CN116008379B - Automatic titration system, method and device based on model fitting and machine learning - Google Patents
Automatic titration system, method and device based on model fitting and machine learning Download PDFInfo
- Publication number
- CN116008379B CN116008379B CN202211464305.9A CN202211464305A CN116008379B CN 116008379 B CN116008379 B CN 116008379B CN 202211464305 A CN202211464305 A CN 202211464305A CN 116008379 B CN116008379 B CN 116008379B
- Authority
- CN
- China
- Prior art keywords
- titration
- measured
- module
- model fitting
- machine learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Investigating Or Analyzing Non-Biological Materials By The Use Of Chemical Means (AREA)
Abstract
The application discloses an automatic system, a method and a device based on model fitting and machine learning. The method is different from the existing method, does not rely on monitoring titration jump for quantitative analysis, adopts a model fitting method to realize quantitative analysis, and can realize quantitative analysis on multiple object systems to be detected. Meanwhile, a method for pre-deploying the machine learning module is introduced, and the pre-deployed machine learning module is called, so that quantitative analysis of a complex system can be realized. The machine learning module does not learn based on historical data, but rather based on a "data enhancement" technique, with large data originating from program modules in Kapok software.
Description
Technical Field
The application relates to the technical field of quantitative analysis, in particular to an automatic potentiometric titration method based on model fitting and machine learning.
Background
Titration techniques are very classical quantitative analysis techniques. An automatic titrator is established, and the existing titration technology is integrated, so that the actual quantitative analysis process is convenient. Current automatic titrators employ steps that are instrumented and automated in nature to classical titration steps.
In the aspect of judging the adopted titration end point, a traditional method for judging the titration jump position is adopted, and the titration end point is judged by utilizing the jump of the electrode potential in the monitoring titration process. This is generally possible for simple systems, but for complex systems consisting of multiple components, it is difficult for existing automatic titrators to achieve automatic quantitative analysis.
In recent years, patents have introduced machine learning in terms of fully automatic titration methods, but are practically difficult to implement. For example, machine learning modeling on an auto-titrator using historical data is essentially impossible. The reason is that: A. machine learning requires big data, and takes a long time to obtain big data of the same feature space from actual measurement; B. machine learning requires good hardware support (such as RTX3090 graphics card, more than 32G memory), and it is basically not feasible to configure these hardware on a full-automatic titrator; C. machine learning requires specialized knowledge and is not adequate for routine analysts.
Disclosure of Invention
The application aims to break through the existing titration method, is not limited to monitoring titration jump any more in quantitative analysis of the object to be detected, and can realize quantitative analysis of multiple object systems to be detected by introducing a model fitting method. Meanwhile, a pre-deployment machine learning module is introduced, and quantitative analysis of a complex system can be realized by calling the pre-deployment machine learning module.
The application provides an automatic potentiometric titration system based on model fitting and machine learning, which comprises:
the data input and output module is used for inputting the parameter file into the instrument and exporting the titration result out of the instrument;
the titration module is used for titrating according to the parameter file and recording titration data;
the data processing module is used for sorting and calculating the titration data and drawing the titration data into a titration curve;
the model fitting module is used for calculating the concentration value of the object to be detected when the titrated solution belongs to a simple system;
and the machine learning module is used for calculating the concentration value of the object to be detected when the titrated solution does not belong to a simple system.
For the purposes of the present application, an auto-titrator can be considered a simple system when the measurement system contains only one analyte (e.g., monoacid, diacid, polyacid, single ion, polyion but forms a 1:1 complex with titrant, etc.).
Further, the parameters in the parameter file include: the method comprises the steps of controlling parameters of hardware operation of a titration process, the volume of a solution to be measured, the amount of a titrant added each time during titration, the volume of the titrant to be added when titration is completed, the number of objects to be measured, the concentration of the objects to be measured and a system complexity identifier. When the object to be detected is acid or alkali, the acid dissociation constants of the object to be detected and the titrant, identifiers of all types of bodies in the solution, the number of hydrogen ions contained in the original acid and the number of hydrogen ions dissociable in the current acid type; when the analyte is an ion that can be measured by the selective electrode, the formation constant of the complex formed by the analyte and the titrant, the formation constant of the complex formed by other ligands in the system, the analyte and the titrant, and the attribute parameters of the other ligands themselves.
Further, the data input/output module transmits the parameter file into the instrument in the form of a text file, reads the parameters in the parameter file when the titrator starts to work, and then carries out an automatic titration process. After titration is completed, the measurement data can be output to a PC end or a mobile equipment end for subsequent data processing.
Further, the data processing module is further configured to determine an accuracy of the concentration value of the to-be-detected object calculated by the model fitting module, and when the accuracy does not reach a preset threshold, the titration process may be continued until the volume number of the titrant to be added when the titration set by the titration parameter file is completed is reached.
Further, the model fitting module is used for calculating the concentration value of the object to be measured when the titrated liquid belongs to a simple system, and specifically comprises data input, data processing, a model fitting process and data output. The model fitting process comprises fitting the calculated titration curve and the measured titration curve; the algorithm of the model fitting treatment is a sequential number theory optimization method, and the sequential number theory optimization method comprises the following steps: and constructing a parameter space containing the concentration value by utilizing the concentration possible value of the object to be detected, uniformly arranging lattice points, sequentially reducing the parameter space according to the optimal point of the parameter space, and finally enabling the parameter space to be small enough so as to enable the optimal point to approach to the real concentration value.
Further, the machine learning module builds big data by using a data enhancement technology, builds a deep learning network by using an expansion convolution technology to build a quantitative model, and comprises the following algorithms: a deep neural network framework is constructed by completely adopting one-dimensional convolution transformation layers, only one-dimensional convolution transformation is carried out in each layer to extract information, the receptive field is expanded by using expansion convolution layers with different amplification coefficients to obtain information of different sections of a titration curve, the gradient disappearance of the deep neural network is prevented by adopting a ResNet technology, each convolution layer is activated by using a Leaky ReLU activation function, and the last output layer is summed by adopting an inactive 1/n weight.
Further, in the step of constructing big data by using the data enhancement technology and constructing a quantitative model by means of a deep learning framework comprising an expansion convolution layer, the source of the big data comprises: large data sets were plotted using Kapok software components.
On the other hand, the application also provides an automatic potentiometric titration method based on model fitting and machine learning, which comprises the following steps:
reading the edited parameter file;
reading a parameter file, and performing titration initialization work;
judging the type of a system of the measured solution according to the system complexity identifier in the parameter file, titrating and recording titration data;
when the measured solution is a simple system, a model fitting module is adopted to process related parameters, and the concentration value of the object to be measured is obtained through calculation;
when the measured solution is a complex system, the machine learning module is adopted to process the related parameters, and the concentration value of the object to be measured is calculated.
In another aspect, the application also provides a full-automatic titration apparatus, which is characterized by comprising a central processing unit and a titration device, wherein the at least one program is used for executing the automatic potentiometric titration method based on model fitting and machine learning.
The beneficial effects of the application are as follows: fitting is carried out through a model fitting module when the concentration value of the object to be measured is measured, and titration endpoint judgment is not carried out any more, so that the accuracy is ensured; by adopting the technical means of machine learning, the complex system can be quantitatively analyzed.
Drawings
FIG. 1 is a schematic diagram of a titrator workflow in accordance with an embodiment of the present application;
FIG. 2 is a schematic diagram of hardware modules of a titrator according to an embodiment of the application.
Detailed Description
The application will be further described with reference to the drawings and specific examples. The described embodiments should not be taken as limitations of the present application, and all other embodiments that would be obvious to one of ordinary skill in the art without making any inventive effort are intended to be within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.
The application does not rely on monitoring titration jump to perform quantitative analysis, but adopts a model fitting method to realize quantitative analysis, and can realize quantitative analysis on multiple object systems to be detected. Meanwhile, a method for pre-deploying the machine learning module is introduced, and the pre-deployed machine learning module is called, so that quantitative analysis of a complex system can be realized. These machine learning modules do not learn based on historical data, but rather on big data generated by "data enhancement" techniques, which originates from Kapok software modules.
According to the scheme provided by the embodiment of the application, the following beneficial effects can be obtained: A. only measuring a titration curve, fitting by a model fitting module, and judging a titration endpoint no longer, so that accuracy is guaranteed; B. for a multi-component system to be detected, a titration curve is calculated based on a Kapok software module, and then the measured titration curve and the calculated titration curve are fitted based on a global optimization method, so that the concentration value of each component to be detected is estimated; C. the pre-deployed machine learning module does not depend on historical data any more, a big data set of a titration curve is calculated through a Kapok software module, and a special deep neural network framework is adopted on a server for learning modeling, so that a quantitative analysis model applicable to an actual system is generated. This process is often referred to as "data enhancement" and can thus solve the quantitative analysis problem of complex systems that cannot be solved by model fitting.
The embodiment of the application provides an automatic potentiometric titration system based on model fitting and machine learning, which comprises a data input/output module, a titration module, a model fitting module and a machine learning module.
Fig. 1 is a workflow in an embodiment of the present application, and the specific workflow is as follows:
s1, editing a parameter file;
s2, performing titration initialization work;
s3, titration is carried out according to the parameter file, titration data are recorded, and a titration curve is calculated;
s4, when the measured solution is a simple system, a model fitting module is adopted to process related parameters;
s401, calculating to obtain a concentration value of an object to be detected, and judging whether the concentration meets the accuracy requirement or not;
s402, ending the titration flow if the concentration meets the accuracy requirement, otherwise continuing the titration until the threshold of the dropwise adding volume is reached;
s5, when the measured solution is a complex system, processing related parameters by adopting a machine learning module, calculating to obtain the concentration value of the object to be measured, and ending the titration flow.
Step S1 in the embodiment of the application, parameter editing can be performed by adopting any text editor supporting UTF-8, and parameter text editing can be performed in advance by a PC end and a mobile equipment end. Parameters related to the parameter file are: the method comprises the steps of controlling parameters of hardware operation of a titration process, the volume of a solution to be measured, the amount of a titrant added each time during titration, the volume of the titrant to be added when titration is completed, the number of objects to be measured, the concentration of the objects to be measured and a system complexity identifier. When the object to be detected is acid or alkali, the acid dissociation constants of the object to be detected and the titrant, identifiers of all types of bodies in the solution, the number of hydrogen ions contained in the original acid and the number of hydrogen ions dissociable in the current type of bodies; when the analyte is an ion that can be measured by the selective electrode, the formation constant of the complex formed by the analyte and the titrant, the formation constant of the complex formed by other ligands in the system, the analyte and the titrant, and the attribute parameters of the other ligands themselves. The written parameter file is stored in the form of a text file, and when the titrator starts to work, parameters in the parameter file are read, and then an automatic titration process is carried out.
Specifically, based on the acid-base proton theory, the acid and the base are conjugates, and the acid dissociation constant can be uniformly used to describe the behavior. Only the "acid dissociation constant" is used herein to describe the characteristic parameters in a unified manner.
Step S2 in the embodiment of the present application, the process of initiating titration includes preparation before a series of official titration operations such as electrode correction, flushing of a titration glass tube, etc., which are conventional operations of titration analysis. The following describes the pH electrode calibration related process and details: the pH electrode correction is a standard process of all titrators, the basic practice is to measure three acid-base buffer solutions by using the pH electrode, and the circuit state of the titrators is adjusted by an electronic circuit module according to the difference between the measured value and the standard value, so that the display value of the titrators is equal to the standard value.
Steps S3 and S4 in the embodiment of the present application, the specific operations in the model fitting module: the method comprises the steps of data input, data processing, model fitting, data output and the like in the module. The data input of the model fitting module comprises a titration curve of the system to be tested and a titration curve calculated according to parameters of the object to be tested in the parameter file. The calculated titration curve may be calculated by a module in the Kapok software package. The measured titration curve is obtained by measuring through the circuit system of the automatic titrator. The concentration of the object to be measured is estimated by a sequential number theory optimization method, and the core method is as follows: and constructing a lattice point set according to the concentration parameter space, wherein each point is a combination of a group of concentration values of the object to be measured, and taking the sum of squares of residual errors subtracted by the calculated titration curve and the measured titration curve as an objective function to realize the minimization of the objective function, thereby obtaining the concentration value of the object to be measured. The Kapok software is a software package which can be used for calculating the titration of a complex acid-base system and the titration curve of a complex coordination system, and the software package can theoretically calculate the titration curve of any complex acid-base titration system and the titration curve of an EDTA-based coordination titration system.
In the embodiment of the application, the basis of calculating the concentration value of the object to be measured, the calculation formula, the meaning of each variable in the calculation formula and the like; the basis sources of the process of calculating the concentration value of the object to be detected are as follows:
for an acid-base titration system, when a plurality of mixed solution of titrant is adopted to drip a plurality of mixed solution of objects to be measured, the titration equation is that
Here, the subscript t represents a titrant; subscript s represents an analyte; delta= [ H ] + ]-[OH - ]The method comprises the steps of carrying out a first treatment on the surface of the F is calculated as follows
Here, the acid dissociation constant K a,0 0.ident; p represents the maximum number of dissociable protons of the acid; q represents the number of protons that the current state of the acid can dissociate. And (3) injection: the acid and base are conjugates in the framework of the acid-base proton theory, where the term acid is used generically to denote both acid and base.
The Kapok software module in the embodiment of the application can solve the titration curve of the acid-base titration system formed by the equation (1) and the equation (2).
For an ion titration system, a titrant R is used for titrating M ions M to be measured j (j=1, 2,) m, the complexation reaction is as follows(for convenience, ionic charge labels are omitted below)
Here, β is a cumulative formation constant;is the standard concentration, unit 1mol/L. Titration equation is
Here the number of the elements is the number,is the volume of titrant added; />Is the initial volume of the metal ion solution; the method comprises the steps of carrying out a first treatment on the surface of the Alpha is the side reaction coefficient of the corresponding form in brackets.
The ionic titrant most commonly used at present is an aminocarboxylic type titrant such as EDTA. Since EDTA forms a 1:1 type complex with metal ions, in this case, the cumulative formation constant is the usual formation constant. The Kapok software module can solve the titration curve of a titration system with EDTA as the titrant. Other coordination titration types are not commonly used, are not currently integrated into Kapok software modules, but can be developed according to equation (4).
In the embodiment of the application, the judgment basis of accuracy is achieved, and the global optimal point is obtained by a sequential number theory optimization method, a global point distribution method and a search space reduction method. The minimum search space size of the preset concentration value can be required according to the accuracy of quantitative analysis, and when the search space of the sequential number theory optimization method is smaller than the preset search space of the concentration value, the required accuracy is achieved.
Step S5, in the embodiment of the application, the machine learning module builds big data by using Kapok software based on a data enhancement technology, and builds a quantitative model by means of an expansion convolution deep learning model.
Fig. 2 is a schematic diagram of a hardware portion of an embodiment of the present application, and the following description refers to the hardware portion of the embodiment of the present application with reference to fig. 2:
central processing unit
The central processing unit of the titrator comprises a CPU and an auxiliary circuit related to the CPU, and is matched with a linux operating system (such as Ubuntu), and other modules are called by writing corresponding programs.
Data input/output module
The data input and output module in the embodiment of the application is responsible for inputting the parameter file and outputting the measurement data. The module comprises a wireless and a wired communication module which are connected with the instrument equipment. The wireless communication module is mainly composed of an industrial common ESP32/ESP8266 module, and can perform data communication with an instrument at a mobile phone end or a computer end through connecting wifi. The wired communication module is mainly composed of an RS485 module commonly used in industry, and is connected with a PC (personal computer) and the like in a connecting mode to realize data transmission.
Machine learning module
The machine learning module in the embodiment of the application is a pre-deployment module, and the related quantitative analysis model is trained by a server (equipped with an RTX3090 display card) in the early stage and then deployed into a titrator in a file form. In the actual titration process, the machine learning prediction program calls out a titration curve which is obtained by titration and used by a corresponding machine learning module, and calculates the concentration value of the object to be measured.
Data processing module
The data processing module in the embodiment of the application is responsible for processing data and mainly comprises various data processing programs written in C, C ++ programming language. The module can calculate a titration curve according to the parameter file, can predict the concentration parameter of the object to be detected through the calculated titration curve and the titration curve obtained by titration by an optimization algorithm, and can predict the concentration parameter of the object to be detected through a pre-deployed machine learning module and the titration curve obtained by titration.
Memory module
The memory module in the embodiment of the application comprises an SD card, an operating system, a program, a model, data and the like are all stored in the memory module, and are uniformly scheduled by the operating system and the central processing unit. The central processing unit is connected with an SPI (serial peripheral interface) protocol of the SD card module. Based on C, C ++ programming language, writing a function of identifying, reading and writing of the related SD card, and storing and reading the SD card data can be realized. The communication mode between the central processing unit and the SD card is FAT16/32 protocol, and through the FAT16/32 protocol, the central processing unit can realize real-time storage of the data file.
Display module
The display module in the embodiment of the application is used for displaying the titration condition of the instrument, the display module consists of a liquid crystal control chip and a liquid crystal screen, and the liquid crystal screen is connected with the liquid crystal control chip through an RGB interface. The interface with the chip is connected in a mode of 8080/SPI and the like, and the specific connection mode is selected according to the chip resource and the actual situation. The module can be used for display of instrument titration data or titration curves.
Titration module
The titration module in the embodiment of the application is composed of a peristaltic pump module and an electrode module. The peristaltic pump module is formed by controlling a stepping motor and a driver, the driver can adjust signals to regulate the speed of the motor, and meanwhile, the peristaltic pump module has a motor protection function. The high-precision flow transmission control can be realized, so that the amount of the titrant dripped in the titration process is controlled. The electrode module is used for measuring the electromotive force change caused by the ion concentration change in a solution system to be measured, the module is composed of an electrode and an electrode signal conditioning module, and the optional electrode module is provided with a pH electrode and an ion selection electrode. The electrode is used for measuring electrode signals of an object to be measured in the solution, and the electrode signal modulation module is used for amplifying the signals. The working principle is as follows: the data of the electrode is extracted by a signal-taking circuit, the signal is processed by a proportional amplifying circuit, and the data is sampled, quantized and encoded by an ADC digital-to-analog conversion module, wherein the sampling frequency is more than 2 times of Shannon law, so that the signal is ensured not to be distorted. Quantization can approximate a finite number of amplitude values to the original continuously varying amplitude values, changing the continuous amplitude of the analog signal to a finite number of discrete values with certain intervals. The coding is according to a certain rule. The quantized values are represented by binary digits. And finally, transmitting the data to a chip, and accurately calculating the electrode potential value through a correction signal reference of the electrode at the beginning of titration.
In an embodiment of the application, the titrator further comprises a power supply module. The power supply module of the embodiment of the application is the same as that of a common titrator in the market.
Claims (5)
1. An automatic potentiometric titration system based on model fitting and machine learning, comprising:
the data input and output module is used for importing the parameter file and exporting titration result data;
the titration module is used for titrating according to the parameter file and recording titration data;
the data processing module is used for sorting and calculating the titration data and drawing the titration data into a titration curve;
the model fitting module is used for calculating the concentration value of the object to be detected when the solution of the object to be detected belongs to a simple system; the simple system is a measurement system which only comprises one object to be measured;
the machine learning module is used for calculating the concentration value of the object to be detected when the solution of the object to be detected does not belong to a simple system;
the model fitting module specifically comprises data input, data processing, a model fitting process and data output; the model fitting process comprises fitting the calculated titration curve and the measured titration curve, wherein the algorithm of the model fitting process is a sequential number theory optimization method, and the sequential number theory optimization method comprises the following steps: constructing a parameter space containing the concentration value by utilizing the concentration possible value of the object to be detected, uniformly arranging lattice points, sequentially reducing the parameter space according to the optimal point of the parameter space, and finally enabling the parameter space to be small enough so as to enable the optimal point to approach to a real concentration value;
the model fitting process of the model fitting module specifically comprises the following steps: constructing a lattice point set according to the parameter space, wherein each point is a concentration value of an object to be measured, taking the sum of squares of residual errors subtracted by a calculated titration curve and a measured titration curve as an objective function, and realizing the minimization of the objective function, thereby obtaining an estimated value of the concentration value of the object to be measured;
the machine learning module specifically includes: constructing big data by using a data enhancement technology, and constructing a quantitative model by means of a deep learning framework comprising an expansion convolution layer, wherein the specific algorithm comprises the following steps: constructing a deep neural network frame by completely adopting one-dimensional convolution transformation layers, and carrying out one-dimensional convolution transformation in each layer; expanding the receptive field by using expansion convolution layers with different amplification coefficients so as to obtain information of different sections of the titration curve; the ResNet technology is adopted to prevent gradient disappearance of the deep network, and each convolution layer activates a function by using a leak ReLU; the output layer of the framework uses inactive 1/n weight summation.
2. An automatic potentiometric titration system based on model fitting and machine learning according to claim 1, wherein the titration experimental parameters include: controlling the hardware operation parameters of the titration process, the volume of the solution to be measured, the volume of the titrant added each time during titration, the volume number of the titrant to be added when the titration is completed, the number of the objects to be measured, the concentration of the objects to be measured and the system complexity identifier; when the object to be detected is acid or alkali, the acid dissociation constants of the object to be detected and the titrant, identifiers of all types of bodies in the solution, the number of hydrogen ions contained in original acid and the number of hydrogen ions dissociable in the current acid type; when the analyte is an ion that can be measured by the selective electrode, the formation constant of the complex formed by the analyte and the titrant, the formation constant of the complex formed by other ligands in the system, the analyte and the titrant, and the attribute parameters of the other ligands themselves.
3. An automatic potentiometric titration system based on model fitting and machine learning according to claim 1, in which the automatic potentiometric titration system stores the parameter file in the form of a text file, and when the titrator is started, the parameters in the parameter file are read to control the subsequent titration process.
4. The automatic potentiometric titration system based on model fitting and machine learning according to claim 1, wherein the data processing module is further configured to fit the calculated titration curve with the measured titration curve during the titration process, determine the accuracy of the concentration value of the analyte calculated by the model fitting module, and continue to drop the titrant until the volume of titrant to be added reaches the volume of titrant to be added when the accuracy does not reach the preset threshold, where the volume of titrant to be added reaches the completion of the titration set by the titration parameter file.
5. An automatic potentiometric titration method based on model fitting and machine learning, applied to an automatic potentiometric titration system according to any one of claims 1-4, comprising:
reading the edited parameter file;
reading a parameter file, and performing titration initialization work;
judging the type of a system of the measured solution according to the system complexity identifier in the parameter file, titrating and recording titration data;
when the measured solution is a simple system, a model fitting module is adopted to process related parameters, and the concentration value of the object to be measured is obtained through calculation;
when the measured solution does not belong to a simple system, the machine learning module is adopted to process related parameters, and the concentration value of the object to be measured is calculated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211464305.9A CN116008379B (en) | 2022-11-22 | 2022-11-22 | Automatic titration system, method and device based on model fitting and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211464305.9A CN116008379B (en) | 2022-11-22 | 2022-11-22 | Automatic titration system, method and device based on model fitting and machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116008379A CN116008379A (en) | 2023-04-25 |
| CN116008379B true CN116008379B (en) | 2023-10-20 |
Family
ID=86021931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211464305.9A Active CN116008379B (en) | 2022-11-22 | 2022-11-22 | Automatic titration system, method and device based on model fitting and machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116008379B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1421223A (en) * | 1973-04-16 | 1976-01-14 | Du Pont | Potentiometric titration method and apparatus therefor |
| FR2504680A1 (en) * | 1981-04-28 | 1982-10-29 | Tacussel Jacques | Automatic electrochemical titration and analysis system - contains acquisition system and memory to measure and plot potential difference change with time as reaction occurs |
| US5640330A (en) * | 1995-04-18 | 1997-06-17 | Ibm Corporation | Method for analyzing pH titration data |
| CN114414648A (en) * | 2022-03-29 | 2022-04-29 | 联泰集群（北京）科技有限责任公司 | Automatic potentiometric titration method and system based on machine learning |
-
2022
- 2022-11-22 CN CN202211464305.9A patent/CN116008379B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1421223A (en) * | 1973-04-16 | 1976-01-14 | Du Pont | Potentiometric titration method and apparatus therefor |
| FR2504680A1 (en) * | 1981-04-28 | 1982-10-29 | Tacussel Jacques | Automatic electrochemical titration and analysis system - contains acquisition system and memory to measure and plot potential difference change with time as reaction occurs |
| US5640330A (en) * | 1995-04-18 | 1997-06-17 | Ibm Corporation | Method for analyzing pH titration data |
| CN114414648A (en) * | 2022-03-29 | 2022-04-29 | 联泰集群（北京）科技有限责任公司 | Automatic potentiometric titration method and system based on machine learning |
Non-Patent Citations (4)
| Title |
|---|
| Hard modeling of titration curve for absolute analysis;Feng Gan 等;Chemometrics and Intelligent Laboratory Systems;第203卷;第4-5页以及图4、5 * |
| 序贯数论优化法在化学定量分析中的应用;龚范 等;化学学报;第56卷;第500-506页 * |
| 神经网络拟合电位滴定法测定铬（Ⅵ）;王金东 等;鞍山钢铁学院学报;第23卷(第2期);第88-91页 * |
| 自动电位滴定中的化学计量方法应用研究;肖励雄;中国优秀硕士学位论文全文数据库 工程科技I辑(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116008379A (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110705717B (en) | Training method, device and equipment of machine learning model executed by computer | |
| CN110388952B (en) | Device and method for verification, calibration and/or adjustment of an online measuring instrument | |
| CN103542875A (en) | Arrangement and Method for Calibrating at Least Two Sensors in Parallel | |
| CN116008379B (en) | Automatic titration system, method and device based on model fitting and machine learning | |
| CN117195083B (en) | Slump prediction method and device based on current curve and readable medium | |
| CN101013120B (en) | Automation titrimetric analysis method and uses thereof | |
| CN113552562A (en) | Automatic calibration system and method for ultrasonic radar | |
| CN104469368A (en) | Universal performance detection method for mobile phone platform VPU video coding and decoding | |
| CN114414648B (en) | Automatic potentiometric titration method and system based on machine learning | |
| CN115436342A (en) | Method and device for reducing LIBS detection uncertainty among multiple batches of samples | |
| CN113818867A (en) | Method, system, medium, equipment and application for constructing pseudo capillary pressure curve | |
| CN110084298B (en) | Method and device for detecting image similarity | |
| CN113445099A (en) | Bath solution analysis method and device and computer readable storage medium | |
| CN115349087A (en) | Inorganic Carbon (IC) exclusion conductivity measurements of aqueous samples | |
| CN110765680A (en) | Intelligent damage identification method and device for engineering structure and electronic equipment | |
| CN1392409A (en) | Automatic potentiometric titration capable of automatically judging terminal point | |
| CN114547914B (en) | Method and device for determining mutual reaction process of fluid and rock and electronic equipment | |
| KR100357527B1 (en) | Method for measuring magnetic flux of cyclotron using vxibus system | |
| US20230133652A1 (en) | Systems and methods for uncertainty prediction using machine learning | |
| RU21322U1 (en) | SYSTEM OF MEASUREMENT OF PARAMETERS AND AUTOMATION OF CONSTRUCTION OF KINETIC MODELS OF BIOCONVERSION PROCESSES | |
| Jakubowska et al. | Deviations from bilinearity in multivariate voltammetric calibration models | |
| CN113740293A (en) | Urea detection analysis method and device based on near-infrared modeling | |
| CN114783535A (en) | Method, device and equipment for estimating gas consumption for gas washing of printing equipment and storage medium | |
| CN117073738A (en) | Batch test method, control device and storage medium of intelligent instrument | |
| JPH0484799A (en) | Water quality control method for plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |