Raw material mixing dynamic adjusting system and method for preparing chemical reagent

Abstract

The invention discloses a raw material mixing dynamic adjusting system and method for preparing a chemical reagent, and relates to the technical field of chemical reagent production. Comprising a data acquisition module, a mixing monitoring module, a monitoring analysis module and a real-time adjustment module, wherein the data acquisition module is used for acquiring the content uniformity of a finished chemical reagent mixed by mixing equipment last time, and comparing the content uniformity with a preset standard threshold value; if yes, extracting the last working data of the mixing equipment as a mixing scheme, and extracting mixing space environment data in the mixing process of the mixing equipment as a comparison scheme; the technical key points are as follows: the previous mixing effect is analyzed during use, the previous mixing effect is judged, when the previous mixing effect meets the standard, the previous data are continuously used, and if the previous mixing effect does not meet the standard, the existing constant mixing parameter setting mode is adjusted and modified, so that the mixing effect can be known in advance, and the mixing efficiency is improved. Corresponding personnel can conveniently manage, and the use effect is good.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of chemical reagent production, in particular to a raw material mixing dynamic adjustment system and method for preparing chemical reagents. BACKGROUND

[0002] Sewage treatment refers to the process of separating, transforming, or degrading pollutants in wastewater through physical, chemical, biological, and other means to make the water quality meet specific standards (such as discharge standards, reuse standards, or environmental acceptance standards). The core goal is to reduce the harm of pollutants to the environment and achieve the recycling or safe discharge of water resources.

[0003] In the sewage treatment system, sewage detection is an indispensable key link, providing data support and effect verification for the whole process of sewage treatment. There are many ways to detect sewage, among which the most common is to use chemical reagents to detect sewage.

[0004] Using chemical reagents to detect sewage refers to an analysis method that through specific chemical reactions between chemical reagents and target pollutants in wastewater, based on color changes, sediment generation, gas release, or other observable / quantifiable chemical phenomena, the type of pollutants is qualitatively judged or the concentration of pollutants is quantitatively determined.

[0005] In order to better produce chemical reagents, the whole process of chemical reagent production needs to be supervised and regulated. For this purpose, people have invented some corresponding management systems;

[0006] The existing patent No. CN115025706B, entitled "Inventive patent of a quantitative dosing control system for reagent mixing", records that it includes a host computer, the host computer transmits signals to the controller through a network transmission module, the controller controls multiple hydraulic cylinders to extend and retract through signal lines, the controller and the hydraulic cylinder are arranged at the top of the mixing bin, the controller controls the motor through the control line, the motor drives multiple conveying boxes in the mixing bin to rotate, the pump body structure in each conveying box respectively transports the reagent in one of the tanks to the mixing bin for mixing during the rotation of the conveying box, the end of the hydraulic cylinder controls the conveying rate of the pump body structure of each conveying box through the transmission structure to control the dosing amount of different reagents, and the present application can realize quantitative dosing control.

[0007] The central idea of the above-mentioned patent is to control multiple hydraulic cylinders to control the conveying rate of the pump body structure, and to achieve the purpose of controlling the conveying rate of the pump body structure. By controlling the conveying rate of the pump body structure, the multiple reagents are delivered in a fixed ratio. Such a control system is simpler and can achieve fixed-ratio reagent delivery, thereby facilitating the preparation of any total amount of reagent. While delivering the reagents in a fixed ratio, mixing can also be performed, thereby achieving mixing while preparing, saving the time for preparing the reagents.

[0008] But in actual use, not all of the medicaments in production only need a short mixing can be achieved uniform mixing, often need a certain reaction time, and need to use mixing equipment mixer cooperation, can realize the mixing of raw materials uniform, and the existing equipment for the weighing technology mature, it can realize the accurate proportioning of raw materials, and for subsequent mixing control is less, the scheme is according to the original set program runs, but in use the device exists loss, and the external environment exists change, using this kind of way makes the uniformity of the reagent produced exists certain change, need subsequent secondary stirring, more troublesome, for this, we developed a kind of preparation of chemical reagent raw material mixing dynamic adjustment system and method. SUMMARY

[0009] (One) solved technical problems

[0010] In view of the deficiencies of the prior art, the present application provides a kind of preparation of chemical reagent raw material mixing dynamic adjustment system and method, it is analyzed to the mixing effect of last time in use, judge the mixing effect of last time, when the mixing effect of last time meets the standard, use the data of last time, if it does not meet the standard, then adjust the modification of the mixing parameter setting mode of one constant, can understand the effect of mixing in advance, it is convenient for corresponding personnel to manage, overall use effect is good, with good use prospect, effectively solve the problems raised in the background art.

[0011] (Two) technical scheme

[0012] In order to achieve the above object, the present application is realized by the following technical scheme:

[0013] A kind of preparation of chemical reagent raw material mixing dynamic adjustment system, including data acquisition module, mixing monitoring module, monitoring analysis module and real-time adjustment module:

[0014] Data acquisition module: the content uniformity of finished chemical reagent of last time mixing of mixing equipment is collected, and the content uniformity is compared with preset standard threshold:

[0015] If it meets the requirement, the working data of last time of mixing equipment is extracted as mixing scheme, and the mixing space environment data in the mixing process of mixing equipment is extracted as comparison scheme;

[0016] If it does not meet the requirement, corresponding adjustment strategy is executed according to the adjustment interval corresponding to the content uniformity, generates mixing scheme, and adjusts the mixing space environment data of last time mixing, generates comparison scheme;

[0017] The mixed monitoring module: the mixed scheme is input into the mixing device, the device working data and the mixing space environment data during the mixing process are collected in real time, the device working data is analyzed, the difference value of the device working data is calculated, and the corresponding processing strategy is executed according to the size of the difference value and the standard value;

[0018] The monitoring analysis module: the change degree of the mixing space environment data and the data in the comparison scheme is calculated in real time, the abnormal score is generated, and the abnormal score is compared with the standard score:

[0019] If the abnormal score is greater than or equal to the standard score, the mixed scheme, the mixing space environment data and the comparison scheme are input into the dynamic prediction model to generate the working real-time adjustment coefficient, and the adjustment scheme is calculated;

[0020] If the abnormal score is less than the standard score, no processing is performed;

[0021] The real-time adjustment module: the adjustment scheme is obtained and input into the mixing device as a new mixed scheme, and the raw material mixing is performed.

[0022] Further, the content uniformity of the finished chemical reagent mixed by the mixing device last time is collected as follows:

[0023] Randomly collect N samples at different positions of the finished chemical reagent, N≥10;

[0024] The content of the target component in the sample is determined by a spectrum analysis method;

[0025] The content uniformity is calculated, and the specific formula is as follows:

[0026]

[0027] In the formula: JD is the content uniformity, A i is the content data of the target component in the i-th sample.

[0028] Further, the adjustment interval includes a normal adjustment interval (JD b -K, JD b ) and an abnormal adjustment interval [0, JD b -K], wherein JD b is a preset standard threshold;

[0029] If the content uniformity JD is less than JD b , if the content uniformity JD is located in the normal adjustment interval (JD b -K, JD b ), the real-time up-regulation ratio S of the mixing speed of the mixing device is calculated, and the specific formula is In the formula, ROUNDUP is the rounding up function, Tzxs is the adjustment conversion ratio, the mixing speed in the last working data of the mixing equipment is adjusted, and the adjusted working data is used as the mixing scheme;

[0030] When adjusting the mixing space environment data in the last mixing process of the mixing equipment, the real-time adjustment ratio S is multiplied by the conversion coefficient of the corresponding category to obtain the adjustment ratio of each category data of the mixing space environment, and the converted adjustment ratio is used to calculate the corresponding mixing space environment category data to form the comparison scheme;

[0031] If the content uniformity JD is in the abnormal adjustment interval [0, JD b -K], a maintenance warning is issued.

[0032] Further, the equipment working data includes stirring shaft speed, vibration data during mixing, motor working current, noise data and energy consumption data, and the mixing space environment data includes cavity temperature, cavity pressure, raw material density ratio and viscosity ratio.

[0033] Further, the step of analyzing the equipment working data to calculate the difference value of the equipment working data is as follows:

[0034] Classify the real-time collected equipment working data;

[0035] Compare the real-time working data with the same working time category data in the mixing scheme in turn, and calculate the difference value to obtain the basic difference value;

[0036] The calculated basic difference value is weighted to calculate the difference value YCz of the equipment working data, and the specific formula is as follows:

[0037]

[0038] In the formula, L is the number of basic difference values, CZ j is the jth basic difference value, Qz j is the weight coefficient corresponding to the jth basic difference value.

[0039] Further, the corresponding processing strategy according to the size of the difference value and the standard value is to compare the difference value with the standard value, if the difference value is less than the standard value, no processing is performed;

[0040] If the difference value is greater than or equal to the standard value, a maintenance warning is issued.

[0041] Further, the step of calculating the change degree of the mixing space environment data and the data in the comparison scheme in real time and generating an abnormal score based on the change degree is as follows:

[0042] Classify the real-time collected mixing space environment data;

[0043] Real-time comparison of the rate of change of each category data at the same mixing time point in the comparison scheme, and calculate the abnormal score based on the rate of change, the specific formula is as follows:

[0044]

[0045] In the formula, FYCz is the abnormal score, M is the number of categories of mixed space environment data, JCh X is the data of the Xth category of the mixing in real-time monitoring, JChs X is the data of the Xth category recorded at the same mixing time point in the comparison scheme, Fzb X is the conversion value between the Xth category rate of change and the abnormal score.

[0046] Further, the dynamic prediction model is a trained convolutional neural network model, and the training steps of the convolutional neural network are as follows:

[0047] Data collection and annotation: retrieve the latest P sets of historical mixing data sets, which include mixing schemes, mixing space environment data, comparison schemes and adjustment schemes;

[0048] Divide several sets of historical mixing data sets into training sets and validation sets;

[0049] Construct a convolutional neural network for regression task, use the data in the training set except the adjustment scheme as the input of the convolutional neural network, use the real-time adjustment coefficient recorded in the adjustment scheme as the output, train the convolutional neural network, and get the initial convolutional neural network;

[0050] Use the validation set to verify the initial convolutional neural network, use the mean square error evaluation index, output the initial convolutional neural network with test accuracy greater than or equal to the preset threshold, as the trained convolutional neural network.

[0051] Further, the adjustment scheme is adjusted by using the real-time adjustment coefficient, which contains L real-time adjustment coefficients, and the L real-time adjustment coefficients are used to modify the device working data in the future time in the mixing scheme, and the adjustment scheme is obtained after summarizing.

[0052] Further, a raw material mixing dynamic adjustment method for preparing chemical reagents comprises the following steps:

[0053] Collect the content uniformity of the finished chemical reagent mixed by the mixing equipment last time, and compare the content uniformity with the preset standard threshold:

[0054] If the requirements are met, the last working data of the mixing device is extracted as a mixing scheme, and the mixing space environment data during the mixing process of the mixing device is extracted as a comparison scheme;

[0055] If the requirements are not met, the corresponding adjustment strategy is executed according to the adjustment interval corresponding to the content uniformity, a mixing scheme is generated, and the mixing space environment data of the last mixing is adjusted to generate a comparison scheme;

[0056] The mixing scheme is input into the mixing device, the device working data and the mixing space environment data during the mixing process of the raw materials are collected in real time, the device working data is analyzed, the difference value of the device working data is calculated, and the corresponding processing strategy is executed according to the size of the difference value and the standard value;

[0057] The change degree of the mixing space environment data and the data in the comparison scheme is calculated in real time, an abnormal score is generated, and the abnormal score is compared with a standard score:

[0058] If the abnormal score is greater than or equal to the standard score, the mixing scheme, the mixing space environment data and the comparison scheme are input into a dynamic prediction model to generate a working real-time adjustment coefficient, and an adjustment scheme is calculated;

[0059] If the abnormal score is less than the standard score, no processing is performed;

[0060] The adjustment scheme is obtained and input into the mixing device as a new mixing scheme, and the raw material mixing is performed.

[0061] (Three) beneficial effects

[0062] The present application provides a raw material mixing dynamic adjustment system and method for preparing chemical reagents, which has the following beneficial effects:

[0063] 1. The raw material mixing dynamic adjustment system and method for preparing chemical reagents provided by the present application analyzes the mixing effect of the last time when in use, judges the mixing effect of the last time, uses the data of the last time when the mixing effect of the last time meets the standard, and adjusts and modifies the existing fixed mixing parameter setting mode when the mixing effect of the last time does not meet the standard. The mixing effect can be known in advance, the corresponding personnel can be conveniently managed, the overall use effect is good, and the use prospect is good.

[0064] 2. The raw material mixing dynamic adjustment system and method for preparing chemical reagents disclosed by the present application further analyzes when the mixing effect of the last time does not meet the requirements, judges whether the device is abnormal, adjusts the mixing data of the last time when there is no abnormality, formulates a mixing scheme, thereby realizing the pre-processing of the scheme, generating a comparison scheme capable of judging whether the mixing is abnormal, thereby conveniently monitoring the mixing of the subsequent device, having a good use effect, and having a good use prospect.

[0065] 3. The application discloses a raw material mixing dynamic adjustment system and method for preparing chemical reagents, which monitors the mixing of subsequent equipment based on a comparative scheme, further analyzes when the mixing space environment data is abnormal, generates a real-time working real-time adjustment coefficient, realizes dynamic adjustment in the raw material mixing process of chemical reagents, makes the mixing effect of raw materials better, has good use effect, and has good use prospect. BRIEF DESCRIPTION OF DRAWINGS

[0066] Figure 1 A flowchart of the raw material mixing dynamic adjustment system for preparing chemical reagents according to the application;

[0067] Figure 2 A flowchart of the raw material mixing dynamic adjustment method for preparing chemical reagents according to the application. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the application.

[0069] The central idea of the existing scheme is to control multiple hydraulic cylinders to control the conveying rate of the pump body structure, and the multiple drugs are delivered in a fixed ratio by controlling the conveying rate of the pump body structure. Such a control system is simpler and can realize fixed-ratio delivery of the drugs, so that the total amount of the drugs can be conveniently adjusted, and the drugs can be mixed while being delivered, so that the drugs can be mixed while being adjusted, thereby saving the time for adjusting the drugs.

[0070] However, in actual use, not all drugs need only short-term mixing during production to achieve uniform mixing. A certain reaction time is often required, and a stirrer in the mixing device needs to be used to achieve uniform mixing of raw materials. Moreover, the weighing technology of the existing device is mature, and it can achieve accurate proportioning of raw materials, but the control of subsequent mixing is less, and the scheme adopted is to run according to the original set program. However, the device is subject to wear during use, and the external environment changes. Using this method makes the uniformity of the produced reagents change to some extent, and secondary stirring is required, which is troublesome. Moreover, when adjusting, a small change in one part will cause a big change in the whole, and the adjustment parameters will have other situations, so further supervision and dynamic adjustment are required to ensure the adjustment effect.

[0071] Therefore, in the process of research and development, the initial condition of the equipment and the implementation work condition of the equipment need to be considered comprehensively, and comprehensive analysis is carried out, so that the uniform mixing of the chemical reagent raw materials can be realized.

[0072] Embodiment 1:

[0073] The hardware part of the raw material mixing dynamic adjustment system for preparing chemical reagents is based on the server and the mixing equipment of the existing production system, and the data collected is also extracted from the controller of the mixing equipment. The existing mixing equipment is provided with corresponding sensors, so that new data acquisition devices need not be separately added. Therefore, the cost of the whole system is relatively low.

[0074] The software part of the raw material mixing dynamic adjustment system for preparing chemical reagents includes a data acquisition module, a mixing monitoring module, a monitoring analysis module and a real-time adjustment module.

[0075] The data acquisition module acquires the content uniformity of the finished chemical reagents mixed by the mixing equipment last time, and compares the content uniformity with a preset standard threshold.

[0076] The step of acquiring the content uniformity of the finished chemical reagents mixed by the mixing equipment last time is as follows:

[0077] N samples are randomly collected at different positions of the finished chemical reagents, and N is greater than or equal to 10;

[0078] The content of the target component in the sample is determined by using a spectrum analysis method.

[0079] The content uniformity is calculated, and the specific formula is as follows:

[0080]

[0081] In the formula, JD is the content uniformity, A i is the data of the content of the target component in the i-th sample.

[0082] The higher the content uniformity is, the better the mixing effect is.

[0083] If the requirement is met, the working data of the mixing equipment last time is extracted as a mixing scheme, and the mixing space environment data in the mixing process of the mixing equipment is extracted as a comparison scheme.

[0084] This kind of situation indicates that the mixing is normal. In this case, the optimal choice is to use the scheme of the last mixing. The reason is that the sudden damage of the normal equipment rarely occurs when the equipment is used. Therefore, the effects of adjacent two mixings are close.

[0085] If not, the corresponding adjustment strategy is executed according to the adjustment interval corresponding to the content uniformity to generate a mixing scheme, and the mixing space environment data of the last mixing is adjusted to generate a comparison scheme.

[0086] This situation indicates that the device is aging or there are certain conditions that require adjustment to achieve the specified mixing time (faster mixing consumes more energy, so full-speed mixing is not used).

[0087] The device operating data includes stirring shaft speed, vibration data during mixing, motor operating current, noise data, and energy consumption data. The mixing space environment data includes cavity temperature, cavity pressure, raw material density ratio, and viscosity ratio.

[0088] The adjustment interval includes a normal adjustment interval (JD b -K, JD b ) and an abnormal adjustment interval [0, JD b -K], where JD b is a preset standard threshold.

[0089] The normal adjustment interval (JD b -K, JD b ) is close to the standard mixing effect, so the mixing effect can be ensured by appropriately increasing the mixing speed.

[0090] The abnormal adjustment interval [0, JD b -K] has poor mixing effect, so large-scale adjustment of the mixing speed is required. At this time, the energy consumption is high, and abnormal conditions such as excessive temperature may occur. Therefore, adjustment by adjusting the speed is not possible, and maintenance of the device is required.

[0091] If JD b , if the content uniformity JD is in the normal adjustment interval (JD b -K, JD b ), the real-time increase ratio S of the mixing speed of the mixing device is calculated, and the specific formula is where ROUNDUP is the upward rounding function, Tzxs is the adjustment conversion ratio, the mixing speed in the last working data of the mixing device is adjusted, and the adjusted working data is used as the mixing scheme.

[0092] When adjusting the mixing space environment data during the mixing process of the last mixing device, the real-time increase ratio S is multiplied by the conversion coefficient of the corresponding category to obtain the increase ratio of each category data of the mixing space environment. The converted increase ratio is used to calculate the corresponding mixing space environment category data to form a comparison scheme.

[0093] If the content uniformity JD is in the abnormal adjustment interval [0, JDb If the value of K] is greater than 0, a maintenance warning is sent out, and a corresponding warning is sent out by a buzzer or a sound-light alarm to remind relevant personnel to handle it.

[0094] In actual use, if there is no adjustment scheme, the content uniformity of the previous two times can also be compared to determine the change of the content uniformity and calculate the fluctuation of the content uniformity, so as to determine the stability of the equipment operation.

[0095] The raw material mixing dynamic adjustment system and method for preparing chemical reagents provided by the application can analyze the mixing effect of the previous time during use, determine the mixing effect of the previous time, use the data of the previous time if the mixing effect of the previous time meets the standard, adjust and modify the existing fixed mixing parameter setting mode if the mixing effect of the previous time does not meet the standard, can understand the mixing effect in advance, facilitate the management of the corresponding personnel, have good overall use effect, and have good use prospect.

[0096] When the mixing scheme is formulated, the mixing scheme is applied, and this process is based on the mixing monitoring module.

[0097] The mixing monitoring module: the mixing scheme is input into the mixing equipment, real-time collection of equipment working data and mixing space environment data of raw materials in the mixing process, analysis of the equipment working data, calculation of the difference value of the equipment working data, and execution of the corresponding processing strategy according to the size of the difference value and the standard value;

[0098] The step of analyzing the equipment working data and calculating the difference value of the equipment working data is as follows:

[0099] The real-time collected equipment working data is classified;

[0100] The real-time working data is compared with the data of the same working time corresponding category in the mixing scheme in turn, and the difference value is calculated to obtain the basic difference value;

[0101] The calculated basic difference value is weighted processed, and the difference value YCz of the equipment working data is calculated, and the specific formula is as follows:

[0102]

[0103] In the formula, L is the number of basic difference values, CZ j is the jth basic difference value, Qz j is the weight coefficient corresponding to the jth basic difference value.

[0104] CZ j ≥ 0, CZ j is the difference value between the real-time working data and the data of the same working time corresponding category in the mixing scheme, which is obtained by subtracting a smaller number from a larger number.

[0105] The difference value of the working data of the computing device is mainly used to analyze whether the device is abnormal and whether the mixing is supported to continue.

[0106] The corresponding processing strategy is executed according to the size of the difference value and the standard value, that is, the difference value is compared with the standard value, if the difference value is less than the standard value, no processing is performed;

[0107] If the difference value is greater than or equal to the standard value, a maintenance warning is issued, and at this time, maintenance is performed, and mixing is not performed.

[0108] When the device supports mixing, the raw materials are mixed, and in order to ensure the effect of mixing, the process of mixing needs to be further supervised at this time, and this step relies on the monitoring and analysis module.

[0109] The application discloses a raw material mixing dynamic adjustment system and method for preparing chemical reagents, which further analyzes when the mixing effect of the last time does not meet the requirements, judges whether the device is abnormal, and adjusts the mixing data of the last time when there is no abnormality, and formulates a mixing scheme, thereby realizing the pre-processing of the scheme, and generating a comparison scheme capable of judging whether the mixing is abnormal, thereby facilitating the supervision of the mixing of subsequent devices, and having good use effect and good use prospect.

[0110] The monitoring and analysis module: real-time calculation of the change degree of the mixing space environment data and the data in the comparison scheme, generation of an abnormal score, and comparison of the abnormal score with a standard score:

[0111] If the abnormal score is greater than or equal to the standard score, the mixing scheme, the mixing space environment data and the comparison scheme are input into a dynamic prediction model to generate a working real-time adjustment coefficient, and an adjustment scheme is calculated;

[0112] If the abnormal score is less than the standard score, no processing is performed;

[0113] The step of real-time calculation of the change degree of the mixing space environment data and the data in the comparison scheme, and generation of an abnormal score based on the change degree is as follows:

[0114] Classify the real-time collected mixing space environment data;

[0115] Real-time comparison of the change rate of each category data at the mixing time point in this and the comparison scheme, and calculation of the abnormal score based on the change rate, and the specific formula is as follows:

[0116]

[0117] In the formula, FYCz is the abnormal score, M is the number of categories of the mixing space environment data, JCh X is the data of the Xth category of this mixing, JChs XFzb X The conversion value between the Xth category change rate and the anomaly score.

[0118] The higher the anomaly score, the more serious the anomaly, which requires further adjustment.

[0119] In order to improve the accuracy of adjustment, a dynamic prediction model that can be continuously optimized is used.

[0120] The dynamic prediction model is a trained convolutional neural network model, and the training steps of the convolutional neural network are as follows:

[0121] Data collection and labeling: retrieve the latest P sets of historical mixed data sets, which include mixed schemes, mixed space environment data, comparison schemes and adjustment schemes;

[0122] Divide several sets of historical mixed data sets into training sets and validation sets;

[0123] Build a convolutional neural network for regression task, use the data in the training set except the adjustment scheme as the input of the convolutional neural network, and use the work real-time adjustment coefficient recorded in the adjustment scheme as the output, train the convolutional neural network, and get the initial convolutional neural network;

[0124] Use the validation set to verify the initial convolutional neural network, use the mean square error evaluation index, output the initial convolutional neural network with a test accuracy greater than or equal to a preset threshold, as a trained convolutional neural network.

[0125] Calculate the adjustment scheme using the work real-time adjustment coefficient, which contains L real-time adjustment coefficients, and use the L real-time adjustment coefficients to modify the device work data in the future time in the mixed scheme, and then get the adjustment scheme after summarizing.

[0126] This process needs to be adjusted for each category, so a computer model is used for analysis, which has high accuracy and fast analysis speed, and good effect.

[0127] When generating the adjustment scheme, the parameters of the mixing device need to be adjusted using the adjustment scheme, and this step depends on the real-time adjustment module.

[0128] The application discloses a raw material mixing dynamic adjustment system and method for preparing chemical reagents, which supervises the mixing of subsequent devices based on comparison schemes, and further analyzes when the mixing space environment data is abnormal, generates real-time work real-time adjustment coefficient, realizes dynamic adjustment in the raw material mixing process of chemical reagents, and has better mixing effect and use effect, and has good use prospect.

[0129] Real-time adjustment module: obtain the adjustment scheme and enter the mixing device as a new mixing scheme to execute the raw material mixing.

[0130] The weight coefficient involved in the above formula is determined by the coefficient of variation method. The coefficient of variation method is a method of weighting each index according to the variation degree of the current value and the target value of each evaluation index. If the numerical difference of an index is large, the index can clearly distinguish each evaluated object, indicating that the index has rich discrimination information, and thus the index should be given a larger weight. Conversely, if the numerical difference of each evaluated object on an index is small, the index has weak ability to distinguish each evaluated object, and thus the index should be given a smaller weight. This method directly utilizes the information contained in each index and obtains the weight of the index by calculation, and thus is objective.

[0131] Embodiment 2:

[0132] On the basis of Embodiment 1, as shown in Figure 2 this embodiment describes a raw material mixing dynamic adjustment method for preparing chemical reagents, comprising the following steps:

[0133] Collecting the content uniformity of the finished chemical reagent mixed by the mixing device last time, and comparing the content uniformity with the preset standard threshold value:

[0134] If the requirement is met, the working data of the mixing device last time is extracted as a mixing scheme, and the mixing space environment data in the mixing process of the mixing device is extracted as a comparison scheme;

[0135] If the requirement is not met, the corresponding adjustment strategy is executed according to the adjustment interval corresponding to the content uniformity, a mixing scheme is generated, and the mixing space environment data of the last mixing is adjusted to generate a comparison scheme;

[0136] The mixing scheme is entered into the mixing device, the device working data and the mixing space environment data in the mixing process of the raw materials are collected in real time, the device working data is analyzed, the difference value of the device working data is calculated, and the corresponding processing strategy is executed according to the size of the difference value and the standard value;

[0137] The change degree of the mixing space environment data and the data in the comparison scheme is calculated in real time, an abnormal score is generated, and the abnormal score is compared with a standard score:

[0138] If the abnormal score is greater than or equal to the standard score, the mixing scheme, the mixing space environment data and the comparison scheme are input into a dynamic prediction model to generate a working real-time adjustment coefficient, and an adjustment scheme is calculated;

[0139] If the abnormal score is less than the standard score, no processing is performed;

[0140] The adjustment scheme is obtained and recorded in the mixing device as a new mixing scheme to perform raw material mixing.

[0141] In the present application, the several formulas involved are dimensionless values, and the establishment of the formulas is based on a large amount of data collected by software simulation to obtain a formula closest to the real situation. Some coefficients or weights in the formulas are set by the person skilled in the art according to the actual situation, and therefore, no further description is given here.

[0142] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solutions.

[0143] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0144] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A system for dynamically adjusting raw material mixing for preparing chemical reagents, characterized by: include: Data acquisition module: collects the content uniformity of the finished chemical reagents mixed on the mixing equipment and compares the content uniformity with the preset standard threshold: If the requirements are met, the previous working data of the mixing equipment is extracted as the mixing scheme, and the mixing space environment data of the mixing equipment during the mixing process is extracted as the comparison scheme; If it does not meet the requirements, the corresponding adjustment strategy is executed according to the adjustment interval corresponding to the content uniformity to generate a mixing plan, and the mixing space environment data of the previous mixing is adjusted to generate a comparison plan; Mixing monitoring module: Input the mixing plan into the mixing equipment, collect the equipment working data and mixing space environment data of the raw materials in real time during the mixing process, analyze the equipment working data, calculate the difference value of the equipment working data, and execute the corresponding processing strategy according to the size of the difference value and the standard value; Monitoring and Analysis Module: Calculates the degree of change between the mixed space environment data and the data in the comparison scheme in real time, generates anomaly scores, and compares the anomaly scores with the standard scores: If the abnormal score is greater than or equal to the standard score, the mixed scheme, mixed space environment data and comparison scheme are input into the dynamic prediction model to generate the real-time adjustment coefficient and calculate the adjustment scheme; If the abnormal score is less than the standard score, no processing will be done; Real-time adjustment module: obtains the adjustment plan and enters it into the mixing equipment as a new mixing plan to perform raw material mixing.

2. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 1, characterized in that: The steps for collecting the content uniformity of the finished chemical reagents mixed in the mixing equipment are as follows: Randomly collect N samples from different locations of the finished chemical reagents, N ≥ 10; Spectral analysis is used to determine the content of target components in the sample; Calculate the content uniformity, the specific formula is as follows: Where: JD is the content uniformity, A i is the data of the content of the target component in the i-th sample.

3. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 2, characterized in that: The adjustment range includes the normal adjustment range (JD b -K,J.D. b ) and abnormal adjustment interval [0, JD b -K], where JD b is the preset standard threshold; Does not meet the requirements for JD<JD b If the content uniformity JD is within the normal adjustment range (JD b -K,J.D. b ), the real-time increase ratio S of the mixing speed of the mixing equipment is calculated. The specific formula is: Where ROUNDUP is the rounding up function, Tzxs is the adjustment conversion ratio, the mixing speed in the previous working data of the mixing equipment is adjusted, and the adjusted working data is used as the mixing plan; When adjusting the mixing space environment data during the last mixing process of the mixing equipment, the real-time upward adjustment ratio S is multiplied by the conversion coefficient of the corresponding category to obtain the upward adjustment ratio of each category of the mixing space environment data. The converted upward adjustment ratio is used to calculate the corresponding data of each category of the mixing space environment to form a comparison scheme; If the content uniformity JD is in the abnormal adjustment range [0, JD b -K], a maintenance warning is issued.

4. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 3, characterized in that: The equipment working data includes the stirring shaft speed, vibration data during mixing, motor working current, noise data and energy consumption data; the mixing space environment data includes the cavity temperature, cavity pressure, density ratio and viscosity ratio of the raw materials.

5. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 4, characterized in that: The steps to analyze the equipment working data and calculate the difference value of the equipment working data are as follows: Classify the equipment working data collected in real time; Compare the real-time working data with the corresponding category data of the same working time in the hybrid solution, calculate the difference, and obtain the basic difference value; The calculated basic difference value is weighted to calculate the difference value YCz of the equipment working data. The specific formula is as follows: Where L is the number of basic difference values, CZ j is the jth basic difference value, Qz j is the weight coefficient corresponding to the j-th basic difference value.

6. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 5, characterized in that: The corresponding processing strategy is executed according to the size of the difference value and the standard value. The difference value is compared with the standard value. If the difference value is smaller than the standard value, no processing is performed. If the difference value is greater than or equal to the standard value, a maintenance warning will be issued.

7. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 6, characterized in that: The steps for calculating the degree of change between the mixed space environment data and the data in the comparison scheme in real time and generating anomaly scores based on the degree of change are as follows: Classify the mixed spatial environment data collected in real time; Compare the change rates of each category of data at the same mixing time point in this and comparison scenarios in real time, and calculate the anomaly score based on the change rate. The specific formula is as follows: Where FYCz is the anomaly score, M is the number of categories of mixed spatial environment data, JCh X For the real-time monitoring of the mixed X-th category data, JChs X For the Xth category data recorded at the same mixing time point in the comparison scheme, Fzb X is the conversion value between the X-th category change rate and the anomaly score.

8. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 7, characterized in that: The dynamic prediction model is a trained convolutional neural network model. The training steps of the convolutional neural network are as follows: Data collection and annotation: Retrieve the most recent P groups of historical mixed data sets, which include mixed schemes, mixed spatial environment data, comparison schemes, and adjustment schemes. Divide several sets of historical mixed data sets into training sets and validation sets; Construct a convolutional neural network to perform the regression task. Use the data in the training set excluding the adjustment plan as the input of the convolutional neural network, use the real-time adjustment coefficient recorded in the adjustment plan as the output, train the convolutional neural network, and obtain an initial convolutional neural network. The initial convolutional neural network is model verified using the validation set, and the mean square error evaluation index is used to output the initial convolutional neural network with a test accuracy greater than or equal to the preset threshold as the trained convolutional neural network.

9. A system for dynamically adjusting raw material mixing for preparing chemical reagents according to claim 8, characterized in that: The calculated adjustment plan is to use the real-time working adjustment coefficient. The real-time working adjustment coefficient includes L real-time adjustment coefficients. The L real-time adjustment coefficients are used to correct the equipment working data in the future time in the mixed plan, and the adjustment plan is obtained after summarizing.

10. A method for dynamically adjusting raw material mixing for preparing chemical reagents, using the system according to any one of claims 1 to 9, characterized in that: The steps include: Collect the content uniformity of the finished chemical reagents mixed on the mixing equipment and compare the content uniformity with the preset standard threshold: If the requirements are met, the previous working data of the mixing equipment is extracted as the mixing scheme, and the mixing space environment data of the mixing equipment during the mixing process is extracted as the comparison scheme; If it does not meet the requirements, the corresponding adjustment strategy is executed according to the adjustment interval corresponding to the content uniformity to generate a mixing plan, and the mixing space environment data of the previous mixing is adjusted to generate a comparison plan; Input the mixing plan into the mixing equipment, collect the equipment working data and mixing space environment data of the raw materials in real time during the mixing process, analyze the equipment working data, calculate the difference value of the equipment working data, and execute the corresponding processing strategy according to the size of the difference value and the standard value; Calculate the degree of change between the mixed space environment data and the data in the comparison scheme in real time, generate anomaly scores, and compare the anomaly scores with the standard scores: If the abnormal score is greater than or equal to the standard score, the mixed scheme, mixed space environment data and comparison scheme are input into the dynamic prediction model to generate the real-time adjustment coefficient and calculate the adjustment scheme; If the abnormal score is less than the standard score, no processing will be done; The adjustment plan is obtained and entered into the mixing equipment as a new mixing plan to perform raw material mixing.

Images