Fermentation monitoring method in dark tea processing process

Abstract

The invention relates to the technical field of dark green tea processing, in particular to a fermentation monitoring method in the dark green tea processing process. The method comprises the following steps: acquiring temperature sequences and oxygen contents of different monitoring positions of a fermentation box in a dark tea processing process; determining a corresponding fluctuation index according to the length corresponding to each sub-sequence section of each monitoring position and the fitting error of each data in the sub-sequence section; the temperature anomaly degree is obtained by combining the difference between the fluctuation indexes of the corresponding sub-sequence segments of each monitoring position and other monitoring positions and the temperature difference; integrating the temperature anomaly degree, the temperature change degree, the oxygen content change degree and the relative distance of the corresponding subsequence segments of each monitoring position and other monitoring positions to obtain contribution factors; and updating the temperature of the current moment based on the time interval between all the sub-sequence segments of all the monitoring positions and the current moment and the contribution factor. According to the invention, the accuracy and credibility of the temperature monitoring result in the dark tea processing process are improved.

Description

Technical Field

[0001] The invention relates to the technical field of dark tea processing, and in particular to a fermentation monitoring method during dark tea processing. Background Art

[0002] Temperature is one of the most critical parameters in the fermentation process of dark tea. At present, the industry generally uses temperature sensors to monitor the temperature of the fermentation environment in real time. By installing the temperature sensor inside the fermentation pile or in the fermentation equipment, the temperature data can be accurately collected, and then dynamically adjusted according to the host computer to achieve precise control of the temperature during the tea fermentation process.

[0003] Fermentation is one of the important links in the tea processing process. The fermentation process mainly depends on the action of microorganisms. Different microorganisms have different growth and metabolic activities in different temperature ranges. When regulating the temperature during the fermentation process, the average of the temperature data of the monitoring positions set in the fermentation box at the same time is generally obtained as the overall temperature of the tea leaves in the fermentation box at the current moment. This method can obtain more accurate monitoring results in the early stage of fermentation. However, as the fermentation time increases, the heat dissipation effect is poor in some locations due to the dense stacking of tea leaves. The local temperature is high, which reduces the credibility of the monitoring results of the overall temperature of the tea leaves in the fermentation box in the late stage of black tea fermentation, and reduces the accuracy of temperature control. Summary of the invention

[0004] In order to solve the problem that the existing method has low credibility of the monitoring results when monitoring the fermentation temperature in the late stage of dark tea fermentation, the purpose of the present invention is to provide a fermentation monitoring method during the dark tea processing process. The technical scheme adopted is as follows: The present invention provides a method for monitoring fermentation during dark tea processing, the method comprising the following steps: Obtain the temperature sequence and oxygen content at different monitoring positions in the fermentation box during the dark tea processing; According to the length corresponding to each subsequence segment at each monitoring position of the fermentation box and the fitting error of each data in the subsequence segment, the fluctuation index of each subsequence segment at each monitoring position is determined; the subsequence segment is obtained based on the fluctuation characteristics of the data in the temperature sequence; the temperature anomaly degree of each subsequence segment at each monitoring position is obtained by combining the difference between the fluctuation index and the temperature difference of the corresponding subsequence segments of each monitoring position and other monitoring positions; The contribution factor of each subsequence segment of each monitoring position is obtained by combining the temperature anomaly degree, temperature change degree, oxygen content change degree and relative distance of each monitoring position and the corresponding subsequence segment of other monitoring positions; Update the temperature at the current moment based on the time intervals between all subsequence segments of all monitoring locations and the current moment, and the contribution factors; The method of determining the fluctuation index of each subsequence segment at each monitoring position of the fermentation box according to the length corresponding to each subsequence segment at each monitoring position and the fitting error of each data in the subsequence segment includes: Calculate the average duration of all subsequence segments corresponding to the candidate position; Calculating a first ratio between the average duration and the subsequence segment to be analyzed and an average value of fitting errors of all data of the subsequence segment to be analyzed; Determine the product of the first ratio and the average value of the fitting error as the fluctuation index of the subsequence segment to be analyzed; The candidate position is any monitoring position of the fermentation box, and the subsequence segment to be analyzed is any subsequence segment of the candidate position; The step of combining the difference between the fluctuation index of each monitoring position and the corresponding subsequence segments of other monitoring positions and the temperature difference to obtain the temperature anomaly degree of each subsequence segment of each monitoring position includes: Calculate the first mean value of the fluctuation index of all subsequence segments corresponding to the subsequence segment to be analyzed at all monitoring positions other than the candidate position; According to the difference between the fluctuation index of the subsequence segment to be analyzed at the candidate position and the first mean value, and the overall difference between the temperature in the subsequence segment to be analyzed at the candidate position and the subsequence segments corresponding to all other monitoring positions except the candidate position, the temperature anomaly degree of the subsequence segment to be analyzed is obtained, and the difference degree and the overall difference are both positively correlated with the temperature anomaly degree; The step of comprehensively analyzing the temperature anomaly degree, temperature change degree, oxygen content change degree and relative distance of each monitoring position and the corresponding subsequence segments of other monitoring positions to obtain the contribution factor of each subsequence segment of each monitoring position includes: According to the difference between the temperature anomaly degree of the subsequence segment to be analyzed at the candidate position and the corresponding subsequence segments of other monitoring positions except the candidate position, the difference between the temperature change degrees and the relative distance between the candidate position and other monitoring positions except the candidate position, the similarity degree corresponding to the subsequence segment to be analyzed at the candidate position is obtained; According to the difference between the temperature change degree and the oxygen content change degree corresponding to each data in the subsequence segment to be analyzed at the candidate position, the temperature anomaly degree of the subsequence segment to be analyzed and the similarity degree, the contribution factor of the subsequence segment to be analyzed at the candidate position is obtained, the difference between the temperature change degree and the oxygen content change degree and the temperature anomaly degree are negatively correlated with the contribution factor, and the similarity degree is positively correlated with the contribution factor.

[0005] Preferably, obtaining the subsequence segment includes: Calculate the average value of the temperature data of all monitoring positions of the fermentation box at each collection time in the current time period as the temperature characteristic value at the corresponding collection time; Perform curve fitting on the temperature characteristic values ​​at all acquisition moments in the current time period to obtain the corresponding curve segments; The slope corresponding to each data on the curve segment is obtained, and the temperature sequences of all monitoring positions are divided into a plurality of subsequence segments based on the magnitude relationship between the slope and a preset slope threshold, and there is a one-to-one correspondence between the subsequence segments of different monitoring positions.

[0006] Preferably, the updating of the temperature at the current moment based on the time intervals between all subsequence segments of all monitoring locations and the current moment and the contribution factor comprises: Obtaining the contribution degree of the candidate position according to the contribution factors of all subsequence segments of the candidate position and the time intervals between all subsequence segments and the current moment, wherein the contribution factor is positively correlated with the contribution degree, and the time interval is negatively correlated with the contribution degree; The updated temperature at the current moment is obtained based on the contribution of all positions.

[0007] Preferably, obtaining the degree of temperature change includes: For any two adjacent temperature data in the sequence segment to be analyzed at the candidate position: the absolute value of the difference between the any two adjacent temperature data is used as the temperature change degree corresponding to the latter temperature data of the any two adjacent temperature data.

[0008] Preferably, obtaining the degree of change in oxygen content includes: The oxygen content data at the collection time corresponding to each temperature data in the sequence segment to be analyzed at the candidate position constitutes an oxygen content sequence; For any two adjacent oxygen content data in the oxygen content sequence: the absolute value of the difference between the two adjacent oxygen content data is used as the oxygen content change degree corresponding to the temperature data corresponding to the latter one of the two adjacent oxygen content data.

[0009] Preferably, obtaining the fitting error of each data includes: For any monitoring location: Performing curve fitting on the temperature data of all acquisition moments in the current time period of the monitoring location to obtain the fitted temperature value of each acquisition moment in the current time period of the monitoring location; The absolute value of the difference between each temperature data in each subsequence segment of the monitoring position and the corresponding fitting temperature value is taken as the corresponding fitting error.

[0010] Preferably, obtaining the temperature sequence of different monitoring positions of the fermentation box includes: For any monitoring position of the fermentation box, the temperature data of all monitoring positions at the collection time in the current time period are arranged in chronological order to obtain the temperature sequence of the monitoring position.

[0011] The present invention has at least the following beneficial effects: The present invention first collects the temperature sequence and oxygen content of different monitoring positions of the fermentation box during the processing of dark tea. At the beginning of fermentation of dark tea, less heat is generated and the temperature rises slowly. With the continuous reproduction of microorganisms and the enhancement of metabolic activities, heat begins to accumulate gradually and the temperature rise speed gradually accelerates. When the temperature rises to a certain level, since the growth and metabolism of microorganisms are restricted by factors such as temperature, the available nutrients in the tea leaves gradually decrease and the temperature tends to be stable. In the later stage of fermentation of dark tea, the activity of microorganisms gradually weakens, the heat generated decreases, and the temperature begins to gradually decrease. Therefore, in order to ensure the credibility of subsequent temperature monitoring results, the temperature sequence is divided based on the fluctuation characteristics of the data in the temperature sequence to obtain corresponding multiple subsequence segments. The closer the change characteristics of the temperature data in the same subsequence segment are, the more likely they are to be in the same stage. According to the length corresponding to each subsequence segment at each monitoring position in the fermentation box and the fitting error of each data in the subsequence segment, the fluctuation situation of the subsequence segment at each monitoring position is analyzed. The condition was evaluated and the fluctuation index was obtained. During the fermentation process of tea, microorganisms undergo oxidation reactions to release a certain amount of heat. Since the looseness and heat dissipation capacity of the stacking at each position may be different, the air can circulate relatively freely in the gaps between the tea leaves at the position where the tea leaves are loosely stacked, while the air circulation in the area where the tea leaves are densely stacked is greatly restricted, and the heat is not easy to dissipate, resulting in a higher temperature at this position, resulting in uneven temperature and inconsistent fermentation degree of the tea leaves. Therefore, by analyzing the differences in fluctuation indicators and temperature differences of subsequence segments at different monitoring positions, the temperature anomaly of each subsequence segment at each monitoring position was obtained, and the temperature anomaly, temperature change degree, oxygen content change degree of the corresponding subsequence segments at different monitoring positions and the relative distance of different monitoring positions were combined to determine the contribution factor of each subsequence segment at each monitoring position, thereby obtaining an updated temperature that can better reflect the overall temperature situation of the fermentation box, thereby improving the accuracy and credibility of the temperature monitoring results in the fermentation box. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 A flow chart of a fermentation monitoring method in a dark tea processing process provided by an embodiment of the present invention; Figure 2 This is a structural block diagram of a fermentation monitoring system in a dark tea processing process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the fermentation monitoring method in the dark tea processing process proposed by the present invention is described in detail as follows in conjunction with the accompanying drawings and preferred embodiments.

[0015] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0016] The specific scheme of the fermentation monitoring method during the dark tea processing provided by the present invention is described in detail below with reference to the accompanying drawings.

[0017] Example of fermentation monitoring method during dark tea processing: The specific scenario targeted by this embodiment is: during the fermentation process of tea leaves, due to the influence of the compactness of the stacking, the heat dissipation capacity of different positions of the tea pile is different, so the temperature in the fermentation box will be uneven, affecting the accuracy of temperature control. This embodiment will use the temperature data of different positions of the fermentation box in the current time period and the oxygen content data to determine the current temperature of the black tea processing process.

[0018] This embodiment proposes a fermentation monitoring method during the dark tea processing, such as Figure 1 As shown, the fermentation monitoring method in the dark tea processing process of this embodiment comprises the following steps: Step S1, obtaining the temperature sequence and oxygen content at different monitoring positions of the fermentation box during the dark tea processing.

[0019] Temperature sensors are set at different positions on the surface of the fermentation box to collect temperature data inside the fermentation box during the black tea processing. Each temperature sensor on the surface of the fermentation box is a monitoring position, that is, there are multiple monitoring positions on the surface of the fermentation box. In specific applications, the implementer selects the setting position of the temperature sensor and the total number of temperature sensors on the surface of the fermentation box according to the specific situation. An oxygen sensor is set inside the fermentation box to collect the oxygen content in the fermentation box. All the set temperature sensors are used to collect the temperature data of each monitoring position in the current time period, and the set oxygen sensor is used to collect the oxygen content in the fermentation box. In this embodiment, the data collection frequency is set to once per second, that is, the temperature data of each monitoring position and the oxygen content data in the fermentation box are collected once every two seconds, that is, the temperature data of each monitoring position of the fermentation box at each collection moment in the current time period and the oxygen content data in the fermentation box at each collection moment are collected. It should be noted that the current time period is the time period for processing black tea using the fermentation box. In this embodiment, the current time period is a set of all historical moments whose time interval between the current moment is less than or equal to the preset time length. In this embodiment, the preset duration is 30 minutes. In specific applications, the implementer can set it according to the specific situation.

[0020] For any monitoring position of the fermentation box, the temperature data of the monitoring position at all acquisition moments in the current time period are arranged in chronological order to obtain the temperature sequence of the monitoring position. Using this method, the temperature sequence of each monitoring position of the fermentation box can be obtained, and one monitoring position corresponds to one temperature sequence.

[0021] So far, the temperature sequence of each monitoring position in the fermentation box during the black tea processing and the oxygen content in the fermentation box at each sampling moment have been obtained.

[0022] Step S2, determining the fluctuation index of each subsequence segment at each monitoring position of the fermentation box according to the length corresponding to each subsequence segment and the fitting error of each data in the subsequence segment; the subsequence segments are obtained based on the fluctuation characteristics of the data in the temperature sequence; combining the difference between the fluctuation index and the temperature difference of the corresponding subsequence segments of each monitoring position and other monitoring positions, to obtain the degree of temperature abnormality of each subsequence segment at each monitoring position.

[0023] The fermentation box is in the shape of a drum. When the tea leaves are fermented inside the drum, the fermentation process of dark tea is a complex biochemical reaction process involving the metabolism of microorganisms, enzymatic reactions, and physical and chemical reactions. Turning the drum all the time may interfere with the normal progress of these biochemical processes, so the drum is not always in a rotating state, but is rotated regularly according to the fermentation state. At the beginning of the fermentation of dark tea, since the microorganisms have just begun to move, the heat generated is less and the temperature rises slowly. At this time, the moisture and nutrients in the tea provide conditions for the growth of microorganisms, and the microorganisms begin to multiply gradually. With the continuous reproduction of microorganisms and the enhancement of metabolic activities, heat begins to accumulate gradually, and the temperature rises gradually. When the temperature rises to a certain level, the growth and metabolism of microorganisms are restricted by factors such as temperature, and the available nutrients in the tea gradually decrease, and the temperature will tend to stabilize. In the late fermentation of dark tea, as the fermentation proceeds, the activity of microorganisms gradually weakens and the heat generated decreases. At the same time, the moisture in the tea leaves also gradually decreases, and the heat dissipation speed increases, causing the temperature to gradually decrease.

[0024] For any monitoring position: the least square method is used to perform curve fitting on the temperature data of all acquisition moments in the current time period of the monitoring position to obtain a temperature fitting curve, the horizontal axis of the curve is the acquisition time, and the vertical axis is the temperature value; the temperature value of each acquisition moment on the fitting curve is used as the fitting temperature value of the corresponding acquisition moment, that is, the fitting temperature value of each acquisition moment of the monitoring position in the current time period is obtained. Since each temperature data in each subsequence segment of the monitoring position corresponds to a collection moment, each temperature data in each subsequence segment corresponds to a fitting temperature value. Curve fitting is a prior art and will not be described in detail here. The absolute value of the difference between each temperature data in each subsequence segment of the monitoring position and its corresponding fitting temperature value is used as the corresponding fitting error, that is, each temperature data in each subsequence segment of the monitoring position corresponds to a fitting error.

[0025] Calculate the average values ​​of the temperature data of all monitoring positions of the fermentation box at each collection moment in the current time period as the temperature characteristic value of the corresponding collection moment, that is, each collection moment in the current time period corresponds to a temperature characteristic value; perform curve fitting on the temperature characteristic values ​​of all collection moments in the current time period to obtain the corresponding curve segment, the horizontal coordinate of the curve segment is the collection moment, and the vertical coordinate is the temperature characteristic value; obtain the slope corresponding to each data on the curve segment, the slope can reflect the change of the temperature data, and therefore, next divide the temperature sequence of all monitoring positions into several subsequence segments based on the relationship between the slope and the preset slope threshold, and there is a one-to-one correspondence between the subsequence segments of different monitoring positions. Specifically, a preset first slope threshold and a preset second slope threshold are set, wherein the preset first slope threshold is less than the preset second slope threshold, and for any monitoring position: the temperature data at the collection time corresponding to the temperature characteristic value at the continuous collection time when the slope is greater than or equal to the preset second slope threshold is taken as data in a subsequence segment; the temperature data at the collection time corresponding to the temperature characteristic value at the continuous collection time when the slope is greater than or equal to the preset first slope threshold and less than the preset second slope threshold is taken as data in a subsequence segment; the temperature data at the collection time corresponding to the temperature characteristic value at the continuous collection time when the slope is less than the preset first slope threshold is taken as data in a subsequence segment. By adopting the above method, the temperature sequence of each monitoring position can be divided into multiple subsequence segments, and there is a one-to-one correspondence between the subsequence segments of different monitoring positions, that is, the collection time contained in the first subsequence segment of all monitoring positions is the same, the length of the first subsequence segment of all monitoring positions is the same, the collection time contained in the second subsequence segment of all monitoring positions is the same, the length of the second subsequence segment of all monitoring positions is the same, and so on. In this embodiment, the first slope threshold is preset to be -0.2, and the second slope threshold is preset to be 0.2. In specific applications, the implementer may set them according to specific circumstances.

[0026] Next, this embodiment is described by taking one of the monitoring positions on the surface of the fermentation box as an example. The method provided in this embodiment can be used to process other monitoring positions on the surface of the fermentation box.

[0027] Specifically, any monitoring position of the fermentation box is recorded as a candidate position, and any subsequence segment of the candidate position is recorded as a subsequence segment to be analyzed. According to the duration corresponding to each subsequence segment of the candidate position, the average duration corresponding to all subsequence segments of the candidate position is calculated; it should be noted that: all subsequence segments of the candidate position correspond to an average duration. For any subsequence segment, the method for obtaining the duration corresponding to the subsequence segment is: the difference between the collection time corresponding to the last data in the subsequence segment and the collection time corresponding to the first data is taken as the duration corresponding to the subsequence segment. Calculate the first ratio between the average duration and the subsequence segment to be analyzed and the average value of the fitting errors of all data of the subsequence segment to be analyzed; determine the product of the first ratio and the average value of the fitting errors as the fluctuation index of the subsequence segment to be analyzed.

[0028] In this embodiment, a specific calculation formula for the fluctuation index is given. The specific calculation formula for the fluctuation index of the i-th subsequence segment at the x-th monitoring position is: in, represents the volatility index of the ith subsequence segment at the xth monitoring position, Indicates the duration corresponding to the ith subsequence segment at the xth monitoring position, represents the average duration of all subsequence segments corresponding to the x-th monitoring position, Indicates the number of temperature data in the ith subsequence segment of the xth monitoring position, Represents the fitting error of the wth temperature data in the ith subsequence segment of the xth monitoring position.

[0029] represents the first ratio, It represents the average value of the fitting errors of all data in the ith subsequence segment of x monitoring positions. The larger the fitting error of the wth temperature data in the ith subsequence segment of the xth monitoring position, the greater the deviation of the wth temperature data from the overall trend of the subsequence segment, and the greater the corresponding temperature fluctuation index.

[0030] During the fermentation process of tea leaves, microorganisms will undergo oxidation reactions and release a certain amount of heat. Since the looseness of the stacking at each location is different, the heat dissipation capacity is also different. In the location where the tea leaves are loosely stacked, the air can circulate relatively freely in the gaps between the tea leaves, making it easier for the heat to dissipate, because the flow of air will take away some of the heat, while the air circulation in the area where the tea leaves are densely stacked is greatly restricted. In this case, the heat is not easy to dissipate and will gradually accumulate locally, causing the temperature at that location to be often higher, resulting in uneven temperature in the pile and inconsistent fermentation of the tea leaves. Therefore, next, the temperature anomaly degree of each subsequence segment of each monitoring location will be obtained based on the difference in fluctuation indicators and temperature difference between the corresponding subsequence segments of each monitoring location and other monitoring locations.

[0031] Specifically, a first mean value of the fluctuation index of all subsequence segments corresponding to the subsequence segment to be analyzed at all monitoring positions except the candidate position is calculated; the temperature anomaly degree of the subsequence segment to be analyzed is obtained according to the degree of difference between the fluctuation index of the subsequence segment to be analyzed at the candidate position and the first mean value, and the overall difference in temperature between the subsequence segment to be analyzed at the candidate position and the subsequence segments corresponding to all monitoring positions except the candidate position, and the degree of difference and the overall difference are both positively correlated with the temperature anomaly degree.

[0032] Among them, the positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by practical applications.

[0033] In this embodiment, a specific calculation formula for the temperature anomaly degree is given, and the temperature anomaly degree of the i-th subsequence segment at the x-th monitoring position can be expressed as: in, represents the temperature anomaly degree of the ith subsequence segment at the xth monitoring position, represents the volatility index of the ith subsequence segment at the xth monitoring position, represents the average value of the fluctuation index of the ith subsequence segment of all monitoring positions on the fermentation box except the xth monitoring position, represents the number of temperature data in the ith subsequence segment of the xth monitoring position, m represents the number of monitoring positions on the fermentation box, represents the wth temperature data of the ith subsequence segment at the xth monitoring position, represents the wth temperature data of the ith subsequence segment of the kth monitoring position on the fermentation box except the xth monitoring position, norm() represents the normalization function, Indicates the absolute value sign.

[0034] represents the first mean, It is used to characterize the difference between the fluctuation index of the ith subsequence segment of the xth monitoring position and the average value of the fluctuation index of the ith subsequence segments of all other monitoring positions except the xth monitoring position. The larger the value, the greater the difference between the two, that is, the greater the degree of deviation of the fluctuation degree of the ith subsequence segment of the xth monitoring position from the overall value, and the greater the temperature anomaly of the ith subsequence segment of the xth monitoring position; It is used to characterize the overall difference in temperature between the ith subsequence segment of the xth monitoring position and the ith subsequence segments of all other monitoring positions except the xth monitoring position. The larger the value, the greater the difference between the temperature data and the greater the degree of temperature anomaly in the ith subsequence segment of the xth monitoring position.

[0035] Thus, the method provided in this embodiment can be used to obtain the temperature abnormality degree of each subsequence segment at each monitoring position on the fermentation box.

[0036] Step S3, comprehensively analyzing the temperature anomaly degree, temperature change degree, oxygen content change degree and relative distance of the corresponding subsequence segments of each monitoring position and other monitoring positions to obtain the contribution factor of each subsequence segment of each monitoring position.

[0037] Since the closer the temperature fluctuation degree of each monitoring position is to the monitoring position that is closer to it, the greater the similarity between the monitoring position and other positions. This embodiment will combine the difference between the temperature anomaly degree of the subsequence segments of different monitoring positions and the relative distance between different monitoring positions to evaluate the similarity between each subsequence segment of each monitoring position and the subsequence segments corresponding to other monitoring positions, and then judge the contribution factor of each subsequence segment of each monitoring position based on the difference between the temperature change degree and the oxygen content change degree corresponding to each data in each subsequence segment of each monitoring position and the corresponding temperature anomaly degree.

[0038] Next, this embodiment is still described by taking the subsequence segment to be analyzed at the candidate position as an example. The method provided in this embodiment can be used to process other subsequence segments of the candidate position or all subsequence segments of other monitoring positions.

[0039] Specifically, the degree of similarity corresponding to the subsequence segment to be analyzed at the candidate position is obtained based on the difference between the degree of temperature anomaly of the subsequence segment to be analyzed at the candidate position and the corresponding subsequence segments at other monitoring positions except the candidate position, as well as the difference between the degree of temperature change and the relative distance between the candidate position and other monitoring positions except the candidate position.

[0040] In this embodiment, a specific calculation formula for the similarity degree is given, and the similarity degree corresponding to the i-th subsequence segment at the x-th monitoring position can be expressed as: in, represents the similarity of the ith subsequence segment at the xth monitoring position, m represents the number of monitoring positions on the fermentation box, represents the temperature anomaly degree of the ith subsequence segment at the xth monitoring position, Indicates the temperature anomaly degree of the ith subsequence segment of the yth monitoring position except the xth monitoring position, Indicates the degree of temperature change of the ith subsequence segment at the xth monitoring position, represents the temperature change degree of the ith subsequence segment at the yth monitoring position except the xth monitoring position, exp( ) represents the exponential function with the natural constant as the base, norm( ) represents the normalization function, Indicates the relative distance between the x-th monitoring position and the y-th monitoring position excluding the x-th monitoring position, Indicates the absolute value sign.

[0041] It indicates the difference in the degree of temperature anomaly between the x-th monitoring position and the ith subsequence segment of the y-th monitoring position excluding the x-th monitoring position. The larger the value, the greater the difference in the degree of temperature difference between the two subsequence segments. The greater the difference in the degree of temperature change between the i-th subsequence segment of the x-th monitoring position and the y-th monitoring position excluding the x-th monitoring position, the larger the value, indicating that the greater the difference in the degree of temperature difference between the two subsequence segments; the closer the distance between the x-th monitoring position and the y-th monitoring position, the higher the similarity between the x-th monitoring position and the y-th monitoring position. The closer the value of is to 1, the more similar the monitoring data of the x-th monitoring position is to the i-th subsequence segment of other monitoring positions. The smaller it is, the greater the similarity corresponding to the i-th subsequence segment of the x-th monitoring position.

[0042] The faster the temperature of the tea pile increases, the more intense the metabolic activity of the microorganisms will be, and the faster the oxygen in the fermentation box will be consumed.

[0043] Next, based on the difference between the temperature change degree and the oxygen content change degree corresponding to each data in the subsequence segment to be analyzed at the candidate position, the temperature anomaly degree of the subsequence segment to be analyzed and the similarity degree, the contribution factor of the subsequence segment to be analyzed at the candidate position is obtained, the difference between the temperature change degree and the oxygen content change degree and the difference between the temperature change degree and the oxygen content change degree are both negatively correlated with the contribution factor, and the similarity degree is positively correlated with the contribution factor.

[0044] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by actual application; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtractive relationship, a division relationship, etc., which is determined by actual application.

[0045] In this embodiment, a specific calculation formula of the contribution factor is given, and the contribution factor of the i-th subsequence segment at the x-th monitoring position can be expressed as: in, represents the contribution factor of the ith subsequence segment at the xth monitoring position, Indicates the similarity of the ith subsequence segment at the xth monitoring position. Indicates the number of temperature data in the ith subsequence segment of the xth monitoring position, Indicates the degree of temperature change corresponding to the wth temperature data in the ith subsequence segment of the xth monitoring position, Indicates the degree of change in oxygen content of the wth temperature data in the ith subsequence segment of the xth monitoring position, Indicates the preset first adjustment parameter.

[0046] The specific process of obtaining the degree of temperature change is as follows: for any two adjacent temperature data in the sequence segment to be analyzed at the candidate position: the absolute value of the difference between the two adjacent temperature data is used as the degree of temperature change of the latter temperature data in the two adjacent temperature data. It should be noted that: since the first temperature data in the sequence segment to be analyzed at the candidate position is the first temperature data of the sequence segment, there is no temperature data before it, so in this embodiment, the degree of temperature change corresponding to the first temperature data in the sequence segment to be analyzed at the candidate position is set to 0.

[0047] The specific process of obtaining the degree of oxygen content change is as follows: the oxygen content data at the collection time corresponding to each temperature data in the sequence segment to be analyzed at the candidate position constitutes an oxygen content sequence; for any two adjacent oxygen content data in the oxygen content sequence: the absolute value of the difference between the two adjacent oxygen content data is used as the degree of oxygen content change corresponding to the temperature data corresponding to the latter oxygen content data in the two adjacent oxygen content data. It should be noted that: since the first oxygen content data in the oxygen content sequence is the first oxygen content data, there is no oxygen content data before it, so in this embodiment, the degree of oxygen content change corresponding to the first temperature data in the sequence segment to be analyzed at the candidate position is set to 0.

[0048] The purpose of introducing a preset first adjustment parameter into the calculation formula of the similarity degree in this embodiment is to prevent the denominator from being 0. The preset first adjustment parameter in this embodiment is 0.01. In specific applications, the implementer may set it according to specific circumstances.

[0049] The greater the similarity corresponding to the ith subsequence segment of the xth monitoring position, the less the actual temperature change at the xth monitoring position is affected by the tea packing density, and the greater the contribution factor of the ith subsequence segment of the xth monitoring position; the smaller the similarity corresponding to the ith subsequence segment of the xth monitoring position, the less similar the temperature fluctuation between the xth monitoring position and all other monitoring positions is. At this time, the temperature anomaly at the xth monitoring position is more likely to be caused by tea packing, and the less it can reflect the actual fermentation temperature of tea, and the smaller the contribution factor.

[0050] By adopting the above method provided in this embodiment, the contribution factor of each subsequence segment of each monitoring position can be obtained.

[0051] Step S4: updating the temperature at the current moment based on the time interval between each subsequence segment of each monitoring position and the current moment, and the contribution factor.

[0052] In step S3, the contribution factor of each subsequence segment of each monitoring position is obtained. The larger the contribution factor, the higher the temperature accuracy of the corresponding position. The temperature data of the position at the current moment should be given a larger weight to ensure the accuracy of temperature control, rather than relying solely on the temperature data of a specific monitoring position.

[0053] Therefore, the contribution degree of the candidate position is obtained according to the contribution factors of all subsequence segments of the candidate position and the time intervals between all subsequence segments and the current moment. The contribution factor is positively correlated with the contribution degree, and the time interval is negatively correlated with the contribution degree.

[0054] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by actual application; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtractive relationship, a division relationship, etc., which is determined by actual application.

[0055] In this embodiment, a specific calculation formula for the contribution degree is given, and the contribution degree of the x-th monitoring position can be expressed as: in, Indicates the contribution of the x-th monitoring position, Indicates the number of temperature data in the ith subsequence segment of the xth monitoring position, Indicates the time interval between the ith subsequence segment at the xth monitoring position and the current moment, Represents the contribution factor of the i-th subsequence segment at the x-th monitoring position.

[0056] For any subsequence segment: the process of obtaining the time interval between the subsequence segment and the current moment is: taking the time difference between the current moment and the acquisition moment corresponding to the last data in the subsequence segment as the time interval between the subsequence segment and the current moment.

[0057] The shorter the time interval between the ith subsequence segment of the xth monitoring position and the current moment, the greater the reference significance of the ith subsequence segment of the xth monitoring position and the greater the weight; the greater the contribution factor of the ith subsequence segment of the xth monitoring position, the more important the ith subsequence segment of the xth monitoring position. Therefore, when the time interval between the subsequence segment of the xth monitoring position and the current moment is shorter and the contribution factor of the subsequence segment of the xth monitoring position is greater, the contribution degree of the xth monitoring position is greater.

[0058] Next, the temperature at the current moment will be updated based on the contribution of all monitoring positions on the surface of the fermentation box and the time interval between each subsequence segment of the monitoring position and the current moment.

[0059] The updated temperature at the current moment can be expressed as: in, Indicates the updated temperature at the current moment, represents the temperature data of the xth monitoring position at the current moment, m represents the number of monitoring positions on the fermentation box, Indicates the contribution of the x-th monitoring position, It is the sum of the contribution levels of all monitoring positions of the fermentation box at the current moment.

[0060] At this point, the updated temperature at the current moment is obtained by the method provided in this embodiment, and is updated. Weighting is used to reduce the temperature fluctuations at individual monitoring locations caused by the stacking density of tea leaves, as well as to reduce the impact of measurement errors or equipment failures that may occur at a single monitoring location, thereby obtaining a smoother, more representative updated temperature of the overall temperature state, thereby improving the accuracy of the overall data and ensuring the accuracy of the temperature monitoring results.

[0061] This embodiment first collects the temperature sequence and oxygen content of different monitoring positions of the fermentation box during the dark tea processing. At the beginning of the fermentation of dark tea, less heat is generated and the temperature rises slowly. With the continuous reproduction of microorganisms and the enhancement of metabolic activities, heat begins to accumulate gradually and the temperature rise rate gradually accelerates. When the temperature rises to a certain level, since the growth and metabolism of microorganisms are restricted by factors such as temperature, the available nutrients in the tea leaves gradually decrease and the temperature tends to be stable. In the later stage of the fermentation of dark tea, the activity of microorganisms gradually weakens, the heat generated decreases, and the temperature begins to gradually decrease. Therefore, in order to ensure the credibility of the subsequent temperature monitoring results, the temperature sequence is divided based on the fluctuation characteristics of the data in the temperature sequence to obtain corresponding multiple subsequence segments. The closer the change characteristics of the temperature data in the same subsequence segment are, the more likely they are in the same stage. According to the length corresponding to each subsequence segment at each monitoring position of the fermentation box and the fitting error of each data in the subsequence segment, the fluctuation of the subsequence segment at each monitoring position is calculated. The situation was evaluated and the fluctuation index was obtained. During the fermentation process of tea, microorganisms undergo oxidation reactions to release a certain amount of heat. Since the looseness and heat dissipation capacity of the stacking at each position may be different, the air can circulate relatively freely among the tea leaves at the position where the tea leaves are loosely stacked, while the air circulation in the area where the tea leaves are densely stacked is greatly restricted, and the heat is not easy to dissipate, resulting in higher temperatures at this position, uneven temperature, and inconsistent fermentation degree of the tea leaves. Therefore, by analyzing the differences in fluctuation indicators and temperature differences of subsequence segments at different monitoring positions, the temperature anomaly of each subsequence segment at each monitoring position was obtained, and the temperature anomaly, temperature change degree, oxygen content change degree of the corresponding subsequence segments at different monitoring positions and the relative distance of different monitoring positions were combined to determine the contribution factor of each subsequence segment at each monitoring position, thereby obtaining an updated temperature that can better reflect the overall temperature situation of the fermentation box, thereby improving the accuracy and credibility of the temperature monitoring results in the fermentation box.

[0062] Implementation example of manufacturing data traceability analysis system for digital transfer printing paper: See also Figure 2, which shows a structural block diagram of a fermentation monitoring system in a dark tea processing process provided by an embodiment of the present invention. The system may include a data acquisition module, a temperature anomaly degree calculation module, a contribution factor determination module and a temperature update module.

[0063] Among them, the data acquisition module is used to obtain the temperature sequence and oxygen content of different monitoring positions in the fermentation box during the black tea processing; The temperature anomaly degree calculation module is used to determine the fluctuation index of each subsequence segment at each monitoring position of the fermentation box according to the length corresponding to each subsequence segment at each monitoring position of the fermentation box and the fitting error of each data in the subsequence segment; the subsequence segment is obtained based on the fluctuation characteristics of the data in the temperature sequence; the temperature anomaly degree of each subsequence segment at each monitoring position is obtained by combining the difference between the fluctuation index and the temperature difference of the corresponding subsequence segments at each monitoring position and other monitoring positions; A contribution factor determination module is used to obtain the contribution factor of each subsequence segment of each monitoring position by comprehensively analyzing the temperature anomaly degree, temperature change degree, oxygen content change degree and relative distance of each monitoring position and the corresponding subsequence segments of other monitoring positions; The temperature updating module is used to update the temperature at the current moment based on the time intervals between all subsequence segments of all monitoring positions and the current moment, and the contribution factor.

[0064] It should be understood that Figure 2 The structural block diagram of the fermentation monitoring system in the dark tea processing process shown and its modules can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software or a combination of software and hardware. Among them, the hardware part can be implemented by using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated hardware design. It can be understood by those skilled in the art that the above-mentioned method and system can be implemented using computer executable instructions and / or contained in a processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the system and its modules of this specification. Not only can the hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc. be implemented, it can also be implemented by software executed by various types of processors, and it can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0065] For more details about the above modules, please refer to other places in this manual and will not be repeated here.

[0066] In other embodiments, a fermentation monitoring device for a dark tea processing process is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the fermentation monitoring method for the dark tea processing process. The device can be a chip, a component or a module, and the chip can include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the fermentation monitoring method for the dark tea processing process provided in the above embodiment.

[0067] In other embodiments, a computer program product is also provided. When the computer program product is run on a computer, the computer is enabled to execute the above-mentioned related steps to implement the fermentation monitoring method in the dark tea processing process provided in the above-mentioned embodiment.

[0068] In other embodiments, a computer-readable storage medium is also provided, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement the fermentation monitoring method in the black tea processing process provided in the above embodiment.

[0069] Among them, the provided system, electronic device, computer program product, and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0070] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A fermentation monitoring method during dark tea processing, characterized in that: The method comprises the following steps: Obtain the temperature sequence and oxygen content at different monitoring positions in the fermentation box during the dark tea processing; According to the length corresponding to each subsequence segment at each monitoring position of the fermentation box and the fitting error of each data in the subsequence segment, the fluctuation index of each subsequence segment at each monitoring position is determined; the subsequence segment is obtained based on the fluctuation characteristics of the data in the temperature sequence; the temperature anomaly degree of each subsequence segment at each monitoring position is obtained by combining the difference between the fluctuation index and the temperature difference of the corresponding subsequence segments of each monitoring position and other monitoring positions; The contribution factor of each subsequence segment of each monitoring position is obtained by combining the temperature anomaly degree, temperature change degree, oxygen content change degree and relative distance of each monitoring position and the corresponding subsequence segment of other monitoring positions; Update the temperature at the current moment based on the time intervals between all subsequence segments of all monitoring locations and the current moment, and the contribution factors; The method of determining the fluctuation index of each subsequence segment at each monitoring position of the fermentation box according to the length corresponding to each subsequence segment at each monitoring position and the fitting error of each data in the subsequence segment includes: Calculate the average duration of all subsequence segments corresponding to the candidate position; Calculating a first ratio between the average duration and the subsequence segment to be analyzed and an average value of fitting errors of all data of the subsequence segment to be analyzed; Determine the product of the first ratio and the average value of the fitting error as the fluctuation index of the subsequence segment to be analyzed; The candidate position is any monitoring position of the fermentation box, and the subsequence segment to be analyzed is any subsequence segment of the candidate position; The step of combining the difference between the fluctuation index of each monitoring position and the corresponding subsequence segments of other monitoring positions and the temperature difference to obtain the temperature anomaly degree of each subsequence segment of each monitoring position includes: Calculate the first mean value of the fluctuation index of all subsequence segments corresponding to the subsequence segment to be analyzed at all monitoring positions other than the candidate position; According to the difference between the fluctuation index of the subsequence segment to be analyzed at the candidate position and the first mean value, and the overall difference between the temperature in the subsequence segment to be analyzed at the candidate position and the subsequence segments corresponding to all other monitoring positions except the candidate position, the temperature anomaly degree of the subsequence segment to be analyzed is obtained, and the difference degree and the overall difference are both positively correlated with the temperature anomaly degree; The step of comprehensively analyzing the temperature anomaly degree, temperature change degree, oxygen content change degree and relative distance of each monitoring position and the corresponding subsequence segments of other monitoring positions to obtain the contribution factor of each subsequence segment of each monitoring position includes: According to the difference between the temperature anomaly degree of the subsequence segment to be analyzed at the candidate position and the corresponding subsequence segments of other monitoring positions except the candidate position, the difference between the temperature change degrees and the relative distance between the candidate position and other monitoring positions except the candidate position, the similarity degree corresponding to the subsequence segment to be analyzed at the candidate position is obtained; According to the difference between the temperature change degree and the oxygen content change degree corresponding to each data in the subsequence segment to be analyzed at the candidate position, the temperature anomaly degree of the subsequence segment to be analyzed and the similarity degree, the contribution factor of the subsequence segment to be analyzed at the candidate position is obtained, the difference between the temperature change degree and the oxygen content change degree and the temperature anomaly degree are negatively correlated with the contribution factor, and the similarity degree is positively correlated with the contribution factor.

2. The fermentation monitoring method in the dark tea processing process according to claim 1, characterized in that: The acquisition of subsequence segments includes: Calculate the average value of the temperature data of all monitoring positions of the fermentation box at each collection time in the current time period as the temperature characteristic value at the corresponding collection time; Perform curve fitting on the temperature characteristic values ​​at all acquisition moments in the current time period to obtain the corresponding curve segments; The slope corresponding to each data on the curve segment is obtained, and the temperature sequences of all monitoring positions are divided into a plurality of subsequence segments based on the magnitude relationship between the slope and a preset slope threshold, and there is a one-to-one correspondence between the subsequence segments of different monitoring positions.

3. The fermentation monitoring method in the dark tea processing process according to claim 1, characterized in that: The updating of the temperature at the current moment based on the time intervals between all subsequence segments of all monitoring locations and the current moment and the contribution factor comprises: Obtaining the contribution degree of the candidate position according to the contribution factors of all subsequence segments of the candidate position and the time intervals between all subsequence segments and the current moment, wherein the contribution factor is positively correlated with the contribution degree, and the time interval is negatively correlated with the contribution degree; The updated temperature at the current moment is obtained based on the contribution of all positions.

4. The fermentation monitoring method during dark tea processing according to claim 1, characterized in that: Acquisition of temperature change degree, including: For any two adjacent temperature data in the sequence segment to be analyzed at the candidate position: the absolute value of the difference between the any two adjacent temperature data is used as the temperature change degree corresponding to the latter temperature data of the any two adjacent temperature data.

5. The fermentation monitoring method in the dark tea processing process according to claim 1, characterized in that: Obtaining the degree of oxygen content change, including: The oxygen content data at the collection time corresponding to each temperature data in the sequence segment to be analyzed at the candidate position constitutes an oxygen content sequence; For any two adjacent oxygen content data in the oxygen content sequence: the absolute value of the difference between the two adjacent oxygen content data is used as the oxygen content change degree corresponding to the temperature data corresponding to the latter one of the two adjacent oxygen content data.

6. The fermentation monitoring method in the dark tea processing process according to claim 1, characterized in that: The fitting error of each data is obtained, including: For any monitoring location: Performing curve fitting on the temperature data of all acquisition moments in the current time period of the monitoring location to obtain the fitted temperature value of each acquisition moment in the current time period of the monitoring location; The absolute value of the difference between each temperature data in each subsequence segment of the monitoring position and the corresponding fitting temperature value is taken as the corresponding fitting error.

7. The fermentation monitoring method in the dark tea processing process according to claim 1, characterized in that: Acquisition of temperature series at different monitoring positions in the fermentation box, including: For any monitoring position of the fermentation box, the temperature data of all monitoring positions at the collection time in the current time period are arranged in chronological order to obtain the temperature sequence of the monitoring position.

Images