Method and device for determining production parameters of chromatographic column efficiency, equipment and storage medium

Abstract

The invention provides a method, device and equipment for determining production parameters of chromatographic column efficiency and a medium, and the method comprises the following steps: determining the type of a target chromatographic column, and determining a chromatographic column efficiency prediction model based on the type; the chromatographic column efficiency prediction model is obtained by training on the basis of numerical values of chromatographic column efficiency generation parameters and column efficiency values corresponding to the numerical values of each group of generation parameters; determining a numerical value adjustment strategy of each generation parameter; determining a parameter matrix based on a numerical adjustment strategy and the initial value of the generated parameter; inputting the parameter matrix into a chromatographic column efficiency prediction model, and outputting a column efficiency value matrix by the chromatographic column efficiency prediction model; and determining the numerical value of the generation parameter corresponding to the maximum value of the column efficiency value as an optimal numerical value based on the column efficiency value matrix, thereby improving the efficiency and accuracy of the chromatographic analysis work.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of chromatographic column efficiency analysis of oil products, and particularly relates to a method and device for determining generation parameters of a chromatographic column, equipment and a storage medium. BACKGROUND

[0002] Chromatography plays a great role in compound analysis, has the characteristics of large peak capacity, high resolution, group separation and plate effect, and is used by various analysis laboratories. As an important tool for separating complex compounds, the chromatographic column plays a decisive role in the separation effect, so it is particularly important to quickly and accurately predict the column efficiency of the chromatographic column. In the existing column efficiency evaluation method, the column efficiency is often calculated according to the retention time, peak width and half-peak width information, which is time-consuming and laborious, and it is not convenient for test operators to adjust the generation parameters according to the column efficiency, so it is not possible to adjust the optimal generation parameters, thereby affecting the efficiency and accuracy of chromatographic analysis work. SUMMARY

[0003] In view of the problems in the prior art, the present application provides a method and device for determining generation parameters of chromatographic column efficiency, equipment and a storage medium.

[0004] The present application provides a method for determining generation parameters of chromatographic column efficiency, comprising: determining the type of the target chromatographic column, and determining a chromatographic column efficiency prediction model based on the type; the chromatographic column efficiency prediction model is trained based on the numerical values of the generation parameters of the chromatographic column efficiency and the column efficiency values corresponding to each group of numerical values of the generation parameters; determining the numerical value adjustment strategy of each generation parameter; determining a parameter matrix based on the numerical value adjustment strategy and the initial value of the generation parameter; inputting the parameter matrix into the chromatographic column efficiency prediction model, outputting a column efficiency value matrix from the chromatographic column efficiency prediction model, and determining the numerical value of the generation parameter corresponding to the maximum value of the column efficiency value as the optimal numerical value based on the column efficiency value matrix.

[0005] According to the method for determining the generation parameters of the chromatographic column efficiency provided by the present application, the numerical value adjustment strategy of each generation parameter is determined, comprising: determining the importance ranking of each generation parameter and the numerical value range corresponding to each generation parameter; determining a plurality of numerical value adjustment ratios, the number of the numerical value adjustment ratios being the same as the number of each generation parameter; sorting each numerical value adjustment ratio from small to large; corresponding the sorting of the numerical value adjustment ratio to the importance ranking of each generation parameter, calculating according to the numerical value range and the numerical value adjustment ratio of each generation parameter, and determining the adjustment step of each generation parameter; The adjustment step of each generation parameter forms a numerical adjustment strategy.

[0006] According to the method for determining generation parameters of column efficiency of a chromatographic column, the importance order of each generation parameter is determined, and the method comprises the following steps: An initial value of each generation parameter and a column efficiency value corresponding to the initial value of each generation parameter are obtained. The initial value of each generation parameter is reduced by a first proportion or increased by a second proportion to obtain a reduced value and an increased value. A first column efficiency value corresponding to the reduced value and a second column efficiency value corresponding to the increased value are obtained. The change rates of the first column efficiency value and the second column efficiency value are compared, and the importance order of each generation parameter is determined based on the change rates.

[0007] According to the method for determining generation parameters of column efficiency of a chromatographic column, the numerical value of the generation parameter corresponding to the maximum column efficiency value in the column efficiency value matrix is determined as the preferred numerical value, and the method comprises the following steps: If there is one maximum value in the column efficiency value matrix, the numerical value of the generation parameter corresponding to the maximum column efficiency value is determined as the preferred numerical value; if there are more than two maximum values in the column efficiency value matrix, the average value of each generation parameter is determined according to the numerical value of the generation parameter corresponding to each maximum value, and the average value is determined as the preferred numerical value.

[0008] The application further provides a device for determining generation parameters of column efficiency of a chromatographic column, which comprises: A determination module is configured to determine the type of a target chromatographic column, and determine a column efficiency prediction model based on the type; the column efficiency prediction model is trained based on the numerical value of the generation parameter of column efficiency and the column efficiency value corresponding to each group of generation parameters. A selection module is configured to determine a numerical adjustment strategy of each generation parameter. A configuration module is configured to determine a parameter matrix based on the numerical adjustment strategy and the initial value of the generation parameter. A processing module is configured to input the parameter matrix into the column efficiency prediction model, and output a column efficiency value matrix from the column efficiency prediction model. A calculation module is configured to determine the numerical value of the generation parameter corresponding to the maximum column efficiency value in the column efficiency value matrix as the preferred numerical value.

[0009] According to the device for determining generation parameters of column efficiency of a chromatographic column, the selection module is specifically configured to determine the importance order of each generation parameter and the numerical value range corresponding to each generation parameter. A plurality of numerical adjustment proportions are determined, and the number of the numerical adjustment proportions is the same as the number of the generation parameters. sorting the value adjustment proportion from small to large; corresponding the sorting of the value adjustment proportion with the importance sorting of each generation parameter, calculating according to the value range of each generation parameter and the value adjustment proportion, and determining the adjustment step of each generation parameter; The adjustment step of each generation parameter constitutes the value adjustment strategy.

[0010] According to the determination device of the generation parameter of the column efficiency of the chromatographic column provided by the application, the selection module is used for: obtaining the initial value of each generation parameter and the column efficiency value corresponding to the initial value of each generation parameter; reducing the initial value of each generation parameter according to a first proportion or increasing the initial value of each generation parameter according to a second proportion, to obtain the reduced value and the increased value; obtaining the first column efficiency value corresponding to the reduced value and the second column efficiency value corresponding to the increased value; comparing the change rate of the first column efficiency value and the second column efficiency value, and determining the importance sorting of each generation parameter based on the change rate.

[0011] According to the determination device of the generation parameter of the column efficiency of the chromatographic column provided by the application, the calculation module is specifically used for: if there is a maximum value in the column efficiency value matrix, the value of the generation parameter corresponding to the maximum value of the column efficiency value is used as the preferred value; if there are more than two maximum values in the column efficiency value matrix, the average value of each generation parameter is determined according to the value of the generation parameter corresponding to each maximum value, and the average value is used as the preferred value.

[0012] The application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to realize the determination method of the generation parameter of the column efficiency of the chromatographic column.

[0013] The application further provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the determination method of the generation parameter of the column efficiency of the chromatographic column.

[0014] The application further provides a computer program product, which includes a computer program, and the computer program is executed by a processor to realize the determination method of the generation parameter of the column efficiency of the chromatographic column.

[0015] The application provides a method and device for determining parameters for generating column efficiency of a chromatographic column, an equipment and a medium. The method comprises the following steps: determining a numerical adjustment strategy of each parameter; determining a parameter matrix based on the numerical adjustment strategy and initial values of the parameters; inputting the parameter matrix into a column efficiency prediction model; outputting a column efficiency value matrix from the column efficiency prediction model; and determining a numerical value of a parameter corresponding to a maximum column efficiency value in the column efficiency value matrix as an optimal numerical value. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 is a flowchart of the method for determining parameters for generating column efficiency of a chromatographic column provided by the present application.

[0018] Figure 2 is a structural diagram of the device for determining parameters for generating column efficiency of a chromatographic column provided by the present application.

[0019] Figure 3 is a structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0020] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] The method, device, equipment and medium for determining parameters for generating column efficiency of a chromatographic column provided by the present application will be described below. Figures 1-3

[0022] Figure 1 is a flowchart of the method for determining parameters for generating column efficiency of a chromatographic column provided by the present application, which is shown in Figure 1 The method comprises the following steps: Step 11: determining the type of a target chromatographic column, and determining a column efficiency prediction model based on the type; the column efficiency prediction model is trained based on the numerical values of the parameters for generating column efficiency and the column efficiency values corresponding to each group of numerical values of the parameters; Step 12: determining a numerical adjustment strategy of each parameter;​ Step 13, determining a parameter matrix based on the numerical adjustment strategy and the initial value of the production parameter; Step 14, inputting the parameter matrix into the column efficiency prediction model to output a column efficiency value matrix from the column efficiency prediction model; Step 15, determining the value of the production parameter corresponding to the maximum column efficiency value as the preferred value based on the column efficiency value matrix.

[0023] It should be noted that, in the present application, the chromatographic column is composed of a column tube, a pressure cap, a sleeve (sealing ring), a screen plate (filter), a joint, a screw, etc., and is a column tube filled with a stationary phase for separating mixed components. The separation effect of the chromatographic column depends on the selected stationary phase, as well as the preparation and operating conditions of the chromatographic column. Different chromatographic columns are used for column efficiency testing of different oil products, and the adapted column efficiency prediction method, i.e. the used column efficiency prediction model, is different. In the present application, the column efficiency prediction model is trained based on the numerical value of the production parameter of the column efficiency and the column efficiency value corresponding to each group of numerical values of the production parameter, which is used to analyze the input numerical value of the production parameter of the column efficiency and output the corresponding column efficiency value.

[0024] In the prior art, the column efficiency is often calculated based on the retention time, peak width, and half-peak width information during column efficiency evaluation. However, the present application considers the production parameters of the oil product passing through the chromatographic column, such as carrier gas flow rate, vaporization chamber temperature, column temperature rise rate, and detector temperature.

[0025] In the present application, the purpose of the method is to determine the optimal numerical value of the production parameter for column efficiency testing of oil products for different chromatographic columns. Therefore, the numerical value of the production parameter needs to be adjusted to screen out the optimal numerical value of the production parameter.

[0026] In the present application, the numerical adjustment strategy of each production parameter is determined for each production parameter. The numerical adjustment strategy can limit the adjustment strength of the numerical value of the production parameter, and can make the influence of the production parameter on the column efficiency value more uniform, thereby facilitating the screening of the optimal numerical value of the production parameter.

[0027] First, a suitable initial value is configured, which can be a numerical value within a certain numerical range. Then, the parameter matrix is determined based on the numerical adjustment strategy and the initial value of the production parameter.

[0028] Then, the parameter matrix is input into the column efficiency prediction model to output a column efficiency value matrix from the column efficiency prediction model. The column efficiency value matrix is plotted, and the numerical value of the production parameter corresponding to the maximum column efficiency value is selected as the preferred value.

[0029] In the present application, the construction of the chromatographic column efficiency prediction model is as follows: A convolutional neural network model is constructed, which has a total of three layers, wherein the input layer has 4 neuron nodes, the output layer has 1 neuron node, the initial neuron structure of the middle layer is 2, and the maximum is 8, the number of neurons is adaptively adjusted to find the optimal number, and the activator uses the ReLU function.

[0030] Neuron number adaptive method: The training set data is divided into several batches, for example, 1000 groups of data are divided into 10 batches, and each batch has 100 groups of data. First, the comprehensive error T1 of the first batch is calculated.

[0031] The controller flag state is set to plus state; when the flag is in the plus state, the number of neurons in the middle layer is automatically increased by 1 to calculate the comprehensive error T2 of the second batch, and compared with T1, if less than T1, the flag state is unchanged; if T2 is greater than T1, the change of neurons is stopped, and the two neurons are the final value (initial value); When calculating the third batch, it is detected that the flag is in the plus state, and the number of neurons is automatically increased by 1; Calculate T3 and compare it with T2, if less than T2, the flag continues to be in the plus state; if greater than T3, the flag state is changed to pending; When calculating the fourth batch, it is detected that the flag state is in the pending state, and the number of neurons is unchanged, and T4 is calculated, if T4 is less than T2 and less than T3, the flag state is set to plus; if T4 is greater than T2 and less than T3, the flag is set to plus; if T4 is greater than T2 and greater than T3, the flag is set to minus.

[0032] Calculate the fifth batch, increase or decrease the number of neurons in the middle layer according to the flag state, and repeat the above process. Select 18000 groups of data of different concentrations of test solutions under different parameters as a test set, train the model, finally complete the prediction of the training data, save the network structure and node parameters.

[0033] The method for determining the generation parameters of the chromatographic column efficiency provided by the present application determines the numerical adjustment strategy of each generation parameter, determines the parameter matrix based on the numerical adjustment strategy and the initial value of the generation parameter, inputs the parameter matrix into the chromatographic column efficiency prediction model, and outputs the column efficiency value matrix from the chromatographic column efficiency prediction model, determines the numerical value of the generation parameter corresponding to the maximum value of the column efficiency value matrix as the optimal numerical value based on the column efficiency value matrix, and improves the efficiency and accuracy of the chromatographic analysis work.

[0034] In the further method of the above method, the process of determining the importance order of each generation parameter is mainly explained, and the details are as follows: determining the importance order of each generation parameter and the numerical range corresponding to each generation parameter; determining a plurality of numerical adjustment ratios, the number of numerical adjustment ratios being the same as the number of each generation parameter; sorting each numerical adjustment ratio from small to large; corresponding the order of numerical adjustment ratio to the importance order of each generation parameter, calculating according to the numerical range of each generation parameter and the numerical adjustment ratio, and determining the adjustment step of each generation parameter; wherein the adjustment step of each generation parameter constitutes the numerical adjustment strategy.

[0035] For this, it needs to be explained that in the present application, different generation parameters have different degrees of influence on column efficiency. Therefore, the importance of each generation parameter can be sorted. Each generation parameter will not be adjusted too much, so a numerical range can be configured for the adjustment of each generation parameter.

[0036] For the adjustment of the numerical value, an adjustment strength needs to be configured, which can be reflected in the adjustment step. For this purpose, a plurality of numerical adjustment ratios are determined, the number of numerical adjustment ratios being the same as the number of each generation parameter. Different numerical adjustment ratios are sorted from small to large and assigned to different generation parameters. Finally, according to the numerical range of each generation parameter and the numerical adjustment ratio, the adjustment step of each generation parameter is determined, and at this time the adjustment step of each generation parameter constitutes the numerical adjustment strategy.

[0037] For example, each numerical adjustment ratio is sorted from small to large, which is 1 / 30, 1 / 20, 1 / 10, 1 / 5. The order of each generation parameter is carrier gas flow rate, vaporization chamber temperature, chromatographic column heating rate, and detector temperature. At this time, for the carrier gas flow rate, 1 / 30 of the numerical range corresponding to the carrier gas flow rate is taken as the adjustment step.

[0038] In the further method of the above method, the process of determining the importance order of each generation parameter is mainly explained, and the details are as follows: obtaining the initial value of each generation parameter and the column efficiency value corresponding to the initial value of each generation parameter; reducing or increasing the initial value of each generation parameter by a first ratio or a second ratio to obtain a reduced value and an increased value; obtaining a first column efficiency value corresponding to the reduced value and a second column efficiency value corresponding to the increased value; comparing the change rate of the first column efficiency value and the second column efficiency value, and determining the importance order of each generation parameter based on the change rate.

[0039] To this end, it should be noted that in the present application, in order to determine the importance of each generation parameter, both the value of the generation parameter is adjusted and the value of the generation parameter is adjusted, and the column efficiency value obtained after the value adjustment is analyzed. Even if the initial value of each generation parameter is reduced by the first proportion or increased by the second proportion, the reduced value and the increased value are obtained. The first column efficiency value corresponding to the reduced value is obtained, and the second column efficiency value corresponding to the increased value is obtained. The change rate of the value is determined based on the first column efficiency value and the second column efficiency value. The change rate here can be the difference between the first column efficiency value and the second column efficiency value, and finally the importance of each generation parameter is determined based on the change rate corresponding to each generation parameter. The importance of the smaller change rate is higher, and the sorting is in front.

[0040] In a further method of the above method, if there is a maximum value in the column efficiency value matrix, the value of the generation parameter corresponding to the maximum value of the column efficiency value is the preferred value; If there are more than two maximum values in the column efficiency value matrix, the average value of each generation parameter is determined according to the value of the generation parameter corresponding to each maximum value, and the average value is used as the preferred value.

[0041] The present application determines the value adjustment strategy of each generation parameter, determines the parameter matrix based on the value adjustment strategy and the initial value of the generation parameter, inputs the parameter matrix into the column efficiency prediction model, and outputs the column efficiency value matrix from the column efficiency prediction model. The value of the generation parameter corresponding to the maximum value of the column efficiency value is determined as the preferred value based on the column efficiency value matrix, which improves the efficiency and accuracy of the chromatographic analysis work.

[0042] The determination device of the chromatographic column efficiency generation parameter provided by the present application is described below. The determination device of the chromatographic column efficiency generation parameter described below can be referred to each other corresponding to the determination method of the chromatographic column efficiency generation parameter described above.

[0043] Figure 2 The structure diagram of a determination device of a chromatographic column efficiency generation parameter provided by the present application is shown, referring to Figure 2 The device comprises a determination module 21, a selection module 22, a configuration module 23, a processing module 24 and a calculation module 25, wherein: the determination module is used to determine the type of the target chromatographic column, and determine the column efficiency prediction model based on the type; the column efficiency prediction model is trained based on the value of the chromatographic column efficiency generation parameter and the column efficiency value corresponding to each group of generation parameter value; The selection module is used to determine the value adjustment strategy of each generation parameter; The configuration module is used to determine the parameter matrix based on the value adjustment strategy and the initial value of the generation parameter; The processing module is configured to input the parameter matrix into the chromatographic column efficiency prediction model, and output a column efficiency value matrix from the chromatographic column efficiency prediction model; The computing module is configured to determine, based on the column efficiency value matrix, a value of a generation parameter corresponding to a maximum value of the column efficiency value as a preferred value.

[0044] In a further method of the above device, the selecting module is specifically configured to: determine an importance ranking of each generation parameter and a value range corresponding to each generation parameter; determine a plurality of value adjustment ratios, the number of the value adjustment ratios being the same as the number of each generation parameter; sort each value adjustment ratio from small to large; correspond the sorting of the value adjustment ratio to the importance ranking of each generation parameter, and calculate according to the value range of each generation parameter and the value adjustment ratio to determine an adjustment step of each generation parameter; wherein the adjustment step of each generation parameter constitutes a value adjustment strategy.

[0045] In a further method of the above device, in the process of determining the importance ranking of each generation parameter, the selecting module is specifically configured to: obtain an initial value of each generation parameter and a column efficiency value corresponding to the initial value of each generation parameter; reduce the initial value of each generation parameter by a first ratio or increase the initial value of each generation parameter by a second ratio to obtain a reduced value and an increased value; obtain a first column efficiency value corresponding to the reduced value and a second column efficiency value corresponding to the increased value; compare the change rates of the first column efficiency value and the second column efficiency value, and determine the importance ranking of each generation parameter based on the change rates.

[0046] In a further method of the above method, the computing module is specifically configured to: if there is one maximum value in the column efficiency value matrix, the value of the generation parameter corresponding to the maximum value of the column efficiency value is the preferred value; if there are more than two maximum values in the column efficiency value matrix, the average value of each generation parameter is determined according to the values of the generation parameters corresponding to each maximum value, and the average value is taken as the preferred value.

[0047] The present application provides a device for determining generation parameters of chromatographic column efficiency. By determining a value adjustment strategy of each generation parameter, a parameter matrix is determined based on the value adjustment strategy and an initial value of the generation parameter, the parameter matrix is input into a chromatographic column efficiency prediction model, a column efficiency value matrix is output from the chromatographic column efficiency prediction model, a value of a generation parameter corresponding to a maximum value of the column efficiency value is determined as a preferred value based on the column efficiency value matrix, and the efficiency and accuracy of chromatographic analysis are improved.

[0048] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 31, a communication interface 32, a memory 33, and a communication bus 34. The processor 31, communication interface 32, and memory 33 communicate with each other via the communication bus 34. The processor 31 can call logical instructions in the memory 33 to execute a method for determining the generation parameters of chromatographic column efficiency. This method includes: determining the type of the target chromatographic column; determining a chromatographic column efficiency prediction model based on the type; the chromatographic column efficiency prediction model is trained based on the values ​​of the generation parameters of chromatographic column efficiency and the column efficiency values ​​corresponding to each set of generation parameter values; determining the numerical adjustment strategy for each generation parameter; determining a parameter matrix based on the numerical adjustment strategy and the initial values ​​of the generation parameters; inputting the parameter matrix into the chromatographic column efficiency prediction model, which outputs a column efficiency value matrix; and determining the value of the generation parameter corresponding to the maximum value of the column efficiency value as the preferred value based on the column efficiency value matrix.

[0049] Furthermore, the logical instructions in the aforementioned memory 33 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0050] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer readable storage medium, and the computer program, when executed by a processor, enables a computer to perform the method for determining the generation parameter of the column efficiency of a chromatographic column provided by any of the above methods, and the method comprises: determining the type of a target chromatographic column, and determining a column efficiency prediction model based on the type; the column efficiency prediction model is trained based on the numerical values of the generation parameters of the column efficiency and the column efficiency values corresponding to each set of numerical values of the generation parameters; determining the numerical value adjustment strategy of each generation parameter; determining a parameter matrix based on the numerical value adjustment strategy and the initial values of the generation parameters; inputting the parameter matrix into the column efficiency prediction model, and outputting a column efficiency value matrix from the column efficiency prediction model; and determining the numerical value of the generation parameter corresponding to the maximum column efficiency value in the column efficiency value matrix as the preferred numerical value.

[0051] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, enables a computer to perform the method for determining the generation parameter of the column efficiency of a chromatographic column provided by any of the above methods, and the method comprises: determining the type of a target chromatographic column, and determining a column efficiency prediction model based on the type; the column efficiency prediction model is trained based on the numerical values of the generation parameters of the column efficiency and the column efficiency values corresponding to each set of numerical values of the generation parameters; determining the numerical value adjustment strategy of each generation parameter; determining a parameter matrix based on the numerical value adjustment strategy and the initial values of the generation parameters; inputting the parameter matrix into the column efficiency prediction model, and outputting a column efficiency value matrix from the column efficiency prediction model; and determining the numerical value of the generation parameter corresponding to the maximum column efficiency value in the column efficiency value matrix as the preferred numerical value.

[0052] The apparatus embodiments described above are merely illustrative, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0053] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0054] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining parameters for generating chromatographic column efficiency, characterized in that, include: Determine the type of the target chromatographic column, and determine the column efficiency prediction model based on the type; The chromatographic column efficiency prediction model is trained based on the values ​​of the parameters that generate chromatographic column efficiency and the column efficiency values ​​corresponding to each set of parameters. Determine the numerical adjustment strategy for each generation parameter; Based on the numerical adjustment strategy and the initial values ​​of the generated parameters, the parameter matrix is ​​determined; The parameter matrix is ​​input into the chromatographic column efficiency prediction model, and the chromatographic column efficiency prediction model outputs a column efficiency value matrix; based on the column efficiency value matrix, the value of the generating parameter corresponding to the maximum value of the column efficiency value is determined as the preferred value.

2. The method for determining the parameters for generating chromatographic column efficiency according to claim 1, characterized in that, The numerical adjustment strategy for determining each generation parameter includes: Determine the importance ranking of each generation parameter and the corresponding numerical range for each generation parameter; Multiple numerical adjustment ratios are determined, the number of which is the same as the number of each generating parameter; Sort the adjustment ratios of each value from smallest to largest; The numerical adjustment ratios are sorted in relation to the importance of each generated parameter. The adjustment step size of each generated parameter is determined by calculating the numerical range and numerical adjustment ratio of each generated parameter. The adjustment step size of each generated parameter constitutes the numerical adjustment strategy.

3. The method for determining the parameters for generating chromatographic column efficiency according to claim 2, characterized in that, Determining the importance ranking of each generation parameter includes: Obtain the initial values ​​of each generation parameter and the corresponding column efficiency values; The initial value of each generated parameter is reduced by a first ratio or increased by a second ratio to obtain the reduced value and the increased value. Obtain the first column effect value corresponding to the reduced value, and the second column effect value corresponding to the increased value; Compare the rate of change of the first column effect value and the second column effect value, and determine the importance ranking of each generation parameter based on the rate of change.

4. The method for determining the parameters for generating chromatographic column efficiency according to claim 1, characterized in that, The step of determining the optimal value of the generation parameter corresponding to the maximum value of the column effect based on the column effect matrix includes: If there is a maximum value in the column effect value matrix, the value of the generation parameter corresponding to the maximum value is taken as the preferred value; if there are two or more maximum values ​​in the column effect value matrix, the average value of each generation parameter is determined according to the value of the generation parameter corresponding to each maximum value, and the average value is taken as the preferred value.

5. A device for determining parameters for the generation of chromatographic column efficiency, characterized in that, include: A determination module is used to determine the type of the target chromatographic column and, based on the type, to determine a column efficiency prediction model. The chromatographic column efficiency prediction model is trained based on the values ​​of the parameters that generate chromatographic column efficiency and the column efficiency values ​​corresponding to each set of parameters. Select a module to determine the numerical adjustment strategy for each generated parameter; A configuration module is used to determine a parameter matrix based on the numerical adjustment strategy and the initial values ​​of the generated parameters; The processing module is used to input the parameter matrix into the chromatography column efficiency prediction model, and the chromatography column efficiency prediction model outputs the column efficiency value matrix. The calculation module is used to determine the value of the generation parameter corresponding to the maximum value of the column effect value as the preferred value based on the column effect value matrix.

6. The apparatus for determining the generation parameters of chromatographic column efficiency according to claim 5, characterized in that, The selection module is specifically used for: Determine the importance ranking of each generation parameter and the corresponding numerical range for each generation parameter; Multiple numerical adjustment ratios are determined, the number of which is the same as the number of each generating parameter; Sort the adjustment ratios of each value from smallest to largest; The numerical adjustment ratios are sorted in relation to the importance of each generated parameter. The adjustment step size of each generated parameter is determined by calculating the numerical range and numerical adjustment ratio of each generated parameter. The adjustment step size of each generated parameter constitutes the numerical adjustment strategy.

7. The apparatus for determining the generation parameters of chromatographic column efficiency according to claim 6, characterized in that, In the process of determining the importance ranking of each generated parameter, the selection module is specifically used for: Obtain the initial values ​​of each generation parameter and the corresponding column efficiency values; The initial value of each generated parameter is reduced by a first ratio or increased by a second ratio to obtain the reduced value and the increased value. Obtain the first column effect value corresponding to the reduced value, and the second column effect value corresponding to the increased value; Compare the rate of change of the first column effect value and the second column effect value, and determine the importance ranking of each generation parameter based on the rate of change.

8. The apparatus for determining the generation parameters of chromatographic column efficiency according to claim 5, characterized in that, The calculation module is specifically used for: If there is a maximum value in the column effect value matrix, the value of the generation parameter corresponding to the maximum value is taken as the preferred value; if there are two or more maximum values ​​in the column effect value matrix, the average value of each generation parameter is determined according to the value of the generation parameter corresponding to each maximum value, and the average value is taken as the preferred value.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for determining the generation parameters of the chromatographic column efficiency as claimed in any one of claims 1-4.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for determining the generation parameters of the chromatographic column efficiency as claimed in any one of claims 1-4.

Images