Automatic nozzle production regulation and control method and system

Abstract

The invention relates to the technical field of regulation and control methods, and particularly discloses a nozzle automatic production regulation and control method and system.The nozzle automatic production regulation and control method comprises the following steps that analysis is conducted according to important process machining parameters, and an important process machining deviation ratio is obtained through output; based on the machining deviation ratio of the important working procedure of the nozzle in the production process, data processing is carried out in a time period, and an important working procedure state coefficient is obtained; if the important process state coefficient is greater than or equal to an important process state coefficient threshold, generating an important process processing high-risk signal; the production line is comprehensively checked, and potential problems are found out; on the basis of the potential problems, potential problem alarms are generated, so that countermeasures can be taken in time, and problem parameters can be regulated and controlled; through a potential problem identification and alarm mechanism, the regulation and control efficiency of nozzle automatic production is improved, and the overall stability and efficiency of a production line are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of production control methods, and in particular to an automatic production control method and system for nozzles. Background Art

[0002] As a key component of fluid control, nozzles are widely used in spraying, irrigation, chemical industry and other fields. Perfume nozzles are part of perfume bottles and are used to spray perfume. They consist of several components, including nozzles, pumps, pipes and spray mechanisms. The design and manufacture of nozzles are crucial to the user experience of perfume, as they can affect the uniformity of the spray, the spray intensity, the spray range and the shelf life of the perfume.

[0003] However, in the prior art, the automated production process of nozzles includes processes such as raw material preparation, molding, surface treatment, micro-hole processing, assembly, and testing, some of which have a crucial impact on the quality of the nozzles finally produced. Currently, in the automated production process of nozzles, it is not possible to monitor and analyze important processes in the production, and it is even more impossible to find problems and adjust parameters based on the conditions existing during the production process to improve the quality of automated production of nozzles. Summary of the invention

[0004] The purpose of the present invention is to provide a nozzle automated production control method and system to solve the technical problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A nozzle automatic production control method comprises the following steps: Step 1: During the nozzle production process, obtain the important process parameters of the nozzle, and then judge whether the important process meets the process standards. If not, analyze according to the important process parameters and output the important process deviation ratio; Step 2: Based on the processing deviation ratio of the important process of the nozzle in the production process, the important process state coefficient is obtained by performing data processing within a time period; Step 3: If the important process status coefficient is greater than or equal to the important process status coefficient threshold, a high-risk signal for important process processing is generated; Step 4: Based on the high-risk signals of important process processing, conduct a comprehensive inspection of important processes to identify potential problems; Step 5: Generate potential problem alerts based on potential problems, so that timely response measures can be taken to adjust and process problem parameters.

[0006] As a further solution of the present invention, the output process of the processing deviation ratio of the important process is: Obtain the precision value and processing time of the nozzle in the important process; compare the precision value and processing time in each important process with the pre-set precision value and processing time respectively. If the precision is not achieved, it means that the important process is unqualified; if the processing time requirement is not met, it means that the important process is unqualified; When the processing of an important process is unqualified, the accuracy value and the processing time are respectively calculated with the preset accuracy value and the preset processing time to obtain the accuracy deviation and the time deviation, and then the accuracy deviation is calculated with the preset accuracy value to obtain the accuracy deviation ratio, and the processing time deviation is calculated with the preset processing time value to obtain the time deviation ratio; The accuracy deviation ratio and the duration deviation ratio are summed to obtain the processing deviation ratio of important processes.

[0007] As a further solution of the present invention, data processing is performed within a time period to obtain the process of important process state coefficients: Set a time period, and obtain the nozzle samples produced by each important process and the important process processing deviation ratio corresponding to each nozzle sample within the time period; Based on the processing deviation ratio of the important process corresponding to each nozzle sample, the production stability of the important process is analyzed, and the first state value CV of the process deviation is calculated; Based on the important process processing deviation ratio corresponding to each nozzle sample, the production heterogeneity of the important process is analyzed to obtain the process deviation second state value FB; wherein the process deviation second state value FB is obtained by multiplying the heterogeneity coefficient and the important process processing deviation ratio peak mean value; By formula: , calculate the important process status coefficient ZT.

[0008] As a further solution of the present invention, the process of obtaining the heterogeneity coefficient is as follows: Obtain the processing deviation ratio of the important process corresponding to the time series, construct a two-dimensional model with time as the X-axis and the processing deviation ratio of the important process as the Y-axis, and draw a line chart of the processing deviation ratio of the important process; Extract all the peak points in the line graph, and for any peak point, obtain the important process processing deviation ratio of the adjacent peak points before and after, calculate the mean of the adjacent peak points before and after, and obtain the reference important process processing deviation ratio; The difference between the important process processing deviation ratio of the peak point and the reference important process processing deviation ratio is calculated to obtain the peak point significant comparison value. If the peak point significant comparison value is greater than the peak point significant comparison threshold, it is marked as a significant peak point. In the line graph, the number of significant peak points is obtained, and the ratio of the number of significant peak points to the number of all peak points in the line graph is calculated to obtain the anisotropy coefficient.

[0009] As a further solution of the present invention, in step three, during the important process of nozzle production, real-time production parameters of the important process are obtained in real time; The parameter offset change value and process change value are used as two time series data to prepare for Granger causality test, and the optimal lag order is determined through the VAR model; Two regression models are constructed, one including the lagged term of process change value, and the other including the lagged term of process change value and the lagged term of parameter offset change value; Compare the residual sums of squares of the two regression models and use the F test to determine whether the parameter shift change value has a significant contribution to the prediction of the output change value; If the F statistic is significant, the null hypothesis is rejected, indicating that the parameter offset change is one of the reasons for the output change, and the real-time production parameters corresponding to the parameter offset change are marked as potential problems.

[0010] As a further solution of the present invention, the process of obtaining the parameter offset change value is as follows: Based on the real-time production parameters, a two-dimensional coordinate system is established with time as the X-axis and the real-time production parameters as the Y-axis to draw the real-time production parameter curve and the preset production parameter curve; Divide the time by the processing time of the nozzle samples in the important processes to obtain multiple sample production periods; The lengths of the real-time production parameter curve and the preset production parameter curve in each sample production period are respectively extracted and marked as the real-time production parameter characterization value and the preset production parameter characterization value; The difference between the real-time production parameter characterization value and the production preset parameter characterization value is calculated, and the absolute value is taken to obtain the parameter offset characterization value, and then the parameter offset characterization value is calculated to the production preset parameter characterization value to obtain the parameter offset value of each sample; Then, the parameter offset values ​​of adjacent samples are differentially calculated to obtain the parameter offset change value.

[0011] As a further solution of the present invention, the process of obtaining the process change value is as follows: The difference of important process processing deviation ratios of adjacent samples is calculated to obtain the process processing change value.

[0012] As a further solution of the present invention, in step 5, the cause of poor nozzle production quality in an important process is determined by F test; Generates potential problem alerts, which include detailed descriptions of potential problems, problem parameters, and problem parameter controls.

[0013] As a further solution of the present invention, when a problem parameter control is received, the set value of the problem parameter in the time period is obtained, and the target parameter is regulated by the control ratio formula CBt=CBd*(1-BPmax), and the target parameter control value CBt is calculated, wherein CBd is the set value of the target parameter in the time period, and BPmax is the vertical coordinate value of the highest significant point in the line graph.

[0014] A nozzle automatic production control system, the system comprising: Data acquisition module: In the nozzle production process, the important process parameters of the nozzle are obtained, and then the important process processing is judged whether it meets the process standards. If it does not meet the standards, the important process processing parameters are analyzed and the deviation ratio of the important process processing is output; Data processing module: Based on the processing deviation ratio of important processes of the nozzle in the production process, the important process state coefficient is obtained by performing data processing within a time period; Status evaluation module: Based on the status coefficients of important processes, it evaluates the overall status of important processes in nozzle production and generates process status signals; Problem analysis module: Based on the high-risk signals of important process processing, conduct a comprehensive inspection of important processes to identify potential problems; Problem control module: Based on potential problems, it generates potential problem alerts and then controls the problem parameters.

[0015] Beneficial effects of the present invention: The present invention analyzes important processing steps in the nozzle production process, and considers the overall fluctuation and mutation degree of the process state by characterizing the process deviation from the first state value of the fluctuation degree of the defective nozzle samples produced by the important process, and characterizing the process deviation from the second state value of the outstanding change degree of the defective degree when the important process produces the nozzle samples, thereby realizing more accurate monitoring of the important processes in the nozzle production; The present invention not only improves the control efficiency of nozzle automation production by adding potential problem identification and alarm mechanisms, as well as problem parameter control, but also enhances the overall stability and efficiency of the production line, achieves rapid response and precise positioning of production hazards, and lays a solid foundation for the continuous optimization and upgrading of nozzle automation production. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1It is a flow chart of a nozzle automatic production control method provided by Embodiment 1 and Embodiment 2 of the present invention; Figure 2 It is a structural schematic diagram of a nozzle automatic production control system provided by Embodiment 3 of the present invention; DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1

[0019] Figure 1 The flowchart of a nozzle automatic production control method provided in the first embodiment of the present invention is applicable to situations where the nozzle production quality is highly affected. The nozzle automatic production control method can be executed by a nozzle automatic production control system, which can be implemented by software and / or hardware, and the nozzle automatic production control system can be configured in a nozzle automatic production control device. Optionally, a nozzle automatic production control device can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0020] See also Figure 1 As shown, a nozzle automatic production control method according to an embodiment of the present invention comprises the following steps: Step 1: During the nozzle production process, obtain the important process parameters of the nozzle, and then judge whether the important process meets the process standards. If not, analyze according to the important process parameters and output the important process deviation ratio; In some embodiments, the production process of the nozzle includes: raw material preparation, molding, surface treatment, micro-hole processing, assembly, testing, etc., among which molding, micro-hole processing, and assembly are important processes in the nozzle production process and have a greater impact on the quality of the final prepared nozzle product; The image of the nozzle sample produced through the important process can be collected by the visual camera, and the corresponding precision features, such as the nozzle diameter, nozzle length, nozzle entrance fillet, and the gap between components during assembly, can be extracted to obtain the precision value of the nozzle in the important process, and the processing time of the nozzle in the important process can be obtained through the timer, as well as the pre-set precision value and preset processing time before processing and production; Compare the accuracy value in each important process with the pre-set accuracy value. If the accuracy requirement is met, it means that the important process is qualified. If the accuracy is not met, it means that the important process is unqualified. Compare the processing time of each important process with the pre-set processing time. If the processing time requirement is met, it means that the important process is qualified. If the processing time requirement is not met, it means that the important process is unqualified. When the processing of an important process is unqualified, the accuracy value and the processing time are respectively calculated with the preset accuracy value and the preset processing time to obtain the accuracy deviation and the time deviation, and then the accuracy deviation is calculated with the preset accuracy value to obtain the accuracy deviation ratio, and the processing time deviation is calculated with the preset processing time value to obtain the time deviation ratio; The precision deviation ratio and the duration deviation ratio are summed to obtain the processing deviation ratio of important processes; Step 2: Based on the processing deviation ratio of the important process of the nozzle in the production process, the important process state coefficient is obtained by performing data processing within a time period; In some embodiments, a time period is set, and within the time period, nozzle samples produced by each important process and the important process processing deviation ratio corresponding to each nozzle sample are obtained; First, based on the processing deviation ratio of each nozzle sample, the production stability of the important process is analyzed, specifically: By formula: , calculate the process deviation first state value CV, where Xi is the important process processing deviation ratio of the i-th nozzle sample, is the mean value of the processing deviation ratio of the important process obtained in the important process, and N is the number of samples produced by the important process; It should be explained that the process deviation from the first state value reflects the degree of fluctuation of the defective rate of the nozzle in the production of important processes, that is, the smaller the process deviation from the first state value is, the higher the defective nozzle samples produced by the process are; Secondly, based on the processing deviation ratio of the important process corresponding to each nozzle sample, the production heterogeneity of the important process is analyzed, specifically: Obtain the processing deviation ratio of the important process corresponding to the time series, construct a two-dimensional model with time as the X-axis and the processing deviation ratio of the important process as the Y-axis, and draw a line chart of the processing deviation ratio of the important process; Extract all the peak points in the line graph, and for any peak point, obtain the important process processing deviation ratio of the adjacent peak points before and after, calculate the mean of the adjacent peak points before and after, and obtain the reference important process processing deviation ratio; The difference between the important process processing deviation ratio of the peak point and the reference important process processing deviation ratio is calculated to obtain the peak point significant comparison value. If the peak point significant comparison value is greater than the peak point significant comparison threshold, it means that the peak point has a large deviation and is marked as a significant peak point. If the peak point significant comparison value is less than or equal to the peak point significant comparison threshold, it means that the peak point has a small deviation and is marked as a non-significant peak point. In the line graph, the number of significant peak points is obtained, and the ratio of the number of significant peak points to the number of all peak points in the line graph is calculated to obtain the heterogeneity coefficient; And obtain the important process processing deviation ratios of all peak points in the line graph, and perform mean calculation to obtain the important process processing deviation ratio peak mean; The anisotropy coefficient is multiplied by the average peak of the important process deviation ratio to obtain the process deviation second state value FB; Based on the process deviation first state value CV and process deviation second state value FB, the formula is: , calculate the important process status coefficient ZT; It should be noted that the important process state coefficient uses the process deviation from the first state value that characterizes the fluctuation degree of the defective nozzle samples produced by the important process, and the process deviation from the second state value that characterizes the outstanding variation degree of the defective degree when the important process produces the nozzle samples. Therefore, the larger the value of the important process state coefficient, the higher the probability of the quality of the nozzle produced by the important process being unqualified, and the greater the abnormality of the operating parameters of the important process; Step 3: Based on the important process status coefficient, the overall status of the important processes in nozzle production is evaluated and a process status signal is generated; In some implementation schemes, an important process state coefficient is obtained, and the important process state coefficient is compared with an important process state coefficient threshold; If the important process status coefficient is greater than or equal to the important process status coefficient threshold, a high-risk signal for important process processing is generated; If the important process status coefficient is less than the important process status coefficient threshold, a low risk signal for important process processing is generated; The technical solution of the embodiment of the present invention is mainly to obtain the important process processing parameters of the nozzle during the nozzle production process, and then judge whether the important process processing meets the process standards. When it does not meet the requirements, the important process processing parameters are analyzed and the important process processing deviation ratio is output; based on the important process processing deviation ratio of the nozzle in the production process, the important process state coefficient is obtained by performing data processing within a time period; based on the important process state coefficient, the overall condition of the important process in the nozzle production is evaluated, and a process state signal is generated; the present invention analyzes the important processing steps in the nozzle production process, and considers the overall fluctuation and mutation degree of the process state through a first state value of process deviation that characterizes the degree of fluctuation of defective nozzle samples produced by an important process, and a second state value of process deviation that characterizes the degree of prominent change of the defective degree when an important process produces nozzle samples, thereby achieving more accurate monitoring of important processes during nozzle production. Embodiment 2

[0021] Based on Example 1, please refer to Figure 1 As shown, the nozzle automatic production control method described in the embodiment of the present invention further includes the following steps: Step 4: Based on the high-risk signals of important process processing, conduct a comprehensive inspection of important processes to identify potential problems; In some embodiments, based on the high-risk signal of processing the important process, the real-time production parameters of the important process are obtained in real time during the important process of nozzle production; It should be explained that the real-time production parameters are determined according to the important processes. For example, when the important process is assembly, the real-time production parameters may be assembly vibration value and assembly noise value. When the important process is micro-hole processing, the real-time production parameters may be temperature, pressure and speed. Based on the real-time production parameters, a two-dimensional coordinate system is established with time as the X-axis and the real-time production parameters as the Y-axis to draw the real-time production parameter curve and the preset production parameter curve; It should be explained that the production preset parameters are production parameters pre-set by those skilled in the art based on the production equipment in the electronic workshop, and the value is an empirical value; Divide the time by the processing time of the nozzle samples in the important processes to obtain multiple sample production periods; The lengths of the real-time production parameter curve and the preset production parameter curve in each sample production period are respectively extracted and marked as the real-time production parameter characterization value and the preset production parameter characterization value; The difference between the real-time production parameter characterization value and the production preset parameter characterization value is calculated, and the absolute value is taken to obtain the parameter offset characterization value, and then the parameter offset characterization value is calculated to the production preset parameter characterization value to obtain the parameter offset value of each sample; Then, the parameter offset values ​​of adjacent samples are calculated to obtain the parameter offset change value; At the same time, the difference of the important process processing deviation ratios of adjacent samples is calculated to obtain the process processing change value; The parameter offset change value and process change value are used as two time series data to prepare for Granger causality test, and the optimal lag order is determined through the VAR model; Two regression models were constructed, one containing only the lagged terms of process change values, and the other containing the lagged terms of process change values ​​and parameter offset change values; Compare the residual sums of squares of the two regression models and use the F test to determine whether the parameter shift change value has a significant contribution to the prediction of the output change value; If the F statistic is significant (i.e., the p value is less than the significance level, such as 0.05), the null hypothesis is rejected, indicating that the parameter offset change is one of the reasons for the output change, and the real-time production parameters corresponding to the parameter offset change are marked as potential problems; Glossary: ​​F-test, also known as the joint hypothesis test or variance homogeneity test, is a test that the statistical value follows the F distribution under the null hypothesis. The basis of the F-test is the F-distribution, which is a continuous probability distribution. The F-statistic refers to the statistic that conforms to the F-distribution when the null hypothesis is true. The calculation formula of the F-statistic is based on the variance, specifically F=between-group variance / within-group variance, where the between-group variance reflects the overall difference between different groups, and the within-group variance reflects the degree of dispersion of the data within the group. It should be explained that when the F statistic is significant (i.e., the p value is less than the set significance level, such as 0.05), it means that there is enough evidence to reject the null hypothesis, where the null hypothesis (usually denoted as H0) is a hypothesis about the population parameter proposed by the researcher before conducting statistical analysis, generally expressed as a state of "no effect" or "no difference"; Step 5: Based on the potential problems, generate potential problem alerts to facilitate timely response measures and adjust the problem parameters; In some implementation schemes, when a potential problem is detected, a potential problem alert is generated, which includes a detailed description of the potential problem (problem parameters), recommended preliminary response measures (checking equipment, adjusting problem parameters), and information such as responsible persons and processing time limits; When receiving the problem parameter control, obtain the set value of the problem parameter in the time period, and adjust the target parameter through the control ratio formula CBt=CBd*(1-BPmax), and calculate the target parameter control value CBt, where CBd is the set value of the target parameter in the time period, and BPmax is the ordinate value of the highest significant point in the line chart; The technical solution of the embodiment of the present invention is mainly: based on the high-risk signals of important process processing, a comprehensive inspection of the production line is carried out to find out potential problems; the present invention not only improves the control efficiency of nozzle automation production, but also enhances the overall stability and efficiency of the production line through the added potential problem identification and alarm mechanism, as well as problem parameter control, and achieves rapid response and precise positioning of production hazards, laying a solid foundation for the continuous optimization and upgrading of nozzle automation production. Embodiment 3

[0022] See also Figure 2 As shown, a nozzle automatic production control system according to an embodiment of the present invention includes: Data acquisition module: In the nozzle production process, the important process parameters of the nozzle are obtained, and then the important process processing is judged whether it meets the process standards. If it does not meet the standards, the important process processing parameters are analyzed and the deviation ratio of the important process processing is output; Data processing module: Based on the processing deviation ratio of important processes of the nozzle in the production process, the important process state coefficient is obtained by performing data processing within a time period; Status evaluation module: Based on the status coefficients of important processes, it evaluates the overall status of important processes in nozzle production and generates process status signals; Problem analysis module: Based on the high-risk signals of important process processing, conduct a comprehensive inspection of important processes to identify potential problems; Problem control module: Based on potential problems, it generates potential problem alerts and then controls the problem parameters.

[0023] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0024] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

[0025] The above thresholds are set for the convenience of comparison. The thresholds depend on the amount of sample data and the number of bases set by technicians in this field for each set of sample data. The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A nozzle automated production control method, characterized in that: The following steps are involved: Step 1: During the nozzle production process, obtain the important process parameters of the nozzle, and then judge whether the important process meets the process standards. If not, analyze according to the important process parameters and output the important process deviation ratio; Step 2: Based on the processing deviation ratio of the important process of the nozzle in the production process, the important process state coefficient is obtained by performing data processing within a time period; Step 3: If the important process status coefficient is greater than or equal to the important process status coefficient threshold, a high-risk signal for important process processing is generated; Step 4: Based on the high-risk signals of important process processing, conduct a comprehensive inspection of important processes to identify potential problems; Step 5: Based on the potential problem, generate a potential problem alert and then adjust the problem parameters.

2. The nozzle automatic production control method according to claim 1, characterized in that: The output process of the important process deviation ratio is as follows: Obtain the precision value and processing time of the nozzle in the important process; compare the precision value and processing time in each important process with the pre-set precision value and processing time respectively. If the precision is not achieved, it means that the important process is unqualified; if the processing time requirement is not met, it means that the important process is unqualified; When the processing of an important process is unqualified, the accuracy value and the processing time are respectively calculated with the preset accuracy value and the preset processing time to obtain the accuracy deviation and the time deviation, and then the accuracy deviation is calculated with the preset accuracy value to obtain the accuracy deviation ratio, and the processing time deviation is calculated with the preset processing time value to obtain the time deviation ratio; The accuracy deviation ratio and the duration deviation ratio are summed to obtain the processing deviation ratio of important processes.

3. The nozzle automatic production control method according to claim 1, characterized in that: The process of processing data within a time period to obtain the important process status coefficients is as follows: Set a time period, and obtain the nozzle samples produced by each important process and the important process processing deviation ratio corresponding to each nozzle sample within the time period; Based on the processing deviation ratio of the important process corresponding to each nozzle sample, the production stability of the important process is analyzed, and the first state value CV of the process deviation is calculated; Based on the important process processing deviation ratio corresponding to each nozzle sample, the production heterogeneity of the important process is analyzed to obtain the process deviation second state value FB; wherein the process deviation second state value FB is obtained by multiplying the heterogeneity coefficient and the important process processing deviation ratio peak mean value; By formula: , calculate the important process status coefficient ZT.

4. The nozzle automatic production control method according to claim 3, characterized in that: The process of obtaining the heterogeneity coefficient is as follows: Obtain the processing deviation ratio of the important process corresponding to the time series, construct a two-dimensional model with time as the X-axis and the processing deviation ratio of the important process as the Y-axis, and draw a line chart of the processing deviation ratio of the important process; Extract all the peak points in the line graph, and for any peak point, obtain the important process processing deviation ratio of the adjacent peak points before and after, calculate the mean of the adjacent peak points before and after, and obtain the reference important process processing deviation ratio; The difference between the important process processing deviation ratio of the peak point and the reference important process processing deviation ratio is calculated to obtain the peak point significant comparison value. If the peak point significant comparison value is greater than the peak point significant comparison threshold, it is marked as a significant peak point. In the line graph, the number of significant peak points is obtained, and the ratio of the number of significant peak points to the number of all peak points in the line graph is calculated to obtain the anisotropy coefficient.

5. The nozzle automatic production control method according to claim 1, characterized in that: In step three, during the important process of nozzle production, real-time production parameters of the important process are obtained in real time; The parameter offset change value and process change value are used as two time series data to prepare for Granger causality test, and the optimal lag order is determined through the VAR model; Two regression models are constructed, one including the lagged term of process change value, and the other including the lagged term of process change value and the lagged term of parameter offset change value; Compare the residual sums of squares of the two regression models and use the F test to determine whether the parameter shift change value has a significant contribution to the prediction of the output change value; If the F statistic is significant, the null hypothesis is rejected, indicating that the parameter offset change is one of the reasons for the output change, and the real-time production parameters corresponding to the parameter offset change are marked as potential problems.

6. The nozzle automatic production control method according to claim 1, characterized in that: The process of obtaining the parameter offset change value is as follows: Based on the real-time production parameters, a two-dimensional coordinate system is established with time as the X-axis and the real-time production parameters as the Y-axis to draw the real-time production parameter curve and the preset production parameter curve; Divide the time by the processing time of the nozzle samples in the important processes to obtain multiple sample production periods; The lengths of the real-time production parameter curve and the preset production parameter curve in each sample production period are respectively extracted and marked as the real-time production parameter characterization value and the preset production parameter characterization value; The difference between the real-time production parameter characterization value and the production preset parameter characterization value is calculated, and the absolute value is taken to obtain the parameter offset characterization value, and then the parameter offset characterization value is calculated to the production preset parameter characterization value to obtain the parameter offset value of each sample; Then, the parameter offset values ​​of adjacent samples are differentially calculated to obtain the parameter offset change value.

7. The nozzle automatic production control method according to claim 6, characterized in that: The process of obtaining the process change value is as follows: The difference of important process processing deviation ratios of adjacent samples is calculated to obtain the process processing change value.

8. The nozzle automatic production control method according to claim 1, characterized in that: In step 5, the F test is used to determine the reasons for poor nozzle production quality in important processes; Generates potential problem alerts, which include detailed descriptions of potential problems, problem parameters, and problem parameter controls.

9. The nozzle automatic production control method according to claim 8, characterized in that: When receiving the problem parameter control, obtain the set value of the problem parameter in the time period, and adjust the target parameter through the control ratio formula CBt=CBd*(1-BPmax), and calculate the target parameter control value CBt, where CBd is the set value of the target parameter in the time period, and BPmax is the vertical coordinate value of the highest significant point in the line graph.

10. A nozzle automatic production control system, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Data acquisition module: In the nozzle production process, the important process parameters of the nozzle are obtained, and then the important process processing is judged whether it meets the process standards. If it does not meet the standards, the important process processing parameters are analyzed and the deviation ratio of the important process processing is output; Data processing module: Based on the processing deviation ratio of important processes of the nozzle in the production process, the important process state coefficient is obtained by performing data processing within a time period; Status evaluation module: Based on the status coefficients of important processes, it evaluates the overall status of important processes in nozzle production and generates process status signals; Problem analysis module: Based on the high-risk signals of important process processing, conduct a comprehensive inspection of important processes to identify potential problems; Problem control module: Based on potential problems, it generates potential problem alerts and then controls the problem parameters.

Images