Valve production parameter optimization method and system based on product requirements
By optimizing valve production parameters through application scenario-based weight allocation and sensitivity analysis, the problems of high parameter debugging costs and low production efficiency in existing technologies have been solved, achieving more efficient production parameter optimization and product quality improvement.
Patent Information
- Application Number
- CN202411027779.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-30
AI Technical Summary
The existing valve production parameter settings rely on experience and standard processes, making it difficult to flexibly adapt to diverse product needs, resulting in high parameter debugging costs and low production efficiency.
Weights are allocated based on the application scenario of the target valve, key performance parameters are screened, and the optimal production parameter strategy is determined through sensitivity analysis and global optimization. Production parameters are then optimized by combining historical production records and real-time monitoring.
This improved the efficiency of parameter optimization, reduced debugging costs, and enhanced the quality and performance adaptability of valve products.
Smart Images

Figure CN118552339B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of valve technology, and in particular to a method and system for optimizing valve production parameters based on product requirements. Background Art
[0002] Valves are important components in fluid control systems and are widely used in the fields of petroleum, chemical industry, electricity, construction, etc. The quality and performance of valves directly affect the safety and reliability of the entire system. The existing valve production parameter settings are usually determined by the experience of relevant technicians and the inherited standard process, which is difficult to flexibly adapt to the diverse product needs. There are technical problems such as high parameter debugging costs and low production efficiency. Summary of the invention
[0003] The present invention provides a valve production parameter optimization method and system based on product requirements to solve the technical problems of high parameter debugging cost and low production efficiency in the prior art, and achieve the technical effect of improving parameter optimization efficiency and reducing debugging cost.
[0004] In a first aspect, the present invention provides a method for optimizing valve production parameters based on product requirements, wherein the method comprises:
[0005] Based on the target application scenario of the target valve, the predetermined performance parameters are weighted to obtain the target weight allocation; based on the target weight allocation, the predetermined performance parameters are screened to obtain the key performance parameters; the first historical record in the historical valve production parameter record is extracted, and the first historical record includes the first historical production parameter information and the first historical performance parameter information; the first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter is used as the dependent variable; the first historical production parameter information is used as the independent variable, and a sensitivity analysis is performed with the dependent variable to obtain a first sensitivity analysis result, and the key production parameters are determined according to the first sensitivity analysis result; the key production parameters are globally optimized to obtain the optimal key production parameter strategy, and the target valve is produced based on the optimal key production parameter strategy.
[0006] In a feasible implementation, the method includes:
[0007] Based on big data, historical working condition records of similar valve products of the target valve in the target application scenario are obtained, and the historical working condition records include historical working environment characteristic information; a first predetermined environmental characteristic threshold is read, and it is determined whether the first historical environmental characteristic data in the historical working environment characteristic information is within the first predetermined environmental characteristic threshold, the first historical environmental characteristic data corresponding to the first environmental characteristic; if so, a first demand performance corresponding to the first environmental characteristic is added to a first weight level, and if not, it is determined whether the first historical environmental characteristic data is within a second predetermined environmental characteristic threshold; if so, the first demand performance is added to a second weight level, and if not, the first demand performance is added to a third weight level; the target weight distribution is generated based on the first weight level, the second weight level and the third weight level.
[0008] In a feasible implementation, the historical working environment characteristic information includes a plurality of characteristic data corresponding to predetermined environmental characteristics, wherein the predetermined environmental characteristics at least include air pressure, working temperature and environmental corrosivity.
[0009] In a feasible implementation, the second predetermined environmental feature threshold includes a first threshold and a second threshold, the first threshold has an adjacent relationship with the lower limit of the first predetermined environmental feature threshold, and the second threshold has an adjacent relationship with the upper limit of the first predetermined environmental feature threshold.
[0010] In a feasible implementation, the method includes:
[0011] A first parameter strategy for the key production parameter is randomly generated; a second historical record is extracted from the historical valve production parameter record, wherein the second historical record includes second historical production parameter information and second historical performance parameter information, wherein the parameter information similarity between the first parameter strategy and the second historical production parameter information reaches a similarity limit; when the second comprehensive performance index obtained by the weighted normalization processing of the second historical performance parameter information reaches a performance index limit, the first parameter strategy is used as the optimal key production parameter strategy.
[0012] In a feasible implementation, the method includes:
[0013] Monitor the first two-end pressure difference of the first valve under the first parameter strategy; introduce a flow coefficient evaluation function to analyze the first two-end pressure difference to obtain the first valve flow coefficient of the first valve; obtain the first bubble rate of the first valve based on the bubble detection principle, and determine the first valve leakage rate according to the first bubble rate; correct the second comprehensive performance index based on the first valve flow coefficient and the first valve leakage rate to obtain the second target comprehensive performance index.
[0014] In a feasible implementation, the expression of the flow coefficient evaluation function is as follows:
[0015] ;
[0016] in, Characterizing the First Valve The first valve flow coefficient, Characterization through the first valve The mass flow rate of the first fluid compared to water, characterizing a first fluid comprehensive property of the first fluid, Characterizing the first fluid performance parameters, Characterizing the The weight of each performance parameter, a characteristic number of fluid performance that is included in the comprehensive performance of the first fluid, characterizing the specific gravity of the first fluid, Characterize the first two-end pressure difference.
[0017] In a second aspect, the present invention further provides a valve production parameter optimization system based on product requirements, wherein the system comprises:
[0018] A weight distribution module is used to distribute weights to predetermined performance parameters based on a target application scenario of a target valve to obtain a target weight distribution.
[0019] A performance parameter screening module is used to screen the predetermined performance parameters based on the target weight distribution to obtain key performance parameters.
[0020] A history record extraction module is used to extract a first history record from a historical valve production parameter record, wherein the first history record includes first historical production parameter information and first historical performance parameter information.
[0021] A historical variable selection module is used to use the first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter as a dependent variable.
[0022] A sensitivity analysis module, wherein the sensitivity analysis module is used to use the first historical production parameter information as an independent variable, perform a sensitivity analysis with the dependent variable, obtain a first sensitivity analysis result, and determine key production parameters based on the first sensitivity analysis result.
[0023] A key parameter optimization module is used to perform global optimization on the key production parameters to obtain an optimal key production parameter strategy, and produce the target valve based on the optimal key production parameter strategy.
[0024] The present invention discloses a valve production parameter optimization method and system based on product requirements, including: weighting predetermined performance parameters based on target application scenarios of target valves to obtain target weighting; screening predetermined performance parameters based on target weighting to obtain key performance parameters; extracting the first historical record in the historical valve production parameter record, the first historical record including the first historical production parameter information and the first historical performance parameter information; using the first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter as the dependent variable; using the first historical production parameter information as the independent variable, and performing sensitivity analysis with the dependent variable to obtain the first sensitivity analysis result, and determining the key production parameters according to the first sensitivity analysis result; performing global optimization on the key production parameters to obtain the optimal key production parameter strategy, and producing the target valve based on the optimal key production parameter strategy. The valve production parameter optimization method and system based on product requirements disclosed by the present invention solves the technical problems of high parameter debugging cost and low production efficiency, and achieves the technical effect of improving parameter optimization efficiency and reducing debugging cost. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 It is a flow chart of the valve production parameter optimization method based on product requirements of the present invention;
[0026] Figure 2 It is a structural schematic diagram of the valve production parameter optimization system based on product requirements of the present invention.
[0027] Explanation of reference numerals: weight allocation module 11, performance parameter screening module 12, historical record extraction module 13, historical variable selection module 14, sensitivity analysis module 15, key parameter optimization module 16. DETAILED DESCRIPTION
[0028] The technical solution provided in the embodiments of the present invention is to solve the technical problems of high parameter debugging cost and low production efficiency in the prior art. The overall idea adopted is as follows:
[0029] First, according to the application scenario of the target valve, the predetermined performance parameters are weighted to obtain the target weight distribution.
[0030] Then, based on these target weight assignments, the predetermined performance parameters are screened to determine the key performance parameters.
[0031] Next, a first historical record is extracted from the historical valve production parameter record, where the record includes first historical production parameter information and first historical performance parameter information.
[0032] The first historical performance parameter information is traversed using the key performance parameters to obtain the first historical key performance parameter information in the first traversal result, and the key performance parameter information is used as the dependent variable.
[0033] The first historical production parameter information is used as an independent variable, and a sensitivity analysis is performed with the dependent variable to obtain a first sensitivity analysis result. According to the first sensitivity analysis result, the key production parameters are determined.
[0034] The key production parameters are globally optimized to obtain the optimal key production parameter strategy. Finally, the target valve is produced based on this optimal key production parameter strategy.
[0035] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.
[0036] Embodiment 1
[0037] Figure 1 The figure is a flow chart of a valve production parameter optimization method based on product requirements of the present invention, wherein the method comprises:
[0038] The predetermined performance parameters are weighted based on the target application scenario of the target valve to obtain a target weight distribution.
[0039] Optionally, based on the target application scenario of the target valve, corresponding weights are assigned to predetermined performance parameters. The obtained target weight distribution represents the degree of attention paid by the target application scenario to different performance parameters of the target valve. Performance parameters with higher levels of attention have a more significant impact on the performance of the target valve in the target scenario and are of higher importance. Therefore, they are assigned higher weight values accordingly.
[0040] Among them, the target application scenarios of the target valve include petrochemical industry, water supply system, thermal power generation, etc. Different application scenarios have different environmental conditions, application requirements and performance parameter attention.
[0041] Furthermore, by analyzing the operating conditions, environmental factors and working requirements in the target application scenario, combined with the functions and application requirements of the valve, predetermined performance parameters can be determined. For example, the predetermined performance parameters include pressure bearing capacity, flow control accuracy, corrosion resistance, temperature resistance, response speed, etc.
[0042] Optionally, weights are assigned to predetermined performance parameters, and the allocation methods may include: an allocation method based on data-driven (such as data mining, machine learning, etc.), analyzing the operating data in the application scenario to determine the weights of the performance parameters; an allocation method based on user needs, specifically, by obtaining the performance parameter requirements of the target valve in the target scenario or the target valve task book, bidding documents and other information, the user's performance parameter requirements and performance parameter preferences for the target valve are obtained, and weight allocation is performed.
[0043] Exemplarily, PCA principal component analysis is used to perform data-driven weight allocation. First, data collection and preprocessing are performed to collect historical data related to various predetermined performance parameters of the target valve in the application scenario, including pressure bearing capacity, flow control accuracy, corrosion resistance, temperature resistance, response speed and other indicators. Then, the collected data is cleaned to remove noise and outliers, and the data of different dimensions are standardized to have the same scale. Next, a data matrix is constructed, that is, the preprocessed data is constructed into a matrix, in which each row represents a sample and each column represents a performance parameter, and the covariance matrix of the data matrix is calculated to measure the linear relationship between different performance parameters. Then, based on the covariance matrix obtained above, eigenvalue decomposition is performed to obtain eigenvalues and eigenvectors, where the eigenvalues represent the variances of each principal component and the eigenvectors represent the directions of each principal component. Then, the eigenvalues are sorted, and based on the preset principal component cumulative contribution rate threshold (such as more than 90%), the first few principal components that meet the requirements are selected, and the principal component contribution rates of the obtained multiple principal components are standardized to calculate the weights of each principal component. The standardized weights are the target weight allocations for each performance parameter.
[0044] Based on the target application scenario, the predetermined performance parameters are weighted and the importance of different performance parameters is quantified, thus providing a basis for optimizing valve production and improving performance, which helps to ensure that valve production products are more in line with actual application needs.
[0045] In some embodiments, weight distribution is performed on the predetermined performance parameters based on the target application scenario of the target valve to obtain the target weight distribution, including:
[0046] Based on big data, historical working condition records of similar valve products of the target valve in the target application scenario are obtained, and the historical working condition records include historical working environment characteristic information; a first predetermined environmental characteristic threshold is read, and it is determined whether the first historical environmental characteristic data in the historical working environment characteristic information is within the first predetermined environmental characteristic threshold, the first historical environmental characteristic data corresponding to the first environmental characteristic; if so, a first demand performance corresponding to the first environmental characteristic is added to a first weight level, and if not, it is determined whether the first historical environmental characteristic data is within a second predetermined environmental characteristic threshold; if so, the first demand performance is added to a second weight level, and if not, the first demand performance is added to a third weight level; the target weight distribution is generated based on the first weight level, the second weight level and the third weight level.
[0047] Optionally, the above big data is constructed based on data sources such as valve selection database, valve supplier, valve use environment or use scenario management system, including a multi-source heterogeneous database of valves of various models and types and their production, work application scenarios, and work record data.
[0048] Optionally, based on a fuzzy search method, historical working condition records of similar valve products of the target valve in the target application scenario are obtained. Among them, similar valve products of the target valve can be classified and obtained according to multiple dimensions such as function, operation mode, structure and application scenario, and exemplary include valve products of the same structure type, same function type, same application scenario but different product specifications and product operation modes.
[0049] In some implementations, the historical working environment characteristic information includes a plurality of characteristic data corresponding to predetermined environmental characteristics, wherein the predetermined environmental characteristics include at least air pressure, working temperature, and environmental corrosivity.
[0050] Optionally, the historical working condition record includes a variety of historical working environment characteristic information, such as working temperature, air pressure, environmental corrosiveness, etc. The working environment characteristic information of the valve is related to the application scenario in which it is located on the one hand, and is affected by the specific working environment on the other hand. For example, for the same power application scenario, the environmental corrosiveness of the working environment at sea or in coastal areas is stronger than that of inland areas.
[0051] Optionally, a first environmental feature is randomly selected from a plurality of predetermined performance parameters, and according to the selection result, a first predetermined environmental feature threshold corresponding to the first environmental feature is read, and then, based on the preset first predetermined environmental feature threshold, it is determined whether the first historical environmental feature data meets the first predetermined environmental feature threshold. The first predetermined environmental feature threshold includes an upper threshold limit and a lower threshold limit, defining a threshold space.
[0052] Furthermore, if the first historical environmental characteristic data is within the first predetermined environmental characteristic threshold range, it can be considered that the first historical environmental characteristic data is located in a better environmental interval, and then the corresponding first demand performance is added to the first weight level. If not, continue to determine whether the first historical environmental characteristic data is within the corresponding range of the second predetermined environmental characteristic threshold.
[0053] In some implementations, the second predetermined environmental characteristic threshold includes a first threshold and a second threshold, the first threshold has an adjacent relationship with the lower limit of the first predetermined environmental characteristic threshold, and the second threshold has an adjacent relationship with the upper limit of the first predetermined environmental characteristic threshold.
[0054] Optionally, the second predetermined environmental feature threshold includes a first threshold and a second threshold, wherein the first threshold is adjacent to the lower limit of the first predetermined environmental feature threshold, and the second threshold is adjacent to the upper limit of the first predetermined environmental feature threshold. In other words, the second predetermined environmental feature threshold specifies a set of threshold spaces adjacent to the threshold space defined by the first predetermined environmental feature threshold, specifically, including a first threshold space between the first threshold and the lower limit of the first predetermined environmental feature threshold, and a second threshold space between the second threshold and the upper limit of the first predetermined environmental feature threshold.
[0055] Specifically, the environmental state represented by a set of threshold spaces formed by the first threshold and the second threshold in the second predetermined environmental characteristic threshold is worse than the environmental state represented by a threshold space defined by the first predetermined environmental characteristic threshold, and if neither the first predetermined environmental characteristic threshold nor the second predetermined environmental characteristic threshold is met, it can be considered that the first historical environmental characteristic data corresponds to a more severe environmental condition. In other words, the first predetermined environmental characteristic threshold defines the environmental characteristic data space of the standard environment, and the second predetermined environmental characteristic threshold defines the environmental characteristic data space of the medium environment and the environmental space of the severe environment (such as high salt, high humidity, high cold, etc.).
[0056] Optionally, if the first historical environmental characteristic data is within the second predetermined environmental characteristic threshold range, the corresponding first demand performance is added to the second weight level. Correspondingly, if the first historical environmental characteristic data is not within any of the above predetermined environmental characteristic threshold ranges, the corresponding first demand performance is added to the third weight level.
[0057] Optionally, based on the first weight level, the second weight level and the third weight level, all required performances are summarized to generate a target weight distribution, wherein different weight levels correspond to different weight values. Exemplarily, the weight value of the first weight level is the lowest, the weight value of the second weight level is slightly higher, and the weight value of the third weight level is the highest.
[0058] The above method ensures the scientificity and rationality of weight allocation by analyzing historical working condition records and judging thresholds. The hierarchical weight allocation method can more accurately reflect the performance requirements under different environmental characteristics and improve the performance of valves in actual applications.
[0059] The predetermined performance parameters are screened based on the target weight allocation to obtain key performance parameters.
[0060] Optionally, based on the above-mentioned weight distribution, first, the performance parameters included in the first weight level are selected as key performance parameters, and subsequent parameter optimization and valve production are carried out. If the parameter optimization results do not meet the requirements of the target scenario, additional key performance parameters are selected based on the performance parameters included in the second weight level.
[0061] A first historical record in the historical valve production parameter record is extracted, wherein the first historical record includes first historical production parameter information and first historical performance parameter information.
[0062] Optionally, a first historical record is extracted from a historical valve production parameter record database, wherein the first historical record includes production and performance parameters collected at a specific time or in a specific production batch.
[0063] Specifically, the first historical production parameter information includes various parameters related to the valve production process, including: material composition, including the specific composition and proportion of the metal or alloy used. Processing technology, including casting, forging, welding, heat treatment and other process parameters. Production equipment parameters, including the setting parameters of the production equipment, such as temperature, pressure, speed, etc. Process control parameters, including control parameters in the production process, such as cooling speed, processing sequence, etc.
[0064] Specifically, the first historical performance parameter information includes the performance test results of the final product, such as: the sealing and stability of the valve under different pressures, the performance of the valve at different temperatures, the corrosion resistance of the valve in different corrosive environments, the sealing effect and leakage of the valve, the durability and reliability of the valve in long-term use, etc.
[0065] By extracting and analyzing historical valve production parameter records and understanding the relationship between historical production parameters and valve performance, it is helpful to subsequently optimize key performance parameters and improve the quality and performance of valve products.
[0066] The first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter is used as a dependent variable.
[0067] Optionally, the first historical performance parameter information is screened and cleaned based on the key performance parameters to obtain the actual data of the key performance parameters in the first historical performance parameter information, thereby reducing the amount of data and reducing non-critical performance parameters. This helps to reduce interference in subsequent analysis. The first historical key performance parameter information is the dependent variable for subsequent analysis. These dependent variables represent the performance parameters that can effectively reflect the valve performance in the historical production records.
[0068] The first historical production parameter information is used as an independent variable to perform a sensitivity analysis with the dependent variable to obtain a first sensitivity analysis result, and key production parameters are determined based on the first sensitivity analysis result.
[0069] Among them, the first historical production parameter information is the independent variable of the analysis, which represents the parameters that may have a significant impact on the valve performance in the historical production records. The first historical production parameter information is used as an independent variable to perform sensitivity analysis with the previously extracted key performance parameters (dependent variables). Through sensitivity analysis, it is possible to determine which production parameters have a significant impact on the key performance parameters, thereby determining the key production parameters.
[0070] Specifically, sensitivity analysis is the process of evaluating the impact of independent variables (production parameters) on dependent variables (performance parameters). Optional sensitivity analysis methods include: Regression analysis, which evaluates the impact of each production parameter on key performance parameters through regression models (such as linear regression, nonlinear regression). Principal component analysis (PCA), which determines the production parameters that have a significant impact on performance parameters by reducing the data dimension. Monte Carlo simulation, which uses random sampling methods to evaluate the impact of changes in production parameters on performance parameters. Local sensitivity analysis, which evaluates the impact of changes in production parameters on performance parameters by making small changes in production parameters.
[0071] Furthermore, based on the results of sensitivity analysis, the production parameters that have a significant impact on key performance parameters, namely key production parameters, are identified, which helps to focus on optimizing key production parameters in the future, thereby improving the efficiency of parameter optimization.
[0072] The key production parameters are globally optimized to obtain an optimal key production parameter strategy, and the target valve is produced based on the optimal key production parameter strategy.
[0073] In some embodiments, performing global optimization on the key production parameters to obtain an optimal key production parameter strategy includes:
[0074] A first parameter strategy for the key production parameter is randomly generated; a second historical record is extracted from the historical valve production parameter record, wherein the second historical record includes second historical production parameter information and second historical performance parameter information, wherein the parameter information similarity between the first parameter strategy and the second historical production parameter information reaches a similarity limit; when the second comprehensive performance index obtained by the weighted normalization processing of the second historical performance parameter information reaches a performance index limit, the first parameter strategy is used as the optimal key production parameter strategy.
[0075] Optionally, first, based on the historical production parameter strategy and the equipment control domain of the target valve production scenario, determine the optimization space for key production parameters. Exemplarily, it includes counting the value range and frequency of the historical production parameter strategy, identifying the commonly used parameter intervals and limit values, and then obtaining the intersection of the above parameter intervals and the equipment control domain of the target valve production scenario, and determining it as the optimization space. Among them, the equipment control domain refers to the adjustable range and operating limit of the production equipment, including temperature range, pressure range, speed range, etc. By obtaining the specific control parameter range of the equipment under the target valve production scenario, it is ensured that the optimization parameters are within the operating capacity of the equipment. Through this optimization space, the generation range of the parameter strategy in the optimization process is specified to limit the reasonable range of parameters, thereby reducing the computational complexity and improving the optimization efficiency.
[0076] Furthermore, a set of key production parameters is randomly generated in the above-mentioned optimization space as the first parameter strategy. Exemplarily, the parameter strategy includes material composition, processing technology, production equipment parameters, process control parameters, etc. Then, based on the similarity with the first parameter strategy, a second historical record is extracted from the historical valve production parameter record. Specifically, if the similarity between the historical production parameter information of a certain historical record and the second historical performance parameter information reaches a preset similarity limit, the historical record is set as the second historical record, and the second historical performance parameter information of the second historical record can be approximately regarded as the performance parameter information of the first parameter strategy.
[0077] Optionally, the second historical performance parameter information is weighted and normalized to obtain a second comprehensive performance index, wherein weighted normalization is used to unify performance parameters of different dimensions to the same scale for comprehensive evaluation.
[0078] Then, the second comprehensive performance index is evaluated to determine whether it reaches the performance index limit. If it reaches it, the first parameter strategy is used as the optimal key production parameter strategy. The performance index limit is a constraint value obtained by performing the same performance evaluation as above on the target performance requirements of the target scenario.
[0079] In some implementations, after taking the first parameter strategy as the optimal key production parameter strategy and producing the target valve based on the optimal key production parameter strategy, the method further includes:
[0080] Monitor the first two-end pressure difference of the first valve under the first parameter strategy; introduce a flow coefficient evaluation function to analyze the first two-end pressure difference to obtain the first valve flow coefficient of the first valve; obtain the first bubble rate of the first valve based on the bubble detection principle, and determine the first valve leakage rate according to the first bubble rate; correct the second comprehensive performance index based on the first valve flow coefficient and the first valve leakage rate to obtain the second target comprehensive performance index.
[0081] Optionally, valve production is performed based on the optimal key production parameter strategy. After obtaining the target valve product, pressure sensors are installed at both ends of the target valve product to perform a working condition simulation test on the target valve product, and the pressure difference when the valve is opened and closed is monitored and recorded in real time. Then, a flow coefficient evaluation function is introduced to analyze the first pressure difference between the two ends. The flow coefficient evaluation function is used to evaluate the flow capacity of the valve under a specific pressure difference.
[0082] Furthermore, the expression of the flow coefficient evaluation function is as follows:
[0083] ;
[0084] in, Characterizing the First Valve The first valve flow coefficient, Characterization through the first valve The mass flow rate of the first fluid compared to water, characterizing a first fluid comprehensive property of the first fluid, Characterizing the first fluid performance parameters, Characterizing the The weight of each performance parameter, a characteristic number of fluid performance that is included in the comprehensive performance of the first fluid, characterizing the specific gravity of the first fluid, Characterize the first two-end pressure difference.
[0085] Among them, the performance parameters of the fluid Including parameters such as fluid viscosity and temperature.
[0086] Optionally, based on the bubble detection principle, an ultrasonic or optical sensor is used to detect the number of bubbles in the fluid and record the first bubble rate. Then, the relationship between the bubble rate and the leakage rate is determined by an empirical formula or a fitting curve fitted by experimental data, and the first valve leakage rate is determined according to the first bubble rate.
[0087] Furthermore, the valve flow coefficient and leakage rate are used to correct the original comprehensive performance index to obtain a more accurate performance evaluation result, i.e., the second target comprehensive performance index. Exemplarily, first, based on the first valve leakage rate, the first valve flow coefficient is corrected to obtain the first real flow coefficient of the first fluid, wherein the first real flow coefficient of the first fluid = the first valve flow coefficient (1-first valve leakage rate). Then, the corrected first real flow coefficient is updated to the second historical performance parameter information, and the update result is evaluated to obtain the second target comprehensive performance index.
[0088] By monitoring and correcting valve performance, accurate valve performance data can be provided. Combined with the bubble rate to detect valve leakage, it is helpful to promptly discover and solve potential problems, optimize valve design and production processes, and improve product quality.
[0089] In summary, the valve production parameter optimization method based on product requirements provided by the present invention has the following technical effects:
[0090] The target weight distribution is obtained by weighting the predetermined performance parameters based on the target application scenario of the target valve; the predetermined performance parameters are screened based on the target weight distribution to obtain the key performance parameters; the first historical record in the historical valve production parameter record is extracted, and the first historical record includes the first historical production parameter information and the first historical performance parameter information; the first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter is used as the dependent variable; the first historical production parameter information is used as the independent variable, and a sensitivity analysis is performed with the dependent variable to obtain the first sensitivity analysis result, and the key production parameters are determined according to the first sensitivity analysis result; the key production parameters are globally optimized to obtain the optimal key production parameter strategy, and the target valve is produced based on the optimal key production parameter strategy. Thus, the technical effect of improving parameter optimization efficiency and reducing commissioning costs is achieved.
[0091] Embodiment 2
[0092] Figure 2 Schematic diagram of the valve production parameter optimization system based on product requirements of the present invention. Figure 1 The flow chart of the valve production parameter optimization method based on product demand of the present invention can be shown as follows: Figure 2 The structure shown is implemented.
[0093] Based on the same concept as the valve production parameter optimization method based on product demand in the above embodiment, the valve production parameter optimization system based on product demand provided by the present invention includes:
[0094] The weight distribution module 11 is used to distribute weights to predetermined performance parameters based on a target application scenario of a target valve to obtain a target weight distribution.
[0095] The performance parameter screening module 12 is used to screen the predetermined performance parameters based on the target weight distribution to obtain key performance parameters.
[0096] The history record extraction module 13 is used to extract the first history record from the historical valve production parameter record, where the first history record includes the first historical production parameter information and the first historical performance parameter information.
[0097] The historical variable selection module 14 is used to use the first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter as a dependent variable.
[0098] The sensitivity analysis module 15 is used to use the first historical production parameter information as an independent variable to perform a sensitivity analysis with the dependent variable to obtain a first sensitivity analysis result, and determine the key production parameters according to the first sensitivity analysis result.
[0099] The key parameter optimization module 16 is used to perform global optimization on the key production parameters to obtain an optimal key production parameter strategy, and produce the target valve based on the optimal key production parameter strategy.
[0100] Among them, the weight distribution module 11 includes:
[0101] A record acquisition unit is used to acquire historical working condition records of similar valve products of the target valve in the target application scenario based on big data, wherein the historical working condition records include historical working environment feature information.
[0102] The first determination unit is used to read a first predetermined environmental characteristic threshold and determine whether first historical environmental characteristic data in the historical working environment characteristic information is within the first predetermined environmental characteristic threshold, wherein the first historical environmental characteristic data corresponds to the first environmental characteristic.
[0103] The second judging unit is configured to add the first demand performance corresponding to the first environmental feature to a first weight level if it is within the first weight level, and to judge whether the first historical environmental feature data is within a second predetermined environmental feature threshold if it is not within the first weight level.
[0104] The third determining unit is configured to add the first demand performance to the second weight level if φ is within the range of φ, and to add the first demand performance to the third weight level if φ is not within the range of φ.
[0105] A hierarchical weight allocation unit is used to generate the target weight allocation based on the first weight level, the second weight level and the third weight level.
[0106] Furthermore, the historical working environment characteristic information includes a plurality of characteristic data corresponding to predetermined environmental characteristics, wherein the predetermined environmental characteristics at least include air pressure, working temperature and environmental corrosivity.
[0107] Furthermore, the second predetermined environmental feature threshold includes a first threshold and a second threshold, the first threshold has an adjacent relationship with the lower limit of the first predetermined environmental feature threshold, and the second threshold has an adjacent relationship with the upper limit of the first predetermined environmental feature threshold.
[0108] In some embodiments, the key parameter optimization module 16 includes:
[0109] An initial strategy generating unit is used to randomly generate a first parameter strategy for the key production parameter.
[0110] An approximate selection unit is used to extract a second historical record from the historical valve production parameter record, wherein the second historical record includes second historical production parameter information and second historical performance parameter information, wherein the parameter information similarity between the first parameter strategy and the second historical production parameter information reaches a similarity limit.
[0111] An evaluation output unit is used to use the first parameter strategy as the optimal key production parameter strategy when the second comprehensive performance index obtained by the second historical performance parameter information after weighted normalization reaches the performance index limit.
[0112] In some embodiments, the key parameter optimization module 16 further includes:
[0113] The pressure acquisition unit is used to monitor the pressure difference between the first two ends of the first valve under the first parameter strategy.
[0114] The pressure difference analysis unit is used to introduce a flow coefficient evaluation function to analyze the pressure difference between the first two ends to obtain a first valve flow coefficient of the first valve.
[0115] The bubble detection unit is used to obtain a first bubble rate of the first valve based on the bubble detection principle, and determine a leakage rate of the first valve according to the first bubble rate.
[0116] A performance index correction unit is used to correct the second comprehensive performance index based on the first valve flow coefficient and the first valve leakage rate to obtain a second target comprehensive performance index.
[0117] In some implementations, the pressure difference analysis unit in the key parameter optimization module 16 includes: a flow coefficient evaluation function, and the expression of the flow coefficient evaluation function is as follows:
[0118] ;
[0119] in, Characterizing the First Valve The first valve flow coefficient, Characterization through the first valve The mass flow rate of the first fluid compared to water, characterizing a first fluid comprehensive property of the first fluid, Characterizing the first fluid performance parameters, Characterizing the The weight of each performance parameter, a characteristic number of fluid performance that is included in the comprehensive performance of the first fluid, characterizing the specific gravity of the first fluid, Characterize the first two-end pressure difference.
[0120] It should be understood that the embodiments mentioned in this specification focus on their differences from other embodiments. The specific embodiments in the aforementioned embodiment one are also applicable to the valve production parameter optimization system based on product requirements described in embodiment two. For the sake of brevity of the specification, they will not be further elaborated here.
[0121] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; 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 invention, and should be included in the protection scope of the present invention.
Claims
1. Valve production parameter optimization method based on product requirements, It is characterized in that include: Weighting the predetermined performance parameters based on the target application scenario of the target valve to obtain a target weighting distribution; Screening the predetermined performance parameters based on the target weight distribution to obtain key performance parameters; Extracting a first historical record from the historical valve production parameter record, wherein the first historical record includes first historical production parameter information and first historical performance parameter information; Using the first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter as a dependent variable; Using the first historical production parameter information as an independent variable, and performing a sensitivity analysis with the dependent variable to obtain a first sensitivity analysis result, and determining key production parameters according to the first sensitivity analysis result; Performing global optimization on the key production parameters to obtain an optimal key production parameter strategy, and producing the target valve based on the optimal key production parameter strategy; Wherein, the method further comprises: Based on big data, obtain historical working condition records of similar valve products of the target valve in the target application scenario, wherein the historical working condition records include historical working environment feature information; Reading a first predetermined environmental characteristic threshold, and determining whether first historical environmental characteristic data in the historical working environment characteristic information is within the first predetermined environmental characteristic threshold, the first historical environmental characteristic data corresponding to the first environmental characteristic; If so, adding the first demand performance corresponding to the first environmental feature to the first weight level; if not, determining whether the first historical environmental feature data is within a second predetermined environmental feature threshold; If so, adding the first demand performance to a second weight level; if not, adding the first demand performance to a third weight level; generating the target weight allocation based on the first weight level, the second weight level, and the third weight level; The historical working environment characteristic information includes a plurality of characteristic data corresponding to predetermined environmental characteristics, wherein the predetermined environmental characteristics at least include air pressure, working temperature and environmental corrosivity; The second predetermined environmental characteristic threshold includes a first threshold and a second threshold, the first threshold is adjacent to the lower limit of the first predetermined environmental characteristic threshold, and the second threshold is adjacent to the upper limit of the first predetermined environmental characteristic threshold.
2. According to the valve production parameter optimization method based on product demand according to claim 1, It is characterized in that include: A first parameter strategy for randomly generating the key production parameters; Extracting a second historical record from the historical valve production parameter record, the second historical record including second historical production parameter information and second historical performance parameter information, wherein the parameter information similarity between the first parameter strategy and the second historical production parameter information reaches a similarity limit; When the second comprehensive performance index obtained by weighted normalization of the second historical performance parameter information reaches the performance index limit, the first parameter strategy is used as the optimal key production parameter strategy.
3. According to the valve production parameter optimization method based on product demand as claimed in claim 2, It is characterized in that Also includes: Monitor the pressure difference between the first two ends of the first valve under the first parameter strategy; Introducing a flow coefficient evaluation function to analyze the pressure difference between the first two ends to obtain a first valve flow coefficient of the first valve; Acquire a first bubble rate of the first valve based on a bubble detection principle, and determine a leakage rate of the first valve according to the first bubble rate; The second comprehensive performance index is corrected based on the first valve flow coefficient and the first valve leakage rate to obtain a second target comprehensive performance index.
4. According to the valve production parameter optimization method based on product demand as claimed in claim 3, It is characterized in that The expression of the flow coefficient evaluation function is as follows: ; in, Characterizing the First Valve The first valve flow coefficient, Characterization through the first valve The mass flow rate of the first fluid compared to water, characterizing a first fluid comprehensive property of the first fluid, Characterizing the first fluid performance parameters, Characterizing the The weight of each performance parameter, a characteristic number of fluid performance that is included in the comprehensive performance of the first fluid, characterizing the specific gravity of the first fluid, Characterize the first two-end pressure difference.
5. Valve production parameter optimization system based on product requirements, It is characterized in that The system is used to execute the valve production parameter optimization method based on product demand according to any one of claims 1 to 4, and the system comprises: A weight distribution module, the weight distribution module is used to distribute weights to predetermined performance parameters based on a target application scenario of a target valve to obtain a target weight distribution; A performance parameter screening module, the performance parameter screening module is used to screen the predetermined performance parameters based on the target weight distribution to obtain key performance parameters; A historical record extraction module, the historical record extraction module is used to extract a first historical record in the historical valve production parameter record, the first historical record includes first historical production parameter information and first historical performance parameter information; A historical variable selection module, the historical variable selection module is used to use the first historical key performance parameter information in the first traversal result obtained by traversing the first historical performance parameter information based on the key performance parameter as a dependent variable; A sensitivity analysis module, wherein the sensitivity analysis module is used to use the first historical production parameter information as an independent variable, perform sensitivity analysis on the dependent variable, obtain a first sensitivity analysis result, and determine key production parameters according to the first sensitivity analysis result; A key parameter optimization module is used to perform global optimization on the key production parameters to obtain an optimal key production parameter strategy, and produce the target valve based on the optimal key production parameter strategy.
Citation Information
Cited By
Parameter optimization method and system in valve production
CN120671899A
