CN118151616A - Technological parameter self-adaptive adjusting system for superplastic forming diffusion connection machining process - Google Patents
Technological parameter self-adaptive adjusting system for superplastic forming diffusion connection machining process Download PDFInfo
- Publication number
- CN118151616A CN118151616A CN202410566010.5A CN202410566010A CN118151616A CN 118151616 A CN118151616 A CN 118151616A CN 202410566010 A CN202410566010 A CN 202410566010A CN 118151616 A CN118151616 A CN 118151616A
- Authority
- CN
- China
- Prior art keywords
- layer
- workpiece
- temperature
- gas pressure
- heating temperature
- 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
- 238000009792 diffusion process Methods 0.000 title claims abstract description 84
- 238000003754 machining Methods 0.000 title claims description 22
- 238000000034 method Methods 0.000 claims abstract description 255
- 230000008569 process Effects 0.000 claims abstract description 221
- 238000012545 processing Methods 0.000 claims abstract description 167
- 230000008859 change Effects 0.000 claims abstract description 86
- 238000010438 heat treatment Methods 0.000 claims abstract description 81
- 238000003745 diagnosis Methods 0.000 claims abstract description 17
- 238000004519 manufacturing process Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000001105 regulatory effect Effects 0.000 claims description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000013139 quantization Methods 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 87
- 241000577395 Thenus Species 0.000 description 21
- 229910001069 Ti alloy Inorganic materials 0.000 description 20
- 238000004458 analytical method Methods 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000004321 preservation Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 239000000463 material Substances 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Shaping Metal By Deep-Drawing, Or The Like (AREA)
Abstract
The invention discloses a superplastic forming diffusion connection processing process technological parameter self-adaptive adjustment system, which comprises an optimal processing parameter setting layer, a process parameter control layer, a process parameter prediction layer, a fault diagnosis layer, a feedforward compensator and a feedback compensator; the optimal processing parameter setting layer sets an ideal temperature curve and a gas pressure change curve; the process parameter control layer adjusts the internal pressure of the workpiece and the internal heating temperature of the workpiece in the processing process through a fuzzy control method; and the optimal processing parameter setting layer is used for optimizing the set ideal temperature curve and gas pressure change curve by combining the comparison result fed back by the feedback compensator, the predicted value of the internal pressure of the workpiece and the internal heating temperature of the workpiece and the judged machine tool state. The invention monitors the processing process in real time and realizes the self-adaptive adjustment of the technological parameters, improves the processing efficiency, ensures the stability of the processing process and the processing quality of the product, and reduces the labor intensity of workers.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing or titanium alloy superplastic forming diffusion connection processing, in particular to a superplastic forming diffusion connection processing process technological parameter self-adaptive adjustment system.
Background
The choice of forming technological parameters such as temperature, pressure and the like in the process of the superplastic forming diffusion connection processing of the titanium alloy directly determines the forming performance of the part, and the microstructure and mechanical properties after forming. In the traditional superplastic forming diffusion connection processing process, a worker determines a relation curve of heating temperature and time and a relation curve of gas pressure and time of superplastic forming diffusion connection equipment in advance through simulation or previous processing experience, and inputs the relation curve of heating temperature and time and the relation curve of gas pressure and time into a control panel of the equipment before processing, and in the processing process, a heating system and a gas path system of the equipment heat and charge air and pressurize according to a set temperature curve and a set pressure curve, so that a finished workpiece is obtained. Due to the specificity of the superplastic forming diffusion connection processing process, the temperature and the pressure in the processing process have risks of deviating from a set temperature curve and a set pressure curve, and after the temperature and the pressure deviate, workers are required to manually adjust the superplastic forming diffusion connection processing process, and risks of lag in adjustment and inaccurate adjustment exist.
Disclosure of Invention
Aiming at the technical problems of difficult monitoring, lag adjustment, inaccurate adjustment, low processing efficiency, high labor intensity of workers and the like of the process parameters of the superplastic forming diffusion connection forming process, the invention provides a self-adaptive adjustment system for the process parameters of the superplastic forming diffusion connection forming process, which monitors the processing process in real time and realizes the self-adaptive adjustment of the process parameters in the superplastic forming diffusion connection forming process, and has important practical significance for improving the processing efficiency of the superplastic forming diffusion connection forming process, ensuring the stability of the superplastic forming diffusion connection forming process and the processing quality of products and reducing the labor intensity of workers.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
in a first aspect, the invention discloses a superplastic forming diffusion connection processing process technological parameter self-adaptive adjustment system, which comprises an optimal processing parameter setting layer, a process parameter control layer, a process parameter prediction layer, a fault diagnosis layer, a feedforward compensator and a feedback compensator;
The optimal processing parameter setting layer sets an ideal temperature curve and a gas pressure change curve through software simulation or based on the past processing experience according to production information including the technological requirements, the operation conditions and the gas characteristics of a product to be processed, the boundary conditions of the superplastic forming diffusion connection process and the equipment information set in the historical superplastic forming diffusion connection process;
The process parameter control layer monitors the heating temperature and the gas pressure in the processing process in real time through a temperature sensor and a gas pressure meter, compares the monitored heating temperature and the monitored gas pressure with an ideal temperature curve and a gas pressure change curve respectively, and adjusts the internal pressure of a workpiece and the internal heating temperature of the workpiece in the processing process through a fuzzy control method;
The feedback compensator compares the detection values of the internal pressure of the workpiece and the internal heating temperature of the workpiece, which are detected by the temperature sensor and the barometer, with the set ideal temperature curve and the gas pressure change curve, and feeds back the comparison result to the optimal processing parameter setting layer;
The process parameter predicting layer predicts the internal pressure of the workpiece and the internal heating temperature of the workpiece in the subsequent processing process, and inputs the predicted value to the optimal processing parameter setting layer through the feedforward compensator;
the fault diagnosis layer analyzes and judges the state of the machine tool through signals directly collected from the machine tool, and inputs the judged state of the machine tool to an optimal processing parameter setting layer through a feedforward compensator;
And the optimal processing parameter setting layer is used for optimizing the set ideal temperature curve and gas pressure change curve by combining the comparison result fed back by the feedback compensator, the predicted value of the internal pressure of the workpiece and the internal heating temperature of the workpiece and the judged machine tool state.
Further, the process parameter control layer compares the monitored internal pressure of the workpiece with a gas pressure change curve of the optimal processing parameter setting layer, and controls the internal pressure of the workpiece in the processing process through a fuzzy control method based on a comparison result;
The process parameter control layer compares the monitored internal heating temperature of the workpiece with the temperature change curve of the optimal processing parameter setting layer, and controls the temperature regulating valve to regulate the heating temperature in real time by a fuzzy control method so as to regulate the internal heating temperature of the workpiece in the processing process.
Further, the process parameter control layer comprises a workpiece internal pressure acquisition unit, a blurring unit, a rule determination unit, a control table generation unit, a blurring judgment unit and a controlled variable change output unit;
The pressure intensity acquisition unit in the workpiece is used for acquiring the air pressure intensity in the workpiece in real time through the barometer;
the blurring unit is used for combining the collected gas pressure inside the workpiece and the gas pressure change curve of the optimal processing parameter setting layer to calculate and obtain the pressure difference And rate of change of pressure differenceFor pressure differenceAnd rate of change of pressure differenceAnd outputting a control quantity U for blurring;
The rule determining unit is used for determining a fuzzy control rule;
The control table generating unit is used for carrying out fuzzy synthesis operation, solving a fuzzy relation matrix and generating a control table;
The fuzzy decision unit is used for carrying out fuzzy decision on the output quantity according to the given input;
The controlled variable change output unit is used for performing anti-blurring on the output controlled variable U through the product operation of the controlled variable U and a given quantization factor, and outputting the change of the controlled variable in the actual processing process of superplastic forming diffusion connection.
Further, the fault diagnosis layer predicts the fault type possibly happening later in the processing process, and alarms according to the predicted fault type.
Further, the process parameter prediction layer comprises a working condition parameter range judging unit, a first process parameter prediction model based on case reasoning, a second process parameter prediction model based on a neural network and a calibration model;
The working condition parameter range judging unit is used for judging whether working condition parameters of the superplastic forming diffusion connection machining process are in a normal range or not; when the working condition parameters of the superplastic forming diffusion connection machining process are in a normal range, the working condition parameter range judging unit calls a second process parameter prediction model to predict the heating temperature and the gas pressure; when working condition parameters of the superplastic forming diffusion connection machining process are not in a normal range, the working condition parameter range judging unit calls a first process parameter prediction model to predict heating temperature and gas pressure;
and the calibration model processes the predicted values of the heating temperature and the gas pressure output by the first process parameter prediction model or the second process parameter prediction model to obtain final predicted values of the heating temperature and the gas pressure.
Further, the calibration model comprises a difference value calculation unit and an error calibration unit;
The difference value calculation unit obtains a temperature difference value between a predicted value of the heating temperature output by the process parameter prediction layer and the heating temperature obtained by actual collection, and a pressure difference value between a predicted value of the gas pressure output by the process parameter prediction layer and the gas pressure obtained by actual collection;
The error calibration unit compares the absolute value of the temperature difference value obtained by solving with the temperature error limit value, if the absolute value of the temperature difference value is smaller than or equal to the temperature error limit value, the predicted value of the heating temperature output by the process parameter predicting layer is used as a final predicted value, otherwise, the temperature difference value is subtracted from the predicted value of the heating temperature output by the process parameter predicting layer to obtain the final predicted value;
And the error calibration unit compares the absolute value of the pressure difference value obtained by solving with the pressure error limit value, if the absolute value of the pressure difference value is smaller than or equal to the pressure error limit value, the predicted value of the gas pressure output by the process parameter prediction layer is used as a final predicted value, otherwise, the pressure difference value is subtracted from the predicted value of the gas pressure output by the process parameter prediction layer to obtain the final predicted value.
In a second aspect, the invention discloses a method for adaptively adjusting technological parameters based on the superplastic forming diffusion connection processing process, which comprises the following steps:
S1, in the initial stage of superplastic forming diffusion connection processing, an optimal processing parameter setting layer sets an ideal temperature curve and a gas pressure change curve through software simulation or based on the past processing experience according to production information including the technological requirements, operation conditions and gas characteristics of a product to be processed, boundary conditions of the superplastic forming diffusion connection process and equipment information sets in the superplastic forming diffusion connection process;
S2, in the superplastic forming diffusion connection processing process, a process parameter control layer monitors heating temperature and gas pressure in the processing process in real time through a temperature sensor, a barometer and an embedded timer, compares the monitored pressure signal with a gas pressure change curve output by an optimal processing parameter setting layer, controls the internal pressure of a workpiece in the processing process through a fuzzy control method, simultaneously compares the monitored temperature signal with a temperature change curve output by the optimal processing parameter setting layer, controls a temperature regulating valve to regulate the heating temperature in real time through a fuzzy control method, and regulates the internal heating temperature of the workpiece in the processing process;
After the pressure inside the workpiece and the heating temperature inside the workpiece are adjusted, detecting the adjusted air pressure signal and the temperature signal in real time through an air pressure gauge and a temperature sensor, comparing the adjusted air pressure signal and the temperature signal with an ideal temperature curve and an ideal gas pressure change curve of the optimal processing parameter setting layer respectively, and feeding back the comparison result to the optimal processing parameter setting layer through a feedback compensation model;
The process parameter prediction layer predicts the subsequent process parameters according to the current working condition parameters of the superplastic forming diffusion connection processing process, and inputs the final predicted value to the optimal processing parameter setting layer through the feedforward compensation model; the fault diagnosis layer analyzes and judges the state of the machine tool through the signals collected from the machine tool directly, and inputs the state of the machine tool into the optimal processing parameter setting layer through the feedforward compensation model;
The feedforward compensation model inputs the workpiece internal heating temperature output by the process parameter prediction layer, the final predicted value of the workpiece internal pressure and the machine tool state output by the fault diagnosis layer to the optimal processing parameter setting layer, and the optimal processing parameter setting layer optimizes an ideal temperature curve and a gas pressure change curve according to feedback results of the feedforward compensation model and the feedback compensation model;
S3, repeating the step S2 until the workpiece is machined.
Further, the fault diagnosis layer comprises a fault prediction system, wherein the fault prediction system is used for predicting the type of fault rate possibly happening in the follow-up process of the superplastic forming diffusion connection, and alarming is carried out according to the type of fault.
Compared with the prior art, the invention has the following beneficial effects:
Firstly, the self-adaptive adjustment system for the technological parameters of the superplastic forming diffusion connection processing process can realize real-time monitoring and self-adaptive adjustment of the technological parameters in the superplastic forming diffusion connection forming process, has good applicability and high controllability, can provide visual temperature and gas pressure curves, is beneficial to understanding the real-time processing state of the superplastic forming diffusion connection, controlling abnormal shutdown, optimizing the processing efficiency, recording the processing process data and is beneficial to process information statistics and process review analysis.
Secondly, compared with the traditional method for setting an ideal temperature curve and a pressure change curve according to experience and simulation results, the superplastic forming diffusion connection processing process parameter self-adaptive adjustment system is characterized in that a feedforward compensator and a feedback compensator are added into the superplastic forming diffusion connection processing process parameter self-adaptive adjustment system, so that when the ideal temperature curve and the ideal pressure change curve are set, the dynamic change of the processing parameters in the processing process, the factors in many aspects such as the past case experience, the prediction result of an artificial neural network, the machine tool state and the like are fully considered, and the set temperature curve and pressure change curve are more scientific and reasonable.
Thirdly, the process parameter self-adaptive adjustment system for the superplastic forming diffusion connection processing process monitors the processing process in real time and realizes the self-adaptive adjustment of the process parameter in the superplastic forming diffusion connection processing process, reduces the risk that the temperature and the pressure in the processing process deviate from a set temperature curve and a pressure curve, ensures the timeliness and the accuracy of adjustment after the deviation of the process parameter, reduces the workload of manually adjusting the process parameter under severe conditions, and reduces the labor intensity of workers.
Fourth, the invention of the superplastic forming diffusion connection processing process parameter self-adaptive adjustment system realizes the control of the internal gas pressure and heating temperature of the workpiece in the processing process by a fuzzy control method, and compared with the traditional manual adjustment, the control method is more scientific and reasonable.
Drawings
FIG. 1 is a schematic diagram of the structural principle of the adaptive adjustment system for the technological parameters in the superplastic forming diffusion connection processing procedure of the invention;
FIG. 2 is a flow chart of an ideal gas variation curve obtained by software simulation;
FIG. 3 is an initial ideal temperature profile and gas pressure profile for a certain type of titanium alloy part;
FIG. 4 is a graph of the temperature monitored during actual processing of a titanium alloy part of a certain model, an ideal temperature curve optimized when the actual temperature deviates, and an ideal gas pressure change curve optimized when the actual temperature deviates;
FIG. 5 is a graph of gas pressure monitored during actual processing of a titanium alloy part of a certain model, an optimized ideal gas pressure change curve when the actual gas pressure deviates, and an optimized ideal temperature curve when the actual gas pressure deviates;
FIG. 6 is a flow chart of fuzzy control of the internal pressure of a part in a process parameter control layer;
FIG. 7 is a prediction flow diagram of a process parameter prediction layer.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings.
As shown in fig. 1, an adaptive adjustment system for process parameters of a superplastic forming diffusion connection process includes an optimal process parameter setting layer, a process parameter control layer, a process parameter prediction layer, a fault diagnosis layer, a feedforward compensator, a feedback compensator, and the like.
In fig. 1, Q s is a target value of the workpiece gas pressure and forming temperature, Q p is a predicted value of the workpiece gas pressure and forming temperature, Q d is a monitored statistical value of the gas pressure and forming temperature, Δq d is a difference between the target value of the workpiece gas pressure and forming temperature and the monitored statistical value thereof, Δq p is a difference between the target value of the workpiece gas pressure and forming temperature and the predicted value thereof, P a is a set value of the workpiece internal pressure and heating temperature set based on software simulation or previous processing experience, P s is a set value of the workpiece internal pressure and temperature compensated by a feedforward model and a feedback model, Δp p is a feedback compensation value of the workpiece internal pressure and temperature, Δp d is a feedforward compensation value of the workpiece internal pressure and temperature, I is a production information set (including an operation condition, a gas characteristic, etc.) in the superplastic forming diffusion connection production process, B is a boundary condition in the superplastic forming diffusion connection process, and F is a device information set (i.e. a fault in the production process).
In an optimal processing parameter setting layer of the self-adaptive adjustment system for the processing parameters of the superplastic forming diffusion connection processing process, an optimal processing parameter setting model sets an ideal temperature curve and an ideal gas pressure change curve through software simulation or based on the past processing experience according to production information such as the process requirements, the operation conditions, the gas characteristics and the like of a product to be processed, boundary conditions of the superplastic forming diffusion connection process and equipment information sets (namely faults in the production process) in the superplastic forming diffusion connection process.
Specifically, when the processing technology of the workpiece to be processed is mature and various finished products are provided, an ideal temperature curve and a gas pressure change curve can be set based on the past processing experience.
Specifically, when a brand new workpiece is processed, the temperature during the superplastic stretching of the workpiece is obtained according to the superplastic stretching curve of the workpiece material to be processed, so that the temperature curve is obtained. By the load control method, finite element analysis is carried out on the processing process based on ABAQUS software to obtain an ideal gas pressure change curve, and the method comprises the following specific steps of:
(1) And establishing a geometric analysis model aiming at a titanium alloy single-layer plate structure of a certain model. The geometric model comprises a forming die and a titanium alloy plate, wherein in the forming process, the plate is in a superplastic deformation state, and compared with the plate, the rigidity of the die is far greater than that of the titanium alloy plate, so that the die is regarded as a rigid body in modeling, the titanium alloy plate is defined as a deformable body, and the outer surface of the part is regarded as the appearance of the die.
(2) The material constant is determined. As the superplastic forming is in an isothermal state, the temperature change in the deformation process is ignored, the material constant K value of the titanium alloy plate is 1315.2MPa s, a time hardening model at a certain temperature is adopted in the creep analysis of the material, and the material constant is shown in Table 1. The constitutive equation is:
；
In the method, in the process of the invention, In order to achieve a rate of strain,The stress is that A, m and n are material constants.
TABLE 1
(3) Contact definition of the die and the titanium alloy sheet is performed. The contact between the forming die and the titanium alloy plate is surface contact, and the friction state (comprising friction force, friction coefficient and the like) between the die and the plate as well as between the plate and the plate in the forming process is difficult to measure and observe because of the particularity of the superplastic forming process, and can only be estimated by experience or assumption, so that a penalty function model is selected to calculate the contact stress, the problem of convergence possibly caused by discontinuity between the bonding state and the sliding state is solved, and the contact friction model adopts a coulomb friction law, wherein the friction coefficient is 0.1.
(4) Boundary conditions and loads are determined. The forming die is applied with full constraint and fixed, the analytic rigid body applies constraint on a defined reference point in ABAQUS, for the titanium alloy plate, the displacement of the titanium alloy plate can be bound with the die by using Tie constraint due to the die clamping effect, the displacement of the plate is restrained at the joint, the gas pressure load is a distribution surface load, and the applied load is consistent with the normal direction of the unit.
(5) Finite element analysis is performed based on a load control method. The main goal of the finite element analysis control is that the superplastic strain rate of any one cell does not exceed the maximum optimized strain rate value at any one stage in the superplastic deformation. The load equation under the maximum strain rate is realized through the load control method, and the loading pressure is a physical quantity which is always changed in the whole simulation process so as to maintain the strain rateAt a predetermined valueOptimized strain rate of nearby titanium alloy sheet materialAbout 0.001/s, and performing finite element analysis on the overspeed forming diffusion joint process by utilizing ABAQU/Standard to obtain an ideal pressure change curve.
The process parameter control layer monitors the heating temperature and the gas pressure in the processing process in real time through the temperature sensor and the gas pressure meter, compares the monitored heating temperature and the monitored gas pressure with an ideal temperature curve and a gas pressure change curve respectively, and adjusts the internal pressure of the workpiece and the internal heating temperature of the workpiece in the processing process through a fuzzy control method.
The feedback compensator compares the detection values of the internal pressure of the workpiece and the internal heating temperature of the workpiece, which are detected by the temperature sensor and the barometer, with the set ideal temperature curve and the gas pressure change curve, and feeds back the comparison result to the optimal processing parameter setting layer so as to adapt to the dynamic change of the superplastic forming diffusion connection processing process.
The process parameter predicting layer predicts the internal pressure of the workpiece and the internal heating temperature of the workpiece in the subsequent processing process, and inputs the predicted value to the optimal processing parameter setting layer through the feedforward compensator.
The fault diagnosis layer analyzes and judges the state of the machine tool through the signals directly collected from the machine tool, and inputs the judged state of the machine tool to the optimal processing parameter setting layer through the feedforward compensator.
And the optimal processing parameter setting layer is used for optimizing the set ideal temperature curve and gas pressure change curve by combining the comparison result fed back by the feedback compensator, the predicted value of the internal pressure of the workpiece and the internal heating temperature of the workpiece and the judged machine tool state.
Specifically, in an ideal processing process, the forming device is required to carry out heat preservation and pressurization strictly according to a set ideal temperature curve and a gas pressure change curve, but in an actual processing process, abnormal fluctuation can occur in parameters such as heat preservation temperature and pressurization speed of the forming device, internal pressure of a workpiece and the like due to the influence of uncertainty factors such as equipment performance attenuation, machine tool state change, control hysteresis and the like, so that the ideal temperature curve and the gas pressure change curve are required to be adjusted according to actual conditions, the actual heating process is guided to be more stable, and the forming quality of the workpiece is ensured. In the actual processing process, when the heat preservation temperature in the forming device is monitored to deviate from an ideal temperature curve, the optimal processing parameter setting layer adjusts the temperature to the ideal temperature according to the deviation time and the temperature, and synchronously translates the initial ideal temperature curve according to the deviation time to form a new ideal temperature curve. Synchronously, the pressure change curve is synchronously prolonged according to the newly generated temperature curve, and a new ideal gas pressure change curve is formed.
Specifically, the process of optimizing the ideal temperature curve and the gas pressure change curve set by the optimal processing parameter setting layer is described by taking the processing process of a certain type of titanium alloy workpiece as an example. An ideal temperature curve of initial setting of a certain type of titanium alloy workpiece is shown in (a) of fig. 3, and an ideal gas pressure change curve of initial setting is shown in (b) of fig. 3. The ideal superplastic forming diffusion connection temperature of the model product is 920 ℃, and in the processing process, the workpiece needs to be kept at 920 ℃ for 65min. Fig. 4 (a) shows an actual processing example of the titanium alloy workpiece with the model, the temperature in the period of 10-20min is monitored to be lower than 920 ℃ in the actual processing process, at this time, the power of the heating equipment is required to be controlled, the forming device is heated to 920 ℃ and is insulated, and the insulation duration is required to be consistent with the insulation duration of the initially set ideal temperature curve. As shown in fig. 4 (b), the optimized temperature curve is shown in fig. 4, the actual heat preservation period is shown in the 0 th to 10 th min, the temperature reduction period in the actual processing process is shown in the 10 th to 20 th min, the optimized heating period is shown in the 20 th to 30 th min, the heat preservation period is shown in the 30 th to 85 th min, and the total heat preservation period is shown in the 920 ℃ environment for 65min. In synchronization, since the ideal temperature profile is optimized, the ideal gas pressure profile needs to be translated synchronously according to the abnormal temperature of the forming device, so as to form a new ideal gas pressure profile, as shown in (c) of fig. 4.
In the actual processing process, when the gas pressure in the forming device deviates from the ideal gas pressure, the ideal gas pressure change curve is synchronously translated backwards according to the deviation time and the gas pressure, a new ideal gas pressure change curve is formed, the heat preservation time of the forming device is synchronously prolonged according to the newly generated ideal gas pressure change curve, and a new temperature change curve is formed. As shown in fig. 5 (a), the gas pressure change condition of the titanium alloy workpiece in the model is monitored in real time in the actual machining process, the gas pressure at 10min is monitored to be 0.2MPa and less than the ideal value of 0.4MPa, so that the forming device should be continuously pressurized, the pressurizing speed should be the same as the pressurizing speed of the initially set ideal gas pressure change curve, that is, the initially set ideal gas pressure change curve is synchronously translated backwards to form a new ideal gas pressure change curve ((b) in fig. 5), and synchronously, since the ideal gas pressure change curve is optimized, the ideal temperature curve should be synchronously prolonged for the heat preservation time of the forming device to form the new ideal gas pressure change curve ((c) in fig. 5).
The process parameter control layer compares the monitored internal pressure of the workpiece with a gas pressure change curve of the optimal processing parameter setting layer, and controls the internal pressure of the workpiece in the processing process by a fuzzy control method based on a comparison result; and comparing the monitored internal heating temperature of the workpiece with the temperature change curve of the optimal processing parameter setting layer, controlling the temperature regulating valve to regulate the heating temperature in real time by a fuzzy control method, and regulating the internal heating temperature of the workpiece in the processing process.
The process parameter control layer comprises a workpiece internal pressure acquisition unit, a blurring unit, a rule determination unit, a control table generation unit, a blurring judgment unit and a controlled variable change output unit. The pressure intensity acquisition unit in the workpiece is used for acquiring the air pressure intensity in the workpiece in real time through the barometer; the blurring unit is used for combining the collected gas pressure inside the workpiece and the gas pressure change curve of the optimal processing parameter setting layer to calculate and obtain the pressure differenceAnd rate of change of pressure differenceFor pressure differenceAnd rate of change of pressure differenceAnd outputting a control quantity U for blurring; the rule determining unit is used for determining a fuzzy control rule; the control table generating unit is used for carrying out fuzzy synthesis operation, solving a fuzzy relation matrix and generating a control table; the fuzzy judgment unit is used for carrying out fuzzy judgment on the output quantity according to the given input; the controlled variable change output unit is used for performing anti-blurring on the output controlled variable U through the product operation of the controlled variable U and a given quantization factor, and outputting the change of the controlled variable in the actual processing process of superplastic forming diffusion connection.
The fault diagnosis layer comprises a fault analysis system and a fault prediction system, wherein the fault analysis system is used for judging the state of the machine tool through the analysis of signals directly collected from the machine tool, and the fault prediction system is used for predicting the fault type possibly happening in the process of superplastic forming diffusion connection processing and giving an alarm according to the fault type.
The process parameter prediction layer comprises a working condition parameter range judging unit, a first process parameter prediction model based on case-based reasoning, a second process parameter prediction model based on a neural network and a calibration model.
The working condition parameter range judging unit is used for judging whether working condition parameters of the superplastic forming diffusion connection machining process are in a normal range or not; when the working condition parameters of the superplastic forming diffusion connection machining process are in a normal range, the working condition parameter range judging unit calls a second process parameter prediction model to predict the heating temperature and the gas pressure; when the working condition parameters of the superplastic forming diffusion connection machining process are not in the normal range, the working condition parameter range judging unit calls a first process parameter prediction model to predict the heating temperature and the gas pressure.
The prediction model comprises a first process parameter prediction model based on case reasoning and a second process parameter prediction model based on a neural network, wherein the two models are determined by the characteristics of the neural network prediction model and the specificity of the superplastic forming diffusion connection machining process. In general, the prediction model based on the neural network can achieve the effect of accurate prediction after training of a training set, when working condition parameters of superplastic forming diffusion connection are in a normal range, the constructed neural network model can be trained based on a normal processing process in the past and can accurately predict subsequent heating temperature and gas pressure, but when working condition parameters of superplastic forming diffusion connection are not in the normal range, because the working condition parameters which are not in the normal range are abrupt and uncertain, and data sets of different abnormal working conditions are less, the requirements of training and prediction of the neural network model are not met, and the prediction of the subsequent heating temperature and gas pressure is needed to be realized according to a model of case reasoning.
Specifically, for a certain type of titanium alloy in (a) in fig. 3 and (b) in fig. 3, for an ideal temperature curve and a gas pressure curve, when an actual working condition parameter basically accords with the ideal curve or deviates less in an actual superplastic forming diffusion connection processing process, a neural network model can be constructed and trained according to a conventional normal processing process, and then the prediction of a subsequent heating temperature and a gas pressure is realized based on the actual working condition parameter and the trained neural network model, but when the actual working condition parameter deviates from the ideal curve greatly and is not in a normal range, the requirements of the neural network model training and the prediction cannot be met due to mutation and uncertainty of an abnormal value, for example, due to the influence of abnormal factors such as equipment faults, when the temperature is mutated from 920 ℃ to 750 ℃, the neural network model trained based on the normal working condition parameter cannot realize accurate prediction of the subsequent temperature and the gas pressure under the working condition, and the requirements of the neural network model training and the prediction cannot be met due to the burstiness and uncertainty of the abnormal condition, and the prediction of the gas pressure can not be realized through a case-based parameter prediction process, and a case-based prediction mode of the abnormal condition.
And the calibration model processes the predicted values of the heating temperature and the gas pressure output by the first process parameter prediction model or the second process parameter prediction model to obtain final predicted values of the heating temperature and the gas pressure.
The calibration model includes a difference calculation unit and an error calibration unit. The difference value calculation unit is used for solving and obtaining a temperature difference value between a predicted value of the heating temperature output by the process parameter prediction layer and the heating temperature obtained by actual collection, and a pressure difference value between a predicted value of the gas pressure output by the process parameter prediction layer and the gas pressure obtained by actual collection; the error calibration unit compares the absolute value of the temperature difference value obtained by solving with the temperature error limit value, if the absolute value of the temperature difference value is smaller than or equal to the temperature error limit value, the predicted value of the heating temperature output by the process parameter predicting layer is used as a final predicted value, otherwise, the predicted value of the heating temperature output by the process parameter predicting layer is subtracted by the temperature difference value to obtain the final predicted value; and comparing the absolute value of the pressure difference obtained by solving with the pressure error limit value, if the absolute value of the pressure difference is smaller than or equal to the pressure error limit value, taking the predicted value of the gas pressure output by the process parameter predicting layer as a final predicted value, otherwise, subtracting the pressure difference from the predicted value of the gas pressure output by the process parameter predicting layer to obtain the final predicted value.
The process parameter self-adaptive adjustment method of the self-adaptive adjustment system based on the process parameters of the superplastic forming diffusion connection processing process specifically comprises the following steps:
S1, in the initial stage of superplastic forming diffusion connection processing, an optimal processing parameter setting layer sets an ideal temperature rise curve and a gas pressure change curve through software simulation or based on the past processing experience according to production information including the technological requirements, operation conditions and gas characteristics of a product to be processed, boundary conditions of the superplastic forming diffusion connection process and equipment information sets in the superplastic forming diffusion connection process;
S2, in the superplastic forming diffusion connection processing process, a process parameter control layer monitors heating temperature and gas pressure in the processing process in real time through a temperature sensor, a barometer and an embedded timer, compares the monitored pressure signal with a gas pressure change curve output by an optimal processing parameter setting layer, controls the internal pressure of a workpiece in the processing process through a fuzzy control method, simultaneously compares the monitored temperature signal with a temperature change curve output by the optimal processing parameter setting layer, controls a temperature regulating valve to regulate the heating temperature in real time through a fuzzy control method, and regulates the internal heating temperature of the workpiece in the processing process;
After the internal pressure of the workpiece and the internal heating temperature of the workpiece are adjusted, detecting the adjusted air pressure signals and temperature signals in real time through an air pressure gauge and a temperature sensor, comparing the adjusted air pressure signals and temperature signals with an ideal temperature rise curve and an ideal gas pressure change curve of an optimal processing parameter setting layer respectively, and feeding back the comparison result to the optimal processing parameter setting layer through a feedback compensation model;
The process parameter prediction layer predicts the subsequent process parameters according to the current working condition parameters of the superplastic forming diffusion connection processing process, and inputs the final predicted value to the optimal processing parameter setting layer through the feedforward compensation model; the fault diagnosis layer analyzes and judges the state of the machine tool through the signals collected from the machine tool directly, and inputs the state of the machine tool into the optimal processing parameter setting layer through the feedforward compensation model;
The feedforward compensation model inputs the internal heating temperature of the workpiece, the final predicted value of the internal pressure of the workpiece and the machine tool state output by the fault diagnosis layer, which are output by the process parameter prediction layer, to the optimal processing parameter setting layer, and the optimal processing parameter setting layer optimizes an ideal temperature rise curve and a gas pressure change curve;
S3, repeating the step S2 until the workpiece is machined.
As shown in fig. 6, the fuzzy control of the internal pressure of the part in the process parameter control layer in step S2 includes the steps of:
S201: collecting the gas pressure inside the workpiece in real time through a barometer;
s202: pressure difference is obtained And rate of change of pressure difference；
S203: for a pair ofAndAnd outputting a control quantity U for blurring;
The range of variation of the pressure difference monitored was divided into 14 total levels of { -6, -5, -4, -3, -2, -1, -0, +0,1,2,3,4,5,6} and the range of variation of the pressure difference was divided into 8 fuzzy sets of negative large (NB), negative Medium (NM), negative Small (NS), negative zero (NO), positive zero (PO), positive Small (PS), medium (PM), positive large (PB), the resulting pressure difference fuzzy table being shown in Table 2.
TABLE 2
Similarly, the rate of change of the pressure difference is divided into { -6, -5, -4, -3, -2, -1,0,1,2,3,4,5,6}13 levels, and the rate of change of the pressure difference is divided into 7 fuzzy sets of negative large (NB), negative Medium (NM), negative Small (NS), zero (ZO), positive Small (PS), medium (PM), positive large (PB), and the resulting fuzzy table of the rate of change of the pressure difference is shown in Table 3.
TABLE 3 Table 3
Similarly, the variable of the "output control amount" is denoted by "U", and is divided into 15 levels of variation in total of { -7, -6, -5, -4, -3, -2, -1,0,1,2,3,4,5,6,7} and is divided into 7 fuzzy sets of negative large (NB), negative Medium (NM), negative Small (NS), zero (ZO), positive Small (PS), medium (PM), positive large (PB), and the fuzzy table of the obtained output variation amounts is shown in table 4.
TABLE 4 Table 4
S204: determining a fuzzy control rule;
the fuzzy control rule of the present invention is described as follows by fuzzy conditional statements:
（1）if （E= NB or NM） and （EI= NB or NM） thenU= PB；
（2）if （E= NB or NM） and （EI= NS or ZO） thenU= PB；
（3）if （E= NB or NM） and （EI= PS） thenU= PM；
（4）if （E= NB or NM） and （EI= PM or PB） thenU= ZO；
（5）if （E= NS） and （EI= NB or NM） thenU= PM；
（6）if （E= NS） and （EI= NS or ZO） thenU= PM；
（7）if （E= NS） and （EI= PS） thenU= ZO；
（8）if （E= NS） and （EI= PM or PB） thenU= NS；
（9）if （E= NO or PO） and （EI= NB or NM） thenU= PM；
（10）if （E= NO or PO） and （EI= NS） thenU= PS；
（11）if （E= NO or PO） and （EI= ZO） thenU= ZO；
（12）if （E= NO or PO） and （EI= PS） thenU= NS；
（13）if （E= NO or PO） and （EI= PM or PB） thenU= NM；
（14）if （E= PS） and （EI= NB or NM） thenU= PS；
（15）if （E= PS） and （EI= NS） thenU= ZO；
（16）if （E= PS） and （EI= ZO or PS） thenU= NM；
（17）if （E= PS） and （EI= PM or PB） thenU= NM；
（18）if （E= PM or PB） and （EI= NB or NM） thenU= ZO；
（19）if （E= PM or PB） and （EI= NS） thenU= NM；
（20）if （E= PM or PB） and （EI= ZO or PS） thenU= NB；
（21）if （E= PM or PB） and （EI= PM or PB） thenU= NB；
the above fuzzy conditional statement may be summarized as a fuzzy control rule as shown in table 5.
TABLE 5
S205: performing fuzzy synthesis operation, solving a fuzzy relation matrix, and generating a control table;
The fuzzy relation R can be obtained according to the fuzzy rule:
R=U（E×EI）×U；
In the formula, x is a membership degree operation symbol in the fuzzy mathematical theory.
After the ambiguity relation R is obtained, the corresponding U is obtained according to the control rule according to the membership degree table of each change grade of E and EI, and then the corresponding control table is obtained through weighted average calculation (see table 6).
TABLE 6
S206: fuzzy judgment is carried out on the output quantity according to the given input; after the input E and the input EI are given, the corresponding output controlled variable U is obtained through inquiring a control table and calculating the weighted average.
S207: and performing anti-blurring on the output controlled quantity U through the product operation of the given quantization factor, and outputting the variation of the controlled quantity in the actual processing process of superplastic forming diffusion connection.
The fuzzy control method of the internal temperature of the part adopted in the process parameter control layer in the step S2 is the same as the fuzzy control method of the internal pressure of the part.
As shown in fig. 7, taking prediction of the gas pressure inside the workpiece as an example, a process of predicting a subsequent process parameter by the process parameter predicting layer in step S2 according to the current working condition parameter of the superplastic forming diffusion connection machining process is described, specifically, the predicting process includes the following steps:
S2-1: model selection is carried out according to working condition parameters of the machining process, M is an output working condition parameter set after model selection, when the working condition parameters of the superplastic forming diffusion connection machining process are in a normal range, a predicted value of heating temperature and gas pressure is obtained through a process parameter prediction model based on a neural network, and P 2 is a predicted value of gas pressure based on the neural network; when the working condition parameters of the superplastic forming diffusion connection processing process are not in the normal range, the predicted values of the heating temperature and the gas pressure are obtained through a process parameter prediction model based on case reasoning, and P 1 is the predicted value of the gas pressure of the prediction model based on case reasoning.
S2-2: solving a difference value between the gas pressure predicted value and the gas pressure in the actually collected workpiece:
e1=P1-P*；
P * is the gas pressure in the workpiece collected in real time, and e 1 is the absolute value of the difference between the predicted value and the actual measured value of the gas pressure of the model based on case-based reasoning;
e2=P2-P*；
e 2 is the absolute value of the difference between the predicted value and the actual measured value of the gas pressure of the prediction model based on case-based reasoning.
S2-3: processing the predicted value through a calibration model, so as to obtain a final predicted value:
when the gas pressure is predicted by adopting a prediction model based on case-based reasoning, if ，Otherwise, the device can be used to determine whether the current,Wherein PB is an artificially preset error limit value,Is the final prediction result; when the neural network-based process parameter prediction model is adopted for gas pressure prediction, if，Otherwise, the device can be used to determine whether the current,。
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be realized by adopting various computer languages, such as object-oriented programming language Java, an transliteration script language JavaScript and the like.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. The self-adaptive adjustment system for the technological parameters of the superplastic forming diffusion connection machining process is characterized by comprising an optimal machining parameter setting layer, a process parameter control layer, a process parameter prediction layer, a fault diagnosis layer, a feedforward compensator and a feedback compensator;
The optimal processing parameter setting layer sets an ideal temperature curve and a gas pressure change curve through software simulation or based on the past processing experience according to production information including the technological requirements, the operation conditions and the gas characteristics of a product to be processed, the boundary conditions of the superplastic forming diffusion connection process and the equipment information set in the historical superplastic forming diffusion connection process;
The process parameter control layer monitors the heating temperature and the gas pressure in the processing process in real time through a temperature sensor and a gas pressure meter, compares the monitored heating temperature and the monitored gas pressure with an ideal temperature curve and a gas pressure change curve respectively, and adjusts the internal pressure of a workpiece and the internal heating temperature of the workpiece in the processing process through a fuzzy control method;
The feedback compensator compares the detection values of the internal pressure of the workpiece and the internal heating temperature of the workpiece, which are detected by the temperature sensor and the barometer, with the set ideal temperature curve and the gas pressure change curve, and feeds back the comparison result to the optimal processing parameter setting layer;
The process parameter predicting layer predicts the internal pressure of the workpiece and the internal heating temperature of the workpiece in the subsequent processing process, and inputs the predicted value to the optimal processing parameter setting layer through the feedforward compensator;
the fault diagnosis layer analyzes and judges the state of the machine tool through signals directly collected from the machine tool, and inputs the judged state of the machine tool to an optimal processing parameter setting layer through a feedforward compensator;
And the optimal processing parameter setting layer is used for optimizing the set ideal temperature curve and gas pressure change curve by combining the comparison result fed back by the feedback compensator, the predicted value of the internal pressure of the workpiece and the internal heating temperature of the workpiece and the judged machine tool state.
2. The adaptive adjustment system for process parameters of a superplastic forming diffusion joint machining process according to claim 1, wherein the process parameter control layer compares the monitored internal pressure of the workpiece with a gas pressure change curve of an optimal machining parameter setting layer, and controls the internal pressure of the workpiece in the machining process by a fuzzy control method based on a comparison result;
The process parameter control layer compares the monitored internal heating temperature of the workpiece with the temperature change curve of the optimal processing parameter setting layer, and controls the temperature regulating valve to regulate the heating temperature in real time by a fuzzy control method so as to regulate the internal heating temperature of the workpiece in the processing process.
3. The system for adaptively adjusting the process parameters of the superplastic forming diffusion connection machining process according to claim 1, wherein the process parameter control layer comprises a workpiece internal pressure acquisition unit, a blurring unit, a rule determination unit, a control table generation unit, a blurring decision unit and a controlled variable change output unit;
The pressure intensity acquisition unit in the workpiece is used for acquiring the air pressure intensity in the workpiece in real time through the barometer;
The blurring unit is used for combining the collected gas pressure inside the workpiece and the gas pressure change curve of the optimal processing parameter setting layer to calculate and obtain the pressure difference And pressure difference rate of change/>For pressure difference/>And rate of change of pressure differenceAnd outputting a control quantity U for blurring;
The rule determining unit is used for determining a fuzzy control rule;
The control table generating unit is used for carrying out fuzzy synthesis operation, solving a fuzzy relation matrix and generating a control table;
The fuzzy decision unit is used for carrying out fuzzy decision on the output quantity according to the given input;
The controlled variable change output unit is used for performing anti-blurring on the output controlled variable U through the product operation of the controlled variable U and a given quantization factor, and outputting the change of the controlled variable in the actual processing process of superplastic forming diffusion connection.
4. The adaptive adjustment system for process parameters of a superplastic forming diffusion joint process according to claim 1, wherein the fault diagnosis layer predicts a fault type possibly occurring later in the process and alarms according to the predicted fault type.
5. The system for adaptively adjusting the process parameters of the superplastic forming diffusion joint processing procedure according to claim 1, wherein the process parameter prediction layer comprises a working condition parameter range judging unit, a first process parameter prediction model based on case-based reasoning, a second process parameter prediction model based on a neural network and a calibration model;
The working condition parameter range judging unit is used for judging whether working condition parameters of the superplastic forming diffusion connection machining process are in a normal range or not; when the working condition parameters of the superplastic forming diffusion connection machining process are in a normal range, the working condition parameter range judging unit calls a second process parameter prediction model to predict the heating temperature and the gas pressure; when working condition parameters of the superplastic forming diffusion connection machining process are not in a normal range, the working condition parameter range judging unit calls a first process parameter prediction model to predict heating temperature and gas pressure;
and the calibration model processes the predicted values of the heating temperature and the gas pressure output by the first process parameter prediction model or the second process parameter prediction model to obtain final predicted values of the heating temperature and the gas pressure.
6. The adaptive adjustment system for process parameters of a superplastic forming diffusion joint process according to claim 5, wherein the calibration model comprises a difference calculation unit and an error calibration unit;
The difference value calculation unit obtains a temperature difference value between a predicted value of the heating temperature output by the process parameter prediction layer and the heating temperature obtained by actual collection, and a pressure difference value between a predicted value of the gas pressure output by the process parameter prediction layer and the gas pressure obtained by actual collection;
The error calibration unit compares the absolute value of the temperature difference value obtained by solving with the temperature error limit value, if the absolute value of the temperature difference value is smaller than or equal to the temperature error limit value, the predicted value of the heating temperature output by the process parameter predicting layer is used as a final predicted value, otherwise, the temperature difference value is subtracted from the predicted value of the heating temperature output by the process parameter predicting layer to obtain the final predicted value;
And the error calibration unit compares the absolute value of the pressure difference value obtained by solving with the pressure error limit value, if the absolute value of the pressure difference value is smaller than or equal to the pressure error limit value, the predicted value of the gas pressure output by the process parameter prediction layer is used as a final predicted value, otherwise, the pressure difference value is subtracted from the predicted value of the gas pressure output by the process parameter prediction layer to obtain the final predicted value.
7. An adaptive adjustment method for process parameters of a superplastic forming diffusion joint process based on an adaptive adjustment system as claimed in any one of claims 1-6, characterized in that the adaptive adjustment method comprises the following steps:
S1, in the initial stage of superplastic forming diffusion connection processing, an optimal processing parameter setting layer sets an ideal temperature curve and a gas pressure change curve through software simulation or based on the past processing experience according to production information including the technological requirements, operation conditions and gas characteristics of a product to be processed, boundary conditions of the superplastic forming diffusion connection process and equipment information sets in the superplastic forming diffusion connection process;
S2, in the superplastic forming diffusion connection processing process, a process parameter control layer monitors heating temperature and gas pressure in the processing process in real time through a temperature sensor, a barometer and an embedded timer, compares the monitored pressure signal with a gas pressure change curve output by an optimal processing parameter setting layer, controls the internal pressure of a workpiece in the processing process through a fuzzy control method, simultaneously compares the monitored temperature signal with a temperature change curve output by the optimal processing parameter setting layer, controls a temperature regulating valve to regulate the heating temperature in real time through a fuzzy control method, and regulates the internal heating temperature of the workpiece in the processing process;
After the pressure inside the workpiece and the heating temperature inside the workpiece are adjusted, detecting the adjusted air pressure signal and the temperature signal in real time through an air pressure gauge and a temperature sensor, comparing the adjusted air pressure signal and the temperature signal with an ideal temperature curve and an ideal gas pressure change curve of the optimal processing parameter setting layer respectively, and feeding back the comparison result to the optimal processing parameter setting layer through a feedback compensation model;
The process parameter prediction layer predicts the subsequent process parameters according to the current working condition parameters of the superplastic forming diffusion connection processing process, and inputs the final predicted value to the optimal processing parameter setting layer through the feedforward compensation model; the fault diagnosis layer analyzes and judges the state of the machine tool through the signals collected from the machine tool directly, and inputs the state of the machine tool into the optimal processing parameter setting layer through the feedforward compensation model;
The feedforward compensation model inputs the workpiece internal heating temperature output by the process parameter prediction layer, the final predicted value of the workpiece internal pressure and the machine tool state output by the fault diagnosis layer to the optimal processing parameter setting layer, and the optimal processing parameter setting layer optimizes an ideal temperature curve and a gas pressure change curve according to feedback results of the feedforward compensation model and the feedback compensation model;
S3, repeating the step S2 until the workpiece is machined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410566010.5A CN118151616A (en) | 2024-05-09 | 2024-05-09 | Technological parameter self-adaptive adjusting system for superplastic forming diffusion connection machining process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410566010.5A CN118151616A (en) | 2024-05-09 | 2024-05-09 | Technological parameter self-adaptive adjusting system for superplastic forming diffusion connection machining process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118151616A true CN118151616A (en) | 2024-06-07 |
Family
ID=91299006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410566010.5A Pending CN118151616A (en) | 2024-05-09 | 2024-05-09 | Technological parameter self-adaptive adjusting system for superplastic forming diffusion connection machining process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118151616A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006178626A (en) * | 2004-12-21 | 2006-07-06 | Central Res Inst Of Electric Power Ind | Method, apparatus, and program for correcting energy system operation plan for coping with parameter change |
| CN103235556A (en) * | 2013-03-27 | 2013-08-07 | 南京航空航天大学 | Feature-based numerical-control method for processing and manufacturing complicated parts |
| CN108549215A (en) * | 2018-06-29 | 2018-09-18 | 南宁学院 | A kind of brshless DC motor blurring Adaptive PID Control optimization method |
| CN112051799A (en) * | 2020-09-10 | 2020-12-08 | 成都广泰威达数控技术股份有限公司 | Self-adaptive control method for machining |
| CN115167283A (en) * | 2022-08-02 | 2022-10-11 | 深圳市雄兴实业有限公司 | Numerical control machining cutting force self-adaptive control method, system, equipment and storage medium |
| CN116184960A (en) * | 2023-02-07 | 2023-05-30 | 大连理工大学 | Numerical control machine tool technological parameter self-adaptive regulation and control method considering cutter state |
-
2024
- 2024-05-09 CN CN202410566010.5A patent/CN118151616A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006178626A (en) * | 2004-12-21 | 2006-07-06 | Central Res Inst Of Electric Power Ind | Method, apparatus, and program for correcting energy system operation plan for coping with parameter change |
| CN103235556A (en) * | 2013-03-27 | 2013-08-07 | 南京航空航天大学 | Feature-based numerical-control method for processing and manufacturing complicated parts |
| CN108549215A (en) * | 2018-06-29 | 2018-09-18 | 南宁学院 | A kind of brshless DC motor blurring Adaptive PID Control optimization method |
| CN112051799A (en) * | 2020-09-10 | 2020-12-08 | 成都广泰威达数控技术股份有限公司 | Self-adaptive control method for machining |
| CN115167283A (en) * | 2022-08-02 | 2022-10-11 | 深圳市雄兴实业有限公司 | Numerical control machining cutting force self-adaptive control method, system, equipment and storage medium |
| CN116184960A (en) * | 2023-02-07 | 2023-05-30 | 大连理工大学 | Numerical control machine tool technological parameter self-adaptive regulation and control method considering cutter state |
Non-Patent Citations (1)
| Title |
|---|
| 苏宏华;王禹封;谯木;赵正彩: "切削加工有限元仿真技术的现状与展望", 《南京航空航天大学学报》, 15 June 2024 (2024-06-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5570282A (en) | Multivariable nonlinear process controller | |
| CN100493748C (en) | Control method for dynamically correcting strip steel thickness deviation by forward slip adaption | |
| CN109212974A (en) | The robust fuzzy of Interval time-varying delay system predicts fault tolerant control method | |
| CN111045326A (en) | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network | |
| CN110769453B (en) | Multi-modal monitoring data dynamic compression control method under unstable network environment | |
| CN104778361B (en) | The method of modified EMD Elman neural network prediction molten iron silicon contents | |
| CN106773718B (en) | Oxygen-carbon ratio control system and gasification furnace oxygen-coal ratio control method thereof | |
| CN111413865B (en) | Disturbance compensation single-loop superheated steam temperature active disturbance rejection control method | |
| CN110673482A (en) | Power station coal-fired boiler intelligent control method and system based on neural network prediction | |
| CN117891161B (en) | Bicycle bottom bracket bearing forging process adjusting method based on self-adaptive control algorithm | |
| CN102873106B (en) | Quick and precise elongation control method for temper mill | |
| CN113488206B (en) | Lead-based fast reactor control system and method | |
| CN118151616A (en) | Technological parameter self-adaptive adjusting system for superplastic forming diffusion connection machining process | |
| CN116627028A (en) | Control method for crosslinked cable production line | |
| CN113655816B (en) | Ladle bottom argon blowing system flow control method and computer readable storage medium | |
| CN107191154B (en) | Wellhead back pressure regulating method and device | |
| CN113095951A (en) | Intelligent regulation and control method, equipment and device for gas extraction and storage medium | |
| CN110243138B (en) | Air separation equipment model feedforward control system and method | |
| CN110687937B (en) | Water tank liquid level control method based on multivariable generalized minimum variance decoupling control | |
| CN111614128A (en) | AGC coordinated control optimization method for heat supply unit under new energy grid-connected background | |
| JP7372171B2 (en) | Control device and control method | |
| CN116719356B (en) | Dynamic control method for air compression station based on load change and prediction | |
| CN113267994B (en) | Main steam pressure control method and system of thermal power generating unit based on three-stage control series connection | |
| US10995171B2 (en) | System for controlling ethylene vinyl acetate copolymerization process and method of controlling the same | |
| CN116880421A (en) | Process control method for PE film surface crystal points and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |