A method, medium and system for optimizing steps of a complex industrial process

Abstract

The application provides a step optimization method, medium and system of a complex industrial process, belongs to the technical field of big data modeling, and comprises the following steps: establishing a multidimensional data acquisition system, installing sensors and monitoring equipment at key nodes of a target industrial process, collecting process parameter data, equipment state data and product quality data in a parallel multithreading mode, forming an original data set, and collecting process connection relationship data; performing time domain decomposition operation on the original data set, decomposing each data into a long-term stable numerical component and a short-term fluctuation numerical component, and respectively obtaining a process parameter stable component, a process parameter fluctuation component, an equipment state stable component and an equipment state fluctuation component; and establishing the process parameter fluctuation component, which can solve the problem that a product cannot be stably operated in an optimal state.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of big data modeling, and in particular, relates to a step optimization method for a complex industrial process, a medium and a system. BACKGROUND

[0002] Currently, complex industrial processes such as large chemical plants, steel plants, and energy enterprises are facing severe challenges in product quality control. These process flows are usually composed of multiple key processes in series, with strong coupling between process parameters and equipment states, and complex effects on the final product quality. For example, the reaction kettle process in a chemical production line is affected by process parameters such as temperature, pressure, and flow rate, as well as equipment states such as motor load and bearing vibration. There are complex nonlinear relationships between these parameters, and the transmission of the process flow will cause attenuation and coupling, bringing great uncertainty to the stability of the product quality.

[0003] To address the above problems, existing technologies usually adopt empirical parameter tuning or simulation optimization methods based on physical models. Empirical tuning methods rely on the rich experience of process experts, and through repeated trial and error to find the best parameter settings, which is not only inefficient, but also difficult to ensure the reliability and repeatability of the final results. Modeling methods based on physical mechanisms, such as reaction kinetics models and heat and mass transfer models, can more accurately describe the overall process, but are also limited by the assumptions of the model, making it difficult to fully reflect the complex situation in actual production. On the other hand, these optimization methods are usually limited to a certain process, lacking global consideration, and difficult to achieve system optimization of the entire process flow.

[0004] Therefore, there is an urgent need for a more systematic and intelligent process flow optimization method that can fully consider the coupling effects of process parameters and equipment states, and should have the ability of simulation verification and adaptive adjustment to ensure the stable operation of product quality in the optimal state. This is the core technical problem that the present application attempts to solve. SUMMARY

[0005] Therefore, the present application provides a step optimization method for a complex industrial process, a medium and a system, which can solve the problem that the product cannot be stably operated in the optimal state.

[0006] The present application is implemented as follows:

[0007] The present application provides a step optimization method for a complex industrial process, a medium and a system, which can solve the problem that the product cannot be stably operated in the optimal state.

[0008] S10, a multi-dimensional data acquisition system is established, sensors and monitoring devices are installed at key nodes of the target industrial process, process parameter data, equipment state data and product quality data are collected in a parallel multi-thread mode to form an original data set, and process connection relationship data is collected;

[0009] S20, time domain decomposition operation is performed on the original data set, each data is decomposed into a long-term stable numerical component and a short-term fluctuation numerical component, process parameter stable components and process parameter fluctuation components, equipment state stable components and equipment state fluctuation components are obtained respectively;

[0010] S30, a mapping relationship equation group of the process parameter fluctuation component, the equipment state fluctuation component and the product quality data is established, a process parameter influence coefficient matrix and an equipment state influence coefficient matrix are generated;

[0011] S40, based on the process parameter influence coefficient matrix and the equipment state influence coefficient matrix, a process operation stability matrix and an equipment operation stability matrix are calculated, and a process mathematical model is constructed by numerical combination operation of the process operation stability matrix, the equipment operation stability matrix, the process parameter stable component and the equipment state stable component;

[0012] S50, a digital mapping technology is used to construct the target industrial process simulation environment, the process mathematical model is input into the simulation environment for numerical verification, and process parameter correction amounts and equipment parameter correction amounts are calculated;

[0013] S60, based on the process parameter correction amounts and the equipment parameter correction amounts, the target industrial process pilot line segment is adjusted in parameters, pilot parameter data is collected, and an optimization effect value is obtained by calculating the deviation value of the pilot parameter data and the product quality data;

[0014] S70, based on the deviation value of the pilot parameter data and the product quality data, a running error value is calculated, a running correction proportion value, a running correction integral value and a running correction differential value are calculated based on the running error value, an automatic adjustment control unit is constructed according to the optimization effect value, a running correction instruction is generated by using a preset instruction correction equation according to the running error value, the running correction proportion value, the running correction integral value and the running correction differential value, and the process parameter dynamic correction of the target industrial process is realized based on the running correction instruction;

[0015] S80, deviation calculation is performed on the process parameter dynamic correction result and the product quality data to generate a process parameter optimization guidance scheme.

[0016] The process parameter data includes production temperature data, production pressure data, production speed data and production time data.

[0017] The equipment state data includes equipment running state data, equipment load rate data, equipment vibration data, equipment temperature data.

[0018] The product quality data includes product size data, product performance data, product appearance data, product defect data.

[0019] Further, the mapping relationship equation group includes a parameter influence mapping equation, a fluctuation attenuation mapping equation, a feature separation mapping equation, and a coefficient calculation mapping equation.

[0020] Further, the parameter influence mapping equation generates quality influence feature data by performing linear correlation operation on the product quality data, the process parameter fluctuation component, and the equipment state fluctuation component.

[0021] Further, the fluctuation attenuation mapping equation generates fluctuation attenuation data by performing iterative operation on the attenuation influence of the process parameter fluctuation component and the equipment state fluctuation component in the process flow connection relationship data.

[0022] Further, the feature separation mapping equation generates feature principal component data by performing principal component decomposition operation on the quality influence feature data and the fluctuation attenuation data.

[0023] Further, the coefficient calculation mapping equation generates the process parameter influence coefficient matrix and the equipment state influence coefficient matrix by performing numerical correspondence operation on the feature principal component data and the quality influence feature data.

[0024] Further, the target industrial flow pilot line segment selects a single complete production line in the process flow for optimization verification.

[0025] The process operation procedure document includes process parameter set values, process parameter adjustment intervals, process parameter dynamic correction strategies, and equipment running parameter limit values.

[0026] The second aspect of the application provides a computer readable storage medium, the computer readable storage medium stores program instructions, the program instructions are used to execute the above-mentioned complex industrial process step optimization method when running in the computer.

[0027] The third aspect of the application provides a complex industrial process step optimization system, which further includes the computer readable storage medium.

[0028] The application provides a step optimization method for a complex industrial process, fully utilizes a data-driven modeling analysis technology, and establishes a comprehensive mathematical model for describing the process-equipment-quality relationship through a series of algorithms such as time domain decomposition, parameter mapping and stability evaluation. On this basis, digital simulation and adaptive control technology are used to realize intelligent optimization of the production line parameters. Compared with the prior art, the method has the following outstanding advantages:

[0029] 1. Data-driven modeling method, which can be more close to the actual production situation. Compared with the method relying on experience debugging or physical mechanism model, the method uses the process parameters, equipment states and product quality data collected on site to obtain the quantitative relationship between the influencing factors through mathematical modeling, which is more suitable for the complexity of the industrial process.

[0030] 2. Systematic optimization strategy, realizing the coordinated improvement of the whole process. The prior art is usually limited to the optimization of a single process, while the method of the application is from the global, considering the interaction of each process parameter and equipment state, and proposing an optimization scheme suitable for the whole production line.

[0031] 3. Simulation verification and adaptive adjustment mechanism, ensuring the reliability of the optimization scheme. Before the actual pilot optimization, the method of the application first carries out sufficient parameter verification in the digital twin model, effectively avoiding the production loss caused by blind adjustment. At the same time, a closed-loop automatic control system is constructed, which can automatically fine-tune the process parameters according to the real-time production situation, and ensure the continuous and stable product quality.

[0032] 4. Strong generalization and universality. The method of the application is not aimed at a specific industry, but has wide applicability. As long as the target industrial process can collect necessary process, equipment and quality data, the optimization method can be applied to systematically improve the quality.

[0033] In summary, the complex industrial process optimization method proposed by the application fully utilizes the advanced technical means such as data analysis, simulation and adaptive control, realizes intelligent optimization of the whole production process, and provides a systematic solution for quality control of complex industrial processes. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 It is a flowchart of a step optimization method for a complex industrial process. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical scheme and advantages of the embodiments of the application more clear, the technical scheme in the embodiments of the application will be described clearly and completely with reference to the drawings in the embodiments of the application.

[0036] AsFigure 1 As shown, it is a flow chart of a step optimization method of a complex industrial process provided by the application, comprising the following steps:

[0037] S10, a multi-dimensional data acquisition system is established, sensors and monitoring equipment are installed at key nodes of the target industrial process, process parameter data, equipment state data and product quality data are acquired in a parallel multi-thread mode, an original data set is formed, and process connection relationship data is acquired;

[0038] S20, time domain decomposition operation is performed on the original data set, each data is decomposed into a long-term stable numerical component and a short-term fluctuation numerical component, and process parameter stable components and process parameter fluctuation components, equipment state stable components and equipment state fluctuation components are obtained respectively;

[0039] S30, a mapping relationship equation set of the process parameter fluctuation component, the equipment state fluctuation component and the product quality data is established, and a process parameter influence coefficient matrix and an equipment state influence coefficient matrix are generated;

[0040] S40, based on the process parameter influence coefficient matrix and the equipment state influence coefficient matrix, a process running stability matrix and an equipment running stability matrix are calculated, and a process running stability matrix, an equipment running stability matrix, a process parameter stable component and an equipment state stable component are combined and operated to construct a process mathematical model;

[0041] S50, a digital mapping technology is used to construct a target industrial process simulation environment, the process mathematical model is input into the simulation environment for numerical verification, and process parameter correction amounts and equipment parameter correction amounts are calculated;

[0042] S60, based on the process parameter correction amounts and the equipment parameter correction amounts, parameter adjustment is performed on a pilot line segment of the target industrial process, pilot parameter data are acquired, and an optimization effect value is obtained by calculating the deviation value of the pilot parameter data and the product quality data;

[0043] S70, based on the deviation value of the pilot parameter data and the product quality data, a running error value is calculated, a running correction proportion value, a running correction integral value and a running correction differential value are calculated based on the running error value, an automatic adjustment control unit is constructed according to the optimization effect value, a running correction instruction is generated by using a preset instruction correction equation according to the running error value, the running correction proportion value, the running correction integral value and the running correction differential value, and process parameter dynamic correction of the target industrial process is realized based on the running correction instruction;

[0044] S80, deviation calculation is performed on the process parameter dynamic correction result and the product quality data, and a process parameter optimization guidance scheme is generated.

[0045] In the technical solution, the process parameter data includes production temperature data, production pressure data, production speed data, and production time data.

[0046] The equipment state data includes equipment running state data, equipment load rate data, equipment vibration data, and equipment temperature data.

[0047] The product quality data includes product size data, product performance data, product appearance data, and product defect data.

[0048] Further, in the technical solution, the mapping relationship equation set includes a parameter influence mapping equation, a fluctuation attenuation mapping equation, a feature separation mapping equation, and a coefficient calculation mapping equation.

[0049] Further, in the technical solution, the parameter influence mapping equation generates quality influence feature data by performing linear correlation operation on the product quality data, the process parameter fluctuation component, and the equipment state fluctuation component.

[0050] Further, in the technical solution, the fluctuation attenuation mapping equation generates fluctuation attenuation data by performing iterative operation on the attenuation influence of the process parameter fluctuation component and the equipment state fluctuation component in the process flow connection relationship data.

[0051] Further, in the technical solution, the feature separation mapping equation generates feature principal component data by performing principal component decomposition operation on the quality influence feature data and the fluctuation attenuation data.

[0052] Further, in the technical solution, the coefficient calculation mapping equation generates a process parameter influence coefficient matrix and an equipment state influence coefficient matrix by performing numerical correspondence operation on the feature principal component data and the quality influence feature data.

[0053] Further, in the technical solution, the target industrial process pilot line segment selects a single complete production line in the process flow for optimization verification.

[0054] The process operation procedure document includes process parameter set values, process parameter adjustment intervals, process parameter dynamic correction strategies, and equipment running parameter limits.

[0055] It also includes S90, forming a process operation procedure document based on the process parameter optimization guidance scheme, and completing the overall optimization of the target industrial process.

[0056] The specific implementation of the above steps is described in detail as follows:

[0057] The specific implementation of step S10 is to establish a multi-dimensional data acquisition system. First, various types of sensors and monitoring devices are installed at key nodes of the target industrial process, such as raw material preparation, pretreatment, main reaction, post-treatment, and finished product processes. The sensors include temperature sensors, pressure sensors, flow rate sensors, etc., and the monitoring devices include motor current detection, vibration monitoring, load monitoring, etc. Process parameter data (temperature, pressure, speed, etc.), equipment state data (load, vibration, temperature, etc.), and product quality data (size, performance, appearance, defects, etc.) are synchronously collected in a parallel multi-thread manner to form an original data set. At the same time, the connection relationships between the processes of the process are also collected and recorded, laying a foundation for subsequent establishment of a process mathematical model.

[0058] The specific implementation of step S20 is to perform time domain decomposition processing on the original data set. Empirical Mode Decomposition (EMD) algorithm is used to perform multi-scale decomposition on various types of collected data. The EMD method can adaptively decompose nonlinear and non-stationary industrial process signals into intrinsic mode functions (IMF) and residual terms of different frequencies. In the decomposition process, first, the maximum and minimum value point sets of the signal are identified, and then cubic spline interpolation is used to construct upper and lower envelope lines to obtain the first layer intrinsic mode function. Then, the high-frequency fluctuation component and the low-frequency stable component are continuously extracted in an iterative manner until the residual meets the convergence condition.

[0059] Through this time domain decomposition operation, the process parameter data and the equipment state data can be decomposed into long-term stable components and short-term fluctuation components, which are denoted as process parameter stable component, process parameter fluctuation component, equipment state stable component, and equipment state fluctuation component. The purpose of this step is to lay a foundation for subsequent establishment of influence mapping relationship.

[0060] The specific implementation of step S30 is to establish the mapping relationship between parameter fluctuations and product quality. First, by performing linear correlation analysis on the product quality data and the process parameter fluctuation component and the equipment state fluctuation component, the influence degree of each parameter fluctuation on the product quality is determined, and quality influence feature data is generated. Second, considering that parameter fluctuations will attenuate and propagate in the process, an exponential decay function is used to model the propagation law of parameter fluctuations, and fluctuation attenuation data is obtained.

[0061] ​Then, the Principal Component Analysis (PCA) method is used to extract features and reduce dimensions of the quality influence feature data and the fluctuation attenuation data, and the principal component feature data is obtained. Finally, the process parameter influence coefficient matrix and the equipment state influence coefficient matrix are calculated by the least square method. The above steps establish the mapping relationship equation set of parameter fluctuation and product quality, which provides the basis for subsequent optimization.

[0062] The specific implementation of step S40 is to construct a process mathematical model. First, based on the process parameter influence coefficient matrix and the equipment state influence coefficient matrix obtained in step S30, the process operation stability matrix and the equipment operation stability matrix are calculated, reflecting the overall stability of the system.

[0063] Secondly, the process parameter stability component, the equipment state stability component and the above two stability matrices are numerically combined to establish a comprehensive process mathematical model. This model uses a linear weighting method, that is, where the weight coefficients w1, w2, w3 are solved by optimizing the objective function J = ∑(Y measured -Y model ) 2 , satisfying the constraint condition w1+w2+w3=1. The random error ω is also considered in the model to improve the adaptability and robustness of the model.

[0064] The purpose of this step is to establish a mathematical model that can describe the overall characteristics of the target industrial process, fully reflect the influence of process parameters, equipment states and their interactions on product quality, and provide a basis for subsequent simulation optimization.

[0065] The specific implementation of step S50 is to construct a simulation environment based on digital mapping technology. First, using digital mapping technologies such as Virtual Reality (VR) or Digital Twin, a simulation environment highly consistent with the actual production line is established. This simulation environment not only includes the geometric model of the process flow, but also includes the mathematical model of physical processes such as heat and momentum transfer.

[0066] Next, the process mathematical model established in step S40 is input into the simulation environment, and the correction amount of the process parameters and the correction amount of the equipment parameters are obtained through numerical simulation. During the simulation process, different process conditions and equipment states can also be set to observe their impact on product quality, providing decision support for the optimization of the actual production line.

[0067] The purpose of this step is to optimize the process parameters and equipment parameters in a computer simulation environment, avoiding blind attempts on the actual production line that may cause production losses.

[0068] The specific implementation of step S60 is to verify the parameter optimization on the actual production line. First, according to the process parameter correction amount and the equipment parameter correction amount obtained in step S50, the parameters of the pilot line segment of the target industrial process are adjusted. The selection of the pilot line segment is usually a single complete production line in the entire process to ensure that the optimization result is representative.

[0069] Next, the adjusted parameter data is collected on the pilot line segment, and the quality indicators of the product are measured. By calculating the deviation value between the pilot parameter data and the product quality data, the numerical evaluation of the optimization effect can be obtained. This evaluation result is the basis for the subsequent automatic adjustment control strategy.

[0070] The purpose of this step is to verify the effectiveness of the simulation optimization in the actual production environment and lay the foundation for further automatic optimization control.

[0071] The specific implementation of step S70 is to construct an automatic adjustment control unit. First, using the pilot parameter data and the product quality data obtained in step S60, the running error value of the actual production process is calculated. Then, according to the running error value, the proportional-integral-derivative (PID) control algorithm is used to calculate the correction proportional value, correction integral value and correction differential value of the process parameters.

[0072] Next, based on the optimization effect value and the above-mentioned PID control parameters, an automatic adjustment control unit is constructed. The control unit takes the running error value, correction proportional value, correction integral value, and correction differential value as input, and generates specific process parameter dynamic correction instructions through a pre-set instruction correction equation.

[0073] The purpose of this step is to establish a closed-loop automatic control mechanism to realize continuous optimization of the target industrial process and ensure that the product quality is stable at the best state.

[0074] The specific implementation of step S80 is to form a process parameter optimization guidance scheme. The deviation calculation between the process parameter dynamic correction results implemented in step S70 and the product quality data is performed to obtain a quantitative evaluation of the optimization effect. Based on this, a targeted process parameter optimization guidance scheme is developed to provide a basis for subsequent overall optimization.

[0075] This optimization guidance scheme includes but is not limited to: the best set value range of the process parameters, the dynamic adjustment range of the process parameters, the sensitivity degree ranking of each parameter on the product quality, and other information. Through these guidelines, the focus of process optimization can be indicated, and clear optimization direction can be provided to the operators.

[0076] The embodiment of step S90 is: completing the overall optimization and forming the operation procedure. The process parameter optimization guide scheme obtained in step S80 is further refined to formulate a detailed process operation procedure document. The document includes the set value of the process parameter, the adjustment interval, the dynamic correction strategy, and the limit value requirement of the equipment operation parameter, etc.

[0077] The preparation of the operation procedure document can not only guide the production personnel to operate according to the optimization scheme, but also serve as the basis for process management and equipment management. By strictly implementing the operation procedure, it can be ensured that the target industrial process is stably operated in the optimal state to continuously meet the product quality requirements.

[0078] Based on the content of the application, the equations of each calculation process are described in detail:

[0079] 1. Time domain decomposition operation:

[0080] The mathematical expression of the time domain decomposition operation is specifically as follows:

[0081]

[0082] In the formula, x(t) is the original collected signal, including process parameter data and equipment state data; c i (t) is the i th intrinsic mode function, indicating the fluctuation component; r n (t) is the residual term, indicating the stable component; n is the decomposition layer number, taking a value of 3-5.

[0083] The decomposition steps include:

[0084] (1) Obtaining the extreme value point:

[0085] E max ={(t i ,x i )|x i >x i-1 ,x i >x i+1 ;

[0086] E min ={(t i ,x i )|x i <x i-1 ,x i <x i+1};

[0087] In the formula, E max is the maximum value point set; E min is the minimum value point set; t i is the time point; x i is the signal value.

[0088] (2) Constructing envelope curve:

[0089]

[0090] where s up (t) is the upper envelope curve; s low (t) is the lower envelope curve; both are obtained by cubic spline interpolation.

[0091] (3) Determine IMF condition:

[0092]

[0093] where SD is the standard deviation; θ is the threshold value, taking 0.2-0.3; k is the iteration number; T is the data length.

[0094] 2. Parameter influence mapping:

[0095] The parameter influence mapping equation is specifically represented as follows:

[0096]

[0097] where Q ij is the quality influence characteristic data; ΔP ik is the process parameter fluctuation component; ΔE jk is the equipment state fluctuation component; α k , β k are weight coefficients; γ ij is a random error, ranging from 0.01 to 0.1; and m is the number of fluctuation components.

[0098] Weight coefficient calculation:

[0099]

[0100]

[0101] where Corr(·) represents the correlation coefficient calculation function.

[0102] 3. Fluctuation attenuation mapping:

[0103] The fluctuation attenuation mapping equation is specifically represented as follows:

[0104]

[0105] where D ij is the fluctuation attenuation data; k is the process sequence number; λ k , η k are attenuation coefficients; μ k , ν k are attenuation exponents; and ξ ijSystematic error, range 0.05-0.15.

[0106] Decay parameter calculation:

[0107]

[0108] Where λ0,η0is initial decay coefficient; a p ,a e is decay rate, obtained by historical data fitting.

[0109] 4. Feature principal component decomposition:

[0110] The feature principal component decomposition is specifically represented as follows:

[0111] F=VQ;

[0112] Where F is the feature principal component matrix; V is the eigenvector matrix; Q is the quality influence feature matrix.

[0113] Eigenvector calculation:

[0114] CV=λV;

[0115]

[0116] Where C is the covariance matrix; λ is the eigenvalue; N is the sample number.

[0117] 5. Influence coefficient calculation:

[0118] The influence coefficient matrix calculation is specifically represented as follows:

[0119] M p =F T Q p / ||F|| 2 +∈ p ;

[0120] M e =F T Q e / ||F|| 2 +∈ e ;

[0121] Where M p ,M e are the process parameter and equipment state influence coefficient matrices respectively; ∈ p ,∈ e is fitting error, range 0.02-0.08.

[0122] 6. Stability evaluation:

[0123] The stability matrix calculation is specifically represented as follows:

[0124]

[0125] where S p ,S e are process and equipment stability matrix respectively; δ p ,δ e are correction terms, range 0.1-0.3.

[0126] 7. Process model construction:

[0127] The process mathematical model is specifically expressed as follows:

[0128]

[0129] where Y is the model output; P s ,E s are stability components; w1, w2, w3 are weight coefficients; is the Kronecker product; ω is the model error, range 0.1-0.2.

[0130] 8. Parameter correction:

[0131] The parameter correction amount is specifically expressed as follows:

[0132]

[0133] where ΔP is the parameter correction amount; e is the operation error; K p ,K i ,K d are PID control parameters.

[0134] Equation principle explanation:

[0135] 1. The EMD method is used to realize multi-scale decomposition, which can adaptively process nonlinear and non-stationary signals;

[0136] 2. The linear superposition principle describes the parameter influence, and the random error is considered to improve the model robustness;

[0137] 3. The exponential decay model describes the wave propagation characteristics, which conforms to the energy dissipation law;

[0138] 4. The PCA method reduces dimensionality to extract features and reduce redundant information;

[0139] 5. The least square method determines the influence coefficient to ensure the fitting accuracy;

[0140] 6. The matrix norm evaluates the stability, which reflects the overall characteristics of the system;

[0141] 7. The Kronecker product describes the parameter interaction, which embodies the coupling effect;

[0142] 8. PID control realizes closed-loop optimization, and guarantees dynamic performance.

[0143] The derivation process of each equation is described in detail.

[0144] The time-domain decomposition operation equation adopts the empirical mode decomposition method, and its mathematical expression is The equation can decompose the complex signal in the industrial process into wave components of different scales. Among them, the original signal x(t contains the temperature signal (such as the temperature of the reaction kettle, heating temperature, cooling temperature, etc.), pressure signal (such as system pressure, local pressure, pressure difference, etc.), speed signal (such as material conveying speed, stirring speed, flow rate, etc.) and equipment signal (such as motor current, bearing vibration, equipment load, etc.) in the industrial field. The decomposition process first identifies the extreme points E max ={(t i ,x i )|x i >x i-1 ,x i >x i+1} and E min ={(t i ,x i )|x i <x i-1 ,x i <x i+1}, and then uses cubic spline interpolation to construct the envelope According to the time scale, the components are divided into wave components and stable components, and the time scale threshold of different parameters is determined according to the process characteristics, such as temperature change 300s, pressure fluctuation 60s, speed fluctuation 30s, and equipment state 600s.

[0145] The parameter influence mapping equation describes the influence relationship of process parameters and equipment state fluctuations on product quality, and the expression is The process parameter fluctuation component ΔP ik includes temperature fluctuation (±2℃), pressure fluctuation (±0.1MPa), speed fluctuation (±5%) and time fluctuation (±30s); the equipment state fluctuation component ΔE jk includes load fluctuation (±10%), vibration fluctuation (±0.5mm / s), temperature rise fluctuation (±5℃) and current fluctuation (±15%); and the quality influence characteristic Q ij contains product size (length, width, thickness), product performance (strength, hardness, density), product appearance (surface quality, color difference, gloss) and product defects (cracks, bubbles, impurities) and other indicators.

[0146] The fluctuation attenuation mapping equation The attenuation law of parameter fluctuation transmission in the process flow is described. and are calculated, where different parameters have different initial attenuation coefficients and attenuation rates, such as temperature attenuation (λ0=1.0, a p =0.2), pressure attenuation (λ0=0.8, a p =0.3), speed attenuation (λ0=0.9, a p =0.25) and equipment attenuation (η0=0.95, a e =0.15).

[0147] Process mathematical model The stable components of process parameters, equipment states and their interactions are comprehensively considered. The stable components include process parameter stable values (temperature set value, pressure set value, speed set value) and equipment state stable values (equipment load stable value, equipment vibration reference value, equipment temperature reference value). The weight coefficient is solved by optimizing the objective function J=∑(Y measured -Y model ) 2 , while satisfying the constraint condition that the weight sum is 1.

[0148] Compared with the traditional manual experience adjustment method, the industrial process optimization method of the present application has significant technical advantages and practical value. From a technical point of view, the method establishes a complete data-driven decision mechanism, real-time acquisition of process parameters, equipment states and product quality data through a multi-dimensional data acquisition system, and accurate modeling and analysis of complex industrial systems using advanced mathematical models. The core is to use time domain decomposition technology to decompose complex signals into stable components and fluctuation components, accurately describe the parameter influence mechanism through mapping relationship equations, realize accurate mathematical description of the process, and avoid the subjectivity and uncertainty of traditional experience models. This data and model-based method can accurately quantify the influence relationship between parameters, predict the impact of parameter adjustment on product quality, and provide a reliable theoretical basis for optimization decisions.

[0149] From the control strategy, the application breaks through the limitation of traditional fixed parameter adjustment, and constructs a closed-loop optimization system with dynamic self-adaptive ability. By establishing an automatic adjustment control unit, the system can calculate the running error and correction amount in real time, automatically generate and execute the running correction instruction, and realize the dynamic optimization adjustment of the process parameters. This intelligent control mechanism not only can adapt to the change of working condition, keep the process parameters in the optimal state all the time, but also greatly reduces the manual intervention, improves the production efficiency and product quality stability. Especially in the complex and changeable industrial environment, the method shows strong adaptability and reliability.

[0150] From the system and standardization point of view, the application adopts the whole optimization idea, realizes the multi-parameter collaborative optimization through matrix operation and numerical mapping technology. The system not only considers the influence of single parameter, but also pays more attention to the interaction between parameters, finds the global optimal solution through scientific weighing analysis. Finally, the standardized process operation procedure is formed, which specifies the parameter setting value, adjustment interval and correction strategy, and provides clear operation guidance for industrial production. This standardized method greatly improves the popularization of technology, and overcomes the problems of difficult standardization and easy experience loss caused by personnel replacement in traditional experience method.

[0151] From the actual application effect, the application establishes a whole process automation system from data acquisition, parameter optimization to instruction execution, which significantly improves the intelligent level of industrial production.

[0152] The second aspect of the application provides a computer readable storage medium, the computer readable storage medium stores program instructions, the program instructions are used to execute the steps of the above-mentioned complex industrial process optimization method when running in the computer.

[0153] The third aspect of the application provides a complex industrial process step optimization system, which also includes the computer readable storage medium.

[0154] Specifically, the principle of the application is:

[0155] 1. Multi-dimensional data acquisition and time domain decomposition: for complex industrial processes, first, deploy multiple sensors and monitoring devices at key nodes, collect process parameter data (such as temperature, pressure, speed, etc.), equipment state data (such as load, vibration, temperature rise, etc.) and product quality data (such as size, performance, appearance, etc.). These raw data often have complex nonlinear and non-stationary characteristics. Therefore, the application adopts empirical mode decomposition (EMD) algorithm to decompose various data into long-term stable components and short-term fluctuation components. This adaptive time domain decomposition method can better capture the dynamic change law of parameters and states in the process.

[0156] 2. Mapping relationship between parameter fluctuation and quality: Based on the above decomposition results, the mapping relationship between process parameter fluctuation, equipment state fluctuation and product quality is established. First, the influence of each parameter fluctuation on quality is determined through correlation analysis; second, considering the attenuation characteristics of parameter fluctuation in the process, an exponential decay function is used for modeling; finally, key features are extracted using principal component analysis and other methods, and a linear regression model is established to obtain the influence coefficient matrix. This series of mapping relationship equations provides necessary quantitative basis for subsequent process optimization.

[0157] 3. Construction of process mathematical model: Based on the establishment of parameter-quality mapping relationship, the invention further constructs a mathematical model to describe the entire process. The model takes into account the stable components of process parameters and equipment states, as well as their interaction, and obtains the final product quality prediction value through weighted linear combination. At the same time, process operation stability and equipment operation stability are modeled and evaluated to reflect the overall characteristics of the system. Such a process mathematical model lays a solid foundation for subsequent digital simulation and adaptive optimization.

[0158] 4. Digital simulation and adaptive optimization: Based on the above process mathematical model, the invention uses virtual reality or digital twin technology to construct a digital simulation environment highly consistent with the actual production line. In this simulation environment, process parameters and equipment states can be fully optimized and verified, and the best parameter correction amount can be calculated.

[0159] Subsequently, the invention constructs an automatic adjustment control unit to realize real-time optimization feedback of production line parameters. The control unit dynamically adjusts the process parameters according to the actual production process error using the PID control algorithm to ensure that the product quality continuously meets the requirements. Through simulation verification and adaptive adjustment mechanism, the invention scheme can effectively avoid the risks brought by blind adjustment, improving the reliability of the optimization scheme.

[0160] A specific embodiment 1 of the invention is provided below, and the specific manner of each step in embodiment 1 is described in detail as follows:

[0161] The specific implementation of step S10 is: first, install various sensors and monitoring equipment at key nodes of the target industrial process, such as raw material preparation, pretreatment, main reaction, post-treatment and finished product processes. The sensors used include temperature sensors, pressure sensors, flow rate sensors, etc., and the monitoring equipment includes motor current detection, vibration monitoring, load monitoring, etc. In order to realize high-speed data acquisition and parallel processing, a parallel multi-threading method is used to synchronously collect process parameter data (temperature T, pressure P, velocity V, etc.), equipment state data (load L, vibration R, temperature T eand product quality data (size D, performance F, appearance A, defects D f and so on), forming the original data set X. At the same time, the connection relationship G between each process of the process flow is also collected and recorded, laying the foundation for subsequent establishment of a mathematical model of the process flow. The purpose of this step is to build a multi-dimensional data collection system, providing necessary original data support for subsequent data analysis and optimization.

[0162] The specific implementation of step S20 is: time domain decomposition processing is performed on the original data set X obtained in step S10. An empirical mode decomposition (EMD) algorithm is used to perform adaptive multi-scale decomposition on each type of collected data. The EMD method can decompose a nonlinear and non-stationary industrial process signal into intrinsic mode functions (IMF) c i (t) and a residual term r n (t). The mathematical expression is:

[0163]

[0164] where x(t) is the original collected signal, c i (t) is the i-th intrinsic mode function (representing a fluctuation component), r n (t) is the remaining term (representing a stable component), and n is the number of decomposition layers, with a value range of 3-5.

[0165] The decomposition process includes: first, by identifying the extreme points E max = {(t i ,x i )|x i >x i-1 ,x i >x i+1} and E min = {(t i ,x i )|x i <x i-1 ,x i <x i+1}, a cubic spline interpolation is used to construct the envelope Then, an iterative method is used to continuously extract high-frequency fluctuation components and low-frequency stable components until the residual error satisfies the convergence condition SD= where θ has a value range of 0.2-0.3.

[0166] Through this time domain decomposition operation, the process parameter data and equipment state data can be decomposed into long-term stable components P s , E s and short-term fluctuation components ΔP, ΔE, laying the foundation for subsequent establishment of influence mapping relationships. The purpose of this step is to perform multi-scale feature extraction on the original data, which is beneficial for subsequent analysis of the internal relationship between parameter fluctuations and quality.

[0167] The specific implementation of step S30 is as follows: Establish the mapping relationship between parameter fluctuations and product quality. First, by performing linear correlation analysis on product quality data Q and process parameter fluctuation components ΔP and equipment status fluctuation components ΔE, the degree of influence of each parameter fluctuation on product quality is determined, and quality impact characteristic data Q is generated. ij Its mathematical expression is:

[0168]

[0169] Where, α k ,β k The weighting coefficients are obtained by calculating the correlation coefficient Corr.

[0170]

[0171] γ ij The value is a random error, ranging from 0.01 to 0.1.

[0172] Secondly, considering that parameter fluctuations will decay and propagate during the process, an exponential decay function is adopted. Modeling the propagation law of parameter fluctuations yields fluctuation decay data D. ij Its mathematical expression is:

[0173]

[0174] Where λ0, η0 are the initial attenuation coefficients, a p ,a e Let ξ be the attenuation rate. ij This represents the systematic error, with a value range of 0.05 to 0.15.

[0175] Then, principal component analysis (PCA) is used to extract features and reduce the dimensionality of the quality impact characteristic data Q and the fluctuation decay data D, obtaining the principal component feature matrix F, where F = VQ, and V is the eigenvector matrix. Let λV = CV be the covariance matrix, and let λV = CV be the eigenvalue-eigenvector relationship.

[0176] Finally, the influence coefficient matrix M of the process parameters was calculated using the least squares method. p And the equipment status influence coefficient matrix M e The mathematical expression is:

[0177] M p =F T Q p / ||F|| 2 +∈ p ;

[0178] M e = F T Q e || F || 2 + ∈ e ;

[0179] where, ∈ p , ∈ e is the fitting error, the value interval is 0.02-0.08.

[0180] The above steps establish the mapping relationship equation group of parameter fluctuation and product quality, which provides the basis for subsequent optimization.

[0181] The specific implementation of step S40 is to construct a process mathematical model. First, based on the process parameter influence coefficient matrix M p and the equipment state influence coefficient matrix M e obtained in step S30, the process running stability matrix S p and the equipment running stability matrix S e are calculated, and the mathematical expression is:

[0182]

[0183] where, δ p , δ e is the correction term, the value interval is 0.1-0.3. The two matrices reflect the overall stability of the system.

[0184] Secondly, the process parameter stability component P s , the equipment state stability component E s and the above two stability matrices are combined to establish a comprehensive process mathematical model Y, and the mathematical expression is:

[0185]

[0186] where, w1, w2, w3 are weight coefficients, which are solved by optimizing the objective function J = ∑(Y measured -Y model ) 2 , satisfying the constraint condition w1+w2+w3=1; ω is the model error, the value interval is 0.1-0.2. The model can describe the influence of process parameters, equipment state and their interaction on product quality, and provide the basis for subsequent simulation optimization.

[0187] The specific implementation of step S50 is to construct a simulation environment based on digital mapping technology. First, virtual reality (VR) or digital twin (Digital Twin) technology is used to establish a simulation environment highly consistent with the actual production line, including geometric model and physical process model.

[0188] Next, the mathematical model of the process established in step S40 will be... The data is input into the simulation environment, and the correction amounts ΔP for the process parameters and ΔE for the equipment parameters are calculated through numerical simulation. During the simulation, different process conditions and equipment states can also be set to observe their impact on product quality.

[0189] The purpose of this step is to optimize process and equipment parameters in a computer simulation environment, avoiding production losses caused by blindly trying on the actual production line.

[0190] The specific implementation of step S60 is as follows: parameter optimization verification is performed on an actual production line. First, based on the process parameter corrections and equipment parameter corrections obtained in step S50, the parameters of a pilot segment of the target industrial process are adjusted. The pilot segment is usually a single complete production line in the entire process to ensure that the optimization results are representative.

[0191] Next, adjusted parameter data were collected on the pilot line segment, and product quality indicators were measured. By calculating the deviation between the pilot parameter data and the product quality data, a numerical evaluation of the optimization effect can be obtained: J = ∑(Y measured -Y model ) 2 The evaluation results will serve as the basis for subsequent automatic adjustment and control strategies.

[0192] The purpose of this step is to verify the effectiveness of simulation optimization in a real production environment and lay the foundation for further automated optimization control.

[0193] The specific implementation of step S70 is as follows: Construct an automatic adjustment and control unit. First, using the pilot parameter data and product quality data obtained in step S60, calculate the actual production process operating error value e = Y. measured -Y model Then, based on this operating error value, the proportional-integral-derivative (PID) control algorithm is used to calculate the correction ratio K for the process parameters. p Corrected integral value K i and the corrected differential value K d The mathematical expression is:

[0194]

[0195] Next, based on the optimized effect values ​​and the aforementioned PID control parameters, an automatic adjustment and control unit is constructed. This control unit will control the operating error value e and the correction ratio value K. p Corrected integral value K i Corrected differential value K dAs input, the specific process parameter dynamic correction instruction is generated by the preset instruction correction equation.

[0196] The purpose of this step is to establish a closed-loop automatic control mechanism to achieve continuous optimization of the target industrial process and ensure stable operation of product quality at the best state.

[0197] The specific implementation of step S80 is to form a process parameter optimization guidance scheme. The deviation calculation is performed between the process parameter dynamic correction result implemented in step S70 and the product quality data to obtain a quantitative evaluation of the optimization effect. Based on this, a targeted process parameter optimization guidance scheme is developed to provide a basis for subsequent overall optimization.

[0198] This optimization guidance scheme includes but is not limited to: the optimal set value range of the process parameters (temperature T s ∈150℃,180℃], pressure P s ∈[0.5MPa,0.8MPa], speed V s ∈[80m / min,100m / min] etc.), the dynamic adjustment range of the process parameters (ΔT∈±2℃, ΔP∈±0.1MPa, ΔV∈±5% etc.), the sensitivity ranking of each parameter to product quality, etc. Through these guidelines, the focus of process optimization can be indicated, and clear optimization direction can be provided to the operator.

[0199] The specific implementation of step S90 is to complete the overall optimization and form an operation procedure. The process parameter optimization guidance scheme obtained in step S80 is further refined to develop a detailed process operation procedure document. This document includes:

[0200] 1) The set value of the process parameter, such as temperature T s =165℃, pressure P s =0.65MPa, speed V s =90m / min, etc.

[0201] 2) The adjustment interval of the process parameter, such as temperature T∈[163℃,167℃], pressure P∈[0.6MPa,0.7MPa], speed V∈[87m / min,93m / min], etc.

[0202] 3) The dynamic correction strategy of the process parameter, such as using the PID control algorithm in step S70 for closed-loop adjustment.

[0203] 4) The limit requirement of the equipment operation parameter, such as load L<90%, vibration R<0.6mm / s, temperature rise ΔT e <10℃, etc.

[0204] The operation procedure document is not only used to guide the production personnel to operate according to the optimization scheme, but also used as the basis for process management and equipment management. Through strict implementation of the operation procedure, the target industrial process can be ensured to be stably operated in the optimal state, and the product quality requirements can be continuously met.

[0205] A specific embodiment 2 of the present application is provided below to optimize the process parameters of the chemical production line. The specific mode of each step in the embodiment 2 is described in detail as follows:

[0206] A chemical plant produces a high-performance polymer product. The entire production process includes raw material preparation, preheating reaction, main reaction, post-treatment and other key processes. Since the accurate control of process parameters such as reaction temperature, pressure and stirring speed has a great influence on product quality, and the change of equipment state (such as reaction kettle motor load, bearing vibration, etc.) also causes interference to the process stability, it has been a major technical problem for the plant.

[0207] The specific implementation steps of the complex industrial process optimization method proposed by the present application are as follows:

[0208] Step S10: Establish a multi-dimensional data acquisition system. Temperature sensors, pressure sensors, speed sensors, etc. are installed at key equipment such as reaction kettles, heat exchangers and mixers, and motor current detectors, vibration monitoring equipment, etc. are also provided to achieve comprehensive acquisition of process parameters and equipment state. The main data collected include reaction temperature T, reaction pressure P, stirring speed V, motor current I, bearing vibration R, product size D, product strength F, product appearance A, etc. The data acquisition frequency is set to 1 Hz to ensure accurate capture of dynamic changes in the process. At the same time, the process flow connection relationship G between each process is also recorded.

[0209] Step S20: Time domain decomposition of the collected data. First, the upper and lower envelope lines of temperature, pressure and speed parameters are constructed by identifying extreme points and using cubic spline interpolation method. Then, the EMD algorithm is used to adaptively decompose these signals, which are divided into long-term stable components T s ,P s ,V s and short-term fluctuation components ΔT, ΔP, ΔV. After decomposition, it is found that the temperature fluctuation is within ±2℃, the pressure fluctuation is within ±0.1MPa, and the speed fluctuation is within ±5%. For the equipment state data, the current fluctuation ΔI ∈ ±15% and the vibration fluctuation ΔR ∈ ±0.5mm / s are also identified.

[0210] Step S30: Establishing the mapping relationship between parameter fluctuation and product quality. First, through correlation analysis of product size D, strength F, appearance A and other quality indicators and process parameter fluctuation, equipment state fluctuation, it is found that temperature fluctuation ΔT and motor load fluctuation ΔI have a greater impact on product size, pressure fluctuation ΔP and bearing vibration fluctuation ΔR mainly affect product strength, and speed fluctuation ΔV and temperature rise fluctuation ΔT e will cause the quality of product appearance to decline. Based on this, the following linear regression model is established:

[0211] D = 0.8 ΔT + 0.6 ΔI + ∈ D ;

[0212] F = 0.7 ΔP + 0.5 ΔR + ∈ F ;

[0213] A = 0.9 ΔV + 0.7 ΔT e + ∈ A ;

[0214] where ∈ D , ∈ F , ∈ A are random error terms.

[0215] At the same time, considering the attenuation characteristics of parameter fluctuation in the process flow, an exponential decay function is established to describe its propagation law:

[0216] ΔT = ΔT0e -0.2k , ΔP = ΔP0e -0.3k , ΔV = ΔV0e -0.25k ;

[0217] ΔI = ΔI0e -0.15k , ΔR = ΔR0e -0.18k , ΔT e = ΔT e0 e -0.12k ;

[0218] where k is the process number, reflecting the transmission attenuation characteristics of parameters in the flow.

[0219] Step S40: Constructing a mathematical model of the process. Based on the above mapping relationship, a mathematical model is further established to describe the performance of the entire production line:

[0220]

[0221] where S T , S P , S V are the stability indexes of temperature, pressure and speed, respectively, S I , S R , S Twhere I, R, V and T are the current, resistance, velocity and temperature, respectively, ΔI, ΔR, ΔV and ΔT are the optimal correction values of the current, resistance, velocity and temperature, respectively, σ is the standard deviation of the product quality, ω is the model error, and T is the temperature set value.

[0222] Step S50: Optimization verification based on simulation environment. A simulation environment highly consistent with the actual production line was established using digital twinning technology, including 3D geometric models of major equipment such as reaction kettles, heat exchangers, and mixers, as well as corresponding heat and momentum transfer models. The above process mathematical model was imported into this simulation environment, and the optimal correction values of the process parameters were obtained through numerical calculation:

[0223] ΔT = -1.5℃, ΔP = +0.08MPa, ΔV = +3%;

[0224] ΔI = -10%, ΔR = -0.3mm / s, ΔT e = +4℃;

[0225] Step S60: Parameter optimization verification on a pilot production line. According to the simulation optimization results, a complete polymer production line was verified on site. The adjusted process parameters and product quality data were collected, and the optimization effect was calculated: the product size qualified rate increased from 92% to 96%; the product strength qualified rate increased from 89% to 94%; and the product appearance qualified rate increased from 85% to 92%.

[0226] Step S70: Construction of automatic adjustment control system. Based on the optimization effect data of the pilot production line, a PID feedback control strategy was established to monitor the product quality deviation in real time and automatically adjust the process parameters:

[0227]

[0228] where T set is the temperature set value, K p , K i , and K d are PID control parameters, which can be optimized online according to actual production conditions.

[0229] Steps S80 and S90: Formulation of process parameter optimization guidance scheme and preparation of operation procedures. Based on the above optimization practice, the following process parameter optimization suggestions were made:

[0230] 1) Temperature set value T s = 165℃, control range T ∈ [163℃, 167℃];

[0231] 2) Pressure set value P s = 0.65MPa, control range P ∈ [0.6MPa, 0.7MPa];

[0232] 3) rotation speed set value V s = 90 rpm, control range V [87 rpm, 93 rpm];

[0233] 4) motor current limit value I max = 85 A, vibration limit value R max = 0.6 mm / s, temperature rise limit value Delta T e,max = 10 DEG C;

[0234] At the same time, detailed process operation procedures are also prepared, and dynamic adjustment strategies of the above parameters are specified, thereby providing clear quality control basis for production personnel.

[0235] Compared with the traditional manual experience debugging method, the present application has the following advantages:

[0236] 1. The data-driven modeling method is closer to the actual situation, and can accurately reflect the internal relationship among process, equipment and quality. Compared with the debugging method relying on expert experience, the present application uses a large amount of data collected on site, and obtains quantitative influence relationship through statistical analysis and mathematical modeling, which is more in line with the actual situation of complex process.

[0237] 2. The systematic optimization strategy improves the overall effect. The traditional method is usually limited to single process parameter adjustment, while the present application considers the coupling influence of each process link and equipment state from the global perspective, and gives an optimization scheme suitable for the whole production line. The pilot verification data shows that the qualified rate of each quality index of the product is improved by an average of 5 percentage points, and the overall performance is obviously improved.

[0238] 3. Simulation verification and adaptive adjustment mechanism ensure the reliability of the optimization scheme. Before actual pilot optimization, sufficient parameter verification is carried out in the digital twin model, which effectively avoids the production loss caused by blind adjustment. At the same time, the present application also constructs a closed-loop automatic control system, which can automatically fine-tune the process parameters according to the real-time production situation, and ensure the continuous and stable product quality. This intelligent feature greatly improves the executability of the scheme.

[0239] In general, the present application fully utilizes the data analysis, simulation optimization and adaptive control and other leading technology means, realizes the systematic optimization of the process parameters of the complex chemical production line, and provides an effective solution for the quality control of the industry. Compared with the traditional experience debugging, not only the optimization effect is better, but also the replicability and universality are stronger.

[0240] A specific embodiment 3 of the present application is provided below to optimize the manufacturing process of aircraft parts, and the specific manner of each step in the embodiment 3 is described in detail as follows:

[0241] An aviation enterprise produces a complex structure of aircraft wing leading edge components, manufacturing process involves metal cutting, heat treatment, surface treatment and other key processes. Because the machining parameters (such as speed, feed, cutting depth, etc.), heat treatment temperature, surface treatment current and so on have great influence on the performance and appearance quality of the components, and there is a coupling relationship with the equipment state (such as tool wear, fixture stability, power fluctuation, etc.), so it has been a technical difficulty for the enterprise.

[0242] The complex industrial process optimization method proposed in the application has the following specific implementation steps:

[0243] Step S10: Establish a multi-dimensional data acquisition system. Speed sensor, feed sensor, temperature sensor, current sensor, vibration sensor and other sensors are installed on key equipment such as numerical control machine tool, heat treatment furnace and electroplating line to realize comprehensive monitoring of process parameters and equipment state. The main data collected include: cutting speed V, feed speed F, cutting depth D, heat treatment temperature T, electroplating current I, component size D p , component strength F p , component appearance A p , etc. The data acquisition frequency is set to 5Hz, and the process flow connection relationship G of each process is recorded.

[0244] Step S20: Time domain decomposition of collected data. First, the upper and lower envelope lines of machining parameters and heat treatment parameters are constructed by identifying extreme points and using cubic spline interpolation method. Then, the EMD algorithm is used to adaptively decompose these signals, which are divided into long-term stable components V s , F s , D s , T s , I s and short-term fluctuation components ΔV, ΔF, ΔD, ΔT, ΔI. After decomposition, it is found that the speed fluctuation is within ±3, the feed fluctuation is within ±5%, the cutting depth fluctuation is within ±0.05mm, the heat treatment temperature fluctuation is within ±3℃, and the electroplating current fluctuation is within ±10%. For the equipment state data, the tool wear fluctuation ΔW ∈ ±15%, the fixture vibration fluctuation ΔR ∈ ±0.4mm / s, and the power voltage fluctuation ΔU ∈ ±4% are identified.

[0245] Step S30: Establish the mapping relationship between parameter fluctuation and component quality. Through the component size D p , strength F p , appearance A pCorrelation analysis between the quality index and the fluctuation of process parameters and the fluctuation of equipment state was carried out. It was found that the fluctuation of cutting speed ΔV and the fluctuation of tool wear ΔW had great influence on the size of the part, the fluctuation of feed ΔF and the fluctuation of fixture vibration ΔR mainly affected the strength of the part, and the fluctuation of cutting depth ΔD and the fluctuation of power supply ΔU led to the decline of the appearance quality of the part. Based on this, the following linear regression model was established:

[0246]

[0247] wherein, is a random error term.

[0248] At the same time, the exponential decay function was also established to describe the propagation law of parameter fluctuation in the process flow:

[0249] ΔV = ΔV0e -0.3k , ΔF = ΔF0e -0.35k , ΔD = ΔD0e -0.4k ;

[0250] ΔT = ΔT0e -0.25k , ΔI = ΔI0e -0.2k ;

[0251] ΔW = ΔW0e -0.18k , ΔR = ΔR0e -0.22k , ΔU = ΔU0e -0.15k ;

[0252] Step S40: constructing a mathematical model of the flow. Based on the above mapping relationship, a mathematical model describing the performance of the entire manufacturing line was further established:

[0253]

[0254] wherein, S V , S F , S D , S T , S I are the stability indexes of speed, feed, cutting depth, temperature and current respectively, S W , S R , S U are the stability indexes of tool wear, fixture vibration and power supply fluctuation, and ω is the model error. The model can quantitatively describe the comprehensive influence of the machining parameters, heat treatment parameters, equipment state and their interaction on the part quality.

[0255] Step S50: optimization verification based on simulation environment. A simulation environment highly consistent with the actual manufacturing line is established using digital twinning technology, including 3D geometric models of main equipment such as numerical control machine tools, heat treatment furnaces, and electroplating lines, as well as corresponding mechanical and heat transfer models. The above process mathematical model is imported into the simulation environment, and the optimal correction amount of the process parameters is obtained through numerical calculation:

[0256] ΔV = -2%, ΔF = -3%, ΔD = -0.03 mm;

[0257] ΔT = -2°C, ΔI = -8%;

[0258] ΔW = -10%, ΔR = -0.2 mm / s, ΔU = -3%;

[0259] Step S60: parameter optimization verification on the pilot production line. According to the simulation optimization results, a complete wing leading edge component production line was verified on site. The adjusted process parameters and component quality data were collected, and the optimization effect was calculated: the component size qualified rate increased from 90% to 95%; the component strength qualified rate increased from 88% to 93%; and the component appearance qualified rate increased from 86% to 92%.

[0260] Step S70: construction of automatic adjustment control system. Based on the optimization effect data of the pilot production line, a PID feedback control strategy was established to monitor the component quality deviation in real time and automatically adjust the process parameters:

[0261]

[0262] where V set , F set , D set are the processing parameter set values, K p , K i , K d are PID control parameters, which can be optimized online according to actual production conditions.

[0263] Steps S80 and S90: formation of process parameter optimization guidance scheme and preparation of operation procedures. Based on the above optimization practice, the following process parameter optimization suggestions are made:

[0264] 1) Cutting speed set value V s = 2500 rpm, control range V ∈ [2450 rpm, 2550 rpm];

[0265] 2) Feed speed set value F s = 0.2 mm / s, control range F ∈ [0.18 mm / s, 0.22 mm / s];

[0266] 3) Depth of cut setting value D s = 0.8mm, control range D [0.75mm, 0.85mm];

[0267] 4) Heat treatment temperature setting value T s = 950℃, control range T [945℃, 955℃];

[0268] 5) Electroplating current setting value I s = 25A, control range I [23A, 27A];

[0269] 6) Upper limit of tool wear W max = 20%, upper limit of jig vibration R max = 0.6mm / s, power supply voltage deviation Delta U max = ±5%;

[0270] At the same time, detailed process operation procedures are also prepared, which stipulate the dynamic adjustment strategy of the above-mentioned parameters, and provide clear quality control basis for production personnel.

[0271] Compared with the traditional manual experience debugging method, the present application has the following advantages:

[0272] 1. The overall quality level is improved by the system optimization of the whole process. The traditional method usually only adjusts the parameters for a single process, ignoring the coupling relationship between process links, and it is difficult to improve the overall quality from a global perspective. In contrast, the present application considers the influencing factors of the whole process of machining, heat treatment and surface treatment, and gives an optimization scheme, and the pilot verification data shows that the qualified rate of each quality index of the parts is improved by an average of 5 percentage points.

[0273] 2. The data-driven modeling method is more accurate and reliable. The traditional experience debugging relies on the subjective judgment of process experts, and it is difficult to quantify the quantitative relationship between parameters, while the present application uses a large amount of data collected on site, and uses statistical analysis and mathematical modeling methods to more scientifically reflect the internal laws of process-equipment-quality.

[0274] 3. The simulation verification and self-adaptive adjustment mechanism ensures the implementability of the scheme. Before actual pilot optimization, sufficient parameter verification is carried out in the digital twin model, effectively avoiding the production loss caused by blind adjustment. At the same time, the present application also constructs a closed-loop automatic control system, which can automatically fine-tune the process parameters according to the real-time production status, ensuring that the part quality continuously meets the requirements. This intelligent feature greatly improves the operability of the scheme.

[0275] It should be noted that the variables involved in the present application are explained in detail as shown in Table 1:

[0276] Table 1 Variable explanation table

[0277]

[0278] The above descriptions are only specific embodiments of the application, but the protection scope of the application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the application, which should be covered in the protection scope of the application.

Claims

1. A method for optimizing steps of a complex industrial process, characterized in that, The method comprises the following steps: S10, a multi-dimensional data acquisition system is established, sensors and monitoring devices are installed at key nodes of a target industrial process, process parameter data, equipment state data and product quality data are collected in a parallel multi-thread mode, an original data set is formed, and process connection relationship data is collected; S20, time domain decomposition operation is performed on the original data set, each item of data is decomposed into a long-term stable numerical component and a short-term fluctuation numerical component, process parameter stable components and process parameter fluctuation components, equipment state stable components and equipment state fluctuation components are obtained respectively; S30, a mapping relationship equation set of the process parameter fluctuation components, the equipment state fluctuation components and the product quality data is established, a process parameter influence coefficient matrix and an equipment state influence coefficient matrix are generated; S40, based on the process parameter influence coefficient matrix and the equipment state influence coefficient matrix, a process operation stability matrix and an equipment operation stability matrix are calculated, a process mathematical model is constructed by performing numerical combination operation on the process operation stability matrix, the equipment operation stability matrix, the process parameter stable components and the equipment state stable components; S50, a digital mapping technology is used to construct a simulation environment of the target industrial process, the process mathematical model is input into the simulation environment for numerical verification, and process parameter correction amounts and equipment parameter correction amounts are calculated; S60, based on the process parameter correction amounts and the equipment parameter correction amounts, parameter adjustment is performed on a pilot line segment of the target industrial process, pilot parameter data are collected, and an optimization effect value is obtained by calculating the deviation value of the pilot parameter data and the product quality data; S70, a running error value is calculated based on the deviation value of the pilot parameter data and the product quality data, a running correction proportion value, a running correction integral value and a running correction differential value are calculated based on the running error value, an automatic adjustment control unit is constructed according to the optimization effect value, a running correction instruction is generated by using a preset instruction correction equation according to the running error value, the running correction proportion value, the running correction integral value and the running correction differential value, and process parameter dynamic correction of the target industrial process is realized based on the running correction instruction; S80, deviation calculation is performed on the process parameter dynamic correction result and the product quality data, and a process parameter optimization guidance scheme is generated.

2. The method for optimizing steps of a complex industrial process according to claim 1, characterized in that, The process parameter data includes production temperature data, production pressure data, production speed data and production time data; The equipment state data includes equipment running state data, equipment load rate data, equipment vibration data and equipment temperature data; The product quality data includes product size data, product performance data, product appearance data and product defect data.

3. The method of claim 2, wherein the step of optimizing a complex industrial process is characterized by, The mapping relationship equation set includes a parameter influence mapping equation, a fluctuation attenuation mapping equation, a feature separation mapping equation and a coefficient calculation mapping equation.

4. The method of claim 3, wherein the step of optimizing a complex industrial process is characterized by, The parameter influence mapping equation generates quality influence feature data by performing linear correlation operation on the product quality data, the process parameter fluctuation components and the equipment state fluctuation components.

5. The method of claim 4, wherein the step of optimizing a complex industrial process is characterized by, The fluctuation attenuation mapping equation generates fluctuation attenuation data by iteratively operating the attenuation influence of the process parameter fluctuation component and the equipment state fluctuation component in the process flow connection relationship data.

6. The method for optimizing steps of a complex industrial process according to claim 5, wherein, The characteristic separation mapping equation generates characteristic principal component data by performing principal component decomposition operation on the quality influence characteristic data and the fluctuation attenuation data.

7. The method of claim 6, wherein the step of optimizing a complex industrial process is characterized by, The coefficient calculation mapping equation generates the process parameter influence coefficient matrix and the equipment state influence coefficient matrix by performing numerical correspondence operation on the characteristic principal component data and the quality influence characteristic data.

8. The method of claim 7, wherein the step of optimizing a complex industrial process is characterized by, The target industrial process pilot line segment selects a single complete production line in the process flow for optimization verification. The process operation procedure document includes process parameter set values, process parameter adjustment intervals, process parameter dynamic correction strategies, and equipment operation parameter limit values.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores program instructions, and the program instructions run in the computer to execute the step optimization method of the complex industrial process according to any one of claims 1-8.

10. A system for optimizing steps of a complex industrial process, characterized in that, The computer readable storage medium according to claim 9 is also included.

Images