CN116880397A - Process control parameter optimization method, device, electronic equipment and storage medium - Google Patents
Process control parameter optimization method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116880397A CN116880397A CN202310897245.8A CN202310897245A CN116880397A CN 116880397 A CN116880397 A CN 116880397A CN 202310897245 A CN202310897245 A CN 202310897245A CN 116880397 A CN116880397 A CN 116880397A
- Authority
- CN
- China
- Prior art keywords
- detection point
- process control
- parameter
- state
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004886 process control Methods 0.000 title claims abstract description 212
- 238000000034 method Methods 0.000 title claims abstract description 157
- 238000005457 optimization Methods 0.000 title claims abstract description 149
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 293
- 238000004519 manufacturing process Methods 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 238000005070 sampling Methods 0.000 claims description 115
- 238000012549 training Methods 0.000 claims description 38
- 238000004422 calculation algorithm Methods 0.000 claims description 37
- 238000011156 evaluation Methods 0.000 claims description 16
- 238000013386 optimize process Methods 0.000 claims description 14
- 230000007613 environmental effect Effects 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 7
- 239000002994 raw material Substances 0.000 claims description 5
- 238000004088 simulation Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 230000002787 reinforcement Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 3
- 238000011217 control strategy Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000003723 Smelting Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The application provides a process control parameter optimization method, a device, electronic equipment and a storage medium, wherein the method comprises the steps of obtaining each piece of prediction state data corresponding to each detection point according to each process control parameter corresponding to each detection point in a process control sequence, determining the target state data of the target detection point in each piece of prediction state data according to the target detection point and the detection point to be adjusted which are determined in each detection point, and obtaining the actual state data of the target detection point; analyzing the target state data and the actual state data, obtaining state analysis data of a target detection point, and optimizing process control parameters of the detection point to be adjusted according to the state analysis data of the target detection point. Therefore, the application can dynamically provide an optimization scheme of the process control parameters in real time in the process of the process treatment so as to improve the production efficiency and the product yield.
Description
Technical Field
The present application relates to the field of industrial automation technologies, and in particular, to a method and apparatus for optimizing process control parameters, an electronic device, and a storage medium.
Background
Real-time production optimization of dynamic systems has been a topic of great concern in industrial processes. The process personnel need to observe the measurement data and the production environment data of the process section in real time, and adjust the process control parameters accordingly so as to improve the production efficiency or ensure the yield.
At present, the optimization treatment of the process control parameters is roughly divided into two main types, namely dynamic optimization and steady-state optimization. Specifically, for an industrial process, if in actual operation, the track shape that is undergone in the course of adjustment from the respective initial values to the target values of a plurality of process control parameters will affect the final production result, it is necessary to perform an optimization process using a dynamic model. In this case, the optimization algorithm needs to give control suggestions to achieve control of the ideal trajectory in each time step. If the value of the stable control parameter is a main factor affecting the production result in actual operation, the steady-state optimization executed by the steady-state model has higher applicability.
In general, in the dynamic optimization processing of the process control parameters, since the current state of the process control system is greatly affected by the historical state and the calculation time of the optimization scheme cannot exceed a given time step, the calculation speed requirement is more strict, and the dynamic optimization processing of the process control parameters is more complex.
Disclosure of Invention
In view of this, the method, the device, the electronic equipment and the storage medium for optimizing the process control parameters can dynamically provide an optimization scheme of the process control parameters in real time in the process of processing, so as to improve the production efficiency and the product yield.
According to a first aspect of an embodiment of the present application, there is provided a process control parameter optimization method, including: predicting each state of the process system to be detected corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtaining each prediction state data corresponding to each detection point; according to at least one target detection point and at least one detection point to be adjusted which are determined in each detection point, at least one target state data corresponding to the at least one target detection point is determined in each prediction state data, the state of the process system to be detected corresponding to the at least one target detection point is detected, and at least one actual state data of the at least one target detection point is obtained; analyzing the at least one target state data and the at least one actual state data to obtain state analysis data of the at least one target detection point; optimizing at least one process control parameter of the at least one point to be adjusted based on the state analysis data of the at least one target point.
According to a second aspect of the embodiment of the present application, there is provided a process control parameter optimizing apparatus, including: the prediction unit is used for predicting each state of the process system to be detected corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtaining each prediction state data corresponding to each detection point; the determining unit is used for determining at least one target state data corresponding to the at least one target detection point in each prediction state data according to the at least one target detection point and the at least one detection point to be adjusted, detecting the state of the process system to be detected corresponding to the at least one target detection point and obtaining at least one actual state data of the at least one target detection point; an analysis unit for analyzing the at least one target state data and the at least one actual state data to obtain state analysis data of the at least one target detection point; and the optimizing unit is used for optimizing at least one process control parameter of the at least one detection point to be adjusted according to the state analysis data of the at least one target detection point.
According to a third aspect of an embodiment of the present application, there is provided an electronic apparatus including: the device comprises a processor, a memory, a communication interface and a bus, wherein the processor, the memory and the communication interface complete mutual communication through the bus; the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform operations corresponding to the process control parameter optimization method according to the first aspect.
According to a fourth aspect of embodiments of the present application, there is provided a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, cause the processor to perform the process control parameter optimization method as described in the second aspect above.
According to the process control parameter optimization scheme provided by the aspects of the application, the target state data and the actual state data of the target detection points in the detection points are analyzed by predicting the predicted state data corresponding to the detection points in the process control sequence, so that the process control parameters of the detection points to be adjusted in the detection points are optimized. Therefore, the application can dynamically provide the optimal combination scheme of the process control parameters in real time, thereby not only improving the production efficiency, but also improving the product yield.
Drawings
Fig. 1 is a flowchart of a process control parameter optimization method according to an exemplary embodiment of the present application.
Fig. 2 is a flow chart of a process control parameter optimization method in accordance with another exemplary embodiment of the present application.
FIG. 3 is a flow chart of a process control parameter optimization method in accordance with another exemplary embodiment of the present application.
Fig. 4 is a schematic structural view of a process control parameter optimizing apparatus in an exemplary embodiment of the present application.
Fig. 5 is a schematic diagram of an electronic device according to an exemplary embodiment of the present application.
List of reference numerals:
102: according to each process control parameter corresponding to each detection point in the process control sequence, predicting the state of the process system to be detected corresponding to each detection point to obtain each prediction state data corresponding to each detection point
104: according to the target detection point and the detection point to be adjusted which are determined in each detection point, determining target state data corresponding to the target detection point in each prediction state data, detecting the state of the process system to be detected corresponding to the target detection point, and obtaining actual state data of the target detection point
106: analyzing the target state data and the actual state data to obtain state analysis data of the target detection points
108: optimizing process control parameters of the detection point to be adjusted according to state analysis data of the target detection point
202: acquiring a training sample set of a process system to be tested
204: determining a current sampling point and a target sampling point in the sampling points
206: predicting the state of the process system to be tested corresponding to the target sampling point according to the process control parameter and the environmental influence factor parameter of the process system to be tested corresponding to the current sampling point by using the state prediction model to be trained, and obtaining preset state data of the target sampling point
208: training a state prediction model to be trained according to the predicted state data and the actual state data of the target sampling points to obtain the state prediction model
302: determining each process control parameter corresponding to each detection point in the process control sequence as each process control parameter to be optimized corresponding to each detection point
304: initializing parameter values of a parameter optimization algorithm
306: based on the parameter value of the parameter optimization algorithm, performing parameter optimization on each process control parameter to be optimized corresponding to each detection point to obtain each intermediate process control parameter corresponding to each detection point
308: according to each intermediate process control parameter corresponding to each detection point, predicting each state of the process system to be detected corresponding to each detection point, and obtaining each intermediate prediction state data corresponding to each detection point and each prediction result evaluation data 310: updating the parameter value of the parameter optimization algorithm according to the prediction result evaluation data corresponding to each detection point, and updating each intermediate process control parameter corresponding to each detection point into each process control parameter to be optimized corresponding to each detection point
312: judging whether the parameter optimization meets the preset parameter optimization ending condition
314: obtaining optimized process control parameters of each detection point
316: predicting each state of the process system to be detected corresponding to each detection point according to each optimized process control parameter corresponding to each detection point to obtain each predicted state data corresponding to each detection point
400: process control parameter optimization device 402: prediction unit 404: determination unit
406: analysis unit 408: the optimizing unit 500: electronic equipment
502: processor 504: communication interface 506: memory device
508: bus 510: program
Detailed Description
In order to better understand the technical solutions in the embodiments of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments derived by a person skilled in the art from the embodiments according to the application shall fall within the scope of protection of the embodiments according to the application.
Some embodiments of the application are described in detail below with reference to the accompanying drawings. In the case where there is no conflict between the embodiments, the embodiments and features in the embodiments described below may be combined with each other. The steps of the method embodiments described below are for illustrative purposes only and are not intended to limit the present application.
As described in the foregoing background section, in the dynamic optimization process of the process control parameters, the current state of the process control system is greatly affected by the historical state, and the calculation time of the optimization scheme cannot exceed a given time step, so that the dynamic optimization process of the process control parameters is more complicated.
Specifically, due to different process characteristics, time sequence of process control parameters, real-time requirements of parameter optimization calculation, influence of production environment factors, high dimensional characteristics of process control data, other uncertain factors in actual production, different customer requirements and the like, the difficulty of solving the optimal control parameter combination in real time is extremely high.
Currently, the method for implementing dynamic optimization of control parameters mainly comprises: dynamic matrix control (Dynamic Matrix Control, DMC for short), fuzzy logic control (Fuzzy Logic Control, FLC for short), mechanism simulation, reinforcement learning based on mechanism simulation, off-line reinforcement learning based on model, and the like. The DMC belongs to one of advanced control, describes a process system through a linear step response model, calculates an optimal combination of optimal control parameters by using a rolling time domain method, and changes the amplitude according to residual error adjustment parameters. FLCs are also one type of advanced control that describe a process system through a priori experience or rules and give an optimized combination of control parameters through a defuzzification method. The mechanism simulation is to describe the process system by simultaneous equations based on basic science principles (physical, biological, chemical and the like), and because the calculation speed is low, a proxy model is often required to be generated first, and then an optimization solver is utilized to give out the control parameter optimization combination. Based on the reinforcement learning of the mechanism simulation, the process system is described by a simultaneous equation set of basic science principles, and then an agent for determining a control strategy is trained interactively with a simulation model. And (3) performing offline reinforcement learning based on a model, describing the characteristics of a process system through a deep neural network, and training out an intelligent body for determining a control strategy through historical data.
The dynamic optimization scheme of each control parameter mainly has the following problems:
first, these methods often fail to take into account uncertainty factors in the production process in performing dynamic optimization of parameters. For example, neither the DMC step response nor the FLC rules take into account uncertainties, but the uncertainty influencing factors in the production process are precisely unexplained by basic scientific principle formulas.
Second, since many basic disciplines of parametric dynamic optimization schemes are not well studied, the optimization effect of these schemes cannot be expected in practical production applications. Meanwhile, the parameter dynamic optimization scheme related to simulation cannot deal with the security technology, so that the current various parameter dynamic optimization schemes have larger application limitations.
Furthermore, the DMC step response model needs to be experimentally measured in a shutdown state and cannot be executed in real time during the production process. In addition, when the characteristics of the process segments shift with the advancement of production time, the algorithm model of the DMC cannot be updated accordingly. The rule design of FLC needs to be very empirical in both the method itself and the process, otherwise very unstable control problems are likely to occur, and there are also difficult maintenance problems. Meanwhile, the mechanism simulation model also needs simulation expert experience to update and maintain. Therefore, the current dynamic optimization schemes of these parameters mostly have the problem of model update maintenance lag.
In addition, aggressive process control parameter optimization recommendations may cause damage to equipment or process segments. Model-based offline reinforcement learning while aggressive or conservative suggestions may be selected, the approach does not take into account the actual feedback information of the process system. Therefore, in the case of imperfect model training, the phenomenon of distribution deviation in the historical data is very likely to cause inaccuracy of the model prediction result and damage to equipment or process segments.
Based on the above-mentioned problems of the dynamic optimization schemes of each parameter, various embodiments of the present application aim to provide a process control parameter optimization scheme combining an advanced control concept and a machine learning algorithm, by predicting each preset state data corresponding to each detection point in a process control sequence, analyzing the preset state data and the actual state data of a target detection point in each detection point, so as to optimize at least one process control parameter of at least one detection point to be adjusted in each detection point according to a state analysis result of the target detection point, thereby dynamically providing an optimization scheme of the process control parameter in real time during the process.
The following describes in detail a process control parameter optimization method, an apparatus, an electronic device and a storage medium according to embodiments of the present application with reference to the accompanying drawings.
Process control parameter optimization method
FIG. 1 is a flow chart of a process control parameter optimization method in accordance with an exemplary embodiment of the present application. As shown in fig. 1, the process control parameter optimization method of the present embodiment includes the following steps:
step 102, predicting the state of the process system to be detected corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtaining each prediction state data corresponding to each detection point.
The process system under test may be used in a variety of process control applications including, but not limited to: metal smelting, water treatment, electric power, energy sources and the like. In some embodiments, the process system under test may include at least one industrial control device.
In various embodiments of the present application, process control parameters refer to controllable parameters that may be manually adjusted during a process control flow, such as current parameters, voltage parameters, bearing speed, etc.
Alternatively, each detection point arranged in time series may be determined according to a preset detection interval time.
In some embodiments, the number of detection points included in the process control sequence may be arbitrarily adjusted according to the actual process control accuracy requirement, for example, but not limited to, 10 or 20 detection points may be included in one process control sequence, and one skilled in the art may arbitrarily adjust the number of detection points included in the process control sequence according to the actual parameter optimization requirement, the equipment performance condition, and the like, which is not limited in the present application.
Alternatively, for each detection point (individual detection point) in the process control sequence, one process control parameter may be set for each detection point (e.g., only one process control parameter C1 is set for detection point T1), or a plurality of process control parameters may be set for each detection point (e.g., a plurality of process control parameters C11, C12, C13 are set for detection point T1).
In some embodiments, each process control parameter in the process control sequence corresponding to each detection point may be identified. For example, detection point T1 corresponds to process control parameter C1, detection point T2 corresponds to process control parameter C2, and so on. And predicting each state of the process system to be detected corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtaining each prediction state data corresponding to each detection point. For example, the system state of the process control parameter C1 of the process system to be measured at the detection point T1 is predicted, the preset state Data FD1 of the process system to be measured corresponding to the detection point T1 (where FD is an abbreviation of Forecast Data) is obtained, the system state of the process control parameter C2 of the process system to be measured at the detection point T2 is predicted, the preset state Data FD2 of the process system to be measured corresponding to the detection point T2 is obtained, and so on.
In some embodiments, a given parameter optimization algorithm may be utilized to optimize each process control parameter corresponding to each detection point in the process control sequence, obtain each optimized process control parameter corresponding to each detection point, and predict each state of the process system to be tested corresponding to each detection point according to each optimized process control parameter corresponding to each detection point, so as to obtain each predicted state data corresponding to each detection point.
Alternatively, the given parameter optimization algorithm may include, but is not limited to, a cross entropy algorithm.
In some embodiments, a state prediction model may be used to predict each state of the process system under test corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, so as to obtain each predicted state data corresponding to each detection point.
The state prediction model may include any type of regression model, among other things. In some embodiments, the state prediction model is a sparse gaussian process regression model (Sparse Gaussian process).
And 104, determining target state data corresponding to the target detection point in the predicted state data according to the target detection point and the detection point to be adjusted which are determined in the detection points, detecting the state of the process system to be detected corresponding to the target detection point, and obtaining actual state data of the target detection point.
Alternatively, the number of target detection points and detection points to be adjusted may be determined according to the actual prediction accuracy requirement. In general, the number of the target detection points and the detection points to be adjusted are each at least one.
Specifically, at least one target state data corresponding to the at least one target detection point can be determined in each prediction state data according to the at least one target detection point and the at least one detection point to be adjusted, and the state of the process system to be detected corresponding to the at least one target detection point can be detected to obtain at least one actual state data of the at least one target detection point.
In some embodiments, a first one of the detection points may be determined as a target detection point, and at least one detection point subsequent to the target detection point of the detection points may be determined as a detection point to be adjusted.
For example, in the case where each detection point in the process control sequence is a detection point T1 to a detection point T10, and the target detection point and the detection point to be adjusted are both set to one, the detection point T1 may be determined as the target detection point, and the detection point T2 may be determined as the detection point to be adjusted.
In some embodiments, according to the target detection point (for example, detection point T1) determined in each detection point, the predicted state Data corresponding to the target detection point (for example, the predicted state Data FD1 corresponding to the detection point T1) may be determined from each predicted state Data corresponding to each detection point, and the system state of the process control parameter C1 running at the detection point T1 of the process system under test may be detected, so as to obtain the Actual state Data of the target detection point, for example, the Actual state Data AD1 corresponding to the detection point T1 (where AD is abbreviated as Actual Data).
And 106, analyzing the target state data and the actual state data to obtain state analysis data of the target detection points.
In some embodiments, a residual analysis (residual analysis) may be performed on at least one target state data and at least one actual state data of at least one target detection point, obtaining state analysis data of the at least one target detection point.
And step 108, optimizing the process control parameters of the detection point to be adjusted according to the state analysis data of the target detection point.
In some embodiments, the adjustment may be performed on at least one process control parameter of at least one point to be adjusted in the process control sequence based on the residual analysis value of the at least one target point to provide an optimization scheme of the process control parameter dynamically in real time.
In some embodiments, the process control parameters of the point to be adjusted in the process control sequence may be selectively adjusted according to the residual analysis value of the target point and a preset adjustment threshold. For example, if the residual analysis value of the target detection point is higher than the preset adjustment threshold, adjusting at least one process control parameter of at least one detection point to be adjusted in the process control sequence, and if the residual analysis value of the target detection point is not higher than the preset adjustment threshold, not adjusting at least one process control parameter of at least one detection point to be adjusted in the process control sequence.
In some embodiments, the more conservative the given process control parameter adjustment scheme will be (e.g., the smaller the magnitude of the optimization adjustment performed on the process control parameters) when the residual analysis value of the target detection point is higher.
In summary, according to the process control parameter optimization scheme provided by the embodiment, the predicted state data and the actual state data of the target detection point in the process control sequence are analyzed, so that the process control parameters of the detection point to be adjusted in the process control sequence are dynamically optimized and adjusted, thereby improving the production efficiency of the industrial process flow and the product yield. In addition, the process control parameter optimization scheme provided by the embodiment can rapidly give the optimal process control parameter optimization scheme in real time due to small system operation amount, and can meet the real-time requirement of the optimization scheme in the complex process production environment.
In addition, according to the process control parameter optimization scheme provided by the embodiment, the states of the process system to be detected corresponding to each detection point are predicted by using the sparse Gaussian process regression model, so that a more accurate state prediction result can be provided, and the parameter optimization effect is further improved.
Furthermore, in the process control parameter optimization scheme provided in this embodiment, the first detection point in the process control sequence is determined as the target detection point, and the process control parameter of at least one detection point to be adjusted after the first detection point is optimally adjusted according to the residual analysis result of the actual state and the predicted state of the first detection point, so that the technical scheme of this embodiment can provide a set of optimized control tracks in each time step, but only execute the process control parameter of the first detection point in the tracks at the current moment, so that the real-time requirement of the process control parameter optimization scheme in the process treatment process can be well met.
FIG. 2 is a process flow diagram of a process control parameter optimization method according to another exemplary embodiment of the present application, which illustrates an exemplary model training scheme for performing the state prediction model of step 102 described above.
As shown in fig. 2, the process control parameter optimization method of the present embodiment includes the following steps:
step 202, obtaining a training sample set of a process system to be tested.
In some embodiments, the training sample set at least includes process control parameters, environmental impact factor parameters, and actual state data of the process system to be tested corresponding to the sampling points.
Alternatively, each sampling point arranged in time sequence may be determined according to a preset detection interval time.
It should be noted that, in the embodiments of the present application, the sampling points and the detection points are substantially the same, so two different names are used to define different usage phases of the state prediction model. The sampling points correspond to training phases of the state prediction model to be trained, and the detection points correspond to actual application phases of the state prediction model after training.
In various embodiments of the present application, process control parameters refer to controllable parameters that may be manually adjusted during a process control flow, such as current parameters, voltage parameters, bearing speed, etc., in order to produce a satisfactory product. The environmental impact parameters refer to conditions that affect the production results but cannot be directly controlled by the process control system.
In some embodiments, for any one of the current sampling points, the process control parameter for the current sampling point may be determined based on the given control parameter and the adjustable parameter for the current sampling point, e.g., where the process control parameter is a drying temperature, the process control parameter may be determined based on the given drying temperature commitment (e.g., 55 degrees) and the adjustable temperature parameter (e.g., ±5 degrees).
In some embodiments, for any one current sampling point of the sampling points, the environmental impact factor parameter of the current sampling point may be obtained by at least one sensing device of the process system under test by sensing at a detection time corresponding to the current sampling point.
In some embodiments, the environmental impact parameter of the current sampling point may include at least one of a production environment detection parameter, a production raw material detection parameter, and a facility parameter of the current sampling point.
Illustratively, the production environment detection parameters may include parameters such as ambient temperature, ambient humidity, air flow, water pressure, etc. at which the process system under test operates. The production raw material detection parameters may include parameters such as the kind, composition, and the like of the production raw material. The device parameters refer to various physical and chemical characteristics of industrial devices during production, such as temperature, pressure, speed, power, etc. In general, the device parameters are typically determined during the design and manufacture of the device, and are fixed for the same device.
Step 204, determining a current sampling point and a target sampling point in the sampling points.
In this embodiment, the target sampling point is one sampling point after the current sampling point in each sampling point, for example, if the current sampling point is S1, the target sampling point is S2.
And 206, predicting the state of the process system to be tested corresponding to the target sampling point according to the process control parameter and the environment influence factor parameter of the process system to be tested corresponding to the current sampling point by using the state prediction model to be trained, and obtaining the preset state data of the target sampling point.
In some embodiments, the state prediction model may include, but is not limited to, a sparse gaussian process regression model.
Specifically, the state prediction model to be trained may be utilized to perform prediction on the state of the target sampling point (i.e., the next sampling point of the current sampling point) of the process system to be tested according to the process control parameter and the environmental impact factor parameter of the process system to be tested corresponding to the current sampling point, so as to obtain preset state data of the process system to be tested corresponding to the target sampling point.
And step 208, training a state prediction model to be trained according to the predicted state data and the actual state data of the target sampling points to obtain the state prediction model.
In some embodiments, the predicted state data and the actual state data of the target sampling points may be compared to obtain a model loss value of the state prediction model to be trained, model parameters of the state prediction model to be trained are updated based on the model loss value, and the step of determining the current sampling point and the target sampling point in each sampling point is re-performed by using the updated state prediction model to be trained (i.e., step 204) until the model loss value meets a preset training end condition, thereby obtaining a state prediction model with completed training.
For example, residual calculation may be performed according to the predicted state data and the actual state data of the target sampling point, to obtain a model loss value of the state prediction model to be trained.
In some embodiments, when the model loss value meets the preset convergence value, a determination result that the model loss value meets the preset training end condition may be obtained.
In some embodiments, when the model loss value (θ i ) Model loss value (θ) updated with the i-1 th iteration i-1 ) And when the difference value is smaller than a preset difference value threshold value, a judgment result that the model loss value meets the preset training ending condition can be obtained.
In summary, the process control parameter optimization scheme provided in this embodiment uses each process control parameter, each environmental impact factor parameter, and each actual state data of each sampling point as a training sample set to train a state prediction model, considers various uncertain factors in an actual production scene, and uses real data to perform model training, so that not only can the accuracy of model prediction results be improved, but also the prediction requirements of the model for complex production conditions can be satisfied, and the stability of model prediction performance can be improved.
Furthermore, the process control parameter optimization scheme provided in this embodiment predicts the state of the next sampling point (i.e., the target sampling point) of the process system to be tested corresponding to the current sampling point by using the state prediction model according to the process control parameter of the current sampling point and the environmental impact factor parameter, so that the trained state prediction model is applicable to the application scenario of multi-condition switching, and can meet the real-time requirement on the prediction result in the actual prediction application, and the training update of the model can be performed by only collecting the latest production data, and the volume of the training data is greatly reduced, so as to reduce the model training cost.
Fig. 3 is a process flow chart of a process control parameter optimization method according to another exemplary embodiment of the present application, which illustrates another implementation of the above step S102, as shown in fig. 3, and mainly includes the following steps:
step 302, determining each process control parameter corresponding to each detection point in the process control sequence as each process control parameter to be optimized corresponding to each detection point.
Specifically, before predicting each state of the process system to be tested corresponding to each detection point, optimization can be performed on each original process control parameter corresponding to each detection point in the process control sequence, so as to promote the final parameter optimization effect.
Step 304, initializing parameter values of a parameter optimization algorithm.
In some embodiments, the initialization process may be performed on the parameter values of the parameter optimization algorithm according to the set parameter initial values. In another embodiment, the initialization process may also be performed on the parameter values of the parameter optimization algorithm using a random initialization method.
And 306, performing parameter optimization on each process control parameter to be optimized corresponding to each detection point based on the parameter value of the parameter optimization algorithm, and obtaining each intermediate process control parameter corresponding to each detection point.
In particular, the present embodiment may utilize a parameter optimization algorithm that iteratively performs iterative optimization of process control parameters during which parameter values of the parameter optimization algorithm are dynamically adjusted. Therefore, the process control parameters to be optimized corresponding to each detection point can be optimized and adjusted based on the current parameter value of the parameter optimization algorithm, and each intermediate process control parameter corresponding to each detection point is obtained.
Step 308, predicting each state of the process system to be detected corresponding to each detection point according to each intermediate process control parameter corresponding to each detection point, and obtaining each intermediate prediction state data and each prediction result evaluation data corresponding to each detection point.
In some embodiments, the training sample set of the process system under test also includes optimization target parameters (or referred to as optimization metrics) of the process system under test. The optimization target parameters of the process system to be tested are used for representing expected production results or ideal production results of the process system to be tested.
In some embodiments, the training of the state prediction model further comprises:
and for any current sampling point in the sampling points, obtaining prediction result evaluation data of the current sampling point according to the optimization target parameter, the process control parameter of the process system to be tested corresponding to the current sampling point and the prediction state data.
In this embodiment, the prediction result evaluation data of the current sampling point is used to characterize the accuracy of the prediction state data of the current sampling point.
In some embodiments, the prediction result evaluation data of the state prediction model corresponding to the current sampling point may be obtained according to the optimization target parameter, the process control parameter of the process system to be measured corresponding to the current sampling point, the environmental impact factor parameter, the prediction state data and the actual state data.
Step 310, updating parameter values of a parameter optimization algorithm according to the prediction result evaluation data corresponding to each detection point, and updating each intermediate process control parameter corresponding to each detection point to each process control parameter to be optimized corresponding to each detection point.
Specifically, the parameter value of the parameter optimization algorithm (for example, cross entropy algorithm) may be updated based on the evaluation data of each prediction result corresponding to each detection point, and each intermediate process control parameter corresponding to each detection point is updated to each process control parameter to be optimized corresponding to each detection point.
Step 312, determining whether the parameter optimization satisfies a preset parameter optimization ending condition, if yes, executing step 314, and if not, executing step 306.
In some embodiments, if the parameter optimization process performed on each process control parameter to be optimized corresponding to each detection point does not meet the preset parameter optimization end condition, the method returns to step 306 to perform parameter optimization on each process control parameter to be optimized corresponding to each detection point based on the parameter value currently updated by the parameter optimization algorithm again.
In some embodiments, when the number of times of processing of parameter optimization performed on each process control parameter to be optimized corresponding to each detection point satisfies a preset iteration optimization threshold, a determination result that the parameter optimization satisfies a preset parameter optimization end condition may be obtained.
In some embodiments, the preset iterative optimization threshold may be set to 200 times, but not limited to this, and those skilled in the art may adjust the iterative optimization threshold according to the actual optimization requirement, which is not limited in the present application.
Step 314, obtaining each optimized process control parameter of each detection point.
Specifically, each process control parameter to be optimized corresponding to each detection point can be determined as each optimized process control parameter of each detection point.
Step 316, predicting each state of the process system to be tested corresponding to each detection point according to each optimized process control parameter corresponding to each detection point, and obtaining each predicted state data corresponding to each detection point.
For details of the embodiment, reference is made to the description of step 102, and details are not repeated herein.
In summary, the process control parameter optimization scheme provided in this embodiment, in combination with the parameter optimization algorithm and the state prediction algorithm, performs multidimensional optimization on each process control parameter in the process control sequence, so as to further improve the optimization effect of the process control parameter and improve the production efficiency and the product yield of the process system.
Process control parameter optimizing device
Corresponding to the above method embodiments, fig. 4 shows a schematic diagram of a process control parameter optimizing apparatus according to an embodiment of the present application. As shown in fig. 4, the process control parameter optimizing apparatus 400 includes:
a prediction unit 402, configured to predict each state of the process system to be measured corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtain each predicted state data corresponding to each detection point;
A determining unit 404, configured to determine at least one target state data corresponding to the at least one target detection point in each predicted state data according to the at least one target detection point and the at least one detection point to be adjusted, and detect a state of the process system to be detected corresponding to the at least one target detection point, so as to obtain at least one actual state data of the at least one target detection point;
an analysis unit 406, configured to analyze the at least one target state data and the at least one actual state data, and obtain state analysis data of the at least one target detection point;
an optimizing unit 408, configured to optimize at least one process control parameter of the at least one detection point to be adjusted according to the state analysis data of the at least one target detection point.
In some embodiments, the prediction unit 402 is further configured to predict each state of the process system to be measured corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence by using a state prediction model, so as to obtain each predicted state data corresponding to each detection point.
In some embodiments, the process control parameter optimization apparatus 400 further includes a training module (not shown) for training the state prediction model, comprising: acquiring a training sample set of the process system to be tested, wherein the training sample set at least comprises process control parameters, environment influence factor parameters and actual state data of the process system to be tested corresponding to sampling points; determining a current sampling point and a target sampling point in all sampling points, wherein the target sampling point is one sampling point after the current sampling point in all sampling points; predicting the state of the process system to be tested corresponding to the target sampling point according to the process control parameter and the environment influence factor parameter of the process system to be tested corresponding to the current sampling point by using a state prediction model to be trained, and obtaining preset state data of the target sampling point; and training the state prediction model to be trained according to the predicted state data and the actual state data of the target sampling points to obtain the state prediction model.
In some embodiments, the state prediction model comprises a sparse gaussian process regression model.
In some embodiments, for any one current sampling point of the sampling points, a process control parameter for the current sampling point is determined according to a given control parameter and an adjustable parameter for the current sampling point; the environmental impact factor parameter of the current sampling point is obtained by sensing at least one sensing device of the process system to be detected at the detection moment corresponding to the current sampling point; the environmental impact factor parameter of the current sampling point at least comprises one of a production environment detection parameter, a production raw material detection parameter and an equipment parameter of the current sampling point.
In some embodiments, the training module is further to: comparing the predicted state data and the actual state data of the target sampling points to obtain a model loss value of the state prediction model to be trained; updating model parameters of the state prediction model to be trained based on the model loss value; executing the step of determining the current sampling point and the target sampling point in each sampling point by using the updated state prediction model to be trained until the model loss value meets the preset training ending condition; and obtaining the state prediction model.
In some embodiments, the training sample set of the process system under test further comprises optimization target parameters of the process system under test. The training module is also used for: for any current sampling point in all sampling points, obtaining prediction result evaluation data of the current sampling point according to the optimization target parameter, the process control parameter of the process system to be tested corresponding to the current sampling point and prediction state data; the prediction result evaluation data of the current sampling point represents the accuracy rate of the prediction state data of the current sampling point.
In some embodiments, the prediction unit 402 is further configured to: determining each process control parameter corresponding to each detection point in the process control sequence as each process control parameter to be optimized corresponding to each detection point; performing iterative optimization on each process control parameter to be optimized corresponding to each detection point at least once by using a given parameter optimization algorithm to obtain each optimized process control parameter corresponding to each detection point; and predicting each state of the process system to be detected corresponding to each detection point according to each optimized process control parameter corresponding to each detection point, and obtaining each prediction state data corresponding to each detection point.
In some embodiments, the given parameter optimization algorithm comprises a cross entropy algorithm.
In some embodiments, the prediction unit 402 is further configured to: initializing a parameter value of the parameter optimization algorithm; performing parameter optimization on each process control parameter to be optimized corresponding to each detection point based on the parameter value of the parameter optimization algorithm to obtain each intermediate process control parameter corresponding to each detection point; predicting each state of the process system to be detected corresponding to each detection point according to each intermediate process control parameter corresponding to each detection point, and obtaining each intermediate prediction state data and each prediction result evaluation data corresponding to each detection point; updating the parameter value of the parameter optimization algorithm according to the prediction result evaluation data corresponding to each detection point, updating each intermediate process control parameter corresponding to each detection point into each process control parameter to be optimized corresponding to each detection point, executing the parameter optimization on each process control parameter to be optimized corresponding to each detection point based on the parameter value of the parameter optimization algorithm, and obtaining each intermediate process control parameter step corresponding to each detection point until the parameter optimization meets the preset parameter optimization ending condition; obtaining each optimized process control parameter of each detection point.
In some embodiments, when the number of processing times of the parameter optimization performed on each process control parameter to be optimized corresponding to each detection point meets a preset iteration optimization threshold, a determination result that the parameter optimization meets a preset parameter optimization end condition is obtained.
In some embodiments, the at least one target detection point comprises a first detection point of the detection points; the at least one detection point to be adjusted comprises at least one detection point after the target detection point in each detection point.
Electronic equipment
Fig. 5 is a schematic diagram of an electronic device according to a fourth embodiment of the present application, which is not limited to the specific implementation of the electronic device according to the embodiment of the present application. Referring to fig. 5, an electronic device 500 provided in an embodiment of the present application includes: a processor 502, a communication interface (Communications Interface) 504, a memory 506, and a bus 508. Wherein:
processor 502, communication interface 504, and memory 506 communicate with each other via bus 508.
A communication interface 504 for communicating with other electronic devices or servers.
The processor 502 is configured to execute the program 510, and may specifically perform relevant steps in the above-described process control parameter optimization method embodiment.
In particular, program 510 may include program code including computer-operating instructions.
The processor 502 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors comprised by the smart device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 506 for storing program 510. Memory 506 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 510 is particularly useful for causing the processor 502 to perform the process control parameter optimization method of any of the embodiments described above.
The specific implementation of each step in the procedure 510 may refer to the corresponding steps and corresponding descriptions in the units in the foregoing process control parameter optimization method embodiment, which are not described herein. It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and modules described above may refer to corresponding procedure descriptions in the foregoing method embodiments, which are not repeated herein.
Computer readable storage medium
The present application also provides a computer readable storage medium storing instructions for causing a machine to perform a process control parameter optimization method as described herein. Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present application.
Examples of the storage medium for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion module connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion module is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
Nouns and pronouns for humans in this patent application are not limited to a particular gender.
In the above embodiments, the hardware module may be mechanically or electrically implemented. For example, a hardware module may include permanently dedicated circuitry or logic (e.g., a dedicated processor, FPGA, or ASIC) to perform the corresponding operations. The hardware modules may also include programmable logic or circuitry (e.g., a general-purpose processor or other programmable processor) that may be temporarily configured by software to perform the corresponding operations. The particular implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.
While the application has been illustrated and described in detail in the drawings and in the preferred embodiments, the application is not limited to the disclosed embodiments, and it will be appreciated by those skilled in the art that the code audits of the various embodiments described above may be combined to produce further embodiments of the application, which are also within the scope of the application.
Claims (14)
1. A process control parameter optimization method comprising:
predicting each state of the process system to be detected corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtaining each prediction state data corresponding to each detection point;
according to at least one target detection point and at least one detection point to be adjusted which are determined in each detection point, at least one target state data corresponding to the at least one target detection point is determined in each prediction state data, the state of the process system to be detected corresponding to the at least one target detection point is detected, and at least one actual state data of the at least one target detection point is obtained;
analyzing the at least one target state data and the at least one actual state data to obtain state analysis data of the at least one target detection point;
optimizing at least one process control parameter of the at least one point to be adjusted based on the state analysis data of the at least one target point.
2. The method according to claim 1, wherein the method comprises:
executing the step of predicting each state of the process system to be detected corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence by using a state prediction model to obtain each prediction state data corresponding to each detection point;
And wherein the state prediction model is obtained by training in the following manner:
acquiring a training sample set of the process system to be tested, wherein the training sample set at least comprises process control parameters, environment influence factor parameters and actual state data of the process system to be tested corresponding to sampling points;
determining a current sampling point and a target sampling point in all sampling points, wherein the target sampling point is one sampling point after the current sampling point in all sampling points;
predicting the state of the process system to be tested corresponding to the target sampling point according to the process control parameter and the environment influence factor parameter of the process system to be tested corresponding to the current sampling point by using a state prediction model to be trained, and obtaining preset state data of the target sampling point;
and training the state prediction model to be trained according to the predicted state data and the actual state data of the target sampling points to obtain the state prediction model.
3. The method of claim 2, wherein the state prediction model comprises a sparse gaussian process regression model.
4. The method of claim 2, wherein,
For any one of the current sampling points,
the process control parameters of the current sampling point are determined according to the given control parameters and the adjustable parameters of the current sampling point;
the environmental impact factor parameter of the current sampling point is obtained by sensing at least one sensing device of the process system to be detected at the detection moment corresponding to the current sampling point;
the environmental impact factor parameter of the current sampling point at least comprises one of a production environment detection parameter, a production raw material detection parameter and an equipment parameter of the current sampling point.
5. The method according to claim 2, wherein the training the state prediction model to be trained according to the predicted state data and the actual state data of the target sampling point to obtain the state prediction model includes:
comparing the predicted state data and the actual state data of the target sampling points to obtain a model loss value of the state prediction model to be trained;
updating model parameters of the state prediction model to be trained based on the model loss value;
executing the step of determining the current sampling point and the target sampling point in each sampling point by using the updated state prediction model to be trained until the model loss value meets the preset training ending condition;
And obtaining the state prediction model.
6. The method of claim 2, wherein the training sample set of the process system under test further comprises optimization target parameters of the process system under test;
and wherein the training of the state prediction model further comprises:
for any one of the current sampling points,
obtaining prediction result evaluation data of the current sampling point according to the optimization target parameter, the process control parameter of the process system to be detected corresponding to the current sampling point and the prediction state data;
the prediction result evaluation data of the current sampling point represents the accuracy rate of the prediction state data of the current sampling point.
7. The method according to claim 1 or 6, wherein predicting each state of the process system under test corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtaining each predicted state data corresponding to each detection point, comprises:
determining each process control parameter corresponding to each detection point in the process control sequence as each process control parameter to be optimized corresponding to each detection point;
performing iterative optimization on each process control parameter to be optimized corresponding to each detection point at least once by using a given parameter optimization algorithm to obtain each optimized process control parameter corresponding to each detection point;
And predicting each state of the process system to be detected corresponding to each detection point according to each optimized process control parameter corresponding to each detection point, and obtaining each prediction state data corresponding to each detection point.
8. The method of claim 7, wherein the given parameter optimization algorithm comprises a cross entropy algorithm.
9. The method of claim 7, wherein performing at least one iterative optimization on each process control parameter to be optimized for each detection point using a given parameter optimization algorithm to obtain each optimized process control parameter for each detection point comprises:
initializing a parameter value of the parameter optimization algorithm;
performing parameter optimization on each process control parameter to be optimized corresponding to each detection point based on the parameter value of the parameter optimization algorithm to obtain each intermediate process control parameter corresponding to each detection point;
predicting each state of the process system to be detected corresponding to each detection point according to each intermediate process control parameter corresponding to each detection point, and obtaining each intermediate prediction state data and each prediction result evaluation data corresponding to each detection point;
updating the parameter value of the parameter optimization algorithm according to the prediction result evaluation data corresponding to each detection point, updating each intermediate process control parameter corresponding to each detection point into each process control parameter to be optimized corresponding to each detection point, executing the parameter optimization on each process control parameter to be optimized corresponding to each detection point based on the parameter value of the parameter optimization algorithm, and obtaining each intermediate process control parameter step corresponding to each detection point until the parameter optimization meets the preset parameter optimization ending condition;
Obtaining each optimized process control parameter of each detection point.
10. The method according to claim 9, wherein the determination that the parameter optimization satisfies a preset parameter optimization end condition is obtained by:
and when the processing times of the parameter optimization executed on each process control parameter to be optimized corresponding to each detection point meet a preset iteration optimization threshold, obtaining a judgment result that the parameter optimization meets a preset parameter optimization ending condition.
11. The method of claim 1, wherein,
the at least one target detection point comprises a first detection point of the detection points;
the at least one detection point to be adjusted comprises at least one detection point after the target detection point in each detection point.
12. A process control parameter optimization apparatus comprising:
the prediction unit is used for predicting each state of the process system to be detected corresponding to each detection point according to each process control parameter corresponding to each detection point in the process control sequence, and obtaining each prediction state data corresponding to each detection point;
the determining unit is used for determining at least one target state data corresponding to the at least one target detection point in each prediction state data according to the at least one target detection point and the at least one detection point to be adjusted, detecting the state of the process system to be detected corresponding to the at least one target detection point and obtaining at least one actual state data of the at least one target detection point;
An analysis unit for analyzing the at least one target state data and the at least one actual state data to obtain state analysis data of the at least one target detection point;
and the optimizing unit is used for optimizing at least one process control parameter of the at least one detection point to be adjusted according to the state analysis data of the at least one target detection point.
13. An electronic device, comprising: the device comprises a processor, a communication interface, a memory and a bus, wherein the processor, the communication interface and the memory are communicated with each other through the bus;
the memory is configured to store at least one executable instruction that causes the processor to perform operations corresponding to the method of any one of claims 1 to 11.
14. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, cause the processor to perform the method of any of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897245.8A CN116880397A (en) | 2023-07-20 | 2023-07-20 | Process control parameter optimization method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897245.8A CN116880397A (en) | 2023-07-20 | 2023-07-20 | Process control parameter optimization method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116880397A true CN116880397A (en) | 2023-10-13 |
Family
ID=88264126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310897245.8A Pending CN116880397A (en) | 2023-07-20 | 2023-07-20 | Process control parameter optimization method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116880397A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117193223A (en) * | 2023-11-06 | 2023-12-08 | 南通瑞童塑业科技有限公司 | Plastic product production control system |
| CN117311170A (en) * | 2023-11-29 | 2023-12-29 | 江苏美特林科特殊合金股份有限公司 | Multi-parameter adjusting method and system for self-adaptively controlled nickel-niobium alloy smelting equipment |
-
2023
- 2023-07-20 CN CN202310897245.8A patent/CN116880397A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117193223A (en) * | 2023-11-06 | 2023-12-08 | 南通瑞童塑业科技有限公司 | Plastic product production control system |
| CN117193223B (en) * | 2023-11-06 | 2024-04-05 | 南通瑞童塑业科技有限公司 | Plastic product production control system |
| CN117311170A (en) * | 2023-11-29 | 2023-12-29 | 江苏美特林科特殊合金股份有限公司 | Multi-parameter adjusting method and system for self-adaptively controlled nickel-niobium alloy smelting equipment |
| CN117311170B (en) * | 2023-11-29 | 2024-02-06 | 江苏美特林科特殊合金股份有限公司 | Multi-parameter adjusting method and system for self-adaptively controlled nickel-niobium alloy smelting equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116880397A (en) | Process control parameter optimization method, device, electronic equipment and storage medium | |
| Liu et al. | Lithium-ion battery remaining useful life estimation based on fusion nonlinear degradation AR model and RPF algorithm | |
| US10387768B2 (en) | Enhanced restricted boltzmann machine with prognosibility regularization for prognostics and health assessment | |
| Liu et al. | Lithium-ion battery remaining useful life estimation based on nonlinear AR model combined with degradation feature | |
| CN109214708B (en) | Electric power system risk assessment method based on cross entropy theory optimization support vector machine | |
| CN110197288A (en) | The remaining life prediction technique of equipment under the influence of failure | |
| El-Koujok et al. | Multiple sensor fault diagnosis by evolving data-driven approach | |
| Li et al. | Residual useful life estimation by a data‐driven similarity‐based approach | |
| Habib et al. | Data-driven modeling: concept, techniques, challenges and a case study | |
| CN103885867B (en) | Online evaluation method of performance of analog circuit | |
| CN105678409A (en) | Adaptive and distribution-free time series abnormal point detection method | |
| Lu et al. | Neural network interpretability for forecasting of aggregated renewable generation | |
| CN115481549A (en) | Cylindrical linear motor multi-objective optimization method, equipment and storage medium | |
| CN108846489A (en) | A kind of large scale equipment health Evaluation method based on SVM | |
| Wang et al. | Multivariate relevance vector regression based degradation modeling and remaining useful life prediction | |
| Benker et al. | A Gaussian process based method for data-efficient remaining useful life estimation | |
| Liu et al. | Multiple optimized online support vector regression for adaptive time series prediction | |
| Li et al. | A wiener-based remaining useful life prediction method with multiple degradation patterns | |
| Chen et al. | Identification of time‐delay Markov jump autoregressive exogenous systems with expectation‐maximization algorithm | |
| Sun et al. | Fault diagnosis method of low noise amplifier based on support vector machine and hidden markov model | |
| CN115640542A (en) | Intelligent electric energy meter state evaluation method and evaluation device based on Bayesian theory | |
| Lin et al. | Smart building uncertainty analysis via adaptive Lasso | |
| CN113205215A (en) | Knowledge-based battlefield situation prediction method | |
| CN113255775A (en) | Method and device for identifying abnormal data of power system and intelligent chip | |
| Lim et al. | Fault detection and remaining useful life estimation using switching Kalman filters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |