarette manufacturing production line by any other suitable means (e.g., by means of firmware).

[0109] 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.

[0110] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can 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 can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] 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 thereof. 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, random access memory (RAM), read-only memory (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 thereof.

[0112] 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).

[0113] 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.

[0114] 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 services, such as high management difficulty and weak business scalability.

[0115] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0116] 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.

[0117] 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 quality processing of tobacco shreds in a cigarette manufacturing production line, characterized in that, include: Acquire the process timing data and equipment operation timing data of the target cigarettes when they reach the target production progress; The target process features corresponding to the target production progress are determined based on the process timing data, and the equipment features corresponding to the target production progress are determined based on the equipment operation timing data. The target process features are input into a pre-trained process quality detection model to determine the process quality detection results of the target cigarette at the target production progress. The equipment features are input into a pre-trained equipment status detection model to determine the equipment status detection result of the target cigarette at the target production progress. Based on the process quality inspection results and the equipment status inspection results, a maintenance work order for maintaining the target cigarette is generated.

2. The method for quality treatment of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 1, characterized in that, The step of determining the target process feature corresponding to the target production progress based on the process timing data includes: The process timing data is divided according to the production process, and process timing data for at least one production process is determined. For a single production process, feature extraction is performed on the process timing data under the production process to obtain the target features corresponding to the production process. The target process features corresponding to the target production progress are determined based on the target features corresponding to at least one of the production processes.

3. The method for quality treatment of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 2, characterized in that, The process timing data includes sub-process data of various data types; the feature extraction of the process timing data under the production process to obtain target features corresponding to the production process includes: For each type of sub-process data in the process timing data, determine the primary feature corresponding to the sub-process data; The primary features corresponding to the sub-process data of various data types are combined to obtain the target features corresponding to the production process.

4. The method for quality processing of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 1, characterized in that, The process quality inspection model includes multiple standard clusters, each containing multiple sample process features; the step of inputting the target process features into the pre-trained process quality inspection model to determine the process quality inspection result of the target cigarette at the target production progress includes: For each standard cluster in the process quality detection model, the deviation data between the target process feature and the standard cluster is determined based on the distance between the target process feature and the centroid of the standard cluster, and the standard deviations corresponding to multiple sample process features in the standard cluster. The process quality inspection results of the target cigarette at the target production progress are determined based on multiple deviation data.

5. The method for quality processing of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 4, characterized in that, After determining the process quality inspection results of the target cigarette at the target production progress based on the multiple deviation data, the method further includes: If the process quality inspection result is the target quality inspection result, a target report is generated based on the deviation data between the target process characteristics and the standard cluster.

6. The method for quality processing of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 4, characterized in that, The methods for obtaining the standard cluster include: The process time series data and sample quality inspection data of the target cigarettes in multiple batches are obtained. The first process feature corresponding to each batch of the sample process time series data is determined. The first process features in multiple batches are clustered to obtain multiple first clusters. Multiple second process features are determined from multiple first clusters based on the sample quality inspection data of multiple batches in each first cluster; Multiple second process features are filtered according to preset screening conditions to determine sample process features, and multiple second clusters are determined based on the multiple sample process features. Standard clusters are determined based on multiple second clusters, wherein different standard clusters correspond to different quality labels.

7. The method for quality treatment of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 1, characterized in that, The step of determining the equipment characteristics corresponding to the target production progress based on the equipment runtime sequence data includes: Based on the data type of the device runtime sequence data, extract the runtime parameter features corresponding to each data type; By combining multiple operating parameter features, equipment features corresponding to the target production progress are obtained.

8. The method for quality treatment of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 1, characterized in that, The step of inputting the equipment features into a pre-trained equipment state detection model to determine the equipment state detection result of the target cigarette at the target production progress includes: The equipment features are clustered, and the equipment production mode corresponding to the equipment features is determined based on the clustering results; Based on the equipment production mode, determine the equipment status detection results for the target cigarette at the target production progress.

9. The method for quality processing of tobacco shreds in a cigarette factory's tobacco processing production line according to claim 1, characterized in that, The step of generating a maintenance work order for the target cigarette based on the process quality inspection results and the equipment status inspection results includes: The production status of the target cigarette is determined based on the process quality inspection results and the equipment status inspection results. When the production status is abnormal, a maintenance work order is generated to maintain the target cigarette.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the tobacco quality processing method for the cigarette manufacturing production line as described in any one of claims 1-9.

Images