Threshing and redrying abnormal working condition influence degree evaluation method and device, medium and terminal

Abstract

The invention discloses a threshing and redrying abnormal working condition influence degree evaluation method and device, a medium and a terminal. The evaluation method comprises the steps that multiple online data in a preset period in the tobacco threshing and redrying processing process are acquired; carrying out standardization processing on various online data, and recording according to a time sequence; performing abnormal data point identification and marking on each type of second-type standardized online data, and segmenting a plurality of second-type standardized online data points of each type of second-type standardized online data into a plurality of time periods to form an original set, selecting continuous n second-class standardized online data points as original subgroups in the total time period of the original set, calculating the standard deviation of each original subgroup, and determining a standard deviation threshold value; identifying the time period when the abnormal working condition occurs, and judging the type of the abnormal working condition; and evaluating the influence degree of the abnormal working condition on the second type of standardized online data. According to the method, the influence degree of the corresponding abnormal working condition on the corresponding second-class standardized online data can be evaluated.

Description

Technical Field

[0001] The present invention belongs to the technical field of tobacco threshing and redrying, and in particular relates to a method, device, medium and terminal for evaluating the degree of influence of abnormal working conditions of threshing and redrying. Background Art

[0002] In the tobacco industry chain, threshing and redrying is an important link between tobacco planting and cigarette production. The stability and uniformity of the threshing and redrying process indirectly affect the quality of cigarette products. Abnormal working conditions such as shutdown and material breakage during the threshing and redrying process directly and seriously affect the quality of the finished tobacco leaves, and easily bring safety hazards to cigarette processing.

[0003] Patent CN111972693A discloses a method for identifying abnormal working conditions in tobacco leaf threshing and redrying. The patent provides abnormal working condition determination rules for each processing step of threshing and redrying based on actual production conditions. However, abnormal working conditions that occur during the actual processing of threshing and redrying are often accompanied by abnormal fluctuations in process quality. These abnormal fluctuations are different from the normal steady-state production process and affect the stability and uniformity of cigarette products. Therefore, threshing and redrying enterprises, on the basis of correctly identifying abnormal working conditions, need to conduct statistics and analysis on the abnormal fluctuations in product quality caused by abnormal working conditions, and need to evaluate the degree of impact of abnormal working conditions on product quality, so as to implement different treatment plans based on the difference in the degree of impact when abnormal working conditions occur, thereby facilitating the comprehensive quality risk management of the threshing and redrying production process.

[0004] Currently, there are no reports on the impact of abnormal operating conditions during threshing and redrying. Establishing a scientific and convenient evaluation method for the impact of abnormal operating conditions during threshing and redrying is of great significance for reducing the impact of abnormal conditions on the quality of finished tobacco strips, further improving the process control capabilities of threshing and redrying enterprises, and enhancing the stability of product formulations in cigarette manufacturers. Summary of the Invention

[0005] In view of the above-mentioned defects of the prior art, the present invention provides a method, device, medium and terminal for evaluating the degree of impact of abnormal working conditions of leaf threshing and redrying, which can evaluate the degree of impact of corresponding abnormal working conditions on corresponding second-category standardized online data.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] A method for evaluating the impact degree of abnormal working conditions of leaf threshing and redrying, comprising the following steps:

[0008] S1. Acquire multiple types of online data within a preset period of a tobacco leaf threshing and redrying process, wherein the process includes multiple processing steps, each of which includes multiple types of online data. Among the multiple types of online data, multiple types of online data related to processing equipment are referred to as first-category online data, and the remaining types of online data related to tobacco leaves are referred to as second-category online data.

[0009] S2. Standardize the plurality of first-category online data to obtain first-category standardized online data, standardize the plurality of second-category online data to obtain second-category standardized online data, and record them in chronological order;

[0010] S3. Identify and mark abnormal data points for each type of second-class standardized online data, and divide multiple second-class standardized online data points of each type of second-class standardized online data into several time periods according to the abnormal data determination rule to form an original set, wherein the time periods of abnormal second-class standardized online data points in the original set constitute the abnormal set, and the time periods of normal second-class standardized online data points constitute the normal set. Select n consecutive second-class standardized online data points within the total time period of the original set as original subgroups, calculate the standard deviation of each original subgroup, and determine the standard deviation threshold based on the distribution of each standard deviation;

[0011] S4. According to the abnormal working condition determination rules, identify the time period when the abnormal working condition occurs for each processing step and determine the type of abnormal working condition;

[0012] S5. For the corresponding abnormal working conditions of the corresponding processing steps, determine the non-steady-state duration before and after the occurrence of the corresponding abnormal working conditions according to the corresponding standard deviation threshold determined in step S3; determine the deviation of the mean of the corresponding second-category standardized online data points in the steady state before and after the occurrence of the corresponding abnormal working conditions; and evaluate the degree of influence of the corresponding abnormal working conditions on the corresponding second-category standardized online data.

[0013] Furthermore, in step S1: the processing process includes a primary leaf moistening process, a secondary leaf moistening process, a leaf stem separation process and a re-roasting process; wherein the first type of online data about the processing equipment in the primary leaf moistening process is the actual frequency of a moistening roller, and the second type of online data about the tobacco leaves is the online moisture content after the primary leaf moistening; wherein the first type of online data about the processing equipment in the secondary leaf moistening process is the actual frequency of two moistening rollers, and the second type of online data about the tobacco leaves is the online moisture content after the secondary leaf moistening and the instantaneous flow rate of the secondary leaf moistening; wherein the first type of online data about the processing equipment in the leaf stem separation process is the primary leaf beating roller speed, and the second type of online data about the tobacco leaves is the total area of ​​online tobacco leaf image pixels; wherein the first type of online data about the processing equipment in the re-roasting process is the main belt motor frequency, and the second type of online data about the tobacco leaves is the instantaneous flow rate before roasting and the online moisture content after re-roasting.

[0014] Furthermore, in step S3,

[0015] Identify and mark abnormal data points for each type of second-class standardized online data. Specifically, take one type of second-class standardized online data as an example, calculate the first quartile Q1, the third quartile Q3, and the interquartile range IQR (Q3-Q1) of multiple second-class standardized online data points in the corresponding second-class standardized online data. If the corresponding second-class standardized online data point is greater than Q3+1.5IQR or less than Q1-1.5IQR, it is identified as an abnormal data point and marked.

[0016] For each type of second-class standardized online data, the standard deviation of the first original subgroup is recorded as LSD1, the standard deviation of the second original subgroup is recorded as LSD2, and so on. The standard deviation of the mth original subgroup is recorded as LSDm, where where x i represents the i-th second-category standardized online data point among the consecutive n second-category standardized online data points, Represents the average value of n consecutive second-category normalized online data points;

[0017] Based on the distribution of each standard deviation, the standard deviation threshold is determined. Specifically, based on the distribution of each standard deviation, LSD1, LSD2, ..., LSDm are sorted from low to high, and the standard deviation of the 75-95% quantile is selected as the standard deviation threshold, which is recorded as the LSD threshold.

[0018] Furthermore, step S4 is specifically as follows: according to the abnormal working condition judgment rule, the time period when the abnormal working condition occurs is identified for each processing step, and the start time T of the abnormal working condition is collected. 开始 and the end time T 结束 , and calculate the abnormal working condition duration T = T 结束 -T 开始 , and determine the type of abnormal operating condition.

[0019] Furthermore, in step S4, the abnormal operating condition determination rule is specifically as follows:

[0020] For a single leaf moistening process, if the actual frequency of a moistening drum is ≥20Hz and the online moisture content after a single moistening is ≥15%, it is determined to be a normal operating condition; otherwise, it is determined to be an abnormal operating condition. For an abnormal operating condition of a single leaf moistening process, if the actual frequency of a moistening drum is <20Hz, it is determined to be a shutdown of the single leaf moistening process; if the actual frequency of a moistening drum is ≥20Hz and the online moisture content after a single moistening is <15%, it is determined to be a material interruption in the single leaf moistening process.

[0021] For the secondary leaf moistening process, if the actual frequency of the secondary lubricating drum is ≥20Hz, the online moisture content after the secondary lubricating is ≥15%, and the instantaneous flow rate of the secondary leaf moistening is between 0.9 and 1.1 times the set flow rate, it is determined to be a normal operating condition; otherwise, it is determined to be an abnormal operating condition; for the abnormal operating condition of the secondary leaf moistening process, if the actual frequency of the secondary lubricating drum is <20Hz, it is determined that the secondary leaf moistening process is shut down; if the actual frequency of the secondary lubricating drum is ≥20Hz and the online moisture content after the secondary leaf moistening is <15%, it is determined that the secondary leaf moistening process is broken; if the instantaneous flow rate of the secondary leaf moistening is less than 0.9 times the set flow rate or the instantaneous flow rate of the secondary leaf moistening is greater than 1.1 times the set flow rate, the actual frequency of the secondary lubricating drum is ≥20Hz, and the online moisture content after the secondary leaf moistening is ≥15%, it is determined that the flow rate of the secondary leaf moistening process is unstable;

[0022] For the leaf stem separation process, if the roller speed of the leaf beating is ≥400 rpm and the total pixel area of ​​the online tobacco leaf image is ≥3×10 7 , it is determined to be a normal working condition; otherwise it is determined to be an abnormal working condition; for abnormal working conditions of the leaf stem separation process, if the speed of the threshing roller is less than 400 rpm, it is determined to be a shutdown of the leaf stem separation process; if the speed of the threshing roller is ≥400 rpm and the total pixel area of ​​the online tobacco leaf image is less than 3×10 7 , it is determined that the material is broken in the leaf stem separation process;

[0023] For the re-drying process, if the main mesh belt motor frequency is ≥20Hz, the instantaneous flow rate before re-drying is ≥2000 kg / h and the online moisture after re-drying is ≥10%, it is determined to be a normal operating condition; otherwise it is determined to be an abnormal operating condition; for the abnormal operating condition of the re-drying process, if the main mesh belt motor frequency is <20Hz, it is determined to be a re-drying process shutdown; if the main mesh belt motor frequency is ≥20Hz, the instantaneous flow rate before re-drying is <2000 kg / h or the online moisture after re-drying is <10%, it is determined to be a re-drying process material cutoff; if the main mesh belt motor frequency is ≥20Hz, and the instantaneous flow rate before re-drying is less than 0.9 times the set flow rate but ≥2000 kg / h or the instantaneous flow rate before re-drying is greater than 1.1 times the set flow rate, it is determined to be an unstable flow rate in the re-drying process.

[0024] Furthermore, in step S5, for the corresponding abnormal working condition of the corresponding processing step, the non-steady-state duration before and after the occurrence of the corresponding abnormal working condition is determined according to the corresponding standard deviation threshold determined in step S3, specifically: from the start time T of the corresponding abnormal working condition 开始 Select a consecutive corresponding second-category standardized online data points as the first front subgroup, and then start from the corresponding abnormal condition starting time T 开始 From the moment before , select a number of corresponding second-class standardized online data points and use them as the second front subgroup. Similarly, multiple front subgroups are formed and the standard deviation LSD' of each front subgroup is calculated. When the LSD' of a front subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state start moment T.非稳态开始 , then use T 开始 -T 非稳态开始 Calculate the non-steady-state duration T1 before the occurrence of the corresponding abnormal working condition; from the end time T 终止 Backward select a consecutive corresponding second type of standardized online data points and use them as the first rear subgroup, and then from the corresponding abnormal condition end time T 结束 At the next moment, select a number of corresponding second-class standardized online data points as the second subgroup, and so on to form multiple subgroups, and calculate the standard deviation LSD" of each subgroup. When the LSD" of a subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state end moment T 非稳态结束 , then use T 非稳态结束 -T 结束 Calculate the non-steady-state duration T2 after the corresponding abnormal operating condition occurs.

[0025] Furthermore, in step S5,

[0026] Determine the deviation of the mean of the corresponding second-category standardized online data points in the steady state before and after the corresponding abnormal operating condition occurs. Specifically, the mean of b consecutive corresponding second-category standardized online data points in the steady state before the corresponding abnormal operating condition is recorded as A1, and the mean of b consecutive corresponding second-category standardized online data points in the steady state after the corresponding abnormal operating condition is recorded as A2. The deviation is recorded as D, and D = (A2-A1) / A1;

[0027] Evaluate the degree of influence of the corresponding abnormal operating condition on the corresponding second-category standardized online data, specifically as follows: calculate the influence degree index H of the corresponding abnormal operating condition on the corresponding second-category standardized online data according to the non-steady-state duration before and after the occurrence of the corresponding abnormal operating condition, and the deviation of the mean value of the corresponding second-category standardized online data points in the steady state before and after the occurrence of the corresponding abnormal operating condition, and then H = (T1 + T2) × D; calculate the comprehensive influence degree index Z of the corresponding abnormal operating condition on the corresponding second-category standardized online data according to the corresponding abnormal operating condition duration T, the influence degree index H of the corresponding abnormal operating condition on the corresponding second-category standardized online data, and the difference Δ between the mean value of the corresponding second-category standardized online data points within the corresponding abnormal operating condition duration T and the mean value of the corresponding second-category standardized online data points in the corresponding normal set, and then Z = H × T × |Δ|.

[0028] A device for evaluating the impact of abnormal working conditions on leaf threshing and redrying,

[0029] A data acquisition unit, used to acquire various online data within a preset period during the tobacco leaf threshing and redrying process;

[0030] a data processing unit, configured to perform standardization processing on a plurality of first-category online data to obtain first-category standardized online data, and perform standardization processing on a plurality of second-category online data to obtain second-category standardized online data, and record the data in chronological order;

[0031] An abnormal data identification and marking unit, used to identify and mark abnormal data points for each type of second-category standardized online data;

[0032] a data segmentation calculation unit, configured to segment the plurality of second-category standardized online data points of each type of second-category standardized online data into a plurality of time periods according to an abnormal data determination rule to form an original set, and to select n consecutive second-category standardized online data points within the total time period of the original set as original subgroups, calculate a standard deviation of each original subgroup, and determine a standard deviation threshold based on the distribution of each standard deviation;

[0033] An abnormal working condition judgment unit is used to identify the time period when the abnormal working condition occurs for each processing step and to judge the type of the abnormal working condition according to the abnormal working condition judgment rules;

[0034] The analysis and evaluation unit is used to determine the non-steady-state duration before and after the occurrence of the corresponding abnormal working condition of the corresponding processing process according to the corresponding standard deviation threshold, and determine the deviation of the mean value of the corresponding second-category standardized online data point in the steady state before and after the occurrence of the corresponding abnormal working condition, and evaluate the impact of the corresponding abnormal working condition on the corresponding second-category standardized online data.

[0035] A computer-readable storage medium stores a computer program, which, when executed, implements the above-mentioned method for evaluating the degree of impact of abnormal leaf threshing and re-drying conditions.

[0036] An electronic terminal includes a communication transmitter, a processor and a memory, wherein the communication transmitter is used for communication transmission, the memory is used for storing computer programs, the communication transmitter and the memory are both communicatively connected to the processor, and the processor is used for executing the computer program stored in the memory, so that the electronic terminal executes the above-mentioned method for evaluating the degree of impact of abnormal working conditions of leaf threshing and re-drying.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The present invention can identify the time period when abnormal working conditions occur for each processing step based on the abnormal working condition judgment rules, and can determine the non-steady-state duration before and after the occurrence of the corresponding abnormal working condition for the corresponding processing step based on the determined corresponding standard deviation threshold, thereby providing an effective implementation plan for the automatic identification and judgment of the non-steady-state working condition caused by the abnormal working condition of leaf threshing and re-roasting.

[0039] 2. Based on the automatic identification of abnormal working conditions and non-steady-state working conditions in leaf threshing and redrying, the present invention provides a method for evaluating the degree of influence of corresponding abnormal working conditions on the corresponding second-category standardized online data, which can effectively measure the degree of influence of the occurrence of abnormal working conditions on the quality of work-in-progress, and then facilitate the formulation of an assessment method for abnormal working conditions and non-steady-state working conditions in the leaf threshing and redrying process based on relevant research and statistical results, thereby helping to improve the processing control capabilities of leaf threshing and redrying enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a schematic diagram of the structure of the device for evaluating the degree of influence of abnormal working conditions of leaf threshing and redrying in the present invention;

[0041] Figure 2 Schematic diagram of the structure of the electronic terminal in the present invention. DETAILED DESCRIPTION

[0042] The specific embodiments of the present invention are further described in detail below with reference to the accompanying drawings. These embodiments are only used to illustrate the present invention and are not intended to limit the present invention. In the description of the present invention, unless otherwise specified, the meaning of "multiple" is two or more.

[0043] A method for evaluating the impact degree of abnormal working conditions of leaf threshing and redrying, comprising the following steps:

[0044] S1. Acquire multiple types of online data within a preset period of a tobacco leaf threshing and redrying process, wherein the process includes multiple processing steps, each processing step includes several types of online data, and each type of online data includes multiple online data points. Among the multiple types of online data, several types of online data related to processing equipment are referred to as first-category online data, and the remaining types of online data related to tobacco leaves are referred to as second-category online data.

[0045] The processing process includes a primary leaf moistening process, a secondary leaf moistening process, a leaf stem separation process and a re-roasting process; the first type of online data about the processing equipment in the primary leaf moistening process is the actual frequency of the first leaf moistening roller, and the second type of online data about the tobacco leaves is the online moisture content after the primary leaf moistening; the first type of online data about the processing equipment in the secondary leaf moistening process is the actual frequency of the second leaf moistening roller, and the second type of online data about the tobacco leaves is the online moisture content after the secondary leaf moistening and the instantaneous flow rate of the secondary leaf moistening; the first type of online data about the processing equipment in the leaf stem separation process is the speed of the primary leaf beating roller, and the second type of online data about the tobacco leaves is the total pixel area of ​​the online tobacco leaf image; the first type of online data about the processing equipment in the re-roasting process is the frequency of the main belt motor, and the second type of online data about the tobacco leaves is the instantaneous flow rate before roasting and the online moisture content after re-roasting;

[0046] S2. Standardizing the plurality of first-category online data to obtain first-category standardized online data, and standardizing the plurality of second-category online data to obtain second-category standardized online data, and recording the data in chronological order, wherein each type of first-category standardized online data includes a plurality of first-category standardized online data points, and each type of second-category standardized online data includes a plurality of second-category standardized online data points, wherein the standardization processing is dimensionless processing or format unification processing, wherein the format unification processing specifically includes recording the process to which the data point belongs, the collection time, the parameter name, the value, and the unit in a unified format;

[0047] S3. Identify and mark abnormal data points for each type of second-category standardized online data. Specifically, taking one type of second-category standardized online data as an example, calculate the first quartile Q1, the third quartile Q3, and the interquartile range IQR (Q3-Q1) of multiple second-category standardized online data points in the corresponding second-category standardized online data. If the corresponding second-category standardized online data point is greater than Q3+1.5IQR or less than Q1-1.5IQR, it is identified as an abnormal data point and marked;

[0048] According to the abnormal data determination rule, multiple second-category standardized online data points of each type of second-category standardized online data are divided into several time periods to form an original set R0, wherein each time period includes several consecutive second-category standardized online data points, wherein the time periods of abnormal second-category standardized online data points in the original set R0 constitute an abnormal set R2, and the time periods of normal second-category standardized online data points constitute a normal set R1;

[0049] Select n consecutive second-category standardized online data points as original subgroups within the total time period of the original set R0, where the standard deviation of the first original subgroup is recorded as LSD1, the standard deviation of the second original subgroup is recorded as LSD2, and so on. The standard deviation of the mth original subgroup is recorded as LSDm, and the standard deviation of each original subgroup is calculated, where where x i represents the i-th second-category standardized online data point among the consecutive n second-category standardized online data points, Represents the average value of n consecutive second-category normalized online data points;

[0050] Based on the distribution of each standard deviation, sort LSD1, LSD2, ..., LSDm from low to high, and select the standard deviation of the 75-95% quantile as the standard deviation threshold and record it as the LSD threshold; or calculate the average value of LSD1, LSD2, ..., LSDm and its standard deviation σ LSD , select LSD+1.5σ LSD as the LSD threshold;

[0051] S4. According to the abnormal working condition judgment rules, identify the time period when the abnormal working condition occurs for each processing step, and collect the start time T of the abnormal working condition 开始 and the end time T 结束 , and calculate the abnormal working condition duration T = T 结束 -T 开始 , and determine the type of abnormal working condition;

[0052] The specific rules for determining abnormal operating conditions are as follows:

[0053] For a single leaf moistening process, if the actual frequency of a moistening drum is ≥20Hz and the online moisture content after a single moistening is ≥15%, it is determined to be a normal operating condition; otherwise, it is determined to be an abnormal operating condition. For an abnormal operating condition of a single leaf moistening process, if the actual frequency of a moistening drum is <20Hz, it is determined to be a shutdown of the single leaf moistening process; if the actual frequency of a moistening drum is ≥20Hz and the online moisture content after a single moistening is <15%, it is determined to be a material interruption in the single leaf moistening process.

[0054] For the secondary leaf moistening process, if the actual frequency of the secondary lubricating drum is ≥20Hz, the online moisture content after the secondary lubricating is ≥15%, and the instantaneous flow rate of the secondary leaf moistening is between 0.9 and 1.1 times the set flow rate, it is determined to be a normal operating condition; otherwise, it is determined to be an abnormal operating condition; for the abnormal operating condition of the secondary leaf moistening process, if the actual frequency of the secondary lubricating drum is <20Hz, it is determined that the secondary leaf moistening process is shut down; if the actual frequency of the secondary lubricating drum is ≥20Hz and the online moisture content after the secondary leaf moistening is <15%, it is determined that the secondary leaf moistening process is broken; if the instantaneous flow rate of the secondary leaf moistening is less than 0.9 times the set flow rate or the instantaneous flow rate of the secondary leaf moistening is greater than 1.1 times the set flow rate, the actual frequency of the secondary lubricating drum is ≥20Hz, and the online moisture content after the secondary leaf moistening is ≥15%, it is determined that the flow rate of the secondary leaf moistening process is unstable;

[0055] For the leaf stem separation process, if the roller speed of the leaf beating is ≥400 rpm and the total pixel area of ​​the online tobacco leaf image is ≥3×10 7 , it is determined to be a normal working condition; otherwise it is determined to be an abnormal working condition; for abnormal working conditions of the leaf stem separation process, if the speed of the threshing roller is less than 400 rpm, it is determined to be a shutdown of the leaf stem separation process; if the speed of the threshing roller is ≥400 rpm and the total pixel area of ​​the online tobacco leaf image is less than 3×10 7 , it is determined that the material is broken in the leaf stem separation process;

[0056] For the re-drying process, if the main mesh belt motor frequency is ≥20Hz, the instantaneous flow rate before re-drying is ≥2000 kg / h, and the online moisture content after re-drying is ≥10%, it is determined to be a normal operating condition; otherwise, it is determined to be an abnormal operating condition. For abnormal operating conditions in the re-drying process, if the main mesh belt motor frequency is <20Hz, it is determined to be a re-drying process shutdown. If the main mesh belt motor frequency is ≥20Hz, the instantaneous flow rate before re-drying is <2000 kg / h, or the online moisture content after re-drying is <10%, it is determined to be a re-drying process material shortage. If the main mesh belt motor frequency is ≥20Hz, the instantaneous flow rate before re-drying is less than 0.9 times the set flow rate but ≥2000 kg / h, or the instantaneous flow rate before re-drying is greater than 1.1 times the set flow rate, it is determined to be an unstable re-drying process flow rate.

[0057] S5, from the start time T of the corresponding abnormal working condition 开始 Select a consecutive corresponding second-category standardized online data points as the first front subgroup, and then start from the corresponding abnormal condition starting time T 开始 From the moment before , select a number of corresponding second-class standardized online data points and use them as the second front subgroup. Similarly, multiple front subgroups are formed and the standard deviation LSD' of each front subgroup is calculated. When the LSD' of a front subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state start moment T. 非稳态开始 , then use T 开始 -T 非稳态开始 Calculate the non-steady-state duration T1 before the occurrence of the corresponding abnormal working condition; from the end time T 终止 Backward select a consecutive corresponding second type of standardized online data points and use them as the first rear subgroup, and then from the corresponding abnormal condition end time T 结束 At the next moment, select a number of corresponding second-class standardized online data points as the second subgroup, and so on to form multiple subgroups, and calculate the standard deviation LSD" of each subgroup. When the LSD" of a subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state end moment T 非稳态结束 , then use T 非稳态结束 -T 结束 Calculate the non-steady-state duration T2 after the corresponding abnormal operating condition occurs;

[0058] Determine the deviation of the mean of the corresponding second-category standardized online data points in the steady state before and after the corresponding abnormal operating condition occurs. Specifically, the mean of b consecutive corresponding second-category standardized online data points in the steady state before the corresponding abnormal operating condition is recorded as A1, and the mean of b consecutive corresponding second-category standardized online data points in the steady state after the corresponding abnormal operating condition is recorded as A2, where the deviation is recorded as D, then D = (A2-A1) / A1;

[0059] Evaluate the impact of the corresponding abnormal working conditions on the corresponding second-category standardized online data, specifically:

[0060] Based on the non-steady-state duration before and after the occurrence of the corresponding abnormal operating condition, and the deviation of the mean of the corresponding second-category standardized online data points in the steady state before and after the occurrence of the corresponding abnormal operating condition, the impact index H of the corresponding abnormal operating condition on the corresponding second-category standardized online data is calculated, and then H = (T1 + T2) × D;

[0061] Based on the duration T of the corresponding abnormal operating condition, the impact index H of the corresponding abnormal operating condition on the corresponding second-category standardized online data, and the difference Δ between the mean value of the corresponding second-category standardized online data points within the corresponding abnormal operating condition duration T and the mean value of the corresponding second-category standardized online data points in the corresponding normal set, the comprehensive impact index Z of the corresponding abnormal operating condition on the corresponding second-category standardized online data is calculated, where Z = H × T × |Δ|.

[0062] like Figure 1 As shown, a device for evaluating the degree of influence of abnormal working conditions of leaf threshing and redrying is provided.

[0063] A data acquisition unit, used to acquire various online data within a preset period during the tobacco leaf threshing and redrying process;

[0064] a data processing unit, configured to perform standardization processing on a plurality of first-category online data to obtain first-category standardized online data, and perform standardization processing on a plurality of second-category online data to obtain second-category standardized online data, and record the data in chronological order;

[0065] An abnormal data identification and marking unit, used to identify and mark abnormal data points for each type of second-category standardized online data;

[0066] a data segmentation calculation unit, configured to segment the plurality of second-category standardized online data points of each type of second-category standardized online data into a plurality of time periods according to an abnormal data determination rule to form an original set, and to select n consecutive second-category standardized online data points within the total time period of the original set as original subgroups, calculate a standard deviation of each original subgroup, and determine a standard deviation threshold based on the distribution of each standard deviation;

[0067] An abnormal working condition judgment unit is used to identify the time period when the abnormal working condition occurs for each processing step and to judge the type of the abnormal working condition according to the abnormal working condition judgment rules;

[0068] The analysis and evaluation unit is used to determine the non-steady-state duration before and after the occurrence of the corresponding abnormal working condition of the corresponding processing process according to the corresponding standard deviation threshold, and determine the deviation of the mean value of the corresponding second-category standardized online data point in the steady state before and after the occurrence of the corresponding abnormal working condition, and evaluate the impact of the corresponding abnormal working condition on the corresponding second-category standardized online data.

[0069] The division of the various units of the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or physically separated. These units can all be implemented in the form of software calling through processing elements, or all in the form of hardware. Some units can also be implemented in the form of software calling through processing elements, and some units can be implemented in the form of hardware. The processing element can be an integrated circuit with signal processing capabilities.

[0070] A computer-readable storage medium stores a computer program, which, when executed, implements the above-mentioned method for evaluating the degree of impact of abnormal leaf threshing and re-drying conditions.

[0071] like Figure 2 As shown, an electronic terminal includes a communication transmitter, a processor and a memory, wherein the communication transmitter is used for communication transmission, the memory is used for storing computer programs, the communication transmitter and the memory are both communicatively connected to the processor, and the processor is used for executing the computer program stored in the memory, so that the electronic terminal executes the above-mentioned method for evaluating the impact degree of abnormal working conditions of leaf threshing and re-drying. Specific embodiments

[0073] Taking three redrying batches A, B, and C from a leaf-threshing and redrying company in the 2021 roasting season as an example, the impact assessment method for abnormal leaf-threshing and redrying conditions in this example includes the following steps:

[0074] S1. Acquire multiple types of online data within a preset period of a tobacco leaf threshing and redrying process, where the process includes a primary moistening step, a secondary moistening step, a stem separation step, and a redrying step. Among the multiple types of online data, several types of online data related to processing equipment are referred to as first-category online data, and the remaining types of online data related to tobacco leaves are referred to as second-category online data.

[0075] S2. Standardize the plurality of first-category online data to obtain first-category standardized online data, standardize the plurality of second-category online data to obtain second-category standardized online data, and record them in chronological order;

[0076] S3. Identify and mark abnormal data points for the second type of online data in the redrying process, i.e., the online moisture content after redrying. Specifically, calculate the first quartile Q1, the third quartile Q3, and the interquartile range (IQR) (Q3-Q1) of multiple online moisture content data points after redrying. If the corresponding online moisture content data point after redrying is greater than Q3+1.5IQR or less than Q1-1.5IQR, it is identified as an abnormal data point and marked.

[0077] According to the abnormal data judgment rule, multiple online moisture data points after redrying are divided into several time periods to form an original set R0, wherein each time period includes several consecutive online moisture data points after redrying. The time periods of abnormal online moisture data points after redrying in the original set R0 constitute the abnormal set R2, and the time periods of normal online moisture data points after redrying constitute the normal set R1. The Q1, Q3, IQR, abnormal range and number of data points in R0 for the online moisture after redrying in the redrying process of redrying batches A, B and C are shown in Table 1;

[0078] Table 1

[0079]

[0080] In the total time period of the original set R0, 10 consecutive online moisture data points after redrying are selected as original subgroups, where the standard deviation of the first original subgroup is recorded as LSD1, the standard deviation of the second original subgroup is recorded as LSD2, and so on. The standard deviation of the mth original subgroup is recorded as LSDm, and the standard deviation of each original subgroup is calculated, where where x i represents the i-th online moisture data point after redrying among 10 consecutive online moisture data points after redrying, It represents the average value of 10 consecutive online moisture data points after redrying;

[0081] Based on the distribution of LSD1, LSD2, ..., LSDm, LSD1, LSD2, ..., LSDm were sorted from low to high, and the standard deviation of the 90% quantile was selected as the standard deviation threshold and recorded as the LSD threshold. The LSD thresholds for online moisture after redrying in redrying batches A, B, and C are shown in Table 2.

[0082] Table 2

[0083] Processing batch LSD threshold A 0.174 B 0.145 C 0.157

[0084] S4. According to the abnormal working condition judgment rules, identify the time period when the abnormal working condition occurs for each processing step, and collect the start time T of the abnormal working condition 开始 and the end time T 结束 , and calculate the abnormal working condition duration T = T 结束 -T 开始 , and judge the type of abnormal working condition. The identification of abnormal working condition in a certain section of the redrying process is shown in Table 3;

[0085] Table 3

[0086]

[0087] S5. Taking the abnormal working condition of a certain section of the redrying process as an example, from the start time T 开始 Select 10 consecutive online moisture data points after redrying as the first front subgroup, and then start from the abnormal working condition starting time T 开始 From the moment before , 10 consecutive online moisture data points after redrying are selected and used as the second front subgroup. Similarly, multiple front subgroups are formed and the standard deviation LSD' of each front subgroup is calculated. When the LSD' of a front subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state start moment T 非稳态开始 , then use T 开始 -T 非稳态开始 Calculate the non-steady-state duration T1 before the abnormal condition occurs; from the end time T 终止 Select 10 consecutive online moisture data points after redrying as the first subgroup, and then start from the abnormal condition end time T 结束 At the next moment after the redrying, 10 consecutive online moisture data points are selected as the second subgroup, and so on to form multiple subgroups, and the standard deviation LSD" of each subgroup is calculated. When the LSD" of a subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state end moment T 非稳态结束 , then use T 非稳态结束 -T 结束 Calculate the non-steady-state duration T2 after the abnormal operating condition occurs; the abnormal operating condition type, total non-steady-state duration, non-steady-state duration T1 before the abnormal operating condition occurs, abnormal operating condition duration, and non-steady-state duration T2 after the abnormal operating condition occurs in the redrying process are shown in Table 4;

[0088] Table 4

[0089]

[0090]

[0091] Determine the deviation of the mean of the corresponding second-category standardized online data points in the steady state before and after the occurrence of the corresponding abnormal operating condition. Specifically, taking an abnormal operating condition in a certain section of the redrying process as an example, the mean of 20 consecutive online moisture data points after redrying in the steady state before the abnormal operating condition is recorded as A1, and the mean of 20 consecutive online moisture data points after redrying in the steady state after the abnormal operating condition is recorded as A2. The deviation of the mean of the online moisture data points after redrying in the steady state before and after the abnormal operating condition is recorded as D, and D = (A2-A1) / A1;

[0092] Calculate the impact index H of the corresponding abnormal working condition on the corresponding second-category standardized online data, specifically:

[0093] Taking an abnormal operating condition in a certain section of the redrying process as an example, the impact index H of the abnormal operating condition on the online moisture content after redrying is calculated based on the non-steady-state duration before and after the abnormal operating condition occurs, as well as the deviation from the mean of the online moisture content data points after redrying in the steady state before and after the abnormal operating condition occurs. H = (T1 + T2) × D;

[0094] The abnormal working condition type, total non-steady-state duration, non-steady-state duration T1 before the abnormal working condition occurs, non-steady-state duration T2 after the abnormal working condition occurs, deviation D of the mean value of the online moisture data points after redrying in the steady state before and after the abnormal working condition occurs, and the influence index H of the abnormal working condition on the online moisture after redrying are shown in Table 5.

[0095] Table 5

[0096]

[0097] From the abnormal working condition duration in Table 4, it can be seen that the duration of abnormal working condition No. 4 in the redrying process is less than the duration of abnormal working condition No. 3, less than the duration of abnormal working condition No. 2, and less than the duration of abnormal working condition No. 1. However, in the actual processing process, abnormal working conditions are often accompanied by abnormal fluctuations in process quality before and after. These abnormal fluctuations are different from the normal steady-state production process and have an impact on product stability and uniformity. Based on the automatic identification of abnormal working conditions in leaf threshing and redrying, this method clarifies the rules of non-steady-state duration before and after the abnormal working conditions. The correlation between the work-in-process material information and quality information in the production process is corrected by the deviation D and the impact index H. The impact of the non-steady-state process caused by the abnormal working condition on product stability is quantified by the specific impact index H. Finally, the impact index H of abnormal working condition No. 4 is less than the impact index H of abnormal working condition No. 1, less than the impact index H of abnormal working condition No. 2, and less than the impact index H of abnormal working condition No. 3. This improves the accuracy of the work-in-process information correlation under abnormal working conditions, realizes the intuitive display of the historical processing experience of materials, and improves the production process control capability of leaf threshing and redrying enterprises.

[0098] Calculate the comprehensive impact index Z of the corresponding abnormal operating condition on the corresponding second-category standardized online data. Specifically, taking the same abnormal operating condition in the redrying process as an example, based on the abnormal operating condition duration T, the impact index H of the abnormal operating condition on the online moisture content after redrying, and the difference Δ between the mean of the online moisture content data points after redrying within the abnormal operating condition duration T and the mean of the online moisture content data points after redrying within the normal set R1, calculate the comprehensive impact index Z of the abnormal operating condition on the online moisture content after redrying, and then Z = H × T × |Δ|;

[0099] The abnormal working condition type of the redrying process, the abnormal working condition duration T, the difference Δ between the average value of the online moisture data points after redrying within the abnormal working condition duration T and the average value of the online moisture data points after redrying within the normal set R1, the influence index H of the abnormal working condition on the online moisture after redrying, and the comprehensive influence index Z of the abnormal working condition on the online moisture after redrying are shown in Table 5.

[0100] Table 5

[0101]

[0102] It can be seen from Table 5 that the comprehensive impact index Z of abnormal operating condition No. 4 in the redrying process is less than the comprehensive impact index Z of abnormal operating condition No. 1, less than the comprehensive impact index Z of abnormal operating condition No. 3, and less than the comprehensive impact index Z of abnormal operating condition No. 2.

[0103] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating the impact of abnormal working conditions during leaf threshing and redrying, characterized in that: The following steps are involved: S1. Acquire multiple types of online data within a preset period of a tobacco leaf threshing and redrying process, wherein the process includes multiple processing steps, each of which includes multiple types of online data. Among the multiple types of online data, multiple types of online data related to processing equipment are referred to as first-category online data, and the remaining types of online data related to tobacco leaves are referred to as second-category online data. S2. Standardize the plurality of first-category online data to obtain first-category standardized online data, standardize the plurality of second-category online data to obtain second-category standardized online data, and record them in chronological order; S3. Identify and mark abnormal data points for each type of second-class standardized online data, and divide multiple second-class standardized online data points of each type of second-class standardized online data into several time periods according to the abnormal data determination rule to form an original set, wherein the time periods of abnormal second-class standardized online data points in the original set constitute the abnormal set, and the time periods of normal second-class standardized online data points constitute the normal set. Select n consecutive second-class standardized online data points within the total time period of the original set as original subgroups, calculate the standard deviation of each original subgroup, and determine the standard deviation threshold based on the distribution of each standard deviation; S4. According to the abnormal working condition determination rules, identify the time period when the abnormal working condition occurs for each processing step and determine the type of abnormal working condition; S5. For the corresponding abnormal working conditions of the corresponding processing steps, determine the non-steady-state duration before and after the occurrence of the corresponding abnormal working conditions according to the corresponding standard deviation threshold determined in step S3; determine the deviation of the mean of the corresponding second-category standardized online data points in the steady state before and after the occurrence of the corresponding abnormal working conditions; and evaluate the degree of influence of the corresponding abnormal working conditions on the corresponding second-category standardized online data.

2. The method for evaluating the degree of influence of abnormal working conditions of leaf threshing and redrying according to claim 1 is characterized in that: In step S1, the processing process includes a primary moistening step, a secondary moistening step, a leaf stem separation step, and a redrying step. The first type of online data about the processing equipment in the primary moistening step is the actual frequency of a moistening drum, and the second type of online data about the tobacco leaves is the online moisture content after the primary moistening step. The first type of online data about the processing equipment in the secondary moistening process is the actual frequency of the secondary moistening drum, and the second type of online data about tobacco leaves is the online moisture content after secondary moistening and the instantaneous flow rate of secondary moistening. The first type of online data about the processing equipment in the leaf stem separation process is the rotation speed of the leaf beating rollers, and the second type of online data about tobacco leaves is the total pixel area of ​​the online tobacco leaf image; The first type of online data about processing equipment in the redrying process is the main belt motor frequency, and the second type of online data about tobacco leaves is the instantaneous flow rate before roasting and the online moisture after redrying.

3. The method for evaluating the degree of influence of abnormal working conditions of leaf threshing and redrying according to claim 1 is characterized in that: In step S3, Identify and mark abnormal data points for each type of second-class standardized online data. Specifically, take one type of second-class standardized online data as an example, calculate the first quartile Q1, the third quartile Q3, and the interquartile range IQR (Q3-Q1) of multiple second-class standardized online data points in the corresponding second-class standardized online data. If the corresponding second-class standardized online data point is greater than Q3+1.5IQR or less than Q1-1.5IQR, it is identified as an abnormal data point and marked. For each type of second-class standardized online data, the standard deviation of the first original subgroup is recorded as LSD1, the standard deviation of the second original subgroup is recorded as LSD2, and so on. The standard deviation of the mth original subgroup is recorded as LSDm, where where x i represents the i-th second-category standardized online data point among n consecutive second-category standardized online data points, and x represents the average value of n consecutive second-category standardized online data points; Based on the distribution of each standard deviation, the standard deviation threshold is determined. Specifically, based on the distribution of each standard deviation, LSD1, LSD2, ..., LSDm are sorted from low to high, and the standard deviation of the 75-95% quantile is selected as the standard deviation threshold, which is recorded as the LSD threshold.

4. The method for evaluating the degree of influence of abnormal working conditions of threshing and redrying leaves according to claim 3 is characterized in that: Step S4 is specifically as follows: according to the abnormal working condition judgment rule, identify the time period when the abnormal working condition occurs for each processing step, and collect the start time T of the abnormal working condition. 开始 and the end time T 结束 , and calculate the abnormal working condition duration T = T 结束 -T 开始 , and determine the type of abnormal operating condition.

5. The method for evaluating the degree of influence of abnormal working conditions of leaf threshing and redrying according to claim 1 is characterized in that: In step S4, the abnormal operating condition determination rule is specifically as follows: For a single leaf moistening process, if the actual frequency of a moistening drum is ≥20Hz and the online moisture content after a single moistening is ≥15%, it is determined to be a normal operating condition; otherwise, it is determined to be an abnormal operating condition. For an abnormal operating condition of a single leaf moistening process, if the actual frequency of a moistening drum is <20Hz, it is determined to be a shutdown of the single leaf moistening process; if the actual frequency of a moistening drum is ≥20Hz and the online moisture content after a single moistening is <15%, it is determined to be a material interruption in the single leaf moistening process. For the secondary leaf moistening process, if the actual frequency of the secondary lubricating drum is ≥20Hz, the online moisture content after the secondary lubricating is ≥15%, and the instantaneous flow rate of the secondary leaf moistening is between 0.9 and 1.1 times the set flow rate, it is determined to be a normal operating condition; otherwise, it is determined to be an abnormal operating condition; for the abnormal operating condition of the secondary leaf moistening process, if the actual frequency of the secondary lubricating drum is <20Hz, it is determined that the secondary leaf moistening process is shut down; if the actual frequency of the secondary lubricating drum is ≥20Hz and the online moisture content after the secondary leaf moistening is <15%, it is determined that the secondary leaf moistening process is broken; if the instantaneous flow rate of the secondary leaf moistening is less than 0.9 times the set flow rate or the instantaneous flow rate of the secondary leaf moistening is greater than 1.1 times the set flow rate, the actual frequency of the secondary lubricating drum is ≥20Hz, and the online moisture content after the secondary leaf moistening is ≥15%, it is determined that the flow rate of the secondary leaf moistening process is unstable; For the leaf stem separation process, if the roller speed of the leaf beating is ≥400 rpm and the total pixel area of ​​the online tobacco leaf image is ≥3×10 7 , it is determined to be a normal working condition; otherwise it is determined to be an abnormal working condition; for abnormal working conditions of the leaf stem separation process, if the speed of the threshing roller is less than 400 rpm, it is determined to be a shutdown of the leaf stem separation process; if the speed of the threshing roller is ≥400 rpm and the total pixel area of ​​the online tobacco leaf image is less than 3×10 7 , it is determined that the material is broken in the leaf stem separation process; For the re-drying process, if the main mesh belt motor frequency is ≥20Hz, the instantaneous flow rate before re-drying is ≥2000 kg / h and the online moisture after re-drying is ≥10%, it is determined to be a normal operating condition; otherwise it is determined to be an abnormal operating condition; for the abnormal operating condition of the re-drying process, if the main mesh belt motor frequency is <20Hz, it is determined to be a re-drying process shutdown; if the main mesh belt motor frequency is ≥20Hz, the instantaneous flow rate before re-drying is <2000 kg / h or the online moisture after re-drying is <10%, it is determined to be a re-drying process material cutoff; if the main mesh belt motor frequency is ≥20Hz, and the instantaneous flow rate before re-drying is less than 0.9 times the set flow rate but ≥2000 kg / h or the instantaneous flow rate before re-drying is greater than 1.1 times the set flow rate, it is determined to be an unstable flow rate in the re-drying process.

6. The method for evaluating the impact of abnormal working conditions during leaf threshing and redrying according to claim 4, characterized in that: In step S5, for the corresponding abnormal working condition of the corresponding processing step, the non-steady-state duration before and after the occurrence of the corresponding abnormal working condition is determined according to the corresponding standard deviation threshold determined in step S3, specifically: from the start time T of the corresponding abnormal working condition 开始 Select a consecutive corresponding second-category standardized online data points as the first front subgroup, and then start from the corresponding abnormal condition starting time T 开始 From the moment before , select a number of corresponding second-class standardized online data points and use them as the second front subgroup. Similarly, multiple front subgroups are formed and the standard deviation LSD' of each front subgroup is calculated. When the LSD' of a front subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state start moment T. 非稳态开始 , then use T 开始 -T 非稳态开始 Calculate the non-steady-state duration T1 before the occurrence of the corresponding abnormal working condition; from the end time T 终止 Backward select a consecutive corresponding second type of standardized online data points and use them as the first rear subgroup, and then from the corresponding abnormal condition end time T 结束 At the next moment, select a number of corresponding second-class standardized online data points as the second subgroup, and so on to form multiple subgroups, and calculate the standard deviation LSD" of each subgroup. When the LSD" of a subgroup is less than the LSD threshold, the corresponding moment is the non-steady-state end moment T 非稳态结束 , then use T 非稳态结束 -T 结束 Calculate the non-steady-state duration T2 after the corresponding abnormal operating condition occurs.

7. The method for evaluating the degree of influence of abnormal working conditions of leaf threshing and redrying according to claim 6, characterized in that: In step S5, Determine the deviation of the mean of the corresponding second-category standardized online data points in the steady state before and after the corresponding abnormal operating condition occurs. Specifically, the mean of b consecutive corresponding second-category standardized online data points in the steady state before the corresponding abnormal operating condition is recorded as A1, and the mean of b consecutive corresponding second-category standardized online data points in the steady state after the corresponding abnormal operating condition is recorded as A2. The deviation is recorded as D, and D = (A2-A1) / A1; Evaluate the degree of influence of the corresponding abnormal operating condition on the corresponding second-category standardized online data, specifically as follows: calculate the influence degree index H of the corresponding abnormal operating condition on the corresponding second-category standardized online data according to the non-steady-state duration before and after the occurrence of the corresponding abnormal operating condition, and the deviation of the mean value of the corresponding second-category standardized online data points in the steady state before and after the occurrence of the corresponding abnormal operating condition, and then H = (T1 + T2) × D; calculate the comprehensive influence degree index Z of the corresponding abnormal operating condition on the corresponding second-category standardized online data according to the corresponding abnormal operating condition duration T, the influence degree index H of the corresponding abnormal operating condition on the corresponding second-category standardized online data, and the difference Δ between the mean value of the corresponding second-category standardized online data points within the corresponding abnormal operating condition duration T and the mean value of the corresponding second-category standardized online data points in the corresponding normal set, and then Z = H × T × |Δ|.

8. A device for evaluating the degree of influence of abnormal working conditions of leaf threshing and redrying, characterized in that: A data acquisition unit, used to acquire various online data within a preset period during the tobacco leaf threshing and redrying process; a data processing unit, configured to perform standardization processing on a plurality of first-category online data to obtain first-category standardized online data, and perform standardization processing on a plurality of second-category online data to obtain second-category standardized online data, and record the data in chronological order; An abnormal data identification and marking unit, used to identify and mark abnormal data points for each type of second-category standardized online data; a data segmentation calculation unit, configured to segment the plurality of second-category standardized online data points of each type of second-category standardized online data into a plurality of time periods according to an abnormal data determination rule to form an original set, and to select n consecutive second-category standardized online data points within the total time period of the original set as original subgroups, calculate a standard deviation of each original subgroup, and determine a standard deviation threshold based on the distribution of each standard deviation; An abnormal working condition judgment unit is used to identify the time period when the abnormal working condition occurs for each processing step and to judge the type of the abnormal working condition according to the abnormal working condition judgment rules; The analysis and evaluation unit is used to determine the non-steady-state duration before and after the occurrence of the corresponding abnormal working condition of the corresponding processing process according to the corresponding standard deviation threshold, and determine the deviation of the mean value of the corresponding second-category standardized online data point in the steady state before and after the occurrence of the corresponding abnormal working condition, and evaluate the impact of the corresponding abnormal working condition on the corresponding second-category standardized online data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for evaluating the degree of impact of abnormal leaf threshing and re-drying conditions as described in any one of claims 1 to 7 is implemented.

10. An electronic terminal, characterized in that: It includes a communication transmitter, a processor and a memory, the communication transmitter is used for communication transmission, the memory is used for storing computer programs, the communication transmitter and the memory are both communicatively connected to the processor, and the processor is used to execute the computer program stored in the memory so that the electronic terminal executes the method for evaluating the degree of impact of abnormal working conditions of leaf beating and re-drying as described in any one of claims 1-7.

Images