Data processing method for monitoring production of sodium chondroitin sulfate

Abstract

The invention discloses a data processing method for sodium chondroitin sulfate production monitoring, relates to the technical field of sodium chondroitin sulfate preparation, and solves the technical problem that various detection data are not accurate enough due to the fact that various detection data are affected by factors in the production process in the existing sodium chondroitin sulfate production process. The method comprises the following steps: 1, acquiring raw material data and control data corresponding to a precipitation stage in the production of sodium chondroitin sulfate; step 2, inputting the raw material data and the control data into a precipitation amount estimation model to obtain an estimated precipitation amount of sodium chondroitin sulfate at each set node; 3, generating an adhesion influence coefficient according to the estimated precipitation amount; 4, acquiring set position data of each detection device, and generating a parameter fluctuation range according to the set position and the adhesion influence coefficient; and step 5, acquiring detection data detected by each detection device, and generating a detection result according to the detection data, the control data and the parameter fluctuation range, thereby ensuring the accuracy of the detection result.

Description

Technical Field

[0001] The present invention belongs to the technical field of sodium chondroitin sulfate preparation, and relates to sodium chondroitin sulfate preparation technology, and specifically to a data processing method for sodium chondroitin sulfate production monitoring. Background Art

[0002] Sodium chondroitin sulfate is rich in a large number of biological functions and has a wide range of uses in clinical medicine. In the existing preparation process of sodium chondroitin sulfate, cartilage tissues such as the larynx, nasal bones, and trachea of ​​pigs are usually used as raw materials, and the products are obtained through reaction extraction processes such as alkaline hydrolysis, salt hydrolysis, and enzymatic hydrolysis, and precipitation. Taking the extraction of sodium chondroitin sulfate from pig cartilage as a raw material as an example, the specific reaction extraction process mainly includes leaching stage, enzymatic hydrolysis stage, adsorption stage, and precipitation stage. Among them, in the leaching stage, NaOH is used to stir, dissolve and filter the pig cartilage residue, and hydrochloric acid is added to the filtrate to neutralize the alkalinity to adjust the pH value to weak alkalinity; in the enzymatic hydrolysis stage, pancreatic enzyme is added for hydrolysis, and the temperature is controlled. The hydrolysis time is usually about 7 hours, and NaOH is added at any time to adjust the pH value; in the adsorption stage, hydrochloric acid is added after the hydrolysis is completed to make the pH value neutral, kaolin and activated carbon are added for adsorption, stirred and adjusted the pH value, and after the adsorption is completed, the pH value is adjusted to weak acidity and precipitated and filtered; in the precipitation stage, NaOH is added to the filtrate to adjust the neutrality and sodium chloride solution is added to dissolve and filter until clear, and ethanol is added and stirred and then allowed to stand for more than 8 hours to produce sodium chondroitin sulfate precipitation product.

[0003] In the existing sodium chondroitin sulfate production process, it is necessary to monitor data such as temperature and pH value in the production process to judge the reaction progress and reaction state of the corresponding reaction stage. However, the temperature detection equipment and pH value detection equipment in the existing chondroitin sulfate production equipment are often arranged inside the reaction equipment and directly contact the reaction medium. Precipitation will be generated during the production of sodium chondroitin sulfate. These precipitations will adhere to the sensor. Especially when a large amount of sodium chondroitin sulfate is produced at one time, the precipitation adhesion is more serious, resulting in fluctuations in the temperature and pH value detected by the detection equipment. This not only reduces the accuracy of the temperature and pH value data, but also further affects the accuracy of the reaction progress and state judged based on these data. Therefore, a data processing method for sodium chondroitin sulfate production monitoring is required. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a data processing method for sodium chondroitin sulfate production monitoring, which is used to solve the technical problem that various test data of the existing sodium chondroitin sulfate during the production process are affected by factors in the production process, making the various test data inaccurate.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a data processing method for monitoring the production of sodium chondroitin sulfate, comprising the following steps:

[0006] Step 1: Obtain the raw material data and control data corresponding to the precipitation stage of this sodium chondroitin sulfate production;

[0007] Step 2: Inputting raw material data and control data into the precipitation amount estimation model to obtain the estimated precipitation amount of sodium chondroitin sulfate at each set node;

[0008] Step 3: Generate adhesion influence coefficient based on estimated sedimentation amount;

[0009] Step 4: Obtain the setting position data of each testing device, and generate the parameter fluctuation range according to the setting position and adhesion influence coefficient;

[0010] Step 5: Obtain the test data detected by each test device, and generate the test results based on the test data, control data and parameter fluctuation range.

[0011] Due to the serious precipitation adhesion in the production of sodium chondroitin sulfate, the temperature and pH value detected by the detection equipment will fluctuate. These temperature fluctuations may be caused by the precipitation adhesion on the detection equipment or by abnormal reactions. They need to be distinguished in time and handled accordingly.

[0012] The present application obtains the raw material data and control data corresponding to the precipitation stage of the sodium chondroitin sulfate production; estimates the precipitation amount of sodium chondroitin sulfate at each node in the precipitation stage according to the raw material data and the control data; generates an adhesion influence coefficient according to the estimated precipitation amount; and obtains the setting position data of each detection device, and generates the position influence coefficient of the corresponding detection device according to the device position data; adjusts the originally set normal fluctuation range according to the adhesion influence coefficient and the position influence coefficient to obtain the corresponding parameter fluctuation range; generates the normal range of the corresponding node using the parameter fluctuation range, and finally uses the normal range to evaluate the detection value obtained by the detection; by taking the precipitation influence into account within the normal fluctuation range of the detection data, the normal fluctuation range is more applicable, and the problem of reduced accuracy of detection data evaluation due to precipitation adhesion is solved.

[0013] Preferably, the precipitation amount estimation model is obtained by training an artificial intelligence model, including:

[0014] Acquire some historical data, extract raw material data, control data and precipitation amount generation curve in the precipitation stage from the historical data; acquire set nodes, and acquire corresponding node precipitation amounts on the precipitation amount generation curve according to the set nodes; integrate the raw material data, control data and several node precipitation amounts in some historical data into several groups of training data and test data;

[0015] The artificial intelligence model is trained using the training data; the trained artificial intelligence model is tested using the test data to obtain an artificial intelligence model whose input is raw material data and control data, and whose output is the sedimentation amount of several nodes; the sedimentation amount of each node is output as the estimated sedimentation amount of the corresponding set node to obtain a sedimentation amount estimation model; wherein the artificial intelligence model includes a BP neural network model and a RBF neural network model.

[0016] Preferably, generating the adhesion influence coefficient according to the estimated precipitation amount includes:

[0017] Get the estimated precipitation amount of each setting node and mark it as YCi, where i is the number of the setting node; the first setting node at the beginning of the precipitation stage is numbered 1;

[0018] By formula The adhesion influence coefficient NFi corresponding to the set node numbered i is calculated; where α is the adjustment coefficient and KFC is the amount of deposit that can be attached to the detection equipment.

[0019] Preferably, the step 4 comprises the following steps:

[0020] S41: Acquire the setting position data of each sensor; extract the device height and the device axis distance in the setting position data;

[0021] S42: Generate a position influence coefficient according to the equipment height and the axis distance;

[0022] S43: Generate parameter fluctuation ranges of each detection device at each setting node according to the position influence coefficient and the adhesion influence coefficient.

[0023] Preferably, generating the position influence coefficient according to the equipment height and the axis distance includes:

[0024] The height of the equipment is marked as SH; the distance of the equipment axis is marked as SZ;

[0025] By formula The position influence coefficient WY of the corresponding detection equipment is calculated; among them, β1 and β2 are proportional coefficients, which are used to adjust the proportional relationship between the equipment height and the equipment axis distance on the attachment; GH is the total height of the reaction equipment; ZZ reflects the maximum axis distance of the equipment.

[0026] Preferably, generating the parameter fluctuation range of each detection device of each setting node according to the position influence coefficient and the adhesion influence coefficient includes:

[0027] Obtain the position influence coefficient WY corresponding to each detection device and the adhesion influence coefficient NFi of each set node;

[0028] By formula JZB i =SB+(γ1×WY+γ2×NF i )×KTB is used to calculate the parameter fluctuation range JZBi of the setting node numbered i; where SB is the normal fluctuation range of the original setting of the corresponding detection equipment; γ1 and γ2 are proportional coefficients; and KTB is the adjustable fluctuation range of the corresponding detection equipment.

[0029] Preferably, generating the test result according to the test data, the control data and the parameter fluctuation range includes:

[0030] Extract the detection value corresponding to each detection device in the detection data, extract the control value corresponding to each detection device in the control data, and the parameter fluctuation range of each detection device corresponding to each setting node;

[0031] Generate the normal range of the corresponding testing equipment at each set node according to the control value and parameter fluctuation range corresponding to the same testing equipment;

[0032] Obtain the normal range of each set node of each detection device, and determine in turn whether the detection value of the current set node of the detection device is within the normal range corresponding to the set node; if yes, mark the node detection result of the corresponding detection device at the set node as normal; if no, mark the node detection result of the corresponding detection device at the set node as abnormal;

[0033] Obtain the node detection results corresponding to the currently set nodes and previously set nodes of each detection device;

[0034] When the node detection results of the detection devices of the same device type as the set number of the currently set nodes are abnormal, the detection value of the corresponding detection device is set to the abnormal value, and the detection result of the corresponding detection device is set to abnormal;

[0035] When the number of abnormal node detection results corresponding to each set node of any detection device exceeds the node abnormality number threshold, the detection device is set as an abnormal device.

[0036] Preferably, generating the normal range of the corresponding detection device at each set node according to the control value and parameter fluctuation range corresponding to the same detection device includes:

[0037] Get the control value of the corresponding setting node of the detection equipment, marked as KS, and its corresponding parameter fluctuation range JZBi

[0038] The lower limit value of the normal range of the detection device at the corresponding setting node is calculated by the formula ZXi=KS-JZBi; the upper limit value of the normal range of the detection device at the corresponding setting node is calculated by the formula ZSi=KS+JZBi; the lower limit of the normal range and the upper limit of the normal range are integrated into the normal range of the corresponding setting node of the detection device.

[0039] Compared with the prior art, the beneficial effects of this application are:

[0040] 1. The present application obtains the raw material data and control data corresponding to the precipitation stage of the sodium chondroitin sulfate production; estimates the precipitation amount of sodium chondroitin sulfate at each node in the precipitation stage according to the raw material data and the control data; generates an adhesion influence coefficient according to the estimated precipitation amount; and obtains the setting position data of each detection device, and generates the position influence coefficient of the corresponding detection device according to the device position data; adjusts the originally set normal fluctuation range according to the adhesion influence coefficient and the position influence coefficient to obtain the corresponding parameter fluctuation range; generates the normal range of the corresponding node using the parameter fluctuation range, and finally uses the normal range to evaluate the detection value obtained by the detection; by taking the precipitation influence into account within the normal fluctuation range of the detection data, the normal fluctuation range is more applicable, and the problem of reduced accuracy of detection data evaluation due to precipitation adhesion is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 This is a schematic diagram of the steps of the data processing method for detecting the generation of sodium chondroitin sulfate in this application;

[0043] Figure 2 A flow chart is provided for generating the parameter fluctuation range for this application. DETAILED DESCRIPTION

[0044] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0045] See also Figure 1 The first aspect of the present application provides a data processing method for monitoring the production of sodium chondroitin sulfate, comprising the following steps:

[0046] Step 1: Obtain the raw material data and control data corresponding to the precipitation stage of the sodium chondroitin sulfate production. The raw material data include several main raw materials in the precipitation stage and their corresponding planned raw material usage, such as the planned usage of cartilage tissue; the control data in the precipitation stage include control temperature and pH value;

[0047] Step 2: Input the raw material data and control data into the precipitation amount estimation model to obtain the estimated precipitation amount of sodium chondroitin sulfate at each set node; the precipitation amount estimation model is a model trained based on historical data for estimating the precipitation amount at each stage of the precipitation process; the estimated precipitation amount is the estimated precipitation amount produced at the corresponding node under the raw material and control conditions;

[0048] Step 3: Generate an adhesion influence coefficient based on the estimated precipitation amount; the adhesion influence coefficient is the influence of the precipitation amount on the precipitation particles attached to the detection device. The larger the adhesion influence coefficient, the greater the probability of precipitation particles adhering to the corresponding detection device;

[0049] Step 4: Obtain the setting position data of each testing device, and generate a parameter fluctuation range according to the setting position and the adhesion influence coefficient; the parameter fluctuation range is the normal fluctuation of the test data of each testing device at each setting node;

[0050] Step 5: Obtain the test data detected by each test device, and generate the test results according to the test data, control data and parameter fluctuation range; the test equipment includes temperature detection equipment and pH value detection equipment, etc.

[0051] Since the precipitation adhesion is serious in the one-time large-scale production process of sodium chondroitin sulfate, the temperature and pH value detected by the detection equipment will fluctuate, and these temperature fluctuations may be caused by the precipitation adhesion on the detection equipment, or by abnormal reactions, and need to be distinguished in time and processed accordingly; this embodiment obtains the raw material data and control data corresponding to the precipitation stage of this sodium chondroitin sulfate production; estimates the precipitation amount of sodium chondroitin sulfate at each node in the precipitation stage according to the raw material data and the control data; generates the adhesion influence coefficient according to the estimated precipitation amount; and obtains the setting position data of each detection device, and generates the position influence coefficient of the corresponding detection device according to the device position data; adjusts the originally set normal fluctuation range according to the adhesion influence coefficient and the position influence coefficient to obtain the corresponding parameter fluctuation range; generates the normal range of the corresponding node using the parameter fluctuation range, and finally uses the normal range to evaluate the detection value obtained by the detection; by taking the precipitation influence into account within the normal fluctuation range of the detection data, the normal fluctuation range is more applicable, solves the problem of reduced accuracy of detection data evaluation due to precipitation adhesion, and enables timely processing when abnormal test data occurs, thereby improving the subsequent production efficiency of sodium chondroitin sulfate.

[0052] The precipitation amount estimation model is obtained through artificial intelligence model training, including: obtaining a number of historical data, extracting raw material data, control data and precipitation amount generation curve in the precipitation stage from the historical data; the precipitation amount production curve is a precipitation amount change curve over time integrated with the precipitation amount of sodium chondroitin sulfate at each time point in the production process of sodium chondroitin sulfate corresponding to the historical data;

[0053] Obtain the set node, and obtain the corresponding node precipitation amount on the precipitation amount generation curve according to the set node; integrate the raw material data, control data and several node precipitation amounts in several historical data into several groups of training data and test data;

[0054] Use training data to train the artificial intelligence model; use test data to test the trained artificial intelligence model; specifically input the raw material data and control data in the test data into the trained artificial intelligence model to obtain the node sedimentation amount of each set node; determine whether the difference between the node sedimentation amount of each set node recorded in the test data and the node sedimentation amount of each corresponding output node is within an acceptable range; if so, it means that this group of test data has passed the test and the next group of test data is tested; if not, adjust the relevant parameters of the artificial intelligence and continue to use this group of test data for testing; until a set proportion of test data passes the test; at this time, obtain an artificial intelligence model with raw material data and control data as input and several node sedimentation amounts as output; output each node sedimentation amount as the estimated sedimentation amount of the corresponding set node to obtain a sedimentation amount estimation model; wherein, the artificial intelligence model includes a BP neural network model and an RBF neural network model.

[0055] It is understandable that the artificial intelligence model needs to be trained in advance, and the set nodes can be nodes with fixed time intervals, or nodes set according to raw material data and control data. For example, the more raw materials there are, the greater the change in the amount of precipitation in a short period of time during the precipitation process; the more suitable the control data is for the optimal data of the reaction, the greater the change in the amount of precipitation in a short period of time; at this time, the time interval between the set nodes needs to be set shorter; so that the conditions affected by precipitation between the subsequently generated set nodes will not change abruptly, thereby reducing the probability of misjudgment of later detection data.

[0056] Generate an adhesion influence coefficient according to the estimated precipitation amount, including: obtaining the estimated precipitation amount of each setting node and marking it as YCi, where i is the number of the setting node; the number of the first setting node at the beginning of the precipitation stage is 1;

[0057] By formula The adhesion influence coefficient NFi corresponding to the set node numbered i is calculated; where α is the adjustment coefficient, the specific value is set according to experience, and KFC is the amount of deposit that can be attached to the detection equipment.

[0058] This embodiment calculates the adhesion influence coefficient corresponding to each setting node through the above formula. When the corresponding precipitation starts to be generated, the more precipitation is generated in the reaction device between each adjacent setting node, the greater the amount of precipitation attached to the corresponding detection device; the greater the impact on the fluctuation of subsequent detection values; therefore, this embodiment sets the corresponding adhesion influence coefficient to be larger.

[0059] See also Figure 2 , step four includes the following steps:

[0060] S41: Acquire the setting position data of each sensor; extract the device height and the device axis distance in the setting position data; the device height is the distance from the setting position of the corresponding detection device to the bottom of the reaction device, and the device axis distance is the distance from the setting position of the corresponding detection device to the inner center axis of the device, and the inner center axis can be a stirring shaft;

[0061] S42: generating a position influence coefficient according to the equipment height and the axis center distance; the position influence coefficient is the correlation between the position where the detection equipment is set and the precipitation adhesion situation, and the larger the position influence coefficient is, the greater the possibility of precipitation adhesion at the position where the corresponding detection equipment is set, and the greater the adhesion amount;

[0062] S43: Generate parameter fluctuation ranges of each detection device at each setting node according to the position influence coefficient and the adhesion influence coefficient.

[0063] Generate a position influence coefficient according to the equipment height and axis distance, including: marking the equipment height as SH; marking the equipment axis distance as SZ;

[0064] By formula The position influence coefficient WY of the corresponding detection equipment is calculated; where β1 and β2 are proportional coefficients, which are used to adjust the proportional relationship between the equipment height and the equipment axis distance on the attachment, and the specific values ​​are set according to experience; GH is the total height of the reaction equipment, that is, the height inside the reaction container; ZZ is the maximum axis distance of the reaction equipment, that is, the maximum distance from the inner surface of the reaction container to the axis.

[0065] This embodiment calculates the influence of the installation position of the detection equipment on the precipitation adhesion through the above formula. Since the density of the precipitation is generally greater than the density of the solution, precipitation particles will be generated at various positions in the solution. However, due to the difference in density, the precipitation particles will move to the lower end of the solution, causing the detection equipment located at the lower end of the solution to be more susceptible to precipitation adhesion; and, the general reaction device is a cylindrical cylinder with a stirring device, and the stirring device is located at the axial position. At this time, the farther the inner wall of the cylinder is from the axis, the weaker the solution's ability to flush the inner wall, and the easier it is for the corresponding precipitation to adhere; the larger the corresponding position influence coefficient is set.

[0066] Generate the parameter fluctuation range of each detection device at each setting node according to the position influence coefficient and the adhesion influence coefficient, including: obtaining the position influence coefficient WY corresponding to each detection device and the adhesion influence coefficient NFi of each setting node;

[0067] By formula JZB i =SB+(γ1×WY+γ2×NF i)×KTB calculates the parameter fluctuation range JZBi of the set node numbered i; wherein SB is the normal fluctuation range of the original setting of the corresponding detection equipment; the normal fluctuation range is the fluctuation range of the original setting that does not take into account the influence of precipitation adhesion on the detection equipment. At this time, the data within the fluctuation range is normal data; γ1 and γ2 are proportional coefficients, which are used to adjust the position influence coefficient and the adhesion influence coefficient to the same scale, and are also used to adjust the proportional relationship between the position influence coefficient and the adhesion influence coefficient, which plays both a regulating role and a weight distribution role. The specific value is set according to experience; KTB is the adjustable fluctuation range of the corresponding detection equipment; the parameter fluctuation range is the fluctuation range of the data collected by the corresponding detection equipment, and the data within the fluctuation range is normal data.

[0068] For example, if the normal fluctuation range of the temperature data is 1, and the set temperature is 50 degrees, then the temperature between 49 and 51 degrees is normal. If the influence of precipitation attachment is taken into account, the parameter fluctuation range is 1.32, then the temperature between 48.68 and 51.32 degrees is normal.

[0069] Generating a test result according to the test data, the control data and the parameter fluctuation range, including: extracting a test value corresponding to each test device in the test data, extracting a control value corresponding to each test device in the control data, and a parameter fluctuation range corresponding to each set node of each test device;

[0070] Generate the normal range of the corresponding testing equipment at each set node according to the control value and parameter fluctuation range corresponding to the same testing equipment;

[0071] Obtain the normal range of each set node of each detection device, and determine in turn whether the detection value of the current set node of the detection device is within the normal range corresponding to the set node; if yes, mark the node detection result of the corresponding detection device at the set node as normal; if no, mark the node detection result of the corresponding detection device at the set node as abnormal;

[0072] Obtain the node detection results corresponding to the currently set nodes and previously set nodes of each detection device;

[0073] When the node detection results of the detection devices of the same device type that exceed the set number at the current set node are abnormal, the detection value of the corresponding detection device is set to the abnormal value, and the detection result of the corresponding detection device is set to abnormal; for example, the control value of the pH value at a set node is 7, and its corresponding normal range is 6.6 to 7.4; at this time, the detection values ​​of 6 of the 10 pH value detection devices on the reaction device are not within the normal range, and the set number is 3, at this time, the detection result of the pH value detection of the corresponding node is abnormal;

[0074] When the number of abnormal node detection results corresponding to each set node of any detection device exceeds the node abnormality number threshold, the abnormality number threshold is set based on experience; at this time, the detection device is set as an abnormal device; when only individual devices have continuous abnormal detection data fluctuations, it means that there may be a problem with the detection device; in this embodiment, when the detection data fluctuations are abnormal due to the own reasons of some detection devices, the detection data of the abnormal devices are not considered in the subsequent detection data processing process, so as to reduce the amount of calculation and improve the efficiency of data processing.

[0075] According to the control values ​​and parameter fluctuation ranges corresponding to the same testing equipment, the normal range of the corresponding testing equipment at each set node is generated, including:

[0076] Get the control value of the corresponding setting node of the detection equipment, marked as KS, and its corresponding parameter fluctuation range JZBi

[0077] The lower limit value of the normal range of the detection device at the corresponding setting node is calculated by the formula ZXi=KS-JZBi; the upper limit value of the normal range of the detection device at the corresponding setting node is calculated by the formula ZSi=KS+JZBi; the lower limit of the normal range and the upper limit of the normal range are integrated into the normal range of the corresponding setting node of the detection device.

[0078] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0079] How this application works:

[0080] The present application obtains the raw material data and control data corresponding to the precipitation stage of the sodium chondroitin sulfate production; estimates the precipitation amount of sodium chondroitin sulfate at each node in the precipitation stage according to the raw material data and the control data; generates an adhesion influence coefficient according to the estimated precipitation amount; and obtains the setting position data of each detection device, and generates the position influence coefficient of the corresponding detection device according to the device position data; adjusts the originally set normal fluctuation range according to the adhesion influence coefficient and the position influence coefficient to obtain the corresponding parameter fluctuation range; generates the normal range of the corresponding node using the parameter fluctuation range, and finally uses the normal range to evaluate the detection value obtained by the detection; by taking the precipitation influence into account within the normal fluctuation range of the detection data, the normal fluctuation range is more applicable, and the problem of reduced accuracy of detection data evaluation due to precipitation adhesion is solved.

[0081] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. A data processing method for monitoring the production of sodium chondroitin sulfate, characterized in that: The following steps are involved: Step 1: Obtain the raw material data and control data corresponding to the precipitation stage of this sodium chondroitin sulfate production; Step 2: Inputting raw material data and control data into the precipitation amount estimation model to obtain the estimated precipitation amount of sodium chondroitin sulfate at each set node; Step 3: Generate adhesion influence coefficient based on estimated sedimentation amount; Step 4: Obtain the setting position data of each testing device, and generate the parameter fluctuation range according to the setting position and adhesion influence coefficient; Step 5: Obtain the test data detected by each test device, and generate the test results based on the test data, control data and parameter fluctuation range.

2. A data processing method for monitoring the production of sodium chondroitin sulfate according to claim 1, characterized in that: The precipitation amount estimation model is obtained through artificial intelligence model training, including: Acquire some historical data, extract raw material data, control data and precipitation amount generation curve in the precipitation stage from the historical data; acquire set nodes, and acquire corresponding node precipitation amounts on the precipitation amount generation curve according to the set nodes; integrate the raw material data, control data and several node precipitation amounts in some historical data into several groups of training data and test data; The artificial intelligence model is trained using training data; the trained artificial intelligence model is tested using test data; an artificial intelligence model is obtained whose input is raw material data and control data, and whose output is the sedimentation amount of several nodes; the sedimentation amount of each node is output as the estimated sedimentation amount of the corresponding set node, to obtain a sedimentation amount estimation model; wherein the artificial intelligence model includes a BP neural network model and a RBF neural network model.

3. A data processing method for monitoring the production of sodium chondroitin sulfate according to claim 1, characterized in that: The adhesion influence coefficient is generated according to the estimated precipitation amount, including: pH value Get the estimated precipitation amount of each setting node and mark it as YCi, where i is the number of the setting node; the first setting node at the beginning of the precipitation stage is numbered 1; By formula The adhesion influence coefficient NFi corresponding to the set node numbered i is calculated; where α is the adjustment coefficient and KFC is the amount of deposit that can be attached to the detection equipment.

4. A data processing method for monitoring the production of sodium chondroitin sulfate according to claim 1, characterized in that: The step 4 comprises the following steps: S41: Acquire the setting position data of each sensor; extract the device height and the device axis distance in the setting position data; S42: Generate a position influence coefficient according to the equipment height and the axis distance; S43: Generate parameter fluctuation ranges of each detection device at each setting node according to the position influence coefficient and the adhesion influence coefficient.

5. A data processing method for monitoring the production of sodium chondroitin sulfate according to claim 4, characterized in that: The generating of the position influence coefficient according to the equipment height and the axis distance includes: The height of the equipment is marked as SH; the distance of the equipment axis is marked as SZ; By formula The position influence coefficient WY of the corresponding detection equipment is calculated; among them, β1 and β2 are proportional coefficients; GH is the total height of the reaction equipment; and ZZ is the maximum axis distance of the reaction equipment.

6. A data processing method for monitoring the production of sodium chondroitin sulfate according to claim 4, characterized in that: The generating of the parameter fluctuation range of each detection device of each setting node according to the position influence coefficient and the adhesion influence coefficient includes: Obtain the position influence coefficient WY corresponding to each detection device and the adhesion influence coefficient NFi of each set node; By formula JZB i =SB+(γ1×WY+γ2×NF i )×KTB is used to calculate the parameter fluctuation range JZBi of the setting node numbered i; where SB is the normal fluctuation range of the original setting of the corresponding detection equipment; γ1 and γ2 are proportional coefficients; and KTB is the adjustable fluctuation range of the corresponding detection equipment.

7. A data processing method for monitoring the production of sodium chondroitin sulfate according to claim 1, characterized in that: The generating of the test result according to the test data, the control data and the parameter fluctuation range includes: Extract the detection value corresponding to each detection device in the detection data, extract the control value corresponding to each detection device in the control data, and the parameter fluctuation range of each detection device corresponding to each setting node; Generate the normal range of the corresponding testing equipment at each set node according to the control value and parameter fluctuation range corresponding to the same testing equipment; Obtain the normal range of each set node of each detection device, and determine in turn whether the detection value of the current set node of the detection device is within the normal range corresponding to the set node; if yes, mark the node detection result of the corresponding detection device at the set node as normal; if no, mark the node detection result of the corresponding detection device at the set node as abnormal; Obtain the node detection results corresponding to the currently set nodes and previously set nodes of each detection device; When the node detection results of the detection devices of the same device type as the set number of the currently set nodes are abnormal, the detection value of the corresponding detection device is set to the abnormal value, and the detection result of the corresponding detection device is set to abnormal; When the number of abnormal node detection results corresponding to each set node of any detection device exceeds the node abnormality number threshold, the detection device is set as an abnormal device.

8. A data processing method for monitoring the production of sodium chondroitin sulfate according to claim 7, characterized in that: The generating of the normal range of the corresponding detection device at each setting node according to the control value and parameter fluctuation range corresponding to the same detection device includes: Get the control value of the corresponding setting node of the detection equipment, marked as KS, and its corresponding parameter fluctuation range JZBi The lower limit value of the normal range of the detection device at the corresponding setting node is calculated by the formula ZXi=KS-JZBi; the upper limit value of the normal range of the detection device at the corresponding setting node is calculated by the formula ZSi=KS+JZBi; the lower limit of the normal range and the upper limit of the normal range are integrated into the normal range of the corresponding setting node of the detection device.

Images