A tea processing machinery fault early warning system

Abstract

The present invention discloses a tea processing machinery fault warning system, which belongs to the field of smart industrial technology. The fault warning system monitors the process of tea frying and drying, obtains temperature and humidity change data in the tea frying and drying machine at different stages, and after eliminating the influence of the factor of fresh leaf moisture content, judges whether the humidity change of the tea leaves and the temperature change in the drum cavity during the frying and drying process are normal as a whole by comparing the real-time temperature and humidity data in the frying and drying process with historical data. In this way, the abnormal increase or decrease of the humidity in the cavity caused by the local excessive or low temperature during the frying and drying process can be discovered in time, thereby reducing the influence of equipment failure on the quality of the processed tea leaves and reducing losses.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing technology, and specifically relates to a tea processing machinery fault early warning system. Background Art

[0002] Tea is one of the three major beverages in the world. With the development of technology, tea processing has gradually changed from pure manual to mechanical processing. Tea drying machine is a commonly used tea processing equipment. It heats and stir-fries fresh leaves while rotating the drum-type cavity. The temperature during the frying process determines the quality of the frying. Therefore, it is very necessary to monitor the temperature of the frying machine cavity during the tea frying process.

[0003] During the tea frying process of a tea drying machine, the moisture content of fresh leaves varies, and the overall frying time of the frying machine will also vary. In traditional technology, the temperature of the frying drum of the tea drying machine is measured by a temperature sensor, which can only monitor the local drum temperature value. In addition, since the contact surface between the drum and the tea leaves changes during the processing, the temperature monitoring results will also fluctuate greatly. However, the problem of fluctuation in the frying processing quality caused by uneven local heating temperature of the drum, changes in the heat conduction effect of the drum, etc. cannot be discovered in time. In order to solve the above problems, a systematic method is provided for timely identification and discovery of faults of the tea frying machine. The present invention provides the following technical solutions. Summary of the Invention

[0004] The purpose of the present invention is to provide a tea processing machinery fault early warning system to solve the problem in the prior art that fluctuations in the frying processing quality caused by uneven local heating temperature of the drum of the tea drying machine, changes in the heat conduction effect of the drum, etc. cannot be discovered in time, resulting in a decline in the quality of tea frying and drying processing.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A tea processing machinery fault early warning system, comprising:

[0007] Temperature sensor, used to collect the temperature value of the tea drying machine cavity;

[0008] Humidity sensor, used to collect the humidity value of the tea drying machine cavity;

[0009] A controller is used to determine whether the tea drying machine has a fault;

[0010] The method for the controller to determine whether the tea drying machine has a fault includes the following steps:

[0011] S1. After the fresh leaves are put into the tea drying machine, during the drying process, the temperature in the tea drying machine is monitored by a temperature sensor, and the humidity in the tea drying machine is monitored by a humidity sensor;

[0012] S2, obtaining a temperature variation curve Q1 and a humidity variation curve Q2 during the frying and drying process of each batch of tea leaves;

[0013] For a set of corresponding Q1 and Q2, Q1 is divided into n temperature segments according to the time sequence;

[0014] Divide Q2 into n humidity segments according to the time sequence;

[0015] For a temperature segment, k temperature values ​​are obtained with equal time differences within the temperature segment, and these k temperature values ​​are marked as W1, W2, ..., Wk in sequence;

[0016] According to the standard deviation calculation formula, the standard deviation U1 of the data set from W1 to Wk is obtained;

[0017] When U1≤Uy1 holds true, the corresponding temperature segment is considered to be a stable temperature segment, and the average value Wp of the k corresponding values ​​from W1 to Wk is calculated, and Wp is used as the average temperature of the corresponding temperature segment; where Uy1 is a preset value;

[0018] Obtain the stable humidity segment and the Dp and U2 corresponding to the stable humidity segment;

[0019] S3. Obtain the average temperature of each stable temperature segment and the average humidity of each stable humidity segment;

[0020] The average temperature and average humidity of the same time period are taken as a mapping data group, and each mapping data group is marked with a serial number according to the time sequence of each mapping data group in the corresponding batch;

[0021] The mapping data groups whose similarity coefficient α is greater than or equal to the preset value α1 are regarded as a group;

[0022] In a combination, if there are two or more mapping data groups belonging to the same batch, the mapping data group with the larger serial number will be deleted, and only the mapping data group with the smallest serial number in the corresponding batch will be retained;

[0023] Obtain the number b of mapping data groups included in each combination;

[0024] Select the combination with the largest number b of corresponding mapping data groups as the source combination;

[0025] S4, obtaining the source combination corresponding to each tea drying machine;

[0026] For a tea drying machine, the time corresponding to each mapped data group in the source combination is used as the starting time period of each corresponding batch;

[0027] For the production process of the same batch, starting from the starting time period and ending at the end of the frying and drying process, the time periods corresponding to the batch are marked as T1, T2, ..., Tm in sequence; each time period corresponds to a mapping data group;

[0028] Continuously obtain the average temperature and average humidity corresponding to the time period T1 to Tm during the production process of B batches;

[0029] For a time period Tj, calculate the average value gj1, average humidity value gj2 and standard deviation value uj of the corresponding B average temperature values; where 1≤j≤m;

[0030] S5. The first time period in the real-time tea frying process that satisfies α=1-β1*|gs1-g11|+β2*|gs2-g12|≥α1 is used as the T1 period of the current tea frying process; wherein β1 and β2 are preset coefficients and satisfy β1+β2=1;

[0031] Where gs1 is the average value of real-time temperature in the corresponding time period, and gs2 is the average value of real-time humidity in the corresponding time period;

[0032] Obtain the number V of time periods Tj that satisfy the corresponding similarity α<α1 during the entire tea frying and drying process;

[0033] S6. When Vy2>V≥Vy1 is established, it is considered that there is an abnormality in the tea drying process of the corresponding batch;

[0034] For the same tea drying machine, when the number of abnormalities H1 during H tea drying processes satisfies H1 / H ≥ μ, the corresponding tea drying machine is considered to have a fault; μ is a preset proportional coefficient;

[0035] When V≥Vy2 is established, it is considered that the tea drying machine used for the corresponding batch of tea drying processing has a fault; Vy1 and Vy2 are preset values.

[0036] As a further solution of the present invention, when there is only one combination with the largest number b of corresponding mapping data groups, this combination is selected as the source combination;

[0037] When there are two or more combinations with the largest number b of corresponding mapping data groups, the combination with the smallest sum of the corresponding mapping data group serial numbers is selected as the source combination.

[0038] As a further solution of the present invention, the similarity α between two mapping data sets is calculated as follows:

[0039] α=1-β1*e1+β2*e2;

[0040] e1 is the absolute value of the difference between the average temperatures in the two corresponding mapping data sets, and e2 is the absolute value of the difference between the average humidity in the two corresponding mapping data sets.

[0041] As a further embodiment of the present invention, the early warning system further comprises an industrial camera for acquiring image information of the tea leaves being transported after processing, and transmitting the image information to a memory;

[0042] After the tea leaves are fried and dried, the tea leaves in the tea frying and drying machine cavity are removed and transported through a conveyor belt. During the transportation of the tea leaves, the industrial camera is used to obtain image information of the tea leaves being transported.

[0043] Acquire several frame images of the same batch of tea leaves;

[0044] Convert the frame image into a grayscale image, and obtain the proportion γ of pixels in the grayscale image whose grayscale value is less than the preset value G; obtain the average value γ1 of γ corresponding to all frame images corresponding to the same batch of tea;

[0045] When γy2>γ1≥γy1 is established, it is considered that there is an abnormality in the tea drying process of the corresponding batch;

[0046] When γ1≥γy2 holds true, it is considered that the tea drying machine used in the tea drying process of the corresponding batch of tea leaves has a fault;

[0047] Among them, γy1 and γy2 are both preset values.

[0048] As a further solution of the present invention, the abnormal coefficient R of the corresponding batch of tea processing is calculated according to the formula R=σ1*V+σ2*γ1;

[0049] Among them, σ1 and σ2 are preset coefficients;

[0050] When Ry2>R≥Ry1 is established, it is considered that there is an abnormality in the tea drying process of the corresponding batch;

[0051] When R≥Ry2 is established, it is considered that the tea drying machine used in the tea drying process of the corresponding batch of tea leaves is faulty;

[0052] Ry1 and Ry2 are preset values.

[0053] As a further solution of the present invention, the early warning system further includes an alarm for issuing an alarm message to remind staff that the corresponding tea leaf drying machine has a fault.

[0054] Beneficial effects of the present invention:

[0055] 1. The present invention monitors the tea frying and drying process to obtain temperature and humidity change data in the tea frying and drying machine at different stages. After eliminating the influence of the moisture content of fresh leaves, the present invention compares the real-time temperature and humidity data during the frying and drying process with historical data to determine whether the humidity change of the tea leaves and the overall temperature change in the drum cavity during the frying and drying process are normal. In this way, the present invention can promptly detect abnormal increases or decreases in humidity in the cavity caused by local excessive or low temperatures during the frying and drying process, thereby reducing the impact of equipment failures on the quality of the processed tea leaves and reducing losses.

[0056] 2. The present invention determines a unified starting time period for each batch before conducting subsequent processing, and judges the temperature and humidity values ​​of each stage based on the determined unified starting time period, thereby reducing the impact of significant differences in moisture content of fresh leaves before entering the pot, which leads to significant differences in humidity in the chamber during the initial stage of the stir-frying process. This reduces the impact of fresh leaves with different initial humidity on monitoring and judgment results, improves the accuracy of fault judgment, and reduces the false alarm rate.

[0057] 3. The present invention monitors the results of tea frying and drying by introducing machine vision, and promptly detects burnt leaves caused by excessive temperature and low moisture content of tea leaves, further supplements the above-mentioned fault warning method, and improves the overall monitoring accuracy. DETAILED DESCRIPTION

[0058] The following is a clear and complete description of the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0059] A tea processing machinery fault early warning system, comprising:

[0060] Industrial camera: Tea leaves processed by the tea drying machine are transported through a conveyor belt. During the transportation of the tea leaves, the industrial camera captures image information of the tea leaves in transit and transmits the image information to the memory;

[0061] Temperature sensor, used to collect the temperature value of the tea drying machine cavity;

[0062] Humidity sensor, used to collect the humidity value of the tea drying machine cavity;

[0063] Memory, used to store data information collected by industrial cameras, temperature sensors and humidity sensors;

[0064] A controller is used to determine whether the corresponding tea drying machine has a fault;

[0065] The alarm is used to send out an alarm message to remind the staff that the corresponding tea drying machine has a fault.

[0066] The method for the controller to determine whether the corresponding tea drying machine has a fault includes the following steps:

[0067] S1. After fresh leaves are put into a tea drying machine, during the drying process, the temperature in the tea drying machine is monitored by a temperature sensor, and the humidity in the tea drying machine is monitored by a humidity sensor. The temperature information and humidity information collected by the temperature sensor and the humidity sensor are transmitted to a memory for storage;

[0068] S2, obtaining the temperature variation curve Q1 and the humidity variation curve Q2 of each batch of tea leaves during the drying process from the memory;

[0069] For a set of corresponding Q1 and Q2, Q1 is divided into n temperature segments according to the time sequence;

[0070] Divide Q2 into n humidity segments according to the time sequence;

[0071] For a temperature segment, k temperature values ​​are obtained with equal time differences within the temperature segment, and these k temperature values ​​are marked as W1, W2, ..., Wk in sequence;

[0072] The standard deviation U1 of the data set from W1 to Wk is calculated according to the standard deviation calculation formula;

[0073] When U1≤Uy1 holds true, the corresponding temperature segment is considered to be a stable temperature segment, and the average value Wp of the k corresponding values ​​from W1 to Wk is calculated, and Wp is used as the average temperature of the corresponding temperature segment;

[0074] Among them, Uy1 is the preset value;

[0075] For a humidity segment, k humidity values ​​are obtained with equal time differences within the humidity segment, and these k humidity values ​​are marked as D1, D2, ..., Dk in sequence;

[0076] The standard deviation U2 of the data set D1 to Dk is calculated according to the standard deviation calculation formula;

[0077] When U2≤Uy2 holds true, the corresponding humidity segment is considered to be a stable humidity segment, and the average value Dp of the k corresponding values ​​from D1 to Dk is calculated, and Dp is used as the average humidity of the corresponding humidity segment;

[0078] Among them, Uy2 is the preset value;

[0079] S3. Obtain the stable temperature segment and stable humidity segment corresponding to each batch;

[0080] A batch refers to the process of a tea drying machine producing tea at the same time;

[0081] Obtain the average temperature of each stable temperature segment and the average humidity of each stable humidity segment;

[0082] The average temperature and average humidity corresponding to the same time period are taken as a mapping data group, and each mapping data group is marked with a serial number according to the time sequence of each mapping data group in the corresponding batch;

[0083] The mapping data groups whose similarity coefficient α is greater than or equal to the preset value α1 are regarded as a group;

[0084] In a combination, if there are two or more mapping data groups belonging to the same batch, the mapping data group with the larger serial number will be deleted, and only the mapping data group with the smallest serial number in the corresponding batch will be retained;

[0085] Obtain the number b of mapping data groups included in each combination;

[0086] Select the combination with the largest number b of corresponding mapping data groups as the source combination;

[0087] Specifically, in one embodiment of the present invention, when there is only one combination with the largest number b of corresponding mapping data groups, this combination is selected as the source combination;

[0088] When there are two or more combinations with the largest number b of corresponding mapping data groups, the combination with the smallest sum of the corresponding mapping data group numbers is selected as the source combination;

[0089] In one embodiment of the present invention, the similarity α between two mapping data sets is calculated as follows:

[0090] α=1-β1*e1+β2*e2;

[0091] Where β1 and β2 are preset coefficients, and satisfy β1+β2=1;

[0092] e1 is the absolute value of the difference between the average temperatures in the two corresponding mapped data sets, and e2 is the absolute value of the difference between the average humidity in the two corresponding mapped data sets;

[0093] In one embodiment of the present invention, β1 takes a value of 0.6 and β2 takes a value of 0.4;

[0094] S4, obtaining the source combination corresponding to each tea drying machine;

[0095] For a tea drying machine, the time corresponding to each mapped data group in the source combination is used as the starting time period of each corresponding batch;

[0096] For the production process of the same batch, starting from the starting time period and ending at the end of the frying and drying process, the time periods corresponding to the batch are marked as T1, T2, ..., Tm in sequence; each time period corresponds to a mapping data group;

[0097] Continuously obtain the average temperature and average humidity corresponding to the time period T1 to Tm during the production process of B batches;

[0098] For a time period Tj, calculate the average value gj1, average humidity value gj2 and standard deviation value uj of the corresponding B average temperature values;

[0099] Where 1≤j≤m;

[0100] S5. During the real-time tea drying process, the temperature of the tea drying machine cavity is monitored by a temperature sensor, and the humidity of the tea drying machine cavity is monitored by a humidity sensor;

[0101] The first time period in the real-time tea frying and drying process that satisfies α=1-β1*|gs1-g11|+β2*|gs2-g12|≥α1 is taken as the T1 period of this tea frying and drying process;

[0102] Where gs1 is the average value of real-time temperature in the corresponding time period, and gs2 is the average value of real-time humidity in the corresponding time period;

[0103] Obtain the number V of time periods Tj that satisfy the corresponding similarity α<α1 during the entire tea frying and drying process;

[0104] Since there is a significant difference in the moisture content of fresh leaves before they are put into the pot, there will be a significant difference in the humidity in the cavity during the initial stage of the frying and drying process. The present invention determines a unified starting time period for each batch before performing subsequent processing, and judges the temperature and humidity values ​​of each stage based on the determined unified starting time period, thereby reducing the impact of fresh leaves with different starting humidity on the monitoring and judgment results, improving the accuracy of fault judgment, and reducing the false alarm rate.

[0105] S6. After the tea leaves are fried and dried, the tea leaves in the tea frying and drying machine cavity are removed and transported via a conveyor belt. During the tea leaves' transportation, an industrial camera is used to capture image information of the tea leaves being transported.

[0106] Acquire several frame images of the same batch of tea leaves;

[0107] The frame image is analyzed by the controller. Specifically, the frame image is converted into a grayscale image, and the proportion γ of pixels in the grayscale image whose grayscale value is less than a preset value G is obtained;

[0108] Get the average value γ1 of γ corresponding to all frame images of the same batch of tea;

[0109] S7. Calculate the abnormal coefficient R of the corresponding batch of tea processing according to the formula R = σ1*V + σ2*γ1;

[0110] Among them, σ1 and σ2 are preset coefficients;

[0111] When one of the following conditions is met: Ry2>R≥Ry1 or Vy2>V≥Vy1 or γy2>γ1≥γy1, it is considered that there is an abnormality in the tea drying process of the corresponding batch;

[0112] For the same tea drying machine, when the number of abnormalities H1 during the H tea drying processes satisfies H1 / H ≥ μ, the corresponding tea drying machine is considered to have a fault;

[0113] When one of the conditions R≥Ry2 or V≥Vy2 or γ1≥γy2 is satisfied, it is considered that the tea drying machine used in the tea drying process of the corresponding batch of tea leaves has a fault;

[0114] Among them, Ry1, Ry2, Vy1, Vy2, γy1 and γy2 are all preset values;

[0115] μ is a preset proportional coefficient. In one embodiment of the present invention, μ is set to 70%.

[0116] In one embodiment of the present invention, when the controller determines that the corresponding tea leaf drying machine has a fault, the alarm device sends an alarm message to remind the staff that the corresponding tea leaf drying machine has a fault.

[0117] The present invention monitors the process of frying and drying tea leaves, obtains temperature and humidity change data in the tea frying and drying machine at different stages, and after eliminating the influence of the water content of fresh leaves, compares the real-time temperature and humidity data during the frying and drying process with historical data to judge whether the humidity change of the tea leaves during the frying and drying process and the overall temperature change in the drum cavity are normal, so that the abnormal increase or decrease of the humidity in the cavity caused by the local excessive temperature or excessive low temperature during the frying and drying process can be discovered in time, thereby reducing the influence of equipment failure on the quality of the processed tea leaves and reducing losses.

[0118] The present invention also monitors the results of tea frying and drying by introducing machine vision, and promptly detects burnt leaves caused by excessive temperature and low moisture content of tea leaves, further supplements the above-mentioned fault warning method, and improves the overall monitoring accuracy.

[0119] Throughout the specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0120] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in similar ways. As long as they do not deviate from the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

Claims

1. A tea processing machinery fault early warning system, characterized in that: include: Temperature sensor, used to collect the temperature value of the tea drying machine cavity; Humidity sensor, used to collect the humidity value of the tea drying machine cavity; A controller is used to determine whether the tea drying machine has a fault; The method for the controller to determine whether the tea drying machine has a fault includes the following steps: S1. After the fresh leaves are put into the tea drying machine, during the drying process, the temperature in the tea drying machine is monitored by a temperature sensor, and the humidity in the tea drying machine is monitored by a humidity sensor; S2, obtaining a temperature variation curve Q1 and a humidity variation curve Q2 during the frying and drying process of each batch of tea leaves; For a set of corresponding Q1 and Q2, Q1 is divided into n temperature segments according to the time sequence; Divide Q2 into n humidity segments according to the time sequence; For a temperature segment, k temperature values ​​are obtained with equal time differences within the temperature segment, and these k temperature values ​​are marked as W1, W2, ..., Wk in sequence; According to the standard deviation calculation formula, the standard deviation U1 of the data set from W1 to Wk is obtained; When U1≤Uy1 holds true, the corresponding temperature segment is considered to be a stable temperature segment, and the average value Wp of the k corresponding values ​​from W1 to Wk is calculated, and Wp is used as the average temperature of the corresponding temperature segment; where Uy1 is a preset value; Obtain the stable humidity segment and the Dp and U2 corresponding to the stable humidity segment; S3. Obtain the average temperature of each stable temperature segment and the average humidity of each stable humidity segment; The average temperature and average humidity of the same time period are taken as a mapping data group, and each mapping data group is marked with a serial number according to the time sequence of each mapping data group in the corresponding batch; The mapping data groups whose similarity coefficient α is greater than or equal to the preset value α1 are regarded as a group; In a combination, if there are two or more mapping data groups belonging to the same batch, the mapping data group with the larger serial number will be deleted, and only the mapping data group with the smallest serial number in the corresponding batch will be retained; Obtain the number b of mapping data groups included in each combination; Select the combination with the largest number b of corresponding mapping data groups as the source combination; S4, obtaining the source combination corresponding to each tea drying machine; For a tea drying machine, the time corresponding to each mapped data group in the source combination is used as the starting time period of each corresponding batch; For the production process of the same batch, starting from the starting time period and ending at the end of the frying and drying process, the time periods corresponding to the batch are marked as T1, T2, ..., Tm in sequence; each time period corresponds to a mapping data group; Continuously obtain the average temperature and average humidity corresponding to the time period T1 to Tm during the production process of B batches; For a time period Tj, calculate the average value gj1, average humidity value gj2 and standard deviation value uj of the corresponding B average temperature values; where 1≤j≤m; S5. The first time period in the real-time tea frying process that satisfies α=1-β1*|gs1-g11|+β2*|gs2-g12|≥α1 is used as the T1 period of the current tea frying process; wherein β1 and β2 are preset coefficients and satisfy β1+β2=1; Where gs1 is the average value of real-time temperature in the corresponding time period, and gs2 is the average value of real-time humidity in the corresponding time period; Obtain the number V of time periods Tj that satisfy the corresponding similarity α<α1 during the entire tea frying and drying process; S6. When Vy2>V≥Vy1 is established, it is considered that there is an abnormality in the tea drying process of the corresponding batch; For the same tea drying machine, when the number of abnormalities H1 during H tea drying processes satisfies H1 / H ≥ μ, the corresponding tea drying machine is considered to have a fault; μ is a preset proportional coefficient; When V≥Vy2 is established, it is considered that the tea drying machine used for the corresponding batch of tea drying processing has a fault; Vy1 and Vy2 are preset values.

2. A tea processing machinery fault early warning system according to claim 1, characterized in that: When there is only one combination with the largest number b of corresponding mapping data groups, this combination is selected as the source combination; When there are two or more combinations with the largest number b of corresponding mapping data groups, the combination with the smallest sum of the corresponding mapping data group serial numbers is selected as the source combination.

3. A tea processing machinery fault early warning system according to claim 1, characterized in that: The similarity α between two mapping data sets is calculated as: α=1-β1*e1+β2*e2; e1 is the absolute value of the difference between the average temperatures in the two corresponding mapping data sets, and e2 is the absolute value of the difference between the average humidity in the two corresponding mapping data sets.

4. A tea processing machinery fault early warning system according to claim 1, characterized in that: It also includes an industrial camera for acquiring image information of the tea leaves being transported after processing and transmitting the image information to a memory; After the tea leaves are fried and dried, the tea leaves in the tea frying and drying machine cavity are removed and transported through a conveyor belt. During the transportation of the tea leaves, the industrial camera is used to obtain image information of the tea leaves being transported. Acquire several frame images of the same batch of tea leaves; Convert the frame image into a grayscale image, and obtain the proportion γ of pixels in the grayscale image whose grayscale value is less than the preset value G; obtain the average value γ1 of γ corresponding to all frame images corresponding to the same batch of tea; When γy2>γ1≥γy1 is established, it is considered that there is an abnormality in the tea drying process of the corresponding batch; When γ1≥γy2 holds true, it is considered that the tea drying machine used in the tea drying process of the corresponding batch of tea leaves has a fault; Among them, γy1 and γy2 are both preset values.

5. A tea processing machinery fault early warning system according to claim 4, characterized in that: The abnormal coefficient R of the corresponding batch of tea processing is calculated according to the formula R = σ1*V + σ2*γ1; Among them, σ1 and σ2 are preset coefficients; When Ry2>R≥Ry1 is established, it is considered that there is an abnormality in the tea drying process of the corresponding batch; When R≥Ry2 is established, it is considered that the tea drying machine used in the tea drying process of the corresponding batch of tea leaves is faulty; Ry1 and Ry2 are preset values.

6. A tea processing machinery fault early warning system according to claim 1, characterized in that: It also includes an alarm for sending out an alarm message to remind staff that the corresponding tea drying machine has a fault.