Intelligent flue-cured tobacco strip maintenance quality evaluation system

Abstract

The invention discloses an intelligent flue-cured tobacco strip maintenance quality evaluation system which comprises a flue-cured tobacco strip data acquisition module used for acquiring evaluation parameters of flue-cured tobacco strip samples to be evaluated in a storage area; the tobacco strip data processing module is used for processing the evaluation parameters and obtaining the processed evaluation parameters; the tobacco strip quality analysis module is used for performing tobacco strip quality analysis based on a preset tobacco strip quality evaluation index system and the processed evaluation parameters to obtain a tobacco strip quality evaluation result; and the curing quality evaluation module is used for comparing the tobacco strip quality evaluation result with the initial tobacco strip quality and the last tobacco strip quality evaluation result to obtain a tobacco strip curing quality evaluation result in the storage area. According to the method, the quality of the tobacco lamina is evaluated, then the curing quality of the tobacco lamina is evaluated according to the evaluation result, and whether the curing measures in the storage area have defects or not can be determined.

Description

Technical Field

[0001] The invention belongs to the technical field of tobacco strip quality assessment, and in particular relates to an intelligent tobacco strip curing quality assessment system. Background Art

[0002] As the raw material for cigarette production, the quality of tobacco strips directly affects the quality of cigarette products. However, tobacco strips need to go through planting and production, primary baking and acquisition, re-baking and processing, and then to aging in the central warehouse, and finally to feeding and processing in the feeding production line. The storage and maintenance of tobacco strips are particularly important in the whole process. The storage of tobacco strips will cause significant changes in the quality of tobacco strips due to fluctuations in the quality of the tobacco strips themselves, storage methods, and storage environment, chemical reactions, and microbial effects. Therefore, a series of maintenance measures need to be taken during the storage process to minimize the changes in the quality of tobacco strips.

[0003] That is to say, during the storage and maintenance of tobacco strips, the quality of tobacco strips needs to be monitored and evaluated in real time, and the maintenance measures need to be adjusted according to the real-time changes in the quality of tobacco strips. The traditional tobacco strip quality evaluation method relies on professional quality graders and sensory quality evaluators. The evaluation indicators are relatively limited, subjective experience is large, and there is a lack of professional and systematic evaluation models. With the development of the industrial Internet, the use of digital, modular and networked quality evaluation can better solve the above technical problems.

[0004] Therefore, there is an urgent need for an intelligent tobacco leaf curing quality assessment system. Summary of the invention

[0005] In order to solve the above-mentioned technical problems existing in the prior art, the present invention provides an intelligent tobacco leaf maintenance quality assessment system, which evaluates the quality of tobacco leaves by screening evaluation indicators, constructing an evaluation indicator system, and collecting evaluation parameters. Then, by comparing the tobacco leaf quality evaluation results at different times, the tobacco leaf maintenance quality in the storage area is evaluated, and it can be determined whether there are defects in the maintenance measures in the storage area.

[0006] The technical solution adopted by the present invention is:

[0007] An intelligent tobacco leaf curing quality assessment system, characterized by comprising:

[0008] A tobacco strip data collection module, used to collect evaluation parameters of tobacco strip samples to be evaluated in the storage area, wherein the evaluation parameters include sensory parameters, appearance parameters and chemical parameters;

[0009] a cigarette strip data processing module, used to process the evaluation parameters collected by the cigarette strip data collection module to obtain the processed evaluation parameters;

[0010] A tobacco strip quality analysis module, used to perform tobacco strip quality analysis based on a preset tobacco strip quality evaluation index system and evaluation parameters processed by the tobacco strip data processing module, and obtain a tobacco strip quality evaluation result;

[0011] and a curing quality assessment module for comparing the tobacco strip quality assessment result obtained by the tobacco strip quality analysis module with the initial tobacco strip quality and the last tobacco strip quality assessment result, respectively, to obtain the tobacco strip curing quality assessment result in the storage area.

[0012] Furthermore, the cigarette data collection module includes:

[0013] A sensory parameter collection unit, used to perform sensory evaluation on the tobacco sample to be evaluated to obtain sensory parameters;

[0014] An appearance parameter acquisition unit, used to perform an external evaluation on the to-be-evaluated tobacco sample to obtain appearance parameters;

[0015] And a chemical parameter acquisition unit is used to measure the chemical composition of the tobacco sample to be evaluated and obtain the chemical composition parameters.

[0016] Furthermore, the cigarette data processing module includes:

[0017] An abnormal data processing unit, used to determine the abnormal data in the evaluation parameters and re-detect it to determine whether it is a false detection. If it is a false detection, it is replaced with correct data; if it is not a false detection, the abnormal data is marked;

[0018] And a cigarette data packaging unit is used to package and store the evaluation parameters and the annotated abnormal data.

[0019] Furthermore, the tobacco quality analysis module includes:

[0020] An evaluation system construction unit, used to determine the tobacco strip quality evaluation index and construct a tobacco strip quality evaluation index system according to the tobacco strip quality evaluation index;

[0021] and a tobacco sheet quality analysis unit, which is used to calculate the evaluation parameters based on the tobacco sheet quality evaluation index system to obtain a tobacco sheet quality evaluation result.

[0022] Furthermore, the evaluation system construction unit includes:

[0023] An evaluation index screening subunit, used to screen sensory evaluation indexes, appearance evaluation indexes, and chemical evaluation indexes respectively;

[0024] An evaluation index weighting subunit, used to respectively assign weight values ​​to the sensory evaluation index, appearance evaluation index, and chemical evaluation index;

[0025] An evaluation index grading subunit, used to grade and assign values ​​to the sensory evaluation index, appearance evaluation index, and chemical evaluation index respectively;

[0026] And an evaluation system construction subunit, which is used to construct the tobacco quality evaluation index system based on the sensory evaluation index, appearance evaluation index, chemical evaluation index and corresponding weight values ​​and graded assignments.

[0027] Furthermore, the sensory evaluation indicators include aroma quality, aroma quantity, permeability, fineness, miscellaneous smell, irritation, sweetness and aftertaste; the appearance evaluation indicators include color, oil content, fullness, uniformity, brightness and smell; the chemical evaluation indicators include polyphenol degradation rate, pigment degradation rate, pH degradation rate and absorbance value.

[0028] Furthermore, the tobacco quality analysis unit comprises:

[0029] An evaluation model building subunit, used to build a tobacco strip quality evaluation model based on a comprehensive discrimination method of influencing factors combined with the tobacco strip quality evaluation index system;

[0030] and a tobacco strip quality analysis subunit, which is used to substitute the evaluation parameters into the tobacco strip quality evaluation index system and the tobacco strip quality evaluation model to obtain a tobacco strip quality analysis result.

[0031] Furthermore, the tobacco quality evaluation model is:

[0032]

[0033] Among them, T is the total score, w i is the weight value of the i-th evaluation index, u i is the score of the i-th evaluation index, and n is the number of evaluation indicators.

[0034] Furthermore, the maintenance quality assessment module includes:

[0035] a curing quality analysis unit, for comparing the tobacco strip quality evaluation result with the initial tobacco strip quality and the last tobacco strip quality evaluation result, respectively, to obtain a first quality difference value and a second quality difference value;

[0036] and a curing quality assessment unit, configured to determine a curing quality assessment result of the tobacco leaves in the storage area according to the first quality difference and the second quality difference.

[0037] Furthermore, the maintenance quality assessment module also includes a maintenance defect determination unit, which is used to determine the defects of the maintenance measures in the storage area based on the tobacco leaf maintenance quality assessment results and the marked abnormal data.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] The present invention evaluates the quality of tobacco strips by screening evaluation indicators, constructing an evaluation indicator system, and collecting evaluation parameters, and then evaluates the maintenance quality of tobacco strips in a storage area by comparing the evaluation results of tobacco strips at different times, so as to determine whether there are defects in the maintenance measures in the storage area; and by annotating and analyzing abnormal data in the evaluation parameters, technical problems in the maintenance measures in the storage area can be discovered in time, so as to facilitate timely adjustments and better ensure the storage quality of tobacco strips. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention is a schematic diagram of the structure of an intelligent tobacco leaf curing quality assessment system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0042] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0043] The present invention will be described in detail below in conjunction with exemplary embodiments with reference to the accompanying drawings.

[0044] refer to Figure 1 , an intelligent tobacco strip curing quality assessment system of the present invention comprises: a tobacco strip data acquisition module, used to collect evaluation parameters of tobacco strip samples to be evaluated in a storage area, wherein the evaluation parameters include sensory parameters, appearance parameters and chemical parameters;

[0045] a cigarette strip data processing module, used to process the evaluation parameters collected by the cigarette strip data collection module to obtain the processed evaluation parameters;

[0046] A tobacco strip quality analysis module, used to perform tobacco strip quality analysis based on a preset tobacco strip quality evaluation index system and evaluation parameters processed by the tobacco strip data processing module, and obtain a tobacco strip quality evaluation result;

[0047] and a curing quality assessment module for comparing the tobacco strip quality assessment result obtained by the tobacco strip quality analysis module with the initial tobacco strip quality and the last tobacco strip quality assessment result, respectively, to obtain the tobacco strip curing quality assessment result in the storage area.

[0048] Specifically, the tobacco strip data collection module includes: a sensory parameter collection unit, an appearance parameter collection unit, and a chemical parameter collection unit;

[0049] The sensory parameter collection unit is used to perform sensory evaluation on the tobacco samples to be evaluated and obtain sensory parameters;

[0050] An appearance parameter acquisition unit is used to perform external observation and evaluation on the tobacco samples to be evaluated and obtain appearance parameters;

[0051] The chemical parameter acquisition unit is used to determine the chemical composition of the tobacco samples to be evaluated and obtain the chemical composition parameters.

[0052] Specifically, the tobacco strip samples to be evaluated are obtained by random sampling in the tobacco strip storage area every a months, with b kilograms of samples being sampled each time. Sensory evaluation, external evaluation, and chemical composition determination are performed on b kilograms of tobacco strip samples to be evaluated to obtain sensory parameters, appearance parameters, and chemical composition parameters.

[0053] Furthermore, the cigarette strip data processing module includes: an abnormal data processing unit, a cigarette strip data packaging unit;

[0054] The abnormal data processing unit is used to determine the abnormal data in the evaluation parameters and re-detect it to determine whether it is a false detection. If it is a false detection, it is replaced with correct data; if it is not a false detection, the abnormal data is marked; wherein the abnormal data is data that is seriously lower or higher than other data, and data that has a reverse change or a large change compared to the data detected in the previous time interval;

[0055] The cigarette data packaging unit is used to package and store the evaluation parameters obtained at each time interval and the annotated abnormal data.

[0056] Specifically, after obtaining sensory parameters, appearance parameters, and chemical composition parameters, select data that is seriously lower or higher than other data, and data that has reversed or significantly changed compared to the data detected in the previous time interval as abnormal data, and re-evaluate or measure the abnormal data to determine whether it is a false detection. If it is a false detection, delete the abnormal data and replace it with the correct data; if it is not a false detection, mark the abnormal data. After completing the processing of the abnormal data, the evaluation parameters and the marked abnormal data are packaged and stored according to the time of this detection, and the processing of the tobacco data is completed.

[0057] Furthermore, the tobacco strip quality analysis module includes: an evaluation system construction unit, a tobacco strip quality analysis unit;

[0058] The evaluation system construction unit is used to determine the evaluation index of the tobacco strip quality and to construct the tobacco strip quality evaluation index system according to the evaluation index;

[0059] The tobacco strip quality evaluation unit is used to calculate the evaluation parameters based on the tobacco strip quality evaluation index system to obtain the tobacco strip quality evaluation results.

[0060] Specifically, the evaluation system construction unit includes: evaluation index screening subunit, evaluation index weighting subunit, evaluation index grading subunit, and evaluation system construction subunit;

[0061] An evaluation index screening subunit, used to screen sensory evaluation indexes, appearance evaluation indexes, and chemical evaluation indexes respectively;

[0062] The evaluation index weighting subunit is used to assign weight values ​​to the sensory evaluation index, appearance evaluation index, and chemical evaluation index respectively;

[0063] Evaluation index grading subunit, used to grade and assign values ​​to sensory evaluation index, appearance evaluation index and chemical evaluation index respectively;

[0064] The evaluation system construction subunit is used to construct a tobacco leaf quality evaluation index system based on sensory evaluation indexes, appearance evaluation indexes, chemical evaluation indexes and corresponding weight values ​​and grading assignments.

[0065] Specifically, the tobacco strip quality analysis unit includes: an evaluation model building subunit and a tobacco strip quality analysis subunit;

[0066] An evaluation model building subunit is used to build a tobacco strip quality evaluation model based on a comprehensive discrimination method of influencing factors combined with a tobacco strip quality evaluation index system;

[0067] The tobacco strip quality evaluation subunit is used to substitute the evaluation parameters into the tobacco strip quality evaluation index system and the tobacco strip quality evaluation model to obtain the tobacco strip quality analysis results.

[0068] Building a hierarchical system:

[0069] In this embodiment, sensory evaluation indicators, appearance evaluation indicators, and chemical evaluation indicators are used as primary indicators, and specific indicators within the sensory evaluation indicators, appearance evaluation indicators, and chemical evaluation indicators are screened out as secondary indicators, wherein the screened sensory evaluation indicators include aroma quality, aroma quantity, permeability, fineness, miscellaneous smell, irritation, sweetness, and aftertaste; the appearance evaluation indicators include color, oil content, fullness, uniformity, brightness, and smell; the chemical evaluation indicators include polyphenol degradation rate, pigment degradation rate, pH degradation rate, and absorbance value.

[0070] Based on the expert advice, data collection, analysis and comparison, and practical experience, each evaluation indicator in each layer is compared with each other, and scores are assigned according to their relative importance. Finally, the scoring results form a judgment matrix. The judgment matrix is ​​denoted as A, and its form is as follows:

[0071]

[0072] In the formula, a ij It represents the relative importance scale between the i-th evaluation index and the j-th evaluation index, and n is the number of evaluation indicators.

[0073] The formula and steps for obtaining the relevant weights of evaluation indicators using the hierarchical analysis method are as follows:

[0074] Step 1. Process the constructed judgment matrix and normalize it by column:

[0075]

[0076] Step 2. Sum the normalized matrix row by row:

[0077]

[0078] Step 3. Normalize the sum vector:

[0079]

[0080] The final calculated value w i The value of is the weight of a certain indicator. After performing the same operation on all indicators, all weights are ordered to form a set. This set is the required weight vector w, which is expressed as follows:

[0081] w=[w1,w2,w3,…,w n ] Τ (6)

[0082] Step 4. Calculate the maximum characteristic root. The maximum characteristic root is the maximum value of the eigenvalue of the matrix. The calculation formula is:

[0083]

[0084] According to the consistency test principle, if and only if the matrix has complete consistency, the maximum eigenvalue of the matrix is ​​consistent with its matrix order, that is, λ max =n, when the matrix does not meet the consistency test, it means that the consistency of the matrix is ​​poor, and it is necessary to introduce the judgment matrix deviation consistency index CI for investigation, and its expression is:

[0085]

[0086] Generally speaking, the larger the judgment matrix hierarchy, the more difficult it is to ensure its complete consistency. It is necessary to introduce the random consistency ratio CR for investigation. Its expression is as follows:

[0087]

[0088] In the formula, RI represents the average random consistency index, and the RI values ​​are shown in Table 1.

[0089] Table 1

[0090]

[0091] In the consistency test, if CR < 0.1, the matrix is ​​judged to have satisfactory consistency; otherwise, the consistency of the matrix is ​​poor, and the judgment matrix needs to be adjusted and normalized to guide the judgment matrix to meet the consistency test.

[0092] According to the above method, the weights of indicators are obtained, among which, the weights of secondary indicators: aroma quality, aroma volume, permeability, fineness, miscellaneous smell, irritation, sweetness and aftertaste are 0.25, 0.20, 0.06, 0.09, 0.08, 0.08, 0.12, 0.12 respectively; the weights of color, oil content, fullness, uniformity, brightness and smell are 0.2, 0.2, 0.1, 0.1, 0.1, 0.3 respectively; the weights of polyphenol degradation rate, pigment degradation rate, pH degradation rate and absorbance value are 0.2, 0.2, 0.3, 0.3 respectively. The weights of primary indicators: sensory, appearance and chemical indicators are 0.38, 0.32 and 0.30 respectively.

[0093] Based on work experience, the specific parameters of each evaluation indicator are graded and scored, and are divided into four levels from high to low, including: Level I 10-7.5 points, Level II 7.5-5 points, Level III 5-2.5 points, and Level IV 2.5-0 points.

[0094] Based on the comprehensive discrimination method of influencing factors and the tobacco strip quality evaluation index system, a tobacco strip quality evaluation model is constructed as follows:

[0095]

[0096] Among them, T is the total score, w i is the weight value of the i-th evaluation index, u i is the score of the i-th evaluation index, and n is the number of evaluation indicators.

[0097] Further, the maintenance quality assessment module includes: a maintenance quality analysis unit and a maintenance quality assessment unit;

[0098] A curing quality analysis unit, used to compare the quality evaluation result of the tobacco strip with the initial tobacco strip quality and the last tobacco strip quality evaluation result, respectively, to obtain a first quality difference value and a second quality difference value;

[0099] The curing quality assessment unit is used to determine the curing quality assessment result of the tobacco strips in the storage area according to the first quality difference and the second quality difference.

[0100] To further optimize the technical solution, the maintenance quality assessment module also includes a maintenance defect determination unit, which is used to determine the defects of maintenance measures in the storage area based on the tobacco leaf maintenance quality assessment results and the marked abnormal data.

[0101] In this embodiment, the evaluation parameters of this detection are substituted into the sheet tobacco quality evaluation index system and the sheet tobacco quality evaluation model, and after obtaining the sheet tobacco quality score value of this detection, the sheet tobacco quality score value of this detection is compared with the initial sheet tobacco quality score value and the previous sheet tobacco quality score value to obtain the first quality difference value and the second quality difference value respectively; then the maintenance quality of the sheet tobacco in the storage area is evaluated by combining the first quality difference value and the second quality difference value with the annotated abnormal data. If the first quality difference value is within the first preset range, the second quality difference value is within the second preset range, and there is no annotated abnormal data, the maintenance quality of the sheet tobacco in the storage area is excellent and the maintenance measures are normal; if the first quality difference value is within the first preset range, the second quality difference value is within the second preset range, but there is annotated abnormal data, the maintenance quality of the sheet tobacco in the storage area is good, and the defects in the maintenance measures are analyzed and improved according to the abnormal data; if at least one of the first quality difference value and the second quality difference value is not within the preset range, regardless of whether there is abnormal data, it is determined that the maintenance quality of the sheet tobacco in the storage area is poor, and the maintenance measures need to be readjusted.

[0102] This embodiment evaluates the quality of tobacco leaves by screening evaluation indicators, constructing an evaluation indicator system, and collecting evaluation parameters. Then, by comparing the evaluation results of tobacco leaves quality at different times, the maintenance quality of tobacco leaves in the storage area is evaluated, and it is possible to determine whether there are defects in the maintenance measures in the storage area; and by annotating and analyzing abnormal data in the evaluation parameters, technical problems in the maintenance measures in the storage area can be discovered in a timely manner, which facilitates timely adjustments and better ensures the storage quality of tobacco leaves.

[0103] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent tobacco curing quality assessment system, characterized in that: include: A tobacco strip data collection module, used to collect evaluation parameters of tobacco strip samples to be evaluated in the storage area, wherein the evaluation parameters include sensory parameters, appearance parameters and chemical parameters; a cigarette strip data processing module, used to process the evaluation parameters collected by the cigarette strip data collection module to obtain the processed evaluation parameters; A tobacco strip quality analysis module, used to perform tobacco strip quality analysis based on a preset tobacco strip quality evaluation index system and evaluation parameters processed by the tobacco strip data processing module, and obtain a tobacco strip quality evaluation result; and a curing quality assessment module for comparing the tobacco strip quality assessment result obtained by the tobacco strip quality analysis module with the initial tobacco strip quality and the last tobacco strip quality assessment result, respectively, to obtain the tobacco strip curing quality assessment result in the storage area.

2. The intelligent tobacco leaf curing quality assessment system according to claim 1, characterized in that: The tobacco strip data collection module comprises: A sensory parameter collection unit, used to perform sensory evaluation on the tobacco sample to be evaluated to obtain sensory parameters; An appearance parameter acquisition unit, used to perform an external evaluation on the to-be-evaluated tobacco sample to obtain appearance parameters; And a chemical parameter acquisition unit is used to measure the chemical composition of the tobacco sample to be evaluated and obtain the chemical composition parameters.

3. The intelligent tobacco leaf curing quality assessment system according to claim 1, characterized in that: The cigarette data processing module comprises: An abnormal data processing unit, used to determine the abnormal data in the evaluation parameters and re-detect it to determine whether it is a false detection. If it is a false detection, it is replaced with correct data; if it is not a false detection, the abnormal data is marked; And a cigarette data packaging unit is used to package and store the evaluation parameters and the annotated abnormal data.

4. The intelligent tobacco leaf curing quality assessment system according to claim 1, characterized in that: The tobacco quality analysis module comprises: An evaluation system construction unit, used to determine the tobacco strip quality evaluation index and construct a tobacco strip quality evaluation index system according to the tobacco strip quality evaluation index; and a tobacco sheet quality analysis unit, which is used to calculate the evaluation parameters based on the tobacco sheet quality evaluation index system to obtain a tobacco sheet quality evaluation result.

5. The intelligent tobacco leaf curing quality assessment system according to claim 4, characterized in that: The evaluation system construction unit includes: An evaluation index screening subunit, used to screen sensory evaluation indexes, appearance evaluation indexes, and chemical evaluation indexes respectively; An evaluation index weighting subunit, used to respectively assign weight values ​​to the sensory evaluation index, appearance evaluation index, and chemical evaluation index; An evaluation index grading subunit, used to grade and assign values ​​to the sensory evaluation index, appearance evaluation index, and chemical evaluation index respectively; And an evaluation system construction subunit, which is used to construct the tobacco quality evaluation index system based on the sensory evaluation index, appearance evaluation index, chemical evaluation index and corresponding weight values ​​and graded assignments.

6. The intelligent tobacco leaf curing quality assessment system according to claim 5, characterized in that: The sensory evaluation indicators include aroma quality, aroma quantity, permeability, fineness, miscellaneous smell, irritation, sweetness and aftertaste; the appearance evaluation indicators include color, oil content, fullness, uniformity, brightness and smell; the chemical evaluation indicators include polyphenol degradation rate, pigment degradation rate, pH degradation rate and absorbance value.

7. The intelligent tobacco leaf curing quality assessment system according to claim 4, characterized in that: The tobacco quality analysis unit comprises: An evaluation model building subunit, used to build a tobacco strip quality evaluation model based on a comprehensive discrimination method of influencing factors combined with the tobacco strip quality evaluation index system; and a tobacco strip quality analysis subunit, which is used to substitute the evaluation parameters into the tobacco strip quality evaluation index system and the tobacco strip quality evaluation model to obtain a tobacco strip quality analysis result.

8. An intelligent tobacco leaf curing quality assessment system as claimed in claim 7, characterized in that: The tobacco strip quality evaluation model is: Among them, T is the total score, w i is the weight value of the i-th evaluation index, u i is the score of the i-th evaluation index, and n is the number of evaluation indicators.

9. The intelligent tobacco leaf curing quality assessment system according to claim 1, characterized in that: The maintenance quality assessment module includes: a curing quality analysis unit, for comparing the tobacco strip quality evaluation result with the initial tobacco strip quality and the last tobacco strip quality evaluation result, respectively, to obtain a first quality difference value and a second quality difference value; and a curing quality assessment unit, configured to determine a curing quality assessment result of the tobacco leaves in the storage area according to the first quality difference and the second quality difference.

10. The intelligent tobacco leaf curing quality assessment system according to claim 3, characterized in that: The maintenance quality assessment module also includes a maintenance defect determination unit, which is used to determine the defects of the maintenance measures in the storage area according to the tobacco leaf maintenance quality assessment result and the marked abnormal data.

Images