Process for the manufacture of a chicory composite preparation

Abstract

The present application relates to the technical field of production process monitoring, and particularly relates to a manufacturing process of a chicory composite preparation, which comprises a data acquisition module, which is used to acquire pH data to be analyzed, a characteristic temperature window, a characteristic pH window, a reference temperature window and a reference pH window corresponding to a tth monitoring moment in the production and manufacturing process of the chicory composite preparation; a drift anomaly identification and correction module, which is used to identify and correct the drift anomaly of the pH data to be analyzed corresponding to the tth monitoring moment, so as to obtain target pH data corresponding to the tth monitoring moment; and a pH monitoring and adjustment module, which is used to monitor and adjust the pH in the production and manufacturing container of the chicory composite preparation at the tth monitoring moment according to the target pH data corresponding to the tth monitoring moment. According to the present application, the pH in the production and manufacturing container of the chicory composite preparation at the tth monitoring moment is monitored and adjusted according to the corrected pH data, so that the adjustment effect can be improved or guaranteed.

Description

Technical Field

[0001] This invention relates to the field of production process monitoring technology, specifically to a manufacturing process for a chicory compound preparation. Background Technology

[0002] Chicory compound preparations are compound products made by mixing chicory as the main raw material with other plant extracts or functional ingredients. Since many functional components in chicory are greatly affected by pH, changes in pH during the manufacturing process can not only affect the flavor of the preparation, but may also lead to changes in the structure of some components, thus affecting the quality of the product. Therefore, it is crucial to monitor and adjust the pH value in real time during the mixing process of raw materials in the manufacturing process of chicory compound preparations.

[0003] Existing methods for pH monitoring and adjustment in the production of chicory compound preparations typically involve directly adjusting the pH based on real-time monitoring. This usually involves using pH sensors to monitor the pH in real time and comparing the monitored value with a preset pH range. When the monitored pH exceeds the preset range, adjustments are typically made by adding acid or alkali to maintain the pH within a reasonable range. However, during the production process, chicory juice may contain impurities such as deposited compounds, plant fibers, and colloid residues. These impurities can cause blockages. Impurities may accumulate on the surface of the pH electrode. When these impurities clog the surface, they can cause abnormal drift in the data monitored by the pH sensor, leading to deviations from the actual values. Consequently, relying solely on the real-time pH readings for pH adjustments during the production of chicory compound formulations is less effective, impacting formulation stability or product quality. For example, the actual pH before adjustment might be within the preset range, but the actual pH after adjustment might exceed it. Therefore, improving or ensuring the effectiveness of pH monitoring and adjustment during the production of chicory compound formulations is a pressing issue that needs to be addressed. Summary of the Invention

[0004] To address the above problems, this invention provides a manufacturing process for chicory compound preparations, the specific technical solution of which is as follows:

[0005] One embodiment of the present invention provides a manufacturing process for a chicory compound preparation, the manufacturing process of which includes:

[0006] The data acquisition module is used to acquire the pH data to be analyzed, the characteristic temperature window, the characteristic pH window, the reference temperature window, and the reference pH window at the t-th monitoring time during the production and manufacturing process of chicory compound formulation.

[0007] The drift anomaly identification and correction module is used to obtain the initial feature value corresponding to the t-th monitoring time based on the similarity between the feature temperature window and the reference temperature window and the difference between the fitting slope of the feature pH window and the fitting slope of the reference pH window; to obtain the target feature value corresponding to the t-th monitoring time based on the difference between the fitted value obtained by fitting the feature pH window and the pH data to be analyzed and the initial feature value; to cluster the target feature values ​​corresponding to the t-th monitoring time and the monitoring times before the t-th monitoring time to obtain the cluster corresponding to the t-th monitoring time; and to identify and correct the drift anomaly of the pH data to be analyzed corresponding to the t-th monitoring time based on the cluster to obtain the target pH data corresponding to the t-th monitoring time.

[0008] The pH monitoring and adjustment module is used to monitor and adjust the pH in the chicory compound preparation production container at the t-th monitoring time based on the target pH data corresponding to the t-th monitoring time.

[0009] Beneficial effects: This invention includes a data acquisition module for acquiring, during the production of chicory compound preparations, the pH data to be analyzed, a characteristic temperature window, a characteristic pH window, a reference temperature window, and a reference pH window corresponding to the t-th monitoring time; a drift anomaly identification and correction module for obtaining the initial feature value corresponding to the t-th monitoring time based on the similarity between the characteristic temperature window and the reference temperature window, and the difference between the fitting slope of the characteristic pH window and the fitting slope of the reference pH window; obtaining the target feature value corresponding to the t-th monitoring time based on the difference between the fitted value obtained by fitting the characteristic pH window and the pH data to be analyzed, and the initial feature value; clustering the target feature values ​​corresponding to the t-th monitoring time and the monitoring times before the t-th monitoring time to obtain the cluster corresponding to the t-th monitoring time; identifying and correcting the drift anomaly of the pH data to be analyzed corresponding to the t-th monitoring time based on the cluster; and a pH monitoring and adjustment module for monitoring and adjusting the pH in the chicory compound preparation production container at the t-th monitoring time based on the target pH data corresponding to the t-th monitoring time. Furthermore, this invention monitors and adjusts the pH in the chicory compound preparation production container at the t-th monitoring time based on the corrected pH data, which can improve or ensure the adjustment effect, thereby guaranteeing the production stability and quality of the chicory compound preparation. Attached Figure Description

[0010] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a structural block diagram of the manufacturing process of a chicory compound preparation according to the present invention. Detailed Implementation

[0012] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the protection scope of the embodiments of the present invention.

[0013] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.

[0014] This embodiment provides a manufacturing process for a chicory compound formulation, which is described in detail below:

[0015] like Figure 1 As shown in this embodiment, a manufacturing process for a chicory compound formulation includes:

[0016] The data acquisition module 01 is used to acquire the pH data to be analyzed, the characteristic temperature window, the characteristic pH window, the reference temperature window, and the reference pH window corresponding to the t-th monitoring time during the production and manufacturing process of chicory compound preparations.

[0017] The purpose of this embodiment is to determine whether the monitored data is affected by impurities and to correct the data accordingly. In other words, it involves identifying and correcting pH data for drift anomalies. Based on the corrected data, the pH is monitored and adjusted during the production process of chicory compound preparations. In this embodiment, the influence of impurities refers to the phenomenon where the monitored pH data deviates from the true pH due to impurities clogging the pH electrode surface, also known as drift anomalies. Impurities mainly refer to fibers, colloids, and some compounds that may deposit in the chicory raw materials. During pH monitoring, these impurities may adhere to the pH electrode surface or block the electrode structure, thus affecting the accuracy of the pH monitoring data or causing the pH sensor data to drift. Furthermore, for ease of analysis and understanding, this embodiment will subsequently describe the pH monitoring and adjustment process during the production of any batch of chicory compound preparations as an example.

[0018] To identify and correct drift anomalies and improve adjustment effectiveness, this embodiment requires real-time acquisition of temperature and pH data during the production of the chicory compound formulation. This involves obtaining the denoised pH data and sensor temperature data at each monitoring moment. The specific process for acquiring these data during the production of the chicory compound formulation is as follows: A pH sensor and a temperature sensor are installed in the mixing tank of the chicory compound formulation manufacturing process. The pH sensor collects real-time pH data in the mixing tank at different monitoring moments, recording the collected pH data as the initial pH data for that monitoring moment. The mixing tank serves as the container for the chicory compound formulation manufacturing process. A temperature sensor collects real-time temperature data in the mixing tank at different monitoring moments, recording the collected temperature data as the initial temperature data for that monitoring moment. The initial pH data is then processed using existing normalization or standardization methods. The obtained data is recorded as the pH data to be denoised. The initial temperature data is processed using existing normalization or standardization methods, and the processed data is recorded as the sensing temperature data. Here, the minimum-maximum normalization method or the Z-Score standardization method can be selected for processing. Since pH changes are sensitive to temperature, and temperature may affect some chemical reactions and may also cause electrode monitoring deviations, in order to distinguish the effects of temperature and impurity components on pH changes, or to more accurately identify drift anomalies, the subsequent identification and correction of drift anomalies in this embodiment also need to refer to temperature data. Therefore, temperature data needs to be collected. In addition, the temperature sensor and pH sensor in this embodiment collect data synchronously. The specific collection frequency or the time interval between adjacent monitoring moments needs to be set by the implementer according to the actual situation such as monitoring accuracy. For example, in this embodiment, the time interval between adjacent monitoring moments can be set to 1 second, and the monitoring moment is also the data collection moment.

[0019] Therefore, this embodiment can acquire the pH data to be denoised and the sensing temperature data corresponding to each monitoring moment in real time during the production of chicory compound preparations through the above process. However, during the production of chicory compound preparations, factors such as suspended impurities and bubbles may cause abrupt noise in the pH data collected by the sensor. Noise will affect the subsequent identification and correction of drift anomalies. Therefore, denoising is required before real-time identification and correction of drift anomalies. That is, after acquiring the pH data to be denoised, the denoised pH data is denoised in real time, and the denoised data is recorded as the pH data to be analyzed corresponding to the monitoring moment, that is, the pH data to be denoised at a certain monitoring moment. The denoised H data is the pH data to be analyzed corresponding to the monitoring time. In this embodiment, the data for identifying and correcting drift anomalies is the pH data to be analyzed. Since the denoising method for the pH data to be denoised at each monitoring time is the same, and for ease of understanding and explanation, this embodiment will describe the process of denoising the pH data to be denoised at any monitoring time r to obtain the pH data to be analyzed at monitoring time r as an example. Therefore, the specific process of denoising the pH data to be denoised at monitoring time r to obtain the pH data to be analyzed at monitoring time r from the start of production of the chicory compound preparation to monitoring time r is as follows:

[0020] First, the absolute value of the difference between the pH data to be denoised at monitoring time r and the target pH data at the previous monitoring time r is calculated and recorded as the first difference. This first difference is then normalized, and the result is recorded as the first evaluation value of the pH data to be denoised at monitoring time r. Next, the pH data at monitoring time r is predicted based on the target pH data at monitoring times preceding r, resulting in the predicted pH data at monitoring time r. The specific process for obtaining the predicted pH data at monitoring time r is as follows: A time series of a predetermined number of consecutive monitoring times preceding and closest to monitoring time r is constructed and recorded as the nearest historical monitoring times to monitoring time r. A two-dimensional space is constructed, with time as the horizontal axis and pH data as the vertical axis. Each monitoring time in the nearest historical monitoring times to monitoring time r and the target pH data corresponding to each monitoring time are mapped to... In a two-dimensional space, data points corresponding to each monitoring time in the nearest historical monitoring time are obtained. The horizontal axis of the data points corresponding to the monitoring time is the time corresponding to the corresponding monitoring time, and the vertical axis is the target pH data corresponding to the corresponding monitoring time. The least squares method is used to fit the data points corresponding to each monitoring time in the nearest historical monitoring time to obtain a fitted straight line. The data corresponding to monitoring time t is obtained on the fitted straight line and recorded as the predicted pH data corresponding to monitoring time r. Then, the absolute value of the difference between the predicted pH data corresponding to monitoring time t and the pH data to be denoised corresponding to monitoring time t is calculated and recorded as the second difference. The second difference is normalized and the result of the normalization is recorded as the second evaluation value of the pH data to be denoised corresponding to monitoring time r. Finally, the mean of the first evaluation value and the second evaluation value of the pH data to be denoised corresponding to monitoring time r is obtained and recorded as the comprehensive evaluation value of the pH data to be denoised corresponding to monitoring time r. Furthermore, since this embodiment performs denoising and drift anomaly identification and correction in real time, and the monitoring times before the current monitoring time are historical monitoring times, denoising and drift anomaly identification and correction have already been completed at these historical monitoring times. Therefore, the corrected data corresponding to the historical monitoring times can be obtained. This corrected data is referred to as the target pH data in this embodiment. Therefore, from the start of production of the chicory compound preparation to monitoring time r, which is the current monitoring time, the target pH data corresponding to the monitoring times before monitoring time r is the denoised pH data obtained from the monitoring times before monitoring time r, after drift anomaly identification and correction. In specific applications, the implementer needs to set a preset number of values ​​according to the actual situation; for example, in this embodiment, the preset number can be set to 10.

[0021] The specific calculation expression for the comprehensive evaluation value of the pH data to be denoised corresponding to monitoring time r is as follows:

[0022]

[0023] in, Norm() is the comprehensive evaluation value of the pH data to be denoised at the monitoring time r, and it is the normalization function. To monitor the pH data to be denoised at time r, This refers to the target pH data corresponding to the monitoring time preceding monitoring time r. The predicted pH data corresponds to monitoring time t; and the difference between the mutation noise and the neighborhood data is greater, and the fluctuation amplitude of the mutation noise is greater relative to the trend of the neighborhood data, therefore when The larger and The larger, or rather The larger the value, the greater the likelihood that the pH data to be denoised at monitoring time r is a sudden noise event, and the greater the probability that subsequent denoising is needed. The smaller the value, the less likely the pH data to be denoised at monitoring time r is a sudden noise, and the less likely it is to require subsequent denoising.

[0024] Next, it is determined whether the comprehensive evaluation value of the pH data to be denoised at monitoring time r is greater than the preset noise threshold. If it is greater, the pH data to be denoised at monitoring time r is determined to be a sudden noise data, and the pH data to be denoised at monitoring time r needs to be denoised. The denoised data is then recorded as the pH data to be analyzed at monitoring time r. If it is not greater, the pH data to be denoised at monitoring time r is determined not to be a sudden noise data, and no denoising processing is required. The pH data to be denoised at monitoring time r can be directly recorded as the pH data to be analyzed at monitoring time r. If it is determined that the pH data to be denoised at monitoring time r needs to be denoised, this embodiment can choose the predicted value replacement method to complete the denoising. That is, if it is determined that the pH data to be denoised at monitoring time r needs to be denoised, this embodiment records the predicted pH data at monitoring time t as the pH data to be analyzed at monitoring time r. As for other real-time methods, existing denoising methods can also be selected to denoise the pH data to be denoised at monitoring time r.

[0025] Furthermore, in practical applications, implementers need to set a preset noise threshold based on the actual situation, such as the range of comprehensive evaluation values. For example, since the changes in non-mutation noise data are based on the actual acid-base conditions of the raw materials, i.e., they change according to a certain trend, the comprehensive evaluation value of non-mutation noise data is relatively small. However, the changes in mutation noise data are random and do not have a regularity with other data, so the comprehensive evaluation value of mutation noise data is relatively large. Therefore, after normalization, the comprehensive evaluation values ​​of mutation noise data and non-noise data differ significantly from those of mutation noise data, i.e., they are concentrated at both ends of the corresponding value range. Therefore, in this embodiment, the preset noise threshold can be set to 0.5. In addition, since the probability of mutation noise occurring at the initial monitoring time is extremely low, in this embodiment, the pH data to be denoised at the initial monitoring time can be directly recorded as the pH data to be analyzed at the monitoring time. For example, the pH data to be denoised within the first 10 seconds of monitoring can be directly recorded as the pH data to be analyzed at the monitoring time.

[0026] In this embodiment, the method for denoising the pH data to be denoised at any monitoring time to obtain the pH data to be analyzed at the corresponding monitoring time is the same as the method described above for denoising the pH data to be denoised at monitoring time r to obtain the pH data to be analyzed at monitoring time r. In this embodiment, the method for identifying and correcting drift anomalies in the pH data to be analyzed at any monitoring time to obtain the target pH data to be denoised at the corresponding monitoring time is the same as the method for denoising the pH data to be analyzed at the t-th monitoring time to obtain the target pH data at the t-th monitoring time.

[0027] This embodiment describes, after denoising, the process of identifying and correcting drift anomalies in the pH data to be analyzed at any monitoring time to obtain the target pH data at that monitoring time, for example, in the case of chicory compound preparation from the start of production to monitoring time t, if the specific process of identifying and correcting drift anomalies in the denoised pH data at monitoring time t to obtain the target pH data at monitoring time t is described in detail, this embodiment needs to first obtain the characteristic temperature window, characteristic pH window, reference temperature window, and reference pH window at monitoring time t. That is, the characteristic temperature window, characteristic pH window, reference temperature window, and reference pH window at monitoring time t are the data support for the subsequent identification and correction of drift anomalies in the pH data to be analyzed at monitoring time t. The specific process of obtaining the characteristic temperature window, characteristic pH window, reference temperature window, and reference pH window at monitoring time t is as follows:

[0028] First, the time period from the start of production of the chicory compound preparation to the t-th monitoring time is obtained and recorded as the production monitoring time period corresponding to the t-th monitoring time. The last moment in the production monitoring time period corresponding to the t-th monitoring time is the t-th monitoring time. Then, a sliding window is constructed, and the rightmost end of the sliding window is aligned with the rightmost moment of the production monitoring time period. Starting from the end moment of the production monitoring time period, the sliding window is moved forward according to a preset step size until it stops when the initial moment of the production monitoring time period is included. All windows obtained from the start of the sliding to the stop are recorded as the time windows corresponding to the t-th monitoring time. Then, among all the time windows corresponding to the t-th monitoring time, the time window that includes the t-th monitoring time is selected and recorded as the feature time window corresponding to the t-th monitoring time. All time windows that do not include the t-th monitoring time are selected and recorded as the reference time windows corresponding to the t-th monitoring time. Next, the time series window consisting of the sensing temperature data corresponding to all monitoring times within the characteristic time window corresponding to the t-th monitoring time is denoted as the characteristic temperature window corresponding to the t-th monitoring time. The time series window consisting of the sensing temperature data corresponding to all monitoring times within the f-th reference time window corresponding to the t-th monitoring time is denoted as the f-th reference temperature window corresponding to the t-th monitoring time. The time series window consisting of the target pH data corresponding to all monitoring times within the f-th reference time window corresponding to the t-th monitoring time is denoted as the f-th reference pH window corresponding to the t-th monitoring time. The other monitoring times within the characteristic time window corresponding to the t-th monitoring time, excluding the t-th monitoring time, are then... The time window formed by the target pH data and the pH data to be analyzed at the t-th monitoring time is denoted as the characteristic pH window corresponding to the t-th monitoring time. The characteristic pH window and the characteristic temperature window are the characteristic data windows corresponding to the characteristic time window. Similarly to the monitoring time r, the target pH data corresponding to other monitoring times before the t-th monitoring time refers to the data after identifying and correcting the drift anomalies of the pH data to be analyzed at the corresponding monitoring time. The method for identifying and correcting the drift anomalies of the pH data to be analyzed at other monitoring times before the t-th monitoring time is the same as the method for identifying and correcting the drift anomalies of the pH data to be analyzed at the t-th monitoring time. In specific applications, the implementer can set the size of the sliding window and the preset step size according to the actual acid-base adjustment frequency and other actual conditions. However, since the liquid mixing stage of chicory compound preparation manufacturing usually lasts from 30 minutes to several hours depending on the complexity of the process, in order to minimize the impact of the pH adjustment process on the analysis, the window should not be set too large or too small. For example, in this embodiment, the length of the sliding window can be set to 1 minute and the preset step size can be set to 1 second.

[0029] Therefore, this embodiment can obtain the pH data to be analyzed, characteristic temperature window, characteristic pH window, reference temperature window, and reference pH window corresponding to the t-th monitoring time through the above process; and this embodiment requires that the characteristic temperature window and the reference temperature window have the same length. If they are not of the same length, they can be filled or truncated, such as truncating the longer window to the same length as the shorter window.

[0030] The drift anomaly identification and correction module 02 is used to obtain the initial feature value corresponding to the t-th monitoring time based on the similarity between the feature temperature window and the reference temperature window and the difference between the fitting slope of the feature pH window and the fitting slope of the reference pH window; to obtain the target feature value corresponding to the t-th monitoring time based on the difference between the fitted value obtained by fitting the feature pH window and the pH data to be analyzed and the initial feature value; to cluster the target feature values ​​corresponding to the t-th monitoring time and the monitoring times before the t-th monitoring time to obtain the cluster corresponding to the t-th monitoring time; and to identify and correct the drift anomaly of the pH data to be analyzed corresponding to the t-th monitoring time based on the cluster to obtain the target pH data corresponding to the t-th monitoring time.

[0031] When no acid or alkali is added for adjustment, pH monitoring values ​​are affected not only by impurities but also by temperature. Temperature can influence the slope or potential of the pH electrode, leading to deviations in pH readings. Different temperatures can also promote certain chemical reactions, causing pH changes. However, the effect of temperature on pH is relatively regular and reproducible. In contrast, data drift caused by impurities depends on factors such as impurity concentration and deposition, and generally lacks a fixed pattern. Furthermore, when temperature conditions are similar across windows without impurities, the corresponding pH trends are also similar. Therefore, in this embodiment, subsequent steps can be based on the similarity of temperature and pH trends between windows. The initial feature value corresponding to the t-th monitoring time is obtained based on the situation. The initial feature value is a key parameter reflecting whether the pH data to be analyzed at the t-th monitoring time is an anomaly due to drift. Therefore, in this embodiment, the next step is to obtain the temperature similarity between the feature temperature window at the t-th monitoring time and the reference temperature windows at the t-th monitoring time based on the absolute value of the difference between the corresponding data in the feature temperature window at the t-th monitoring time and the corresponding position data in the reference temperature windows at the t-th monitoring time. The temperature similarity is the key data for accurately identifying whether there is an anomaly due to drift. The specific process for obtaining the temperature similarity between the feature temperature window at the t-th monitoring time and the reference temperature windows at the t-th monitoring time is as follows:

[0032] For the characteristic temperature window corresponding to the t-th monitoring time and the f-th reference temperature window corresponding to the t-th monitoring time, in the characteristic temperature window corresponding to the t-th monitoring time, starting from the initial data in the characteristic temperature window, a preset number of data points are marked every once until the last data point in the characteristic temperature window is reached. All marked data in the characteristic temperature window are recorded as marked data in the characteristic temperature window. Similarly, in the f-th reference temperature window, starting from the initial data in the f-th reference temperature window, a preset number of data points are marked every once until the last data point in the reference temperature window is reached. All marked data in the f-th reference temperature window are recorded as marked data in the f-th reference temperature window. Furthermore, if the g-th data point in the characteristic temperature window is marked, then the g-th data point in the f-th reference temperature window is also marked. Based on the marked data in the characteristic temperature window corresponding to the t-th monitoring time and the f-th reference temperature window corresponding to the t-th monitoring time... The absolute value of the difference between the marked data at corresponding positions in the mouth is used to obtain the temperature difference sequence between the characteristic temperature window corresponding to the t-th monitoring time and the reference temperature window corresponding to the t-th monitoring time. The a-th temperature difference in the temperature difference sequence is the absolute value of the difference between the a-th marked data in the characteristic temperature window and the a-th marked data in the f-th reference temperature window. The cumulative result of all data in the temperature difference sequence is negatively correlated and then normalized. This result is denoted as the temperature similarity between the characteristic temperature window corresponding to the t-th monitoring time and the f-th reference temperature window corresponding to the t-th monitoring time. Here, negative correlation mapping followed by normalization means adding a preset constant to the cumulative result of all data in the temperature difference sequence, taking the reciprocal, and then processing it using the normalization function Norm(). The preset constant is to prevent the denominator from being 0. The specific expression for the temperature similarity between the characteristic temperature window corresponding to the t-th monitoring time and the f-th reference temperature window corresponding to the t-th monitoring time is:

[0033]

[0034] in, Let A be the temperature similarity between the characteristic temperature window corresponding to the t-th monitoring time and the f-th reference temperature window corresponding to the t-th monitoring time. Norm() is the normalization function, and A is the total number of labeled data in either the characteristic temperature window or the f-th reference temperature window corresponding to the t-th monitoring time, which can also be called the total number of data in the temperature difference sequence. This represents the a-th labeled data point within the characteristic temperature window corresponding to the t-th monitoring time. This refers to the a-th labeled data point within the f-th reference temperature window corresponding to the t-th monitoring time. Let c be the a-th temperature difference value in the temperature difference sequence, and c be a preset constant. c can take any constant, such as 0.01 in this embodiment. The smaller, that is A larger value indicates a greater similarity in temperature between the characteristic temperature window corresponding to the t-th monitoring time and the f-th reference temperature window corresponding to the t-th monitoring time, and vice versa. When it is larger, that is The smaller the value, the less similar the characteristic temperature window corresponding to the t-th monitoring time is to the f-th reference temperature window corresponding to the t-th monitoring time.

[0035] Because the pH value needs to be continuously adjusted during the liquid mixing stage of chicory compound preparation manufacturing to achieve the final effect, the normal pH value at different times may vary. However, the influence trend of the pH value under the same temperature conditions is similar. Therefore, after analyzing the similarity between the characteristic temperature window and the reference temperature window, this embodiment will next obtain the similarity of the pH change trend between the characteristic pH window corresponding to the t-th monitoring time and the reference pH window corresponding to the t-th monitoring time by fitting the slope of the straight line obtained from all data in the characteristic pH window corresponding to the t-th monitoring time with the slope of the straight line obtained from all data in the reference pH window corresponding to the t-th monitoring time. The specific process for obtaining the similarity of the pH change trend between the characteristic pH window corresponding to the t-th monitoring time and the f-th reference pH window corresponding to the t-th monitoring time is as follows: the data in the characteristic pH window corresponding to the t-th monitoring time are fitted using the least squares method, and... The slope of the fitted line is recorded as the trend characterization value of the characteristic pH window. The data in the f-th reference pH window corresponding to the t-th monitoring time is fitted using the least squares method, and the slope of the fitted line is recorded as the trend characterization value of the f-th reference pH window. The absolute value of the difference between the trend characterization value of the characteristic pH window and the trend characterization value of the f-th reference pH window is calculated, negatively correlated, and then normalized. This result is recorded as the pH change trend similarity between the characteristic pH window corresponding to the t-th monitoring time and the f-th reference pH window corresponding to the t-th monitoring time. The characteristic pH window and the characteristic temperature data belong to the characteristic time window, and the f-th reference pH window and the f-th reference temperature window belong to the f-th reference time window corresponding to the t-th monitoring time. Here, the negative correlation mapping followed by normalization means adding a preset constant to the absolute value of the difference, taking the reciprocal, and then processing it with the normalization function Norm(). The preset constant is also to prevent the denominator from being 0.

[0036] The specific formula for calculating the similarity of pH change trends between the characteristic pH window corresponding to the t-th monitoring time and the f-th reference pH window corresponding to the t-th monitoring time is:

[0037]

[0038] in, Let K1 be the trend representation value of the characteristic pH window corresponding to the t-th monitoring time and K2 be the trend representation value of the f-th reference pH window corresponding to the t-th monitoring time. The smaller the absolute value of the difference between the trend representation value of the characteristic pH window and the trend representation value of the f-th reference pH window, the better. A larger value indicates that the pH change trend of the characteristic pH window corresponding to the t-th monitoring time is more similar to the pH change trend of the f-th reference pH window corresponding to the t-th monitoring time. Conversely, a larger absolute value indicates a greater difference between the trend characteristic value of the characteristic pH window and the trend characteristic value of the f-th reference pH window. The smaller the value, the less similar the pH change trend of the characteristic pH window corresponding to the t-th monitoring time is to the pH change trend of the f-th reference pH window corresponding to the t-th monitoring time.

[0039] Since the data corresponding to the window closer to the t-th monitoring time has greater reference value, this embodiment, after obtaining the temperature similarity between the characteristic temperature window and the reference temperature window corresponding to the t-th monitoring time, and the pH change trend similarity between the characteristic pH window and the reference pH window corresponding to the t-th monitoring time, further combines the time interval between the characteristic pH window and the reference pH window to determine the initial feature value corresponding to the t-th monitoring time. In other words, this embodiment will obtain the initial feature value corresponding to the t-th monitoring time based on the temperature similarity between the characteristic temperature window and the reference temperature window corresponding to the t-th monitoring time, the pH change trend similarity between the characteristic pH window and the reference pH window corresponding to the t-th monitoring time, and the time interval between the time windows corresponding to the characteristic pH window and the reference pH window corresponding to the t-th monitoring time. The initial feature value corresponding to the t-th monitoring time is a key parameter for determining the target feature value, and the target feature value is key data for identifying whether there is a drift anomaly. Therefore, the specific process for obtaining the initial feature value corresponding to the t-th monitoring time is as follows:

[0040] Based on the temperature similarity between the characteristic temperature window corresponding to the t-th monitoring time and each reference temperature window corresponding to the t-th monitoring time, the pH change trend similarity between the characteristic pH window corresponding to the t-th monitoring time and each reference pH window corresponding to the t-th monitoring time, and the time interval between the characteristic pH window corresponding to the t-th monitoring time and each reference pH window corresponding to the t-th monitoring time, a comprehensive characterization value set corresponding to the t-th monitoring time is obtained. The b-th comprehensive characterization value in the comprehensive characterization value set is the temperature similarity between the characteristic temperature window and the b-th reference temperature window corresponding to the t-th monitoring time, and the pH change trend similarity between the characteristic pH window and the b-th reference temperature window corresponding to the t-th monitoring time. The negative correlation mapping result of pH change trend similarity between the b-th reference pH windows and the time weighting factor between the feature pH window and the b-th reference pH window corresponding to the t-th monitoring time is calculated by multiplying the feature pH window with the time weighting factor between the feature pH window and the b-th reference pH window corresponding to the t-th monitoring time. The negative correlation mapping result of pH change trend similarity is the reciprocal of the pH change trend similarity. The time weighting factor between the feature pH window and the b-th reference pH window corresponding to the t-th monitoring time is the result of normalizing the time interval between the time window corresponding to the feature pH window and the time window corresponding to the b-th reference pH window corresponding to the t-th monitoring time before performing the negative correlation mapping. , This time interval is the time window corresponding to the characteristic pH window and the time window corresponding to the b-th reference pH window at the t-th monitoring time. The time interval between the characteristic pH window and the b-th reference pH window at the t-th monitoring time can also be the time interval between the end of the characteristic pH window and the end of the b-th reference pH window. The maximum time interval between the time window corresponding to the characteristic pH window and the time windows corresponding to all reference pH windows at the t-th monitoring time is denoted as . Its function is to Normalization is performed by subtracting the constant 1. To perform a negative correlation mapping so that the similarity of temperature and pH change trends closer to the t-th monitoring time dominates the initial feature value, all data in the comprehensive characterization value set are accumulated, and the accumulated result is used as the initial feature value corresponding to the t-th monitoring time; the expression for obtaining the b-th comprehensive characterization value in the comprehensive characterization value set is as follows: ,in, Let be the temperature similarity between the characteristic temperature window corresponding to the t-th monitoring time and the b-th reference temperature window corresponding to the t-th monitoring time. The similarity of pH change trends between the characteristic pH window corresponding to the t-th monitoring time and the b-th reference pH window corresponding to the t-th monitoring time.

[0041] Because the closer the temperature conditions of the characteristic temperature window and the reference temperature window are, the closer the pH change trends between the characteristic pH window and the reference pH window are, indicating that the pH change in the characteristic pH window is more likely to be a normal change. In other words, the data in the characteristic pH window is less likely to be caused by impurities or drift anomalies. Furthermore, the closer the reference window is to the characteristic pH window or the t-th monitoring time, the greater its reference value. It better reflects the interference of impurities on the pH data at the t-th monitoring time or whether the pH data at the t-th monitoring time is drift anomaly. Therefore, the smaller the time interval between the time window corresponding to the characteristic pH window and the time window corresponding to the reference pH window, the stronger the response of the reference pH window to the authenticity of the characteristic pH window data, or the better the reference pH window reflects whether the pH data at the t-th monitoring time is drift anomaly. Thus, when... The larger the value, the more consistent the temperature influence between the characteristic temperature window and the b-th reference temperature window, and the greater the reference value of the b-th reference pH window. The more credible, the more... The smaller the value of the reference pH window, the stronger its response to the authenticity of the characteristic pH window data. In other words, the greater the trend similarity between the characteristic pH window and the reference pH window, the better it reflects whether the pH data to be analyzed at the t-th monitoring time is drifting or abnormal. The more credible, The smaller the value, the higher the degree of drift anomaly in the characteristic pH window, indicating that the characteristic pH window or the pH data to be analyzed corresponding to the t-th monitoring time is more likely to be drift anomaly data. The larger, smaller and The smaller the value, that is, the larger the initial characteristic value corresponding to the t-th monitoring time, the higher the degree of drift anomaly of the characteristic pH window, indicating that the characteristic pH window or the pH data to be analyzed corresponding to the t-th monitoring time is more likely to be drift anomaly data.

[0042] However, at the initial stage of drift anomaly, that is, in the initial stage when fibers, colloids, and deposited compounds adhere to the pH electrode surface or block the electrode structure, most of the data in the characteristic data window corresponding to the characteristic time window is normal data. At this time, the drift anomaly of the characteristic pH window is low, or the calculated initial characteristic value is low. Therefore, it is difficult to identify the initial drift anomaly based solely on the initial characteristic value. In order to avoid identifying the initial drift anomaly data as normal data, this embodiment needs to combine the deviation of the pH data to be analyzed at the monitoring time from the fitted value on the fitted curve of the characteristic pH window at the monitoring time to obtain the final characterization value, that is, the target characteristic value, of the pH data to be analyzed at the monitoring time. That is, the target characteristic value will be obtained based on the difference between the fitted value obtained by fitting the characteristic pH window at the t-th monitoring time and the pH data to be analyzed at the t-th monitoring time, as well as the initial characteristic value at the t-th monitoring time. The specific process of obtaining the target characteristic value at the t-th monitoring time is as follows:

[0043] The straight line obtained by fitting the data in the characteristic pH window corresponding to the t-th monitoring time using the least squares method is denoted as the characteristic line. The value corresponding to the t-th monitoring time is obtained on the characteristic line and denoted as the fitted pH data corresponding to the t-th monitoring time. The absolute value of the difference between the fitted pH data corresponding to the t-th monitoring time and the pH data to be analyzed corresponding to the t-th monitoring time is calculated and denoted as the characteristic difference. The ratio of the characteristic difference to the fitted pH data corresponding to the t-th monitoring time is denoted as the relative deviation. The product of the relative deviation and the initial characteristic value corresponding to the t-th monitoring time is calculated and denoted as the target characteristic value corresponding to the t-th monitoring time. The specific calculation expression for the target characteristic value corresponding to the t-th monitoring time is as follows:

[0044]

[0045] Where Q is the target feature value corresponding to the t-th monitoring time, and q is the initial feature value corresponding to the t-th monitoring time. Let t be the pH data to be analyzed at the t-th monitoring time. Here is the fitted pH data corresponding to the t-th monitoring time; and as q increases, The larger Q is, the higher the degree of drift anomaly performance of the characteristic pH window, and the greater the probability that the pH data to be analyzed corresponding to the characteristic pH window or the t-th monitoring time is drift anomaly data. Conversely, the smaller Q is, the lower the degree of drift anomaly performance of the characteristic pH window, and the smaller the probability that the pH data to be analyzed corresponding to the characteristic pH window or the t-th monitoring time is drift anomaly data.

[0046] Furthermore, since the similarity of the target feature values ​​corresponding to normal data, or non-drift anomaly data, is higher than that of drift anomaly data, this embodiment, after obtaining the target feature values ​​corresponding to the monitoring time, uses the DBSCAN algorithm to cluster the target feature values ​​corresponding to the t-th monitoring time and the target feature values ​​corresponding to all monitoring times before the t-th monitoring time, and records the clustering results as the cluster corresponding to the t-th monitoring time. The clustering process is well-known, and the method for obtaining the target feature values ​​corresponding to all monitoring times before the t-th monitoring time is the same as the method for obtaining the target feature values ​​corresponding to the t-th monitoring time. Then, based on the cluster corresponding to the t-th monitoring time, the pH data to be analyzed corresponding to the t-th monitoring time is used to identify and correct drift anomalies, thus obtaining the target pH data corresponding to the t-th monitoring time. The specific process of identifying and correcting drift anomalies in the pH data to be analyzed corresponding to the t-th monitoring time based on the cluster corresponding to the t-th monitoring time to obtain the target pH data corresponding to the t-th monitoring time is as follows:

[0047] In the cluster corresponding to the t-th monitoring time, obtain the cluster to which the target feature value belongs and the cluster with the most data within that cluster. Record the cluster with the most data as the largest cluster. Then, determine whether the cluster to which the target feature value belongs at the t-th monitoring time belongs to the largest cluster. If it does, it is determined that there is no drift anomaly at the t-th monitoring time, or that the pH data to be analyzed at the t-th monitoring time is not drift anomaly data. In this case, no correction is needed for the pH data to be analyzed at the t-th monitoring time; the pH data to be analyzed at the t-th monitoring time can be directly used as the target pH data at the t-th monitoring time. If it is determined that the cluster to which the target feature value belongs at the t-th monitoring time belongs does not belong to the largest cluster, then the cluster to be analyzed at the t-th monitoring time is determined to be drift anomaly data. If drift anomalies exist or the pH data to be analyzed at the t-th monitoring time is determined to be drift anomaly data, then the pH data to be analyzed at the t-th monitoring time needs to be corrected. The correction process is as follows: predict the pH data at the t-th monitoring time based on the target pH data at the monitoring time before the t-th monitoring time to obtain the predicted pH data at the t-th monitoring time. Then, use the predicted pH data at the t-th monitoring time as the target pH data at the t-th monitoring time. That is, given the target pH data at the monitoring time before the t-th monitoring time, the LSTM algorithm is used to predict the data at the t-th monitoring time to obtain the predicted pH data at the t-th monitoring time. The process of the LSTM algorithm for data prediction is well known. Alternatively, as another real-time method, a preset anomaly threshold can be used to identify drift anomalies in the pH data to be analyzed at the t-th monitoring time. For example, if the target feature value at the t-th monitoring time is greater than the preset anomaly threshold, it can be determined that there is a drift anomaly at the t-th monitoring time, or that the pH data to be analyzed at the t-th monitoring time is drift anomaly data and needs to be corrected. If the target feature value at the t-th monitoring time is not greater than the preset anomaly threshold, it can be determined that no correction is needed for the pH data to be analyzed at the t-th monitoring time, and the pH data to be analyzed at the t-th monitoring time can be directly used as the target pH data at the t-th monitoring time. The preset anomaly threshold can be set by the implementer according to the actual situation. In addition, this embodiment does not identify and correct drift anomalies in the pH data to be analyzed at the initial monitoring time; it simply records the pH data to be analyzed at the initial monitoring time as the target pH data. For example, the pH data to be analyzed within the first 10 seconds of monitoring can be directly recorded as the target pH data at the monitoring time.

[0048] Therefore, this embodiment completes the identification and correction of the pH data drift anomaly corresponding to the t-th monitoring time through the above process.

[0049] pH monitoring and adjustment module 03 monitors and adjusts the pH in the chicory compound preparation production container at the t-th monitoring time based on the target pH data corresponding to the t-th monitoring time.

[0050] In this embodiment, after identifying and correcting the anomaly in the pH data to be analyzed corresponding to the t-th monitoring time, that is, after obtaining the target pH data corresponding to the t-th monitoring time, the pH in the chicory compound preparation production container at the t-th monitoring time is monitored and adjusted based on the target pH data corresponding to the t-th monitoring time. Monitoring and adjusting the pH in the chicory compound preparation production container at the t-th monitoring time is equivalent to adjusting the pH value during the raw material mixing process. The process of monitoring and adjusting the pH corresponding to the t-th monitoring time based on the pH data is well-known. If it is determined that the target pH data corresponding to the t-th monitoring time exceeds the preset pH range, it is determined that the pH in the mixing tank needs to be adjusted at this time. If it is determined that the target pH data corresponding to the t-th monitoring time does not exceed the preset pH range, it is determined that the pH in the mixing tank does not need to be adjusted at this time. The process of adjusting the pH in the mixing tank is well-known, so it will not be described in detail. The mixing tank is the container for the production of the chicory compound preparation, and the preset pH range is an empirical value.

[0051] Thus, this embodiment completes the monitoring and adjustment of pH during the production of chicory compound preparations, and can guarantee or improve the effect of the adjustment.

[0052] In summary, this embodiment includes a data acquisition module for acquiring the pH data to be analyzed, a characteristic temperature window, a characteristic pH window, a reference temperature window, and a reference pH window at the t-th monitoring time during the production of chicory compound formulations; a drift anomaly identification and correction module for obtaining the initial feature value at the t-th monitoring time based on the similarity between the characteristic temperature window and the reference temperature window, and the difference between the fitting slope of the characteristic pH window and the fitting slope of the reference pH window; obtaining the target feature value at the t-th monitoring time based on the difference between the fitted value obtained by fitting the characteristic pH window and the pH data to be analyzed, and the initial feature value; clustering the target feature values ​​at the t-th monitoring time and the monitoring times before the t-th monitoring time to obtain the cluster at the t-th monitoring time; identifying and correcting the drift anomaly of the pH data to be analyzed at the t-th monitoring time based on the cluster; and a pH monitoring and adjustment module for monitoring and adjusting the pH in the chicory compound formulation production container at the t-th monitoring time based on the target pH data at the t-th monitoring time. Furthermore, this embodiment uses the corrected pH data to monitor and adjust the pH in the chicory compound preparation production container at the t-th monitoring time, which can improve or ensure the adjustment effect, thereby ensuring the production stability and quality of the chicory compound preparation.

[0053] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A process for the manufacture of a chicory composite preparation, characterized in that, The manufacturing process of the chicory composite preparation comprises: The data acquisition module is configured to acquire the pH data to be analyzed, the characteristic temperature window, the characteristic pH window, the reference temperature window, and the reference pH window corresponding to the tth monitoring time during the production and manufacturing process of the chicory composite preparation; The drift anomaly identification and correction module is configured to obtain an initial characteristic value corresponding to the tth monitoring time according to the similarity between the characteristic temperature window and the reference temperature window and the difference between the fitting slope of the characteristic pH window and the fitting slope of the reference pH window, obtain a target characteristic value corresponding to the tth monitoring time according to the difference between the fitting value obtained by fitting the characteristic pH window and the pH data to be analyzed and the initial characteristic value, cluster the target characteristic values corresponding to the tth monitoring time and the monitoring time before the tth monitoring time to obtain a cluster corresponding to the tth monitoring time, identify and correct the drift anomaly of the pH data to be analyzed corresponding to the tth monitoring time according to the cluster to obtain target pH data corresponding to the tth monitoring time, and not identify and correct the drift anomaly of the pH data to be analyzed corresponding to the initial monitoring time, but directly record the pH data to be analyzed corresponding to the initial monitoring time as the target pH data; The pH monitoring and adjustment module is configured to monitor and adjust the pH in the chicory composite preparation production and manufacturing container at the tth monitoring time according to the target pH data corresponding to the tth monitoring time. The method for obtaining the characteristic temperature window, the characteristic pH window, the reference temperature window, and the reference pH window comprises: Obtaining sensing temperature data corresponding to each monitoring time during the production and manufacturing process of the chicory composite preparation; The time period from the beginning of the production of the chicory compound preparation to the tth monitoring moment is recorded as a production monitoring time period corresponding to the tth monitoring moment, a sliding window is constructed, the sliding window is slid forward from the end time of the production monitoring time period to obtain all time windows corresponding to the tth monitoring moment, in all the time windows, the time window containing the tth monitoring moment is recorded as a characteristic time window corresponding to the tth monitoring moment, all the time windows not containing the tth monitoring moment are recorded as reference time windows corresponding to the tth monitoring moment, a time sequence window composed of the sensing temperature data corresponding to all the monitoring moments in the characteristic time window is recorded as a characteristic temperature window corresponding to the tth monitoring moment, a time sequence window composed of the sensing temperature data corresponding to all the monitoring moments in the reference time window is recorded as a reference temperature window corresponding to the tth monitoring moment, a time sequence window composed of the target pH data corresponding to all the monitoring moments in the reference time window is recorded as a reference pH window corresponding to the tth monitoring moment, a time sequence window composed of the target pH data corresponding to the monitoring moments other than the tth monitoring moment in the characteristic time window and the to-be-analyzed pH data corresponding to the tth monitoring moment is recorded as a characteristic pH window corresponding to the tth monitoring moment, the target pH data corresponding to the monitoring moments before the tth monitoring moment is data after drift anomaly identification and correction of the to-be-analyzed pH data corresponding to the corresponding monitoring moment, and the method of drift anomaly identification and correction of the to-be-analyzed pH data corresponding to the tth monitoring moment is the same as the method of drift anomaly identification and correction of the to-be-analyzed pH data corresponding to the tth monitoring moment; The method of drift anomaly identification and correction of the to-be-analyzed pH data corresponding to the tth monitoring moment according to the clustering cluster comprises the following steps: It is judged whether the target characteristic value corresponding to the tth monitoring moment belongs to the largest cluster in all the clustering clusters corresponding to the tth monitoring moment, if it belongs, it is determined that there is no drift anomaly in the tth monitoring moment, and the to-be-analyzed pH data corresponding to the tth monitoring moment is directly taken as the target pH data corresponding to the tth monitoring moment, otherwise, it is determined that there is drift anomaly in the tth monitoring moment, and the pH data corresponding to the tth monitoring moment is predicted according to the target pH data corresponding to the monitoring moments before the tth monitoring moment, and the predicted value is taken as the target pH data corresponding to the tth monitoring moment, and the largest cluster is a normal data cluster.

2. A process for the production of a chicory composite preparation according to claim 1, characterized in that, The method for obtaining the initial characteristic value corresponding to the tth monitoring moment comprises the following steps: The absolute value of the difference between each marked data in the characteristic temperature window and the corresponding marked data in the reference temperature window is obtained, and the temperature similarity between the characteristic temperature window and the reference temperature window is obtained according to the absolute value. The difference between the slope of the straight line obtained by fitting all data in the characteristic pH window and the slope of the straight line obtained by fitting all data in the reference pH window is obtained, and the pH change trend similarity between the characteristic pH window and the reference pH window is obtained. The initial characteristic value corresponding to the tth monitoring moment is obtained according to the time interval between the characteristic pH window and the reference pH window, the temperature similarity, and the pH change trend similarity.

3. A process for the production of a chicory composite preparation according to claim 2, characterized in that, The temperature similarity between the characteristic temperature window and the reference temperature window is obtained by: The sequence composed of the absolute value of the difference between each marked data in the characteristic temperature window and the corresponding marked data in the reference temperature window is referred to as a temperature difference sequence, and the result of negatively correlating and then normalizing the cumulative result of all data in the temperature difference sequence is referred to as the temperature similarity between the characteristic temperature window and the reference temperature window.

4. A process for the production of a chicory composite preparation according to claim 2, characterized in that, The pH change trend similarity between the characteristic pH window and the reference pH window is the result of negatively correlating and then normalizing the absolute value of the difference between the slope of the straight line obtained by fitting all data in the characteristic pH window and the slope of the straight line obtained by fitting all data in the reference pH window.

5. A process for the production of a chicory composite preparation according to claim 2, characterized in that, The method for obtaining the initial characteristic value corresponding to the tth monitoring moment according to the time interval between the characteristic pH window and the reference pH window, the temperature similarity, and the pH change trend similarity includes: A comprehensive characteristic value set corresponding to the tth monitoring moment is obtained, the bth comprehensive characteristic value in the comprehensive characteristic value set is the result of multiplying the temperature similarity between the characteristic temperature window and the bth reference temperature window corresponding to the tth monitoring moment, the negatively correlated mapping result of the pH change trend similarity between the characteristic pH window and the bth reference pH window corresponding to the tth monitoring moment, and the time weight factor between the characteristic pH window and the bth reference pH window, the time weight factor between the characteristic pH window and the bth reference pH window is the result of negatively correlating and then normalizing the time interval between the characteristic pH window and the bth reference pH window, and the cumulative result of all data in the comprehensive characteristic value set is taken as the initial characteristic value corresponding to the tth monitoring moment.

6. A process for the production of a chicory composite preparation according to claim 1, characterized in that, The method for obtaining the target characteristic value corresponding to the tth monitoring moment includes: The fitting pH data corresponding to the tth monitoring moment is obtained by fitting all the data in the characteristic pH window, the absolute value of the difference between the fitting pH data and the pH data to be analyzed corresponding to the tth monitoring moment is recorded as a characteristic difference value, the ratio of the characteristic difference value to the fitting pH data is recorded as a relative deviation degree, and the product of the relative deviation degree and the initial characteristic value is recorded as a target characteristic value corresponding to the tth monitoring moment.

7. A process for the production of a chicory composite preparation according to claim 1, characterized in that, The method for obtaining the pH data to be analyzed corresponding to any monitoring moment comprises the following steps: For any monitoring moment in the production process of the chicory compound preparation, the pH data collected by the sensor at the monitoring moment is normalized and recorded as the denoised pH data corresponding to the monitoring moment, and the denoised pH data corresponding to the monitoring moment is denoised to obtain the pH data to be analyzed corresponding to the monitoring moment.

8. A process for the production of a chicory composite preparation according to claim 7, characterized in that, The method for denoising the pH data to be analyzed corresponding to the monitoring moment comprises the following steps: The absolute value of the difference between the denoised pH data corresponding to the monitoring moment and the target pH data corresponding to the monitoring moment before the monitoring moment is normalized to obtain a first evaluation value, the pH data corresponding to the monitoring moment is predicted according to the target pH data corresponding to the monitoring moment before the monitoring moment to obtain predicted pH data corresponding to the monitoring moment, the absolute value of the difference between the predicted pH data corresponding to the monitoring moment and the denoised pH data corresponding to the monitoring moment is normalized to obtain a second evaluation value, the average of the first evaluation value and the second evaluation value is recorded as a comprehensive evaluation value, and it is determined whether the comprehensive evaluation value is greater than a preset noise threshold value; if yes, the denoised pH data corresponding to the monitoring moment is denoised, and the data obtained after denoising is recorded as the pH data to be analyzed corresponding to the monitoring moment; and if no, the denoised pH data corresponding to the monitoring moment is directly recorded as the pH data to be analyzed corresponding to the monitoring moment.

Images