Cigarette packet slicing process quality detection method, device, equipment, medium and product

Abstract

The invention discloses a cigarette packet slicing process quality detection method and device, equipment, a medium and a product, and the method comprises the steps: collecting the thickness information of each cigarette block, carrying out the grouping of the thickness information to obtain a location thickness cluster, and carrying out the grouping according to the order of the cigarette blocks to obtain a location order thickness sub-cluster; and calculating an overall thickness mean value and a standard deviation according to the thickness information, calculating a location thickness mean value and a standard deviation according to the location thickness cluster, calculating a location order thickness mean value and a standard deviation according to the location order thickness sub-cluster, calculating evaluation parameters, and performing quality evaluation. By automatically measuring the thickness and calculating the evaluation parameters, the defect of qualitative evaluation of the quality in the tobacco bale slicing process is overcome by means of quantitative data, the detection efficiency is improved, and comprehensive evaluation is achieved. Based on the evaluation result, the process quality of different production cycles, batches and single-batch different feeding sequences is evaluated, and the existing problems are reversely traced and analyzed, so that the slicing process and equipment parameters are optimized, and the stability of the subsequent product process processing quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of quality inspection in the production process, and particularly relates to a method, device, equipment, medium and product for inspecting the quality of the cigarette packet slicing process. Background Art

[0002] In the cigarette making workshop, the leaf making section is one of the key production links, and its production process involves multiple important processes. Specifically, the cigarette packet raw materials are fed packet by packet according to the leaf group formula, and successively go through processes such as unpacking, slicing, loose re-drying and flavoring. Among them, the slicing process is a key link in the processing deformation of the cigarette packet raw materials. The thickness of the cigarette blocks after slicing the cigarette packet should be uniform, ensuring that indicators such as the looseness of the tobacco leaves and the moisture content of the materials meet the process requirements, so as to ensure the smoking performance and sensory quality of the cigarette products. Therefore, the quality inspection and evaluation of the cigarette packet slicing process is a key link in the production process and is of great significance for maintaining the stability and consistency of the cigarette products. Summary of the Invention

[0003] The present invention provides a method, device, equipment, medium and product for inspecting the quality of the cigarette packet slicing process, so as to solve the problems of low efficiency of the quality inspection of the cigarette packet slicing process, lack of quantitative basis for evaluation, and poor stability of the processing quality of the product process caused thereby.

[0004] According to one aspect of the embodiments of the present invention, a method for inspecting the quality of the cigarette packet slicing process is provided, including:

[0005] After continuously placing multiple cigarette packets of the current production batch on the production line and slicing them into cigarette blocks by a slicing machine, at multiple acquisition positions on the cigarette blocks, multiple thickness information of each cigarette block is acquired; the thickness information is grouped by location according to the acquisition positions to obtain location thickness clusters corresponding to each location respectively, and according to the cigarette block order of each cigarette block in the cigarette packet to which it belongs, the location thickness clusters are grouped again to obtain location order thickness sub-clusters of each cigarette block in each location for each cigarette block order.

[0006] According to the thickness information of each cigarette block, the overall thickness mean value and the overall standard deviation are calculated, according to the thickness information in each location thickness cluster, the location thickness mean value and the location standard deviation corresponding to each location are calculated respectively, and according to each location order thickness sub-cluster, the location order thickness mean value and the location order standard deviation of each cigarette block in each location for each cigarette block order are calculated.

[0007] According to the overall thickness mean value, the overall standard deviation, the location thickness mean value, the location standard deviation, the location order thickness mean value and the location order standard deviation, multiple cigarette packet slicing evaluation parameters are calculated, and according to the calculated multiple cigarette packet slicing evaluation parameters, the quality of the cigarette packet slicing process of the feeding cigarette packets of the current production batch is evaluated.

[0008] According to another aspect of the embodiments of the present invention, a detection device for the quality of the cigarette packet slicing process is provided, including:

[0009] A thickness acquisition module, configured to, after continuously placing a plurality of cigarette packets of the current production batch on a production line and slicing them into cigarette blocks via a slicing machine, acquire a plurality of thickness information of each cigarette block at a plurality of acquisition positions on the cigarette blocks;

[0010] A thickness grouping module, configured to group the thickness information by location according to the acquisition positions, obtain location thickness clusters respectively corresponding to each location, and re-group the location thickness clusters according to the cigarette block order of each cigarette block in the cigarette packet to which it belongs, so as to obtain location order thickness sub-clusters of each cigarette block in each location for each cigarette block order;

[0011] A parameter calculation module, configured to calculate an overall thickness mean value and an overall standard deviation according to the thickness information of each cigarette block, calculate a location thickness mean value and a location standard deviation respectively corresponding to each location according to the thickness information in each location thickness cluster, and calculate a location order thickness mean value and a location order standard deviation of each cigarette block in each location for each cigarette block order according to the location order thickness sub-clusters;

[0012] A quality evaluation module, configured to calculate a plurality of cigarette packet slicing evaluation parameters according to the overall thickness mean value, the overall standard deviation, the location thickness mean value, the location standard deviation, the location order thickness mean value, and the location order standard deviation, and perform quality evaluation on the cigarette packet slicing process of the feeding cigarette packets of the current production batch according to the calculated plurality of cigarette packet slicing evaluation parameters.

[0013] According to another aspect of the embodiments of the present invention, an electronic device is provided, and the electronic device includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the detection method for the quality of the cigarette packet slicing process according to any embodiment of the present invention.

[0017] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the detection method for the quality of the cigarette packet slicing process according to any embodiment of the present invention is implemented.

[0018] According to another aspect of the embodiments of the present invention, there is also provided a computer program product, including a computer program which, when executed by a processor, implements the steps of the method according to any one of the embodiments of the present invention.

[0019] In the technical solution of the embodiments of the present invention, after the cigarette packs in the current production batch are cut into cigarette blocks, the thickness information of each cigarette block is collected at the collection positions on the cigarette blocks, and these thickness information are grouped by location to obtain location thickness clusters. Then, according to the cigarette block order grouping, location order thickness sub-clusters are obtained, and the overall thickness mean and standard deviation, location thickness mean and standard deviation, and location order thickness mean and standard deviation are calculated, so as to calculate multiple cigarette pack slice evaluation parameters. By automatically measuring the thickness and calculating the evaluation parameters, the deficiency of qualitative evaluation of the quality in the cigarette pack slicing process is filled by means of quantitative data, the detection efficiency is improved, and the real-time comprehensive quality evaluation of the whole and local combination in the cigarette pack slicing process is realized. According to the quality operation evaluation results of the cigarette pack slicing process, the quality of the slicing process of cigarette packs with different production cycles, different production batches and different feeding orders in a single batch can be compared and evaluated, and the reasons for the differences can be reversely searched and analyzed by using the production data, aiming to further optimize the slicing process and equipment parameters, and improve the stability of the subsequent product process processing quality.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0022] Figure 1 is a flowchart of a method for detecting the quality of a cigarette pack slicing process provided in Embodiment 1 of the present invention;

[0023] Figure 2 is a flowchart of another method for detecting the quality of a cigarette pack slicing process provided in Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic diagram of the process of a method for detecting and evaluating the quality of a cigarette pack slicing process applicable to the embodiments of the present invention;

[0025] Figure 4 is a scene diagram of detecting the thickness of cigarette blocks after cigarette packs are sliced applicable to the embodiments of the present invention;

[0026] Figure 5 It is a schematic diagram of a cigarette pack slice applicable to an embodiment of the present invention;

[0027] Figure 6 It is another schematic diagram of a cigarette pack slice applicable to an embodiment of the present invention;

[0028] Figure 7 It is yet another schematic diagram of a cigarette pack slice applicable to an embodiment of the present invention;

[0029] Figure 8 It is a schematic diagram of a 10×6 dimensional location data matrix of cigarette blocks applicable to an embodiment of the present invention;

[0030] Figure 9 It is a box plot of the deviation coefficients of the slicing processes of four batch numbers applicable to an embodiment of the present invention;

[0031] Figure 10 It is a schematic structural diagram of a detection device for the quality of the cigarette pack slicing process provided in Embodiment III of the present invention;

[0032] Figure 11 It is a schematic structural diagram of an electronic device for implementing the detection method of the quality of the cigarette pack slicing process of the embodiment of the present invention. Detailed implementation manners

[0033] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment I

[0036] In cigarette production, the irregularity of cigarette pack raw materials, the flipping during the unpacking process, and the transportation of the conveyor belt often cause the cigarette packs to be biased and misaligned before entering the slicing machine, making it impossible to ensure that the cigarette packs enter the slicing machine neatly and evenly. As a result, the thickness of the cut tobacco blocks after slicing is uneven, affecting the slicing quality. In addition, the working condition of the slicing machine and the fouling of the blades will also have an adverse impact on the slicing quality, resulting in the cut tobacco blocks being too thick or too thin. The cut tobacco blocks that are too thick are prone to caking and clumping during the loose and moistening process, while the cut tobacco blocks that are too thin will cause breakage during the subsequent processing, resulting in raw material loss.

[0037] After the cigarette packs pass through the slicing machine, if they cannot be cut into tobacco blocks of equal thickness, it will further lead to a decrease in the alignment of the cut tobacco blocks on the conveyor belt and an unstable conveying material flow rate. This not only affects the accurate measurement of the electronic belt scale before loose and moistening, but also causes uneven feeding of the subsequent cut tobacco block processing. The loose and moistening system cannot accurately apply steam and control the water addition amount to the cut tobacco blocks according to the measurement of the electronic scale, further affecting the regulation of the moisture content and temperature of the tobacco leaves after moistening and unable to provide a reliable reference for the subsequent production process. Therefore, the quality of slicing directly determines the uniformity of the thickness of the cut tobacco blocks and the stability of the subsequent production process. At present, the average thickness is mainly measured manually with a tape measure and calculated as the basis for slicing quality, but this method has the disadvantages of low efficiency, inconvenient data processing, and lack of real-time performance.

[0038] Figure 1 The following is a flowchart of a method for detecting the quality of the cigarette pack slicing process provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of detecting the quality of the cigarette pack slicing process. This method can be executed by a detection device for the quality of the cigarette pack slicing process. The detection device for the quality of the cigarette pack slicing process can be implemented in the form of hardware and / or software and is generally configured in an electronic device. As Figure 1 shown, the method includes:

[0039] S110. After continuously placing multiple cigarette packs of the current production batch on the production line and cutting them into tobacco blocks through a slicing machine, collect multiple thickness information of each tobacco block at multiple collection positions on the tobacco blocks.

[0040] Specifically, multiple cigarette packs of the current production batch are sequentially placed on the production line. The slicing machine cuts each cigarette pack into multiple cigarette blocks, and a measuring device (such as a laser rangefinder or an ultrasonic sensor) collects the thickness information of the cigarette blocks at each acquisition position. When collecting the thickness information of each sampling point of the cigarette blocks, these measuring devices can collect the thickness data corresponding to multiple acquisition positions in real time or regularly. Among them, the number of cut cigarette blocks = the number of cutting times + 1. Preferably, the number of cutting times is 4, 5, or 6. In addition, since the measuring device continuously collects data during the entire production process of the production line, it is necessary to divide the continuously measured data into single-cigarette-block measurement data. Specifically, it can be calculated by obtaining the flat length of the cut cigarette blocks on the conveyor belt and the preset running speed of the conveyor belt. The running time required for measuring the thickness of a single cigarette block = flat length / running speed of the conveyor belt, and then the data is divided according to the running time. Preferably, the flat length of the cut cigarette blocks on the conveyor belt can be set to the height of the cigarette pack before cutting, and the height of the cigarette pack can be measured by a pair of laser ranging gratings before slicing the cigarette pack.

[0041] S120. Group the thickness information according to the acquisition positions to obtain a location thickness cluster corresponding to each location, and re-group the location thickness clusters according to the block order of each cigarette block in its corresponding cigarette pack to obtain a location order thickness sub-cluster of each cigarette block in each location for each block order.

[0042] In the embodiment of the present invention, the location thickness cluster can be specifically understood as a set of thickness data obtained by grouping the thickness information of a single cigarette block according to the acquisition positions. On each cigarette block, multiple acquisition positions are selected as a group (such as divided into a left part and a right part according to an equal ratio or a set ratio, or divided into an upper part and a lower part according to an equal ratio or a set ratio, etc.), and the thickness information of each position is collected and grouped according to the acquisition positions to form a location thickness cluster. For example, if 2 acquisition positions, namely the left part and the right part, are selected on each cigarette block, then the thickness data of each position forms a location thickness cluster.

[0043] Preferably, according to the division of different parts of the cigarette block, the data matrix of a single cigarette block is horizontally divided into a left part, a middle part, and a right part, and the location measurement data is divided according to 1:1:1; vertically divided into an upper part, a middle part, and a lower part, and the location measurement data is divided according to 3:4:3, and the location data corresponds to the parts of the cigarette block. Then when the data matrix of the cigarette block obtained by collection is 10 location dimensions, divided according to the above ratio, the width of each of the left part, the middle part, and the right part is 2 units, and the heights of the upper part, the middle part, and the lower part are 3, 4, and 3 units respectively.

[0044] In the embodiments of the present invention, the regional order thickness sub-cluster can be specifically understood as a set of thickness data obtained by re-grouping the thickness information in the regional thickness cluster according to the order of the tobacco blocks in the tobacco package to which they belong. When the tobacco package passes through the slicing machine, the slicing machine cuts according to a preset cutting order, and each cut will produce a tobacco block. Therefore, the first cut produces the first tobacco block, the second cut produces the second tobacco block, and so on. The thickness information of each tobacco block in different regions is grouped according to the order of the tobacco blocks. For example, the first tobacco block cut from each tobacco package can be grouped into one group, the last tobacco block can be grouped into one group, and the middle ones can be grouped into one group. The first tobacco block is usually affected by the initial cutting of the slicing machine, and there may be problems such as uneven thickness or cutting deviation. Grouping the first tobacco block separately can specifically analyze and solve the problems that may occur during the initial cutting process. The last tobacco block may be affected by the final cutting of the slicing machine, and there may also be problems such as uneven thickness or cutting deviation. Grouping the last tobacco block separately can specifically analyze and solve the problems that may occur during the final cutting process. The middle tobacco blocks are usually affected by the stable cutting of the slicing machine and have relatively uniform thickness. Grouping the middle tobacco blocks separately can analyze and evaluate the performance of the slicing machine during the stable cutting process. After grouping, each tobacco block is classified into a group according to the order, and each group contains the thickness data corresponding to each tobacco block. This set of data is called the regional order thickness sub-cluster. For example: it can be divided into a first group, a middle group, and a last group, and each group includes the thickness data of the left part, the middle part, and the right part.

[0045] Preferably, the tobacco blocks belonging to the same tobacco block order in all the tobacco packages of the current batch are divided into one group. For example: the first tobacco block in the slicing process of all tobacco packages is divided into one group, the second tobacco block in the slicing process of all tobacco packages is divided into one group, and so on, and the last tobacco block in the slicing process of all tobacco packages is divided into one group. The thickness clusters of each tobacco block in each region for each tobacco block order are grouped to form a regional order thickness sub-cluster. For example: the left part thickness cluster, the middle part thickness cluster, and the right part thickness cluster of the first tobacco block of each tobacco package form a regional order thickness sub-cluster. The left part thickness cluster, the middle part thickness cluster, and the right part thickness cluster of the second tobacco block of each tobacco package form a regional order thickness sub-cluster. And so on, the thickness clusters of the tobacco blocks of each tobacco package in each region are assigned to the corresponding regional order thickness sub-clusters according to each tobacco block order. Grouping the tobacco blocks with the same tobacco block order into one group can more accurately analyze the thickness distribution of the tobacco blocks in each order, thereby discovering possible systematic deviations during the slicing process and improving the pertinence of the analysis. By comparing the tobacco blocks with the same order in different tobacco packages, the consistency and stability of the slicing process can be more intuitively evaluated. By analyzing the data of the regional order thickness sub-clusters of different tobacco block orders, the problems can be quickly located and corresponding adjustments and optimizations can be made, which is convenient for problem troubleshooting and solution, and improves the slicing quality and production efficiency.

[0046] S130. Calculate the overall thickness mean and overall standard deviation based on the thickness information of each tobacco block, calculate the location thickness mean and location standard deviation corresponding to each location according to the thickness information in each location thickness cluster, and calculate the location order thickness mean and location order standard deviation of each tobacco block in each location according to the location order thickness sub-clusters of each location.

[0047] Specifically, according to calculate the thickness mean μ, and according to calculate the standard deviation σ; x i is the thickness measurement value at a single acquisition position, and n is the total number of measurement values. When x i is the thickness measurement value at a single acquisition position of the whole tobacco block, and n is the total number of measurement values of the whole tobacco block, the overall thickness mean and overall standard deviation can be calculated. When x i is the thickness measurement value at a single acquisition position in a single location thickness cluster, and n is the total number of measurement values in a single location thickness cluster, the location thickness mean and location standard deviation can be calculated. When x i is the thickness measurement value at a single acquisition position in a single location order thickness sub-cluster, and n is the total number of measurement values in a single location order thickness sub-cluster, the location order thickness mean and location order standard deviation can be calculated.

[0048] S140. Calculate multiple cigarette pack slice evaluation parameters based on the overall thickness mean, overall standard deviation, location thickness mean, location standard deviation, location order thickness mean, and location order standard deviation, and evaluate the quality of the feeding cigarette pack slicing process of the current production batch according to the calculated multiple cigarette pack slice evaluation parameters.

[0049] Specifically, the overall thickness uniformity index can be calculated by the ratio of the overall standard deviation to the overall thickness mean to reflect the uniformity of the slice thickness, that is, the overall thickness uniformity index = overall standard deviation / overall thickness mean. Similarly, the local thickness uniformity index = location standard deviation / location thickness mean can be calculated. The location thickness difference coefficient is obtained by calculating the deviation degree of each location thickness mean from the overall thickness mean, that is, the location thickness difference coefficient = (location thickness mean - overall thickness mean) / overall thickness mean. The location order stability coefficient is calculated by the ratio of the location order standard deviation to the location order thickness mean to evaluate the stability of the slice thickness of different orders within the same location, that is, the location order stability coefficient = location order standard deviation / location order thickness mean.

[0050] If the overall thickness uniformity index or the local thickness uniformity index is lower than the preset threshold value, it indicates that the slice thickness is uniform. Otherwise, it indicates that there are sources of variation in the production process. By checking the local thickness uniformity index, poorly performing locations can be identified, the reasons for their occurrence can be analyzed, and targeted improvement measures can be taken. If the thickness means of certain locations deviate significantly from the overall mean, that is, the coefficient of variation of the location thickness is greater than the preset threshold value, it indicates that there are systematic problems, such as improper adjustment of the cutting equipment or non-uniformity in the material supply. If the location order stability coefficient is greater than the preset threshold value, it means that even within the same location, the slice thickness changes with the order, which may be related to tool wear or improper adjustment during the cutting process, and problem troubleshooting and process improvement are required.

[0051] In the technical solution of the embodiment of the present invention, after the cigarette packets of the current production batch are cut into cigarette blocks, the thickness information of each cigarette block is collected at the collection positions on the cigarette blocks, and these thickness information are grouped by location to obtain location thickness clusters, and then grouped by cigarette block order to obtain location order thickness sub-clusters. The overall thickness mean and standard deviation, location thickness mean and standard deviation, and location order thickness mean and standard deviation are calculated, so as to calculate multiple cigarette packet slice evaluation parameters. By automatically measuring the thickness and calculating the evaluation parameters, the deficiency of qualitative evaluation of the quality of the cigarette packet slicing process is filled by means of quantitative data, the detection efficiency is improved, and real-time comprehensive quality evaluation of the overall and local combination of the cigarette packet slicing process is realized. According to the quality operation evaluation results of the cigarette packet slicing process, the quality of the slicing process of cigarette packets with different production cycles, different production batches, and different feeding orders in a single batch can be compared and evaluated, and the reasons for the differences are analyzed by reverse searching using production data, aiming to further optimize the slicing process and equipment parameters, and improve the stability of the processing quality of subsequent products.

[0052] Optionally, on the basis of the above embodiments, collecting multiple thickness information of each cigarette block at multiple collection positions on the cigarette block may include:

[0053] By using multiple laser ranging sensors in the laser ranging sensor array arranged above the cigarette block conveyor belt, multiple groups of thickness information are collected for a single cigarette block passing by at multiple time points;

[0054] Among them, by using the laser ranging sensor array for single-time multi-data collection, it is used to collect thickness information at the collection positions within multiple horizontal cigarette block locations of the passing cigarette block. By performing multiple repeated collections on the same cigarette block at multiple time points, it is used to collect thickness information at the collection positions within multiple vertical cigarette block locations of the passing cigarette block.

[0055] Specifically, a set of linear array laser distance sensors can be installed above the conveyor belt. For example, a total of 6 distance sensors are fixed on the bracket at equal intervals, and the bracket is fixed on the side baffles of the conveyor belt. By using the laser distance sensor array to collect multiple data at one time, the thickness information of the collection positions in multiple transverse cigarette block areas of the passing cigarette blocks is collected. Configure the collection parameters of the laser distance sensor to collect multiple thickness information at equal time intervals for each cigarette block along the running direction of the cigarette block. Preferably, it can be set to collect data 10 times. By repeatedly collecting multiple times at multiple time points for the same cigarette block, the thickness information of the collection positions in multiple longitudinal cigarette block areas of the passing cigarette blocks is collected. Record the collected thickness information to form a 10×6 dimensional data matrix data set. Among them, the distance from the laser rangefinder to the bottom plate of the conveyor belt is d 1 , the distance from the laser rangefinder to the measurement point of the cigarette block is d 2 , then the thickness information d of the measurement point cigarette block point = d 1 - d 2 . By setting the laser distance sensor array above the cigarette block conveyor belt, it is possible to collect the thickness information of the cigarette block at multiple positions and multiple time points in the horizontal and vertical directions, accurately obtain the thickness data of the cigarette block, and contribute to improving the quality control and evaluation of the slicing process.

[0056] Embodiment 2

[0057] Figure 2 The figure is a flowchart of another method for detecting the quality of cigarette pack slicing provided in Embodiment 2 of the present invention. This embodiment is a refinement of the operation of "calculating multiple cigarette pack slicing evaluation parameters according to the overall thickness mean, overall standard deviation, regional thickness mean, regional standard deviation, regional order thickness mean, and regional order standard deviation" in the above embodiment. Specifically, it can be: according to the overall thickness mean and overall standard deviation, calculate the overall process quality index of the cigarette pack slicing for the current production batch of input materials, and according to the regional thickness mean and regional standard deviation, calculate the local process quality index corresponding to different regions respectively; according to the overall thickness mean and overall standard deviation, calculate the overall process deviation coefficient of the cigarette pack slicing for the current production batch of input materials, and calculate the overall process quality distribution concentration degree according to the overall process deviation coefficient; according to the regional order thickness mean and regional order standard deviation, calculate the local process deviation coefficient of each cigarette block in each region for each cigarette block order, and calculate the local process quality deviation consistency according to each local process deviation coefficient.

[0058] Correspondingly, as Figure 2 shown, the method includes:

[0059] S210. After continuously placing multiple cigarette packs of the current production batch on the production line and cutting them into cigarette blocks by a slicing machine, multiple thickness information of each cigarette block is collected at multiple collection positions on the cigarette blocks.

[0060] S220. Group the thickness information by location according to the collection positions to obtain location thickness clusters corresponding to each location respectively, and then re-group the location thickness clusters according to the block order of each cigarette block in the cigarette pack to which it belongs, so as to obtain location order thickness sub-clusters of each cigarette block in each location for each block order.

[0061] S230. Calculate the overall thickness mean and overall standard deviation according to the thickness information of each cigarette block, calculate the location thickness mean and location standard deviation corresponding to each location respectively according to the thickness information in each location thickness cluster, and calculate the location order thickness mean and location order standard deviation of each cigarette block in each location for each block order according to each location order thickness sub-cluster.

[0062] S240. Calculate the overall process quality index of the sliced cigarette packs of the current production batch according to the overall thickness mean and overall standard deviation, and calculate the local process quality indices corresponding to different locations according to the location thickness mean and location standard deviation.

[0063] Specifically, the process quality index TC can be calculated according to where μ is the mean of the cigarette block thickness data, σ is the standard deviation of the cigarette block thickness data, T pk and T usl and T lsl are the upper and lower specification limits of the target value respectively. For example, when the target value of the slice thickness is 180mm and the tolerance is ±10mm, the upper and lower specification limits are 190mm and 170mm respectively. Among them, μ and σ are calculated according to the collected thickness information, the target value and tolerance of the slice thickness are preset empirical values, T usl and T lsl are calculated according to the target value and tolerance of the slice thickness, T usl = slice thickness target value + tolerance, T lsl = slice thickness target value - tolerance. When μ is the mean of the overall cigarette block thickness data and σ is the standard deviation of the overall cigarette block thickness data, the overall process quality index is calculated. When μ is the mean of the location cigarette block thickness data and σ is the standard deviation of the location cigarette block thickness data, the local process quality index is calculated.

[0064] S250. Calculate the overall process deviation coefficient of the sliced cigarette packs of the current production batch according to the overall thickness mean and overall standard deviation, and calculate the overall process quality distribution concentration degree according to the overall process deviation coefficient.

[0065] Specifically, it can be based on Calculate the overall process deviation coefficient K of the input cigarette pack slices in the current production batch. Here, μ is the overall thickness mean, σ is the overall standard deviation, μ and σ are calculated based on the collected thickness information, and m is the target slice thickness value preset according to experience. It can be based on Calculate the concentration degree f of the overall process quality distribution.

[0066] S260. Calculate the local process deviation coefficient of each cigarette block at each location according to the thickness mean and standard deviation of the location order, and calculate the local process quality deviation consistency according to each local process deviation coefficient.

[0067] Specifically, it can be based on Calculate the local process deviation coefficient K of each cigarette block at each location according to the order of each cigarette block. Here, μ is the thickness mean of the location order, σ is the standard deviation of the location order, and m is the target slice thickness value. It can be based on Calculate the local process quality deviation consistency f.

[0068] S270. Evaluate the quality of the input cigarette pack slicing process in the current production batch according to the calculated multiple cigarette pack slice evaluation parameters.

[0069] By calculating the overall process quality index and the local process quality index and comparing them with the set threshold values, quality evaluation can be carried out. If the overall or local process quality index is lower than the threshold value, it indicates that there are quality problems in the slicing process and further analysis and improvement are needed. By calculating the overall process deviation coefficient and the concentration degree of the overall process quality distribution and comparing them with the set threshold values, if the overall process deviation coefficient is greater than the threshold value, it indicates that the overall process deviation degree is too large and further analysis and improvement are needed. If the concentration degree of the overall process quality distribution is less than the threshold value, it indicates that the concentration degree of the overall process quality distribution is insufficient and the slicing process is unstable, and further analysis and improvement are needed. By calculating the local process deviation coefficient and the local process quality deviation consistency and comparing them with the set threshold values, if the local process deviation coefficient is greater than the threshold value, it indicates that the local process deviation degree is too large and further analysis and improvement are needed. If the local process quality deviation consistency is less than the threshold value, it indicates that the consistency of the local process quality distribution is insufficient and the slicing process is unstable, and further analysis and improvement are needed.

[0070] The technical solution of the embodiment of the present invention can calculate the overall process quality index and local process quality index of the input cigarette package slices in the current production batch by comprehensively using data indicators such as the overall thickness mean, overall standard deviation, regional thickness mean, and regional standard deviation, so as to comprehensively evaluate the quality level of the slicing process. Further, based on the calculation of the overall process deviation coefficient and the overall process quality distribution concentration, the deviations and their distribution characteristics existing in the slicing process can be analyzed, providing data support for optimizing the slicing process. In addition, by calculating the local process deviation coefficient and local process quality deviation consistency for each cigarette block order in different regions, the slicing quality stability of each cigarette block in a specific region can be detected, which helps to timely discover and solve local quality problems in the slicing process, and improve the quality and stability of the overall production process.

[0071] Optionally, based on the above embodiments, calculating the overall process quality index of the input cigarette package slices in the current production batch according to the overall thickness mean and overall standard deviation may include:

[0072] According to Calculate the overall process quality index TC before correction pk ;

[0073] According to Calculate the overall process quality index TC after correction pmk ; where m is the target value of the slice thickness, μ is the overall thickness mean, σ is the overall standard deviation, T usl and T lsl are the upper and lower specification limits of the target value m respectively.

[0074] Specifically, μ and σ are calculated based on the collected thickness information, m is a preset empirical value, and T usl and T lsl are calculated according to the preset slice thickness target value m and the preset tolerance. When μ is the overall thickness mean and σ is the overall standard deviation, the overall process quality index TC before correction pk and the overall process quality index TC pmk can be calculated through the above formula. When μ is the regional thickness mean and σ is the regional standard deviation, the local process quality index TC before correction pk and the local process quality index TC pmk are calculated through the above formula. The overall process quality index TC before correction pk considers the deviation between the overall thickness mean and the target value, reflecting the deviation degree of the overall slicing process. The overall process quality index TC after correction pmk further corrects TC through the correction factor pk ​The degree of deviation also takes into account the centralization degree of the process, thus more comprehensively evaluating the process quality and making the evaluation results more accurate and reliable. Similarly, the deviation degree is corrected by a correction factor, making the evaluation results of the local process quality index more accurate and reliable, which helps to discover and solve problems in the production process, optimize the slicing process, and improve the product quality. Correspondingly, the six sigma process evaluation and control standard is adopted to grade the slicing process quality index, where TC pmk ≥1.67 indicates that the slicing process quality is excellent, 1.33 ≤ TC pmk <1.67 indicates that the slicing process quality is good, 1 ≤ TC pmk <1.33 indicates that the slicing quality is average, and TC pmk <1 indicates that the slicing quality is poor.

[0075] Optionally, based on the above embodiments, according to the overall thickness mean and the overall standard deviation, calculate the overall process deviation coefficient of the input cigarette packet slicing in the current production batch, and calculate the overall process quality distribution concentration degree according to the overall process deviation coefficient, which may include:

[0076] According to K = |TC pu / TC pl |, calculate the overall process deviation coefficient K of the slicing; where μ is the overall thickness mean, σ is the overall standard deviation, TC pu is the upper unilateral limit of the overall process deviation coefficient of the slicing, TC pl is the lower unilateral limit of the overall process deviation coefficient of the slicing, T usl and T lsl are the upper and lower specification limits of the target value respectively;

[0077] Draw a box plot of the overall process deviation coefficient of the slicing, statistically analyze the distribution characteristics of the overall process deviation coefficient, and calculate the overall process quality distribution concentration degree f = f 3 -f 1 ; where f 1 is the first quartile of the box distribution, and f 3 is the third quartile of the box distribution.

[0078] Specifically, μ and σ are calculated based on the collected thickness information, T usl and T lslIt is calculated based on a preset target value of the slice thickness and a preset tolerance. By calculating the overall process deviation coefficient K, the deviation degree of the slicing process can be quantified, reflecting the deviation of the overall thickness of the tobacco block from the slicing target value. When K > 1, it indicates that the slice thickness is too thin. The larger the K value, the more the slice thickness deviates from the target operating value, and the thinner the slice thickness. When K < 1, it indicates that the slice thickness is too thick. The smaller the K value, the more the slice thickness deviates from the target operating value, and the thicker the slice thickness. When K ≈ 1, it indicates that the slice thickness is close to the slicing target value. The closer the K value is to 1, the closer the slice thickness is to the target operating value. Further, by plotting a box plot of the overall process deviation coefficient, the distribution characteristics of the deviation coefficient can be visually displayed, and then the overall process quality distribution concentration degree f can be calculated. If the f value is lower than the threshold value, it means that the distribution range is narrower, the deviation degree of the slicing process is more consistent, and the lower the f value, the better the concentration degree and the more stable the quality. If the f value is higher than the threshold value, it means that the distribution range is wider, the deviation degree of the slicing process fluctuates greatly, the higher the f value, the worse the concentration degree, and the worse the quality stability. By calculating the overall process deviation coefficient and the overall process quality distribution concentration degree, the quality deviation degree and quality stability of the slicing process can be accurately evaluated to discover abnormal fluctuations in the slicing process, optimize the slicing process, and improve product quality.

[0079] Optionally, based on the above embodiments, according to the thickness mean value of the location order and the standard deviation of the location order, calculate the local process deviation coefficient of each tobacco block at each location in each tobacco block order, and calculate the local process quality deviation consistency according to each local process deviation coefficient, including:

[0080] According to K = |TC pu / TC pl |, calculate the local process deviation coefficient K of the slice; where μ is the thickness mean value of the location order, σ is the standard deviation of the location order, TC pu is the upper unilateral limit of the local process deviation coefficient of the slice, TC pl is the lower unilateral limit of the local process deviation coefficient of the slice, T usl and T lsl are the upper and lower specification limits of the target value respectively;

[0081] According to (Z,H)R c =(Z,H)K max -(Z,H)K min , calculate the local process quality deviation consistency R c ;

[0082] where, K max is the maximum value of the local process deviation coefficient, K minis the minimum value of the local process deviation coefficient, c is the order of the tobacco blocks after cigarette pack slicing, and (Z, H) is the location of the tobacco block. When (Z, H) takes Z, it represents the longitudinal tobacco block location, and when (Z, H) takes H, it represents the transverse tobacco block location.

[0083] Specifically, μ and σ are calculated based on the collected thickness information, and T us1 and T lsl are calculated based on the preset target value m of the slicing thickness and the preset tolerance. By calculating the local process deviation coefficient K, the deviation degree of the slicing process can be quantified, reflecting the thickness deviation of different parts of the tobacco block from the slicing target value. K > 1 indicates that the slicing thickness is too thin. The larger the K value, the more the slicing thickness deviates from the target operating value, and the thinner the slicing thickness. K < 1 indicates that the slicing thickness is too thick. The smaller the K value, the more the slicing thickness deviates from the target operating value, and the thicker the slicing thickness. The smaller K indicates that the slicing thickness is closer to the slicing target value. The closer the K value is to 1, the closer the slicing thickness is to the target operating value. Further, calculate and evaluate the local process quality deviation consistency of the longitudinal and transverse tobacco block locations respectively. If the consistency is lower than the threshold value, it indicates better consistency, and the smaller the value, the better the consistency of the quality deviation in the slicing process. If the consistency is higher than the threshold value, it indicates poor consistency, and the larger the value, the worse the consistency of the local slicing process quality deviation. By calculating the local process deviation coefficient and the local process quality deviation consistency, the local quality deviation degree and quality stability in the slicing process can be accurately evaluated to discover abnormal fluctuations in the slicing process, optimize the slicing process, and improve product quality.

[0084] Optionally, based on the above embodiments, a weighted evaluation method can be adopted to realize the interactive calculation of data from different batches, which can specifically include: determining the overall and local indicators to be evaluated, such as the overall process quality index, the overall process deviation coefficient, and the overall process quality distribution concentration degree, as well as the local process quality index, the local deviation coefficient, and the local process quality deviation consistency. Standardize the data from different batches to ensure the same dimension for different indicators. Specifically, the min-max normalization method can be used: where x ij is the original value of the i-th batch on the j-th indicator, is the value after standardization, min(x j ) and max(x j ) are the minimum and maximum values of the j-th indicator respectively.

[0085] Use the analytic hierarchy process to determine the weight of each indicator, that is, by constructing a hierarchical structure model (target layer, criterion layer, and scheme layer), constructing a judgment matrix through expert scoring or historical data, and then calculating the weight vector and conducting a consistency test. Use the weighted scoring method to calculate the comprehensive score of each batch, that is where si is the comprehensive score of the i-th batch, w j is the weight of the j-th indicator, is the standardized score of the i-th batch on the j-th indicator. Subsequently, the comprehensive scores of all batches are sorted to identify the best and worst performing batches. Calculate the differences in comprehensive scores between different batches, analyze which batches perform better and which batches perform worse, and use statistical test methods (such as t-tests) to test whether the differences between different batches are significant. Compare the different indicators within each batch, analyze which indicators have a greater impact on the comprehensive score, and use correlation analysis methods (such as Pearson correlation coefficients) to analyze the correlation between different indicators. Dynamically adjust the indicator weights according to the data distribution of different batches. For example, if the local indicators of a certain batch fluctuate greatly, the weights of the local indicators can be increased. By adopting a weighted evaluation method, interactive calculations of data for different batches can be achieved, calculate the comprehensive score of each batch, and sort the comprehensive scores of all batches to identify the best and worst performing batches, so as to more comprehensively and accurately evaluate the quality of the slicing process.

[0086] Specific application scenarios

[0087] For ease of understanding, the specific application scenarios applicable to each embodiment of the present disclosure will now be described. The cigarette leaf-making workshop includes key processes such as the leaf-making section, the silk-making section, blending and flavoring, and silk storage. During the production process of the leaf-making section, cigarette package raw materials are fed into the production line one by one according to the leaf group formula, and successively go through processes such as unpacking, slicing, loose rewetting, and feeding. Slicing is a key process for the processing and deformation of cigarette package raw materials. The cigarette manufacturing process specifications require that the thickness of the cigarette blocks after slicing should be uniform, and the range of thickness of the cigarette blocks should not be greater than 15 millimeters.

[0088] In the actual production process, the irregularity of the cigarette package raw materials themselves, as well as the flipping of the cigarette packages and the transportation of the conveyor belt during the unpacking process, result in situations such as bias and misalignment of the cigarette packages before entering the slicing machine, so that it is impossible to ensure that the cigarette packages are arranged neatly and evenly into the slicing machine, resulting in uneven thickness of the cigarette blocks after slicing and affecting the slicing quality; at the same time, the working condition of the slicing machine, the fouling of the blades, etc. will also cause the slicing quality to be not guaranteed. When the sliced cigarette blocks are too thick, they are prone to caking and agglomeration during loose rewetting, and when the sliced cigarette blocks are too thin, breakage will occur during subsequent processing, resulting in raw material loss.

[0089] Meanwhile, if the cigarette package cannot be cut into cigarette blocks of equal thickness after passing through the slicing machine, it will further reduce the alignment of the cigarette blocks arranged on the conveyor belt after slicing and make the flow rate of the conveyed material unstable, affecting the accurate measurement of the electronic belt scale before the loose and re-damping process, and further causing uneven feeding of the subsequent cigarette block processing; the loose and re-damping system cannot accurately apply steam to the cigarette blocks and control the water addition amount according to the measurement of the electronic scale, further affecting the regulation of the moisture content and temperature of the tobacco leaves after re-damping, and unable to provide a reference for the subsequent production process. Therefore, the quality of slicing determines the uniformity of the thickness of the cigarette blocks and the stability of the subsequent production process. If the quality of the slicing process cannot be evaluated and the abnormalities in the slicing process cannot be detected in time during the production process, the quality of the subsequent product processing process will not be guaranteed. At present, manual measurement is mainly carried out with a tape measure, and the average thickness is calculated as the basis for slicing quality. However, this method has the disadvantages of low efficiency, inconvenient data processing, lack of real-time performance, etc., and lacks specific evaluation methods and quantitative bases, unable to provide accurate slicing quality assessment, and difficult to meet the high requirements for slicing quality in modern cigarette production.

[0090] To solve the above problems, an embodiment of the present invention proposes a method for detecting the quality of the cigarette package slicing process. Figure 3 It is a schematic flow chart of a method for detecting and evaluating the quality of the cigarette package slicing process applicable to an embodiment of the present invention, which specifically may include:

[0091] Obtain the total number of cigarette package master cartons of the raw material formula for the production batch. Each cigarette package is cut a times by the slicing machine in the feeding order and cut into a + 1 cigarette blocks, where a can take any integer. Preferably, a can be set to 4, 5 or 6 times. Continuously measure the point thickness of all single cigarette blocks after slicing the cigarette packages of the formula feeding, and collect and record the measurement data in order. Preferably, the device for measuring the thickness of the sampling points of the cigarette blocks can be: install a linear array of laser rangefinders above the conveyor belt, and the ranging sensors are fixed on the bracket at equal distances and are in the same horizontal plane. A total of 6 laser ranging sensors are selected, and the bracket is fixed on the side baffles of the conveyor belt. Figure 4 It is a scene diagram of detecting the thickness of the cigarette blocks after slicing the cigarette package applicable to an embodiment of the present invention, as Figure 4 shown, 1 is the conveyor belt, 2 is the cigarette block after slicing, 3 is the laser rangefinder, and 4 is the mounting bracket. Correspondingly, the calculation method for measuring the thickness of the sampling points of the cigarette blocks can be: the distance collected by the laser rangefinder to the bottom plate of the conveyor belt is d 1 and the distance collected to the measurement point of the cigarette block is d 2 , then the point thickness d of the measurement point of the cigarette block = d 1 -d 2 , and the measurement accuracy is ±0.01, with the unit of millimeter.

[0092] Taking the running time required for measuring the thickness of a single cigarette block as a node, the data obtained from continuous measurement is divided into single cigarette block measurement data. For example, according to the laying length L of the single cigarette block on the conveyor belt and the running speed v of the conveyor belt, the running time t for the single cigarette block to pass through the laser rangefinder can be calculated as t = L / v, and the division is carried out according to t. Preferably, the laying length L of the single cigarette block on the conveyor belt is the height before the cigarette pack is sliced, and the two are equal as a fixed value. The height of the cigarette pack is measured by a pair of laser ranging gratings before the cigarette pack is sliced, with the unit of millimeter. The running speed of the conveyor belt is v, with the unit of millimeter per second. The running time t for the single cigarette block to pass through the laser rangefinder is t = L / v, with the unit of second.

[0093] Calculate the quality index TC of the cigarette pack slicing process for the entire batch of input materials pmk , and divide the measurement data into horizontal and vertical location data according to the cigarette block location. For example, it is divided into upper and lower or left and right two parts in the form of equal proportion or other proportions, and further calculate the quality index of the cigarette pack slice location process, and grade the quality index of the slice process. Among them, In the formula where m is the target value of the slice thickness, μ is the mean value of the measured values, σ is the standard deviation, x i is a single measured value, n is the total number of measured values, T usl and T lsl are the upper and lower specification limits of the target value m respectively. μ and σ are calculated based on the collected thickness information, m is a preset empirical value, T usl and T lsl are calculated based on the preset target value m of the slice thickness and the preset tolerance. T usl = slice thickness target value + tolerance, T lsl = slice thickness target value - tolerance. When μ is the mean value of the overall measured values and σ is the overall standard deviation, the overall process quality index TC is calculated pmk , when μ is the mean value of the local measured values and σ is the local standard deviation, the local process quality index TC is calculated pmk . Using the six sigma process evaluation and control standard, grade the quality index of the slice process, where 1.67 ≤ TC pmk indicates that the quality of the slice process is excellent, 1.33 ≤ TC pmk < 1.67 indicates that the quality of the slice process is good, 1 ≤ TC pmk < 1.33 indicates that the slice quality is average, and TC pmk<0 indicates that the slice quality is poor. Preferably, each tobacco block is collected at equal time intervals by a rangefinder along the running direction of the tobacco block, and a total of 10 times are collected. Each time, 6 groups of data are collected. Correspondingly, according to different parts of the tobacco block, the 10 data of a single tobacco block, the data matrix of the dimension, is horizontally divided into the left part, the middle part and the right part, and the location measurement data is divided according to 1:1:1; vertically divided into the upper part, the middle part and the lower part, and the location measurement data is divided according to 3:4:3, and the location data corresponds to the part of the tobacco block.

[0094] Calculate the deviation coefficient K of the slicing process after slicing the cigarette pack, and make a box plot of the deviation coefficient of the cigarette pack slicing process, and statistically analyze the distribution characteristics of the deviation coefficient of the tobacco block after slicing all cigarette packs, so as to obtain the quality distribution concentration f of the slicing process. Among them, the deviation coefficient K of the slicing process = |TC pu / TC pl |, where TC pu is the deviation coefficient of the slicing process of the unilateral upper limit, and TC pl is the deviation coefficient of the slicing process of the unilateral lower limit; the quality distribution concentration f of the slicing process = f 3 -f 1 , where f 1 is the first quartile of the box plot, and f 3 is the third quartile of the box plot.

[0095] Group the tobacco blocks of different slicing orders after slicing the cigarette pack. For example, according to the order, the tobacco blocks corresponding to each cigarette pack can be grouped in pairs to calculate the local deviation coefficients H K and Z K in the horizontal and vertical directions of different slicing order arrays, and then obtain the local slicing process quality deviation consistency R c . Among them, the local slicing process quality deviation consistency R c , and the calculation method is (Z,H)R c =(Z,H)K max -(Z,H)K min , where K max is the maximum value of the local slicing deviation coefficient, and K min is the minimum value of the local slicing deviation coefficient, and c is the order of the tobacco block after slicing the cigarette pack. (Z,H) is the location of the tobacco block. When (Z,H) takes Z, it represents the vertical location of the tobacco block, and when (Z,H) takes H, it represents the horizontal location of the tobacco block. Preferably, the grouping method of tobacco blocks of different slicing orders is that the first tobacco block in the slicing process of all cigarette packs is divided into a group, the second tobacco block in the slicing process of all cigarette packs is divided into a group, and so on, and the (a + 1)-th tobacco block is divided into a group.

[0096] The deviation coefficient K of the cutting area position is used to reflect the deviation of the thickness of different parts of the tobacco block from the target value of slicing. When K > 1, it indicates that the slicing thickness is too thin. The larger the K value, the more the slicing thickness deviates from the target operating value, and the thinner the slicing thickness. When K < 1, it indicates that the slicing thickness is too thick. The smaller the K value, the more the slicing thickness deviates from the target operating value, and the thicker the slicing thickness. The smaller K indicates that the slicing thickness is closer to the target value of slicing. The closer the K value is to 1, the closer the slicing thickness is to the target operating value. The consistency of deviation in the slicing process is used to reflect the consistency of the quality deviation of the tobacco block in the transverse and longitudinal directions during the local slicing process after the cigarette pack is sliced. The smaller the value, the better the consistency of the quality deviation in the slicing process. The larger the value, the worse the consistency of the quality deviation in the local slicing process. The consistency of deviation in the slicing process only indicates the consistency of the quality in the slicing process.

[0097] The quality index of the cigarette pack slicing process is adopted, and combined with the quality distribution characteristics and distribution concentration degree of the slicing process, to characterize and evaluate the overall quality of the cigarette pack slicing process. The quality index of the cutting area position process of the cigarette pack is adopted, and combined with the local slicing deviation coefficient and the consistency of deviation in the slicing process, to characterize and evaluate the local quality of the cigarette pack slicing process, so as to realize the evaluation of the comprehensive quality of the cigarette pack slicing process.

[0098] In a specific example, a total of 4 batches of cigarette pack formula feeding materials of a certain cigarette brand in different production cycles are selected, numbered from 1 to 4, and the total number of feeding cigarette packs obtained for each batch is 15 packs. Each batch of cigarette packs is cut 5 times by a slicing machine in the feeding order and cut into 6 tobacco blocks. Figure 5 It is a schematic diagram of cigarette pack slicing applicable to the embodiment of the present invention. Figure 6 It is another schematic diagram of cigarette pack slicing applicable to the embodiment of the present invention. Figure 7 It is yet another schematic diagram of cigarette pack slicing applicable to the embodiment of the present invention. In Figures 5 to 7 it, the phenomenon of the upper part being narrow and the lower part being wide or the upper part being wide and the lower part being narrow generally appears in the cut tobacco blocks. This may be due to the inclination of the cigarette pack during the cutting process, or the uneven distribution of materials, or the inconsistent feeding distance of the cigarette pack between slicing orders, and there may also be problems with the cutting equipment, and it is also possible that the cigarette pack itself has local deformation. These factors will all lead to uneven cutting depth, resulting in the phenomenon of the upper part being narrow and the lower part being wide or the upper part being wide and the lower part being narrow.

[0099] Using a laser rangefinder, along the running direction of the tobacco blocks, continuously measure the point thickness of all single tobacco blocks after slicing the tobacco packets in the formula feeding. Each tobacco block passes through the laser rangefinder at equal time intervals and is measured and collected 10 times in total, and the measurement data is recorded in sequence; among them, the linear array of the laser rangefinder is arranged above the conveyor belt and fixed on the baffle plates on both sides of the conveyor belt with brackets, with a total of 6 laser rangefinders. Taking the running time required for measuring a single tobacco block as the unit node, divide the continuously measured data into the measurement data of each tobacco block; among them, the flat laying length L of the tobacco blocks on the conveyor belt is the height before slicing the tobacco packet, and the two are equal and are fixed values. The height of the tobacco packet is measured by a pair of laser ranging gratings before slicing the tobacco packet. Calculate the quality index TC of the whole batch of formula feeding tobacco packet slicing process pmk (Equivalent to the overall process quality index above). In this example, the target value of the slice thickness is 180 mm, the tolerance is ±10 mm, and the upper and lower specification limits are 190 mm and 170 mm respectively. Table 1 shows the overall and regional slice process quality indexes of 4 batches of formula feeding tobacco packets, and the calculation results are shown in Table 1. Divide the 10×6 dimensional data matrix of single tobacco blocks into different regional data according to the tobacco block parts. Horizontally, it is divided into the left part, the middle part and the right part, and the measurement data is divided into regions according to 1:1:1; vertically, it is divided into the upper part, the middle part and the lower part, and the measurement data is divided into regions according to 3:4:3. The regional data corresponds to the tobacco block parts, Figure 8 is a schematic diagram of a 10×6 dimensional regional data matrix of tobacco blocks applicable to the embodiment of the present invention. Calculate the quality index of the regional slice process of the batch feeding tobacco packet (equivalent to the local process quality index above), and the calculation results are shown in Table 1

[0100] Adopt the six sigma process control evaluation standard to grade and compare the quality indexes of the slice processes of 4 batches of formula feeding tobacco packets calculated. Among them, the overall slice process quality TC of production batch number 1 pmk > 1.67, the slice process quality reaches excellent, and the quality indexes of the regional slice processes are excellent both horizontally and vertically; the overall slice process quality index TC of production batch number 2 pmk < 1, the slice process quality is poor, and the quality indexes of the regional slice processes are poor both horizontally and vertically; the overall slice process quality index of production batch number 3 is 1.33 ≤ TC pmk < 1.67, the slice process quality reaches medium, the quality index of the horizontal slice process of the regional slice process reaches medium, the quality of the vertical slice process is average, the middle part reaches excellent and the lower part reaches medium; the overall slice process quality index TC of production batch number 4 pmk < 1, the slice process quality is poor, and the quality indexes of the regional slice processes are equally poor both horizontally and vertically

[0101] Table 1

[0102]

[0103] Calculate the deviation coefficient K of the cigarette block slicing process after the cigarette pack is sliced respectively, make a box plot of the deviation coefficient K of the cigarette block slicing process, statistically analyze the distribution characteristics of the deviation coefficient of the cigarette blocks after all cigarette packs are sliced, and calculate the concentration degree of the quality distribution in the slicing process. Figure 9 It is a box plot of the deviation coefficient of the slicing process of four batch numbers applicable to the embodiment of the present invention. The calculation results are as Figure 9 shown. By comparing the deviation coefficients of the slicing processes of production batch numbers 1-4, statistically analyzing the quality distribution in the slicing process, it is calculated that the median values of the deviation coefficients of the slicing processes of production batch numbers 1-4 are 1.515, 1.007, 0.987, and 0.520 respectively. Among them, the medians of production batch numbers 2 and 3 are closest to the mean value, and the numerical value of K indicates that the slice thickness is relatively close to the target operating value. While the median of production batch number 1 is the largest, K>1, indicating that the slice thickness is on the thin side. The median of production batch number 4 is the smallest, K<1, indicating that the slice thickness is on the thick side; the concentration degrees are 1.742, 0.055, 0.373, and 1.042 respectively. The quality distributions of the slicing processes of production batch numbers 2 and 3 are the most concentrated, while the quality distribution of the slicing process of production batch number 1 is the most dispersed.

[0104] Group the measurement data of the first to sixth cigarette blocks after each cigarette pack is sliced according to the slicing order of each cigarette pack. The measurement data is divided into 6 groups in total. Calculate the local deviation coefficients of the slices in the vertical and horizontal directions of different slicing order arrays respectively, and use Z K and H K to represent them respectively. Further calculate the local slicing process deviation consistency R c . Statistically analyze the local slicing process quality of the production processes of batch numbers 1-4 respectively. Tables 2 to 5 show the calculation results of the deviation coefficients in the horizontal and vertical directions of the local slices and the slicing process deviation consistency of batch numbers 1 to 4 respectively.

[0105] As shown in Table 2, from the calculation results, it can be obtained that the horizontal slicing process deviation consistency HR 1 and HR 6 of batch number 1 are greater than those of other order cigarette blocks, indicating that the deviation consistency of the local slicing processes of the first order and the sixth order is slightly worse than that of other order cigarette blocks. Specifically, for the first horizontal block H K左 <H K右 , and H K左 <1 and H K右 >1, indicating that there is a situation of thicker left part and thinner right part in the first order cigarette block after the cigarette pack is sliced. For the sixth order cigarette block, H K左 >H K右 , and H K左 >1 and H K右 <1, indicating that there is a situation of thinner left part and thicker right part in the sixth order cigarette block after the cigarette pack is sliced. While the local deviation coefficients H of other order cigarette blocksK All are greater than 1, indicating that the quality of the local slicing process is on the thinner side; in the longitudinal direction, the slicing process deviates from the consistency ZR 1 to ZR 6 There is no obvious difference, but there are differences between the local deviation coefficients of the first order and the sixth order and those of the second to fourth orders. The local deviation coefficients Z K上 、Z K中 and Z K下 of the first order and the sixth order are all less than 1, while the local deviation coefficients Z K of the second to fifth orders are all greater than 1, indicating that the quality of the local slicing process of the first order and the sixth order tobacco blocks is on the thicker side, and the quality of the local slicing process of the second to fifth order tobacco blocks is on the thinner side. In summary, through the quality analysis of the local slicing process of batch number 1, it is found that there is a situation where the left part of the local slicing process of the first order tobacco block is thicker and the right part is thinner, while there is a situation where the left part of the local slicing process of the sixth order tobacco block is thinner and the right part is thicker, and there is a thinner situation in the local slicing process of the second to fifth order tobacco blocks.

[0106] As shown in Table 3, for batch number 2, the deviation consistencies HR 1 to HR 6 、ZR 1 to ZR 6 of the tobacco block slicing process in different orders in the horizontal and longitudinal directions have little difference, and the local slicing process deviation coefficients are all relatively close to 1, indicating that the quality of the local slicing process of the tobacco blocks from the first order to the sixth order is relatively close to the target value, and the deviation consistency of the local slicing process quality is good, and there is no obvious deviation in the slicing process quality.

[0107] As shown in Table 4, for batch number 3, in the horizontal slicing process, the deviation consistencies HR 1 to HR 6 are all small and there is no obvious difference, indicating that the deviation consistency of the slicing process is good, but there are differences between the local deviation coefficients of the first order and the sixth order and those of the second to fourth orders. Specifically, in the horizontal direction, the local deviation coefficients H K左 、H K中 and Z K右 of the first order and the sixth order are all less than 1, while the local deviation coefficients H K of the second to fifth orders are all greater than 1, indicating that the quality of the local slicing process of the first order and the sixth order tobacco blocks is on the thicker side, and the quality of the local slicing process of the second to fifth order tobacco blocks is on the thinner side. In the longitudinal direction, the deviation consistencies ZR 1 and ZR 6 of the first order and the sixth order are significantly greater than those of the tobacco blocks of other orders, indicating that the deviation consistency of the local slicing process of the first order and the sixth order is slightly worse than that of the tobacco blocks of other orders. Specifically, in the longitudinal direction, the first block Z K中 <Z K上 <Z K下 ,and ZK上 <1 and Z K下 >1, indicating that after the cigarette pack is sliced, the first-order cigarette blocks have a thicker upper and middle parts and a thinner lower part, and the sixth-order cigarette block Z K下 <Z K上 <Z K中 , and Z K上 >1 and Z K下 <1, indicating that after the cigarette pack is sliced, the sixth-order cigarette blocks have a thinner upper part and a thicker lower part.

[0108] Table 2

[0109]

[0110] Table 3

[0111]

[0112] As shown in Table 5, for batch number 4, during the local slicing process in the horizontal direction, the quality deviation consistency HR 6 is significantly greater than that of other orders, indicating that the local slicing process of the sixth-order cigarette blocks has a slightly worse deviation from consistency than that of other-order cigarette blocks. Specifically, the local deviation coefficients H of the first, second, and fifth-order cigarette blocks in the horizontal direction K are all greater than 1, indicating that the quality of the local slicing process is on the thinner side. The local deviation coefficients H of the third and fourth-order cigarette blocks K are all less than 1, indicating that the quality of the local slicing process is on the thicker side. And the local deviation coefficient H of the sixth-order cigarette blocks K左 >H K中 >H K右 , indicating that there is a situation where the left part of the sixth-order cigarette blocks is thinner and the middle and right parts are thicker during the slicing process; in the vertical direction, the quality deviation consistency ZR of the local slicing process 1 is significantly greater than that of other orders, indicating that the local slicing process of the first-order cigarette blocks has a slightly worse deviation from consistency than that of other-order cigarette blocks. Specifically, the local deviation coefficients Z of the first, second, and fifth-order cigarette blocks in the vertical direction K are all greater than 1, indicating that the quality of the local slicing process is on the thinner side. The local deviation coefficients Z of the third, fourth, and sixth-order cigarette blocks K are all less than 1, indicating that the quality of the local slicing process is on the thicker side.

[0113] Table 4

[0114]

[0115] Through the statistical analysis of the quality-related data in the cigarette pack slicing process, the quality of the cigarette pack slicing process for 4 batches of formula feeding was analyzed and compared. For batch number 1, the overall quality of the slicing process was poor, the quality distribution in the slicing process was relatively dispersed, and the slicing thickness was on the thin side; for the local slicing process quality, both the horizontal and vertical slicing process qualities were poor. Specifically, for the first-order cigarette blocks in the horizontal direction, the left part was thick and the right part was thin, and for the sixth-order cigarette blocks, the left part was thin and the right part was thick. For the first-order and sixth-order cigarette blocks in the vertical direction, the slicing process quality was thick, while for the second-order to fifth-order cigarette blocks, the slicing process quality was thin, and there were differences in the deviation consistency of the local slicing process quality, but the deviation consistency in the vertical slicing process was better than that in the horizontal direction. For batch number 2, the overall quality of the slicing process reached excellent, the quality distribution in the slicing process was relatively concentrated, and the slicing thickness was closest to the target operating value. For batch number 3, the overall slicing process quality reached medium, the quality distribution in the slicing process was relatively concentrated, and the slicing thickness was relatively close to the target operating value; for the local slicing process quality, the horizontal slicing process quality reached medium, and the slicing process qualities of the first-order and sixth-order cigarette blocks were thick. In the vertical direction, the upper slicing process quality was average, the middle reached excellent, and the lower reached medium. For the first-order cigarette blocks, the upper and middle parts were thick and the lower part was thin, and for the sixth-order cigarette blocks, the upper part was thin and the lower part was thick, and there were differences in the deviation consistency of the local slicing process quality, and the deviation consistency in the horizontal slicing process was better than that in the vertical direction. For batch number 4, the overall slicing process quality was poor, the quality distribution in the slicing process was relatively dispersed, and the overall slicing process quality was thick; for the local slicing process quality, there were obvious differences in the deviation consistency between the horizontal and vertical slicing processes, and the slicing process qualities of cigarette blocks in different orders were uneven and there was no obvious pattern.

[0116] Table 5

[0117]

[0118] Further analyzing and finding the reasons from the results of the slicing process quality evaluation, no abnormalities were found in the cigarette pack slicing process quality of production batch number 2; for production batch number 1, due to the tilting factor of the cigarette pack before entering the slicing machine, the slicing thickness of different parts of the cigarette blocks in the horizontal direction was inconsistent during the slicing process; for production batch number 3, during the production process, due to the tilting during the vertical slicing of the cigarette pack by the slicing machine, the slicing thickness of different parts of the cigarette blocks in the vertical direction was inconsistent; for production batch number 4, during the production process, there were changes in the feeding distance of the cigarette packs between slicing orders, resulting in inconsistent thicknesses of different sliced cigarette blocks; in the next step, the reasons for the slicing quality problems will be solved one by one.

[0119] Optionally, based on the above embodiments, a weighted evaluation method can be adopted to achieve the interactive calculation of data in different batches, which specifically includes: determining the overall and local indicators to be evaluated, such as the overall process quality index, the overall process deviation coefficient, and the overall process quality distribution concentration, as well as the local process quality index, the local deviation coefficient, and the local process quality deviation consistency. Standardize the data in different batches to ensure the consistency of the dimensions of different indicators. Specifically, the min-max normalization method can be used: where x ij is the original value of the i-th batch on the j-th indicator, is the value after standardization, min(x j ) and max(x j ) are the minimum and maximum values of the j-th indicator respectively.

[0120] Use the analytic hierarchy process to determine the weight of each indicator, that is, by constructing a hierarchical structure model (objective layer, criterion layer, and scheme layer), constructing a judgment matrix through expert scoring or historical data, and then calculating the weight vector and performing a consistency test. Use the weighted scoring method to calculate the comprehensive score of each batch, that is where s i is the comprehensive score of the i-th batch, w j is the weight of the j-th indicator, is the standardized score of the i-th batch on the j-th indicator. Subsequently, sort the comprehensive scores of all batches to identify the best and worst performing batches. Calculate the difference in comprehensive scores between different batches, analyze which batches perform better and which batches perform worse, and use statistical test methods (such as t-test) to test whether the differences between different batches are significant. Compare the different indicators within each batch, analyze which indicators have a greater impact on the comprehensive score, and use correlation analysis methods (such as Pearson correlation coefficient) to analyze the correlation between different indicators. Dynamically adjust the indicator weights according to the data distribution of different batches. For example, if the local indicators of a certain batch fluctuate greatly, the weight of the local indicators can be increased. By adopting the weighted evaluation method, the interactive calculation of data in different batches can be achieved, the comprehensive score of each batch can be calculated, and the comprehensive scores of all batches can be sorted to identify the best and worst performing batches, so as to more comprehensively and accurately evaluate the quality of the slicing process.

[0121] The detection method for the quality of the cigarette pack slicing process proposed in the embodiment of the present invention obtains the total number of cigarette packs in the production batch, and after the cigarette packs are sliced, a laser rangefinder is used to continuously measure the point thickness of the cigarette blocks along the running direction of the cigarette blocks, and the measurement data is divided into single-piece cigarette block measurement data; secondly, the slicing process quality index of the entire batch of cigarette packs and the slicing location process quality index are calculated based on the measurement data, and the slicing process quality index is graded; then, the slicing process deviation coefficient after the cigarette packs are sliced ​​is calculated, the distribution characteristics of the cigarette block deviation coefficient and the slicing process quality distribution concentration are statistically analyzed, and the cigarette blocks with different slicing orders are further grouped, and the local deviation coefficients of the slices of different slicing order groups are calculated, so as to obtain the local slicing process deviation consistency; finally, the cigarette pack slicing process quality index is used, and the slicing process quality distribution characteristics and distribution concentration are combined to characterize and evaluate the overall quality of the cigarette pack slicing process, and the cigarette pack slicing location process quality index is used, and the local slicing deviation coefficient and the slicing process deviation consistency are combined to characterize and evaluate the local quality of the cigarette pack slicing process, so as to achieve the evaluation of the comprehensive quality of the cigarette pack slicing process. The lack of qualitative evaluation of the quality of the cigarette pack slicing process is made up by quantitative data. The defined slicing process deviation coefficient objectively reflects the deviation of the thickness of the cigarette block from the target value after the cigarette pack is sliced; the slicing process deviation consistency objectively reflects the consistency of the local slicing process quality of the cigarette block in the horizontal and vertical directions after the cigarette pack is sliced, so as to further reflect the difference in slicing process quality between different slicing orders. According to the evaluation results of the cigarette pack slicing process quality operation, the slicing process quality of cigarette packs with different production cycles, different production batches, and different feeding orders in a single batch can be compared and evaluated. The reasons for the differences can be analyzed by reverse searching the production data, and the slicing process and equipment parameters can be optimized to provide support for the stability of the subsequent product process processing quality.

[0122] Embodiment 3

[0123] Figure 10 This is a schematic diagram of the structure of a device for detecting the quality of a cigarette pack slicing process provided by the third embodiment of the present invention. Figure 10 As shown, the device includes: a thickness acquisition module 1010, a thickness grouping module 1020, a parameter calculation module 1030 and a quality assessment module 1040, wherein:

[0124] The thickness collection module 1010 is used to collect multiple thickness information of each cigarette block at multiple collection positions on the cigarette block after the multiple cigarette packs of the current production batch are continuously put on the production line and cut into cigarette blocks by the slicer;

[0125] The thickness grouping module 1020 is used to group the thickness information into location groups according to the collection position, obtain location thickness clusters corresponding to each location, and further group the location thickness clusters according to the order of the cigarette blocks in the cigarette pack to which they belong, to obtain location order thickness sub-clusters of each cigarette block in each location of each cigarette block order;

[0126] A parameter calculation module 1030 is configured to calculate an overall thickness mean value and an overall standard deviation based on the thickness information of each tobacco block, calculate a regional thickness mean value and a regional standard deviation corresponding to each region respectively based on the thickness information in each regional thickness cluster, and calculate a regional order thickness mean value and a regional order standard deviation of each tobacco block in each region corresponding to the order of each tobacco block based on each regional order thickness sub-cluster.

[0127] A quality evaluation module 1040 is configured to calculate a plurality of cigarette pack slice evaluation parameters based on the overall thickness mean value, the overall standard deviation, the regional thickness mean value, the regional standard deviation, the regional order thickness mean value, and the regional order standard deviation, and perform a quality evaluation on the cigarette pack slice process of the current production batch based on the calculated plurality of cigarette pack slice evaluation parameters.

[0128] The technical solution of the embodiment of the present invention, after the cigarette pack of the current production batch is cut into tobacco blocks, collects the thickness information of each tobacco block at the collection position on the tobacco block, groups these thickness information into regional thickness clusters, and then groups according to the order of the tobacco blocks to obtain regional order thickness sub-clusters, calculates the overall thickness mean value and standard deviation, the regional thickness mean value and standard deviation, and the regional order thickness mean value and standard deviation, thereby calculating a plurality of cigarette pack slice evaluation parameters. By automatically measuring the thickness and calculating the evaluation parameters, it fills the deficiency of qualitative evaluation of the quality of the cigarette pack slice process with quantitative data, improves the detection efficiency, and realizes the real-time comprehensive quality evaluation of the overall and local combination of the cigarette pack slice process. According to the quality operation evaluation results of the cigarette pack slice process, it is possible to compare and evaluate the quality of the slice processes of cigarette packs with different production cycles, different production batches, and different feeding orders in a single batch, and use the production data to inversely search and analyze the reasons for the differences, aiming to further optimize the slice process and equipment parameters, and improve the stability of the processing quality of subsequent products.

[0129] On the basis of the above embodiments, the quality evaluation module 1040 is specifically configured to:

[0130] Calculate an overall process quality index of the cigarette pack slice of the current production batch based on the overall thickness mean value and the overall standard deviation, and calculate a local process quality index corresponding to different regions respectively based on the regional thickness mean value and the regional standard deviation;

[0131] Calculate an overall process deviation coefficient of the cigarette pack slice of the current production batch based on the overall thickness mean value and the overall standard deviation, and calculate an overall process quality distribution concentration degree based on the overall process deviation coefficient;

[0132] Calculate the local process deviation coefficient of each tobacco block at each location according to the thickness mean value and standard deviation of the location order, and calculate the consistency of the local process quality deviation based on each local process deviation coefficient.

[0133] Optionally, based on the above embodiments, the quality assessment module 1040 may include: a first calculation unit and a second calculation unit, where:

[0134] The first calculation unit is used to calculate the overall process quality index TC before correction according to ; pk ;

[0135] The second calculation unit is used to calculate the overall process quality index TC after correction according to ; where m is the target value of the slice thickness, μ is the overall thickness mean value, σ is the overall standard deviation, T pmk and T usl and T lsl are the upper and lower specification limits of the target value m respectively.

[0136] Optionally, based on the above embodiments, the second calculation unit may include: a first calculation subunit and a second calculation subunit, where:

[0137] The first calculation subunit is used to calculate the overall process deviation coefficient K of the slice according to K = |TC pu / TC pl |; where μ is the overall thickness mean value, σ is the overall standard deviation, TC pu is the upper single limit of the overall process deviation coefficient of the slice, TC pl is the lower single limit of the overall process deviation coefficient of the slice, T usl and T lsl are the upper and lower specification limits of the target value respectively;

[0138] The second calculation subunit is used to draw a box plot of the overall process deviation coefficient of the slice, statistically analyze the distribution characteristics of the overall process deviation coefficient, and calculate the overall process quality distribution concentration degree f = f 3 - f 1 ; where f 1 is the first quartile of the box distribution, and f 3 is the third quartile of the box distribution.

[0139] Optionally, based on the above embodiments, the quality assessment module 1040 may include: a third calculation unit and a fourth calculation unit, where:

[0140] The third calculation unit is used to calculate according to K = |TC pu / TC pl|, calculate the local process deviation coefficient K of the slice; where μ is the mean value of the location order thickness, σ is the standard deviation of the location order, and TC pu is the upper unilateral limit of the local process deviation coefficient of the slice, and TC pl is the lower unilateral limit of the local process deviation coefficient of the slice, and T us1 and T lsl are the upper and lower specification limits of the target value respectively;

[0141] The fourth calculation unit is used to calculate the local process quality deviation consistency R according to (Z, H)R c =(Z, H)K max -(Z, H)K min ; c ;

[0142] where, K max is the maximum value of the local process deviation coefficient, K min is the minimum value of the local process deviation coefficient, c is the order of the cigarette blocks after cigarette packet slicing, (Z, H) is the location of the cigarette block. When (Z, H) takes Z, it represents the longitudinal cigarette block location, and when (Z, H) takes H, it represents the transverse cigarette block location.

[0143] Based on the above embodiments, the thickness acquisition module 1010 is specifically used for:

[0144] Collect multiple groups of thickness information for a single cigarette block passing by at multiple time points respectively through a plurality of laser distance sensors in the laser distance sensor array arranged above the cigarette block conveyor belt;

[0145] Among them, the use of the laser distance sensor array for single - time multi - data acquisition is used to collect thickness information at the acquisition positions within multiple transverse cigarette block locations of the passing cigarette block. The multiple repeated acquisitions of the same cigarette block at multiple time points are used to collect thickness information at the acquisition positions within multiple longitudinal cigarette block locations of the passing cigarette block.

[0146] The detection device for the quality of the cigarette packet slicing process provided by the embodiments of the present invention can execute the detection method for the quality of the cigarette packet slicing process provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0147] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved are all in compliance with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0148] Embodiment 4

[0149] Figure 11The schematic structural diagram of the electronic device 10 that can be used to implement the 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, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0150] As Figure 11 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0151] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0152] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for detecting the quality of the cigarette pack slicing process, that is:

[0153] After continuously placing multiple cigarette packs of the current production batch on the production line and slicing them into cigarette blocks by a slicing machine, multiple thickness information of each cigarette block is collected at multiple collection positions on the cigarette blocks;

[0154] Group the thickness information by location according to the collection positions to obtain location thickness clusters corresponding to each location respectively, and re-group the location thickness clusters according to the block order of each cigarette block in the cigarette pack to which it belongs, so as to obtain location order thickness sub-clusters of each cigarette block in each location for each block order;

[0155] Calculate the overall thickness mean and overall standard deviation according to the thickness information of each cigarette block, calculate the location thickness mean and location standard deviation corresponding to each location respectively according to the thickness information in each location thickness cluster, and calculate the location order thickness mean and location order standard deviation of each cigarette block in each location for each block order according to each location order thickness sub-cluster;

[0156] Calculate multiple cigarette pack slice evaluation parameters based on the overall thickness mean, overall standard deviation, location thickness mean, location standard deviation, location order thickness mean and location order standard deviation, and perform quality assessment on the cigarette pack slicing process of the current production batch according to the calculated multiple cigarette pack slice evaluation parameters.

[0157] In some embodiments, the method for detecting the quality of the cigarette pack slicing process can be implemented as a computer program, which is tangibly included 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 onto the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by the processor 11, one or more steps of the method for detecting the quality of the cigarette pack slicing process described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for detecting the quality of the cigarette pack slicing process by any other suitable means (for example, by means of firmware).

[0158] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0159] The computer programs for implementing 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, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0160] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can 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, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0162] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0163] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated 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 a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0164] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0165] The above specific embodiments do not constitute a limitation on the protection scope of the present 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 the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for detecting the quality of cigarette pack slicing process, characterized in that: include: After a plurality of cigarette packs of the current production batch are continuously put on the production line and cut into cigarette blocks by a slicer, a plurality of thickness information of each cigarette block is collected at a plurality of collection positions on the cigarette block; The thickness information is grouped by location according to the collection position to obtain location thickness clusters corresponding to each location, and the location thickness clusters are grouped again according to the order of the cigarette blocks in the cigarette pack to which they belong, to obtain the location order thickness sub-clusters of each cigarette block in each location of each cigarette block order; The overall thickness mean and overall standard deviation are calculated according to the thickness information of each cigarette block, the location thickness mean and location standard deviation corresponding to each location are calculated according to the thickness information in each location thickness cluster, and the location order thickness mean and location order standard deviation of each cigarette block of each cigarette block order at each location are calculated according to each location order thickness sub-cluster; According to the overall thickness mean, overall standard deviation, location thickness mean, location standard deviation, location order thickness mean and location order standard deviation, multiple cigarette pack slicing evaluation parameters are calculated, and based on the calculated multiple cigarette pack slicing evaluation parameters, the quality of the cigarette pack slicing process of the current production batch is evaluated.

2. The method according to claim 1, characterized in that According to the overall thickness mean, overall standard deviation, location thickness mean, location standard deviation, location order thickness mean and location order standard deviation, multiple cigarette pack slice evaluation parameters are calculated, including: The overall process quality index of the current production batch of cigarette pack slices is calculated based on the overall thickness mean and overall standard deviation, and the local process quality index corresponding to different locations is calculated based on the location thickness mean and location standard deviation; According to the overall thickness mean and overall standard deviation, the overall process deviation coefficient of the current production batch of cigarette pack slices is calculated, and the overall process quality distribution concentration is calculated according to the overall process deviation coefficient; According to the location order thickness mean and location order standard deviation, the local process deviation coefficient of each cigarette block of each cigarette block order at each location is calculated, and the local process quality deviation consistency is calculated according to each local process deviation coefficient.

3. The method according to claim 2, characterized in that According to the overall thickness mean and overall standard deviation, the overall process quality index of the current production batch of cigarette pack slices is calculated, including: according to Calculate the overall process quality index TC before correction pk ; according to Calculate the corrected overall process quality index TC pmk ; where m is the target slice thickness, μ is the overall thickness mean, σ is the overall standard deviation, T usl and T lsl are the upper and lower specification limits of the target value m, respectively.

4. The method according to claim 3, characterized in that: According to the overall thickness mean and overall standard deviation, the overall process deviation coefficient of the current production batch of cigarette pack slices is calculated, and the overall process quality distribution concentration is calculated according to the overall process deviation coefficient, including: According to K=|TC pu / TC pl |, calculate the overall process deviation coefficient K of the slice; where, μ is the overall thickness mean, σ is the overall standard deviation, TC pu is the unilateral upper limit of the overall process deviation coefficient of the slice, TC pl is the unilateral lower limit of the overall process deviation coefficient of the slice, T usl and T lsl are the upper and lower specification limits of the target value, respectively; Draw a box plot of the overall process deviation coefficient of the slice, count the distribution characteristics of the overall process deviation coefficient, and calculate the overall process quality distribution concentration f=f3-f1; where f1 is the first quartile of the box distribution, and f3 is the third quartile of the box distribution.

5. The method according to claim 2, characterized in that: According to the location order thickness mean and location order standard deviation, the local process deviation coefficient of each cigarette block of each cigarette block order at each location is calculated, and the local process quality deviation consistency is calculated according to each local process deviation coefficient, including: According to K=|TC pu / TC pl |, calculate the local process deviation coefficient K of the slice; where, μ is the mean thickness of the location order, σ is the standard deviation of the location order, TC pu is the unilateral upper limit of the local process deviation coefficient of the slice, TC pl is the unilateral lower limit of the local process deviation coefficient of the slice, T usl and T lsl are the upper and lower specification limits of the target value, respectively; According to (Z,H)R c =(Z,H)K max -(Z,H)K min , calculate the local process quality deviation consistency R c ; Among them, K max is the maximum deviation coefficient of the local process, K min is the minimum value of the local process deviation coefficient, c is the order of the tobacco pieces after the cigarette pack is sliced, (Z, H) is the location of the tobacco pieces, when (Z, H) takes Z, it represents the longitudinal location of the tobacco pieces, and when (Z, H) takes H, it represents the transverse location of the tobacco pieces.

6. The method according to any one of claims 1 to 5, characterized in that: At multiple collection positions on the cigarette block, multiple thickness information of each cigarette block is collected, including: By using a plurality of laser distance measuring sensors in a laser distance measuring sensor array disposed above the tobacco block conveyor belt, a plurality of sets of thickness information are collected at a plurality of time points for a single tobacco block passing by; Among them, a laser ranging sensor array is used to collect multiple data in a single time, so as to collect thickness information of the collection positions in multiple horizontal smoke block areas of the passed smoke block. By performing multiple repeated collections on the same smoke block at multiple time points, it is used to collect thickness information of the collection positions in multiple longitudinal smoke block areas of the passed smoke block.

7. A device for detecting the quality of cigarette pack slicing process, characterized in that: include: A thickness collection module is used to collect multiple thickness information of each cigarette block at multiple collection positions on the cigarette block after the multiple cigarette packs of the current production batch are continuously put on the production line and cut into cigarette blocks by the slicer; The thickness grouping module is used to group the thickness information by location according to the collection position, obtain the location thickness clusters corresponding to each location, and group the location thickness clusters again according to the order of the cigarette blocks in the cigarette pack to which they belong, to obtain the location order thickness sub-clusters of each cigarette block in each location of each cigarette block order; A parameter calculation module, used to calculate the overall thickness mean and overall standard deviation according to the thickness information of each cigarette block, calculate the location thickness mean and location standard deviation corresponding to each location according to the thickness information in each location thickness cluster, and calculate the location order thickness mean and location order standard deviation of each cigarette block of each cigarette block order at each location according to each location order thickness sub-cluster; The quality assessment module is used to calculate multiple cigarette pack slicing evaluation parameters based on the overall thickness mean, overall standard deviation, location thickness mean, location standard deviation, location order thickness mean and location order standard deviation, and perform quality assessment on the current production batch's cigarette pack slicing process based on the calculated multiple cigarette pack slicing evaluation parameters.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for detecting the quality of the cigarette package slicing process according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for detecting the quality of the cigarette package slicing process according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements a method for detecting the quality of a cigarette packet slicing process according to any one of claims 1 to 6.

Images