134 results about "Process variable" patented technology

The invention discloses an AI model adaptive tuning method based on deep reinforcement learning, and belongs to the technical field of industrial process control, the method comprises the following steps: firstly, constructing a deep reinforcement learning environment comprising a state space, an action space and a reward function, the state space comprising a process variable measurement value, a controller parameter and a performance index; the action space is a parameter adjustment quantity vector, and the reward function comprehensively considers the stability, rapidity and accuracy of the system; then, based on a deep Q learning network of a dual-network structure, training data are stored and sampled by adopting an experience playback mechanism, and network parameters are iteratively optimized through a deep Q learning algorithm; and finally, realizing online adaptive adjustment of controller parameters by using the optimized deep Q network. The method has the advantages of being high in adaptability, good in optimization performance, high in practicability and the like, intelligent optimization control over an industrial process control system can be achieved, and the overall performance of the system is improved.

The invention relates to the field of metallurgical automation control, and discloses an intelligent metallurgical automation control method and system, and the method comprises the steps: collecting the real-time operation data of multiple working procedures of metallurgical production, carrying out the time alignment processing, and quantifying the correlation features between the working procedures, thereby obtaining an initial quantification feature set; dynamically simulating the feature set, acquiring intensity and direction parameters of process variable fluctuation conduction, and constructing a cross-process influence model; a global coordination instruction set is generated by combining downstream constraint feedback optimization distributed controller coordination parameters; updating a multi-process state vector, and if a local optimal risk exists, correcting a conduction path; and generating an optimal control scheme based on downstream real-time feedback iterative optimization, and distributing adjustment parameters to realize multi-process cooperative control. The process coupling relation can be accurately quantified, and the metallurgical production efficiency and the quality stability are improved.

The invention relates to the technical field of investment casting, and particularly provides an investment casting automatic wax pattern welding equipment control method which comprises the following steps: extracting a peak value and duration from heating curve data, and judging a uniformity numerical value of interface temperature distribution through a numerical simulation method; according to the fusion depth change trend and the interface temperature distribution data, the quantized value of the quality index is calculated, and an evaluation result of the welding effect is obtained; if the quality index quantized value is lower than a preset threshold value, historical test data are extracted from a data analysis module, and the adjustment range of the process variable is determined; according to the process variable adjustment range, optimizing the parameter combination of the heating curve and the pressure curve, and generating new control strategy data through an iterative algorithm; new control strategy data is adopted to drive equipment to operate, and dynamic feedback values of the interface temperature and the fusion depth are obtained through a real-time monitoring system; and extracting abnormal fluctuation data from the dynamic feedback value, and judging the influence degree of the solidification rate change on the quality index in combination with a data analysis result.

The invention belongs to the technical field of dry quenching, and provides a dry quenching boiler inlet temperature prediction method based on a DeepSeek large model. According to the method, the inlet temperature T6 of the coke dry quenching boiler is predicted by using the data, namely the process variable, changed in real time in the coke dry quenching process; the key control variable is a manually controlled variable, the change of the process variable is controlled / adjusted by changing the key control variable, and automatic control is realized by utilizing a prediction-control joint optimization method and by means of reinforcement learning. According to the prediction method provided by the invention, a complex nonlinear relationship and interaction among multiple variables can be captured, and strong coupling and nonlinear influence among multiple process parameters in the dry quenching process can be processed; through fine tuning on a large amount of historical data, the method can automatically learn and adapt to different working conditions, reduces the dependence on artificial feature engineering, and improves the generalization capability and prediction performance of the model.

The invention discloses a real-time quality monitoring method based on a production process parameter dynamic optimization model, relates to the technical field of intelligent quality monitoring, and solves the technical problems of empirical parameter adjustment and insufficient pertinence of exception handling. The method captures time sequence association of process parameters, process variables and quality indexes through a dynamic optimization model, quantifies uncertainty in combination with a probability density function, avoids limitation of a fixed threshold value, realizes early warning accuracy through deviation degree grading, reduces false alarm and missing alarm, screens core influence parameters based on model feature importance, and improves early warning accuracy. Quantitative adjustment suggestions are generated in combination with historical cases and inversion calculation, and empirical operation is replaced; multiple parameters are ranked and adjusted according to influence degrees, coupling interference is avoided, a single-point problem and a linkage problem are distinguished through parameter association chain analysis, a processing flow is formulated in a targeted mode, the single-point problem focuses on local repair and rapid recovery, the linkage problem focuses on cutting off a conduction chain and radically treating the source, and invalid intervention is reduced.

The invention discloses a real-time comprehensive working condition superiority evaluation method in a cement calcination process. The method comprises the following steps: step 1, carrying out working condition category grading on a historical operation data set in a cement production process; step 2, screening process variables with high relevancy with the key indexes to train a CVAE network to obtain a pre-trained CVAE network; 3, calculating four groups of reconstruction error control limits by adopting a kernel density estimation (KDE) method; 4, constructing an SFA network, obtaining a chronic feature mapping matrix, and calculating a statistic control limit S2; 5, fusing dual-channel monitoring results to obtain a working condition comprehensive scoring index CSI and a working condition dynamic index DI; step 6, monitoring current operation data, inputting the optimality evaluation model, calculating corresponding statistics and indexes, and outputting a current monitoring state and a real-time score; according to the invention, multi-index comprehensive optimization evaluation and visual monitoring of the quality, the yield, the energy consumption and the working condition stability of the cement calcining operation working condition can be realized.

The invention provides a PID parameter setting method based on a large language model, and belongs to the technical field of industrial automation control. Aiming at the problems that a traditional PID setting method depends on expert experience, is long in debugging period and lacks theoretical interpretation, adaptive optimization of PID parameters is realized by fusing dynamic response characteristics of a control system and inference capability of a large language model. The method comprises the following steps: collecting time sequence data of process variables, and extracting dynamic characteristics such as overshoot, oscillation period, attenuation ratio and integral absolute error (IAE); comparing the feature vector with a preset industrial standard threshold value, and generating a natural language cue word containing quantitative analysis; inputting the large language model, and outputting adjustment suggestions including proportion, integral and differential parameters; evaluating a parameter effect through a closed-loop verification experiment, and if the parameter effect does not reach the standard, combining historical debugging data to carry out iterative optimization; and finally, an optimal PID parameter is generated. Experiments prove that the method has a good effect in the industrial process containing pure delay and large inertia.

The invention provides a PID (Proportion Integration Differentiation) loop performance rating and diagnosing method based on a fluctuation variable coefficient, which is used for solving the problems that the control performance of a PID control loop is reduced and parameters need to be reset in industrial production. According to the method, data of a process variable (PV), a set value (SV), controller output (MV) and a mode point (MODE) are collected through a DCS, and after data preprocessing is carried out, core performance indexes such as a fluctuation variable coefficient (CV), a relative performance index (RPI) and an autocorrelation coefficient are calculated. The fluctuation variable coefficient CV is used as a dimensionless quantity, the data volatility can be effectively quantified, and the limitation of a traditional evaluation method in a multi-dimensional scene is overcome. The system grades the loops according to the indexes, the loops are divided into excellent loops, good loops, general loops and poor loops, and fault diagnosis and optimization suggestions are provided for the general loops or the poor loops. The method further comprises the steps of establishing a loop rating history library and tracking an optimization effect. The method improves the real-time performance evaluation precision and diagnosis efficiency of the PID loop, and is suitable for the field of industrial automation control.

The invention relates to the technical field of control and monitoring of an industrial production process, in particular to a KPI (Key Performance Indicator) related fault diagnosis method and device for a multi-mode manufacturing process. The method comprises the step of using supervised variant SMGU of MGU for KPI related feature extraction. The process variables and the KPI are used as inputs of the SMGU, and the SMGU effectively keeps the relation between the process variables and the KPI information by learning potential hidden states. The sparse variant SBLS of the BLS is used for fault diagnosis, so that network structure redundancy is reduced, and model overfitting is avoided. According to the method, the problems of poor universality and low diagnosis accuracy of a traditional fault diagnosis method based on deep learning are solved, and the timeliness and precision of fault diagnosis are improved. The fault diagnosis method has good expansibility, a complete training process does not need to be repeated when new training data is added, and the fault diagnosis method can be effectively applied to multi-mode manufacturing processes such as strip steel hot rolling.

The invention discloses a gate valve opening degree control method and device, and relates to the technical field of industrial automation control, and the method comprises the following steps: obtaining valve structure data and actuator types, reading an initial value of a valve position sensor, building a valve position zero point, and loading an initial valve position-flow mapping model; an error is calculated according to the target process variable and the current measured value, and a valve position target value is generated through an outer ring controller; querying the valve position-flow mapping model according to the valve position target value, and performing deviation correction in combination with real-time flow measurement to obtain a corrected valve position target value; the friction state is predicted according to the valve position change rate and the actuator current signal, the friction compensation amount is generated, the corrected valve position target value is corrected, and a final valve position instruction is obtained; and the final valve position instruction is compared with the actual valve position, the driving amount is calculated through an inner ring controller, an actuator is driven to act, and the actual valve position is made to approach the final valve position instruction.

The invention provides a performance causal discovery and fault diagnosis method and system in a strip steel hot rolling process, and belongs to the field of industrial process fault diagnosis. The method comprises the following steps: acquiring historical process data and real-time data of each process of a production line, screening performance-related process variables after preprocessing, and constructing a historical multi-dimensional data set and a real-time data set of each process; constructing a QGRU-SAE model based on the process variables, training to obtain historical performance characteristics of the sub-processes, constructing a performance constraint prediction network, analyzing a performance causal relationship among the process variables in the processes after the training is completed, and merging to obtain a global performance causal graph; extracting performance characteristics in the real-time data set, constructing a process performance monitoring model, obtaining and fusing performance monitoring information of each process, and judging whether performance abnormity exists or not; and after abnormity is monitored, a fault related variable candidate set is constructed, a fault propagation path is identified according to a global performance causality graph, and a fault root variable is positioned. According to the invention, the accuracy and real-time performance of fault diagnosis are improved.

The invention provides an automatic temperature control method and system for an environment-friendly brick roasting kiln, and the method comprises the steps: constructing a thermotechnical process knowledge graph skeleton, associating a thermodynamic law with an actual process variable, dynamically correcting a causal structure through multi-batch production data, and forming a multi-version causal path set through combining anti-fact deduction, context causal branches and graph labels; based on a causal atlas and a reinforcement learning mechanism, an intelligent temperature control strategy network is designed, action-causal chain-effect collaborative interpretation is realized, control suggestions with physical feasibility and process context self-adaption are generated, and continuous optimization is performed through closed-loop feedback. And the dynamic collaborative optimization capability of temperature control intellectualization and product quality gain is enhanced.

The invention provides a blast furnace influence factor importance analysis method and system based on a big data platform, and a computer readable storage medium, and the blast furnace influence factor importance analysis method based on the big data platform comprises the following steps: based on a preset analysis target; a target dependent variable and a source variable or a process variable corresponding to the target dependent variable are determined from all the influence variables of the target blast furnace as independent variables, all the variables are sampled, and data values at all sampling time points form a to-be-analyzed data set; based on a to-be-analyzed data set, in combination with a screening processing method, importance analysis is carried out by utilizing GCA causal logic analysis, PCA principal component analysis and PCC correlation analysis, so that key independent variables influencing target dependent variables are determined. According to the method, the key factors influencing the furnace condition of the blast furnace can be effectively extracted, so that corresponding countermeasures can be taken according to the furnace condition of the blast furnace.

The invention provides a method for evaluating the operation state of a complex industrial process based on a SelfAtt-EvolveGCN. Establishing a running state offline evaluation model; evaluating and classifying the operation state; obtaining a sequence data set X with consistent sample quantity; mining a topological structure relationship At among variables in the sliding window, and constructing association graph structure sequence data G; inputting the graph structure data into the operation state offline evaluation model for training, inputting online data into the trained evaluation model, obtaining a weight probability value belonging to each state level in the classifier, and taking the state level where the maximum probability value is located as a current prediction state; and when the operation state evaluation model evaluates that the current operation state is non-optimal, performing non-optimal factor tracing, and positioning specific variables causing the occurrence of the non-optimal state. According to the method, disturbance influence caused by a complex industrial severe environment can be resisted, effective extraction of time sequence structural features in process variable data is realized, and a complete and accurate operation state evaluation model is established.

The invention discloses an intelligent control method for equipment for chemical production, and relates to the technical field of intelligent control, and the method comprises the following steps: collecting process variable data, an automatic control instruction, an operator intervention behavior and equipment health state information; based on the collected process variable data, constructing a causal association relationship model between the operator intervention behavior and the equipment health state; identifying abnormal points by combining sliding time window prediction and a dynamic tolerance threshold value, and removing polluted data; constructing a multivariable causal diagram based on process variable deviation, and distinguishing control error paths caused by equipment degradation and intervention; deploying a multi-version control strategy model in the control system, and evaluating and screening an optimal strategy; an operator is guided to record the intervention purpose and mode on a human-computer interface; continuously evaluating the performance of the control strategy, and triggering a model retraining and replacing mechanism; the control logic is always close to the real state.

In order to solve the problems of parameter optimization blindness and insufficient reliability in the prior art, the optimization method of the integrated wheel red press forming process comprises the following steps: based on a response surface method, obtaining process variable data and carrying out a test; performing binomial fitting through a response surface method according to a test result to obtain a response model corresponding to each response value, performing variance analysis on the test result and the response model, determining a corresponding relationship between the process variable and the response value, drawing a response surface diagram, performing constraint and importance definition on the data value of the process variable and the response value, and obtaining a response model corresponding to each response value; the method comprises the following steps of: establishing a fault tree, solving pre-selected process parameters, and determining the die pressing size of the die according to a simulation result of a first-order forming process based on an upper-end first-order forming process, and the reliability evaluation system comprises the steps of establishing the fault tree, calculating the reliability of the system and the probability importance of a basic event, and calculating the average fault-free time of the process through simulation.

The invention discloses an automatic control method and system for a gas power generation boiler burner in the iron and steel industry. The method comprises the steps that an initial pressure set value is generated according to the mapping relation between a target load and main steam pressure, and the initial pressure set value is superposed with manual bias to serve as set value input of a proportional-integral-derivative controller; actual main steam pressure is collected to serve as process variable input of a proportional-integral-derivative controller, and then a first feed-forward signal is output through proportional-integral adjustment; the deviation between the main steam pressure set value and the actual main steam pressure is calculated to serve as steam pressure deviation, the steam pressure deviation is corrected through a lead-lag function, and then a second feedforward signal is generated through filtering processing; and calculating the deviation between the target load and the actual load, and generating a third feed-forward signal through piecewise linear function mapping. According to the design scheme, disturbance factors directly act on feed-forward compensation by bypassing a traditional control method, adjustment is rapid, and system fluctuation is reduced.

The application discloses a numerical calculation method and system for fuel blending turbulent combustion differential diffusion, and belongs to the field of turbulent combustion numerical simulation. The method comprises the following steps: a small flame table is established based on one-dimensional counterflow flame equation; through a mapping algorithm, thermodynamic state is parameterized as a function of mixing fraction and reaction process variable; a differential diffusion term of multi-fuel component is derived; control equations of a differential diffusion two-equation small flame model suitable for multi-fuel component under a large eddy simulation framework are established and solved; the model is discretized and coupled with a pressure-velocity field; in the process, simulation results of a small flame model without considering the differential diffusion effect are used as a comparison by the same method to highlight the influence of the differential diffusion effect. The application extends the differential diffusion two-equation model to multi-fuel blending conditions, takes a hydrogen-ammonia blended combustion two-fuel turbulent diffusion flame as an example, compares the mass fraction and temperature distribution of main components through a priori and posteriori method, and quantitatively analyzes the influence of the differential diffusion effect.

The application relates to the technical field of intelligent temperature control, and discloses a pressure roller heating temperature control method and system of a PE packaging line and a storage medium, the method comprising the following steps: taking process variables and environmental variables in high-dimensional time sequence data as nodes and taking dynamic causal relationships as edges to construct a dynamic causal structure diagram of the packaging line; taking the pressure roller temperature as a target node, screening a causal influence relationship to obtain a local network, tracing a key path to obtain a precursor variable; mapping a dynamic behavior mode of the precursor variable to generate a pressure roller temperature feedforward compensation strategy; analyzing the feedforward compensation strategy and a real-time state vector of the precursor variable to obtain a predictive compensation amount; based on the predictive compensation amount, a pressure roller temperature control instruction is cooperatively decided, and a comprehensive control instruction is generated; according to the execution effect of the comprehensive control instruction and topological consistency, the strategy applicability is judged, and a reconstruction trigger signal is obtained; and the application can improve the pressure roller temperature control operation efficiency of the PE packaging line.

The invention provides a blast furnace ironmaking process anomaly detection method based on score co-integration, which comprises the following steps: acquiring key process variables in a blast furnace ironmaking process, and forming a time sequence by the key process variables; carrying out stationarity analysis on the time sequence by adopting an augmented Dickey-Fuller test method, and identifying non-stationary variables in the data to obtain a non-stationary time sequence; extracting a non-stationary trend part of the non-stationary time sequence by adopting a trend extraction algorithm; modeling the trend part of the non-stationary variable by using the FCVAR, and constructing an anomaly detection model based on the FCVAR; through the control limit detection of the statistical magnitude, the abnormality detection of the blast furnace ironmaking process is realized, and if the statistical magnitude exceeds the control limit, the abnormality exists in the blast furnace ironmaking process. The method solves the problem of non-stability of variables in the ironmaking process, is particularly suitable for variables with long memory characteristics, and can accurately capture the long-term equilibrium relation between the variables, find tiny abnormal changes in time and ensure the safety and stability of production.

There is provided an apparatus including: a first acquisition unit which acquires a deviation between a process variable of a state in relation to a control target, and a set point; a second acquisition unit which acquires a control parameter supplied to the control target; a supply unit which supplies the acquired deviation and the acquired control parameter, to a control model that has a plurality of sub-control models respectively associated with a plurality of aspects preset for the state, the control model using a sub-control model associated with an aspect in accordance with the process variable, to output a recommendation control parameter that is recommended to be supplied to the control target, in response to inputs of a deviation and a control parameter; and an output unit which outputs the recommendation control parameter that is output from the control model.

The invention relates to the technical field of automatic programming, and provides a method, a device and equipment for dynamically creating a sub-process instance of a workflow engine, and the method comprises the following steps: when the workflow engine runs to a sub-process calling activity, identifying whether the sub-process instance is allowed to be dynamically created or not according to a parameter value of a target parameter in a subscription function; if so, reading a flow variable value set of each sub-flow of the workflow engine from the sub-flow splitting configuration information; determining a business variable value set corresponding to each process variable value set; calculating a Cartesian product of the business variable value set; modifying a configuration item cardinal number of a sub-process calling activity of the workflow engine into a combined number of Cartesian products; starting a sub-process instance of the workflow engine according to the modified configuration item cardinal number; and modifying a sub-process starting mark in the sub-process starting event to be started. Through the embodiment of the invention, the creation flexibility of the sub-process instance of the workflow engine can be improved.

A method (100) for generating a dynamic model (10) of an industrial plant (1), the method comprising: obtaining (110) a representation of the plant (1) into partitions of subunits (1a, 1b), the subunits (1a, 1b) being characterized by respective subsets (5a, 5b) of setpoints (51-57) of low-level controllers (31-37), subsets (4a, 4b) of current values ​​of process variables (41-49) and subsets (4a', 4b') of future predicted values ​​(41'-49') of the process variables (41-49); obtaining (120) for each subunit (1a, 1b) Dynamic sub-models (13a, 13b), wherein the inputs include a subset (5a, 5b) of set points (51-57) and a subset (4a, 4b) of current values ​​of process variables (41-49), and the outputs include a subset (4a', 4b') of future predicted values ​​(41'-49'); correlations (14) between the sub-units (1a, 1b) are obtained (130) from the layout of the plant (1) and / or from the composition of the plant from physical process modules; and the sub-models (13a, 13b) are combined (140) into a model (10) of the plant (1) based on the correlations (14).

An optimized simulation method for the internal high-pressure forming process of preformed aluminum alloy truck axle housing tubes includes the following steps: Step 1: Determine the basic simulation parameters and performance evaluation indicators, and clarify the initial dimensions, material properties, and key process variables of the tube blank; Step 2: Construct an ABAQUS simulation model and a sequential simulation process, establish a finite element model including geometry, material, mesh, and contact, and set up a multi-analysis step process that can sequentially simulate diameter reduction and internal high-pressure forming; Step 3: Perform bidirectional multi-slider diameter reduction simulation and parameter screening; Step 4: Perform preliminary preforming simulation and parameter optimization; Step 5: Perform a second internal high-pressure forming simulation, and based on the preliminary forming results, collaboratively optimize various parameters to obtain better second forming process parameters and final product parameters; Step 6: Compare and verify the simulation results and output the process parameter set. This invention reduces the number of experiments, saves investment, and produces qualified products more efficiently.

A method for generating a prediction system for a machine, the machine being subjected to cyclically variable ambient conditions, the prediction system being configured to predict at least one process variable of the machine. The method comprises a first step, in which a set of training data is provided, the set of training data comprising a plurality of ambient parameters of the machine, a plurality of performance parameters of the machine, and at least one process variable of the machine. Furthermore, the method comprises that a correlation value between the at least one process variable and each of the plurality of ambient parameters and each of the performance parameters of the machine is determined for a first time interval. In a further step, at least one model relevant ambient parameter and at least one model relevant performance parameter are determined based on the corresponding correlation values. Still further, the at least one model relevant ambient parameter, the at least one model relevant performance parameter, and the process variable are being fed into a model generating algorithm and generating a prediction model for the first time interval, the prediction model for the first time interval being a part of the prediction system. In the disclosed method, the model generating algorithm is a Generalized Additive Model (GAM).

This invention relates to the fields of industrial control and intelligent manufacturing, and particularly to an adaptive method, system, device, and medium for control parameters in variable-distribution process industries. The method includes: extracting features from process variable data, combining their distribution offset with control performance indicators for collaborative judgment, and outputting a trigger signal; upon receiving the trigger signal or system startup, parsing historical operating data to construct a behavioral proxy model and a historical benchmark distribution, and determining initial parameters by optimizing the consistency measure between the predicted behavioral distribution under the parameters to be optimized and the historical benchmark distribution; shaping the process variable data and inputting it into a strategy model to perform component extraction and inference to adjust the control parameters and obtain the parameters to be activated; evaluating the parameters to be activated, and if they exceed limits, reverting the parameters to the initial parameters, and adjusting the strategy model based on system response data. This invention improves the performance stability and adaptability of process industry control systems under complex and variable operating conditions.

The present application relates to the technical field of industrial process control, in particular to an intelligent control method for multi-process collaborative management of injection stretch blow molding machines, comprising: in the mold cooling main process for medical consumable production, when the monitored main process variable reaches the preset threshold value, based on the material property model associated with the rheological melt index, the operation instruction of the preparatory process executor is adaptively generated, and the preparatory process parallel to the main process is started; using the model prediction double-loop control loop, through real-time control of the inner loop, according to the dynamic prediction of the synchronization deviation of the two process procedures, the preparatory process executor is continuously adjusted to realize synchronization, and at the same time, through online learning of the outer loop, according to historical error feedback, the prediction model inside the loop is continuously self-corrected. Through the establishment of a model prediction double-loop self-correcting control loop, the present application realizes predictive collaborative control of multiple asynchronous executed process procedures.

A process system according to an embodiment may include a plurality of process equipments configured to process a wafer based on a plurality of process variables, a structural parameter estimation circuit configured to generate, based on a first plurality of actually measured correlated parameter values which are provided from the plurality of process equipments and corresponding to a first target structural parameter of the wafer, a first estimated target structural parameter value for the first target structural parameter, and a process equipment control device configured to control at least one process variable among the plurality of process variables based on the first estimated target structural parameter value.

To provide systems and methods for optimizing process control or monitoring of manufacturing processes in manufacturing environments.SOLUTION: Systems and methods can generate predictions or recommendations for process variables, target properties, or root causes of anomalies. Systems can include data and machine learning layers, and the data and machine learning layers can include: a data collector configured to receive data from a client application layer; a dataset generator configured to enable a user to create customized datasets from the data; a model management module configured to enable the user to build, train and / or update machine learning models; and an inference module configured to use the machine learning models for generating predictions or recommendations.SELECTED DRAWING: None