CN116047919A - Method, device, equipment and medium for optimizing boring parameters of intersection point holes - Google Patents
Method, device, equipment and medium for optimizing boring parameters of intersection point holes Download PDFInfo
- Publication number
- CN116047919A CN116047919A CN202310341179.6A CN202310341179A CN116047919A CN 116047919 A CN116047919 A CN 116047919A CN 202310341179 A CN202310341179 A CN 202310341179A CN 116047919 A CN116047919 A CN 116047919A
- Authority
- CN
- China
- Prior art keywords
- boring
- parameters
- optimization
- rough
- population
- 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.)
- Granted
Links
Images
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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The application discloses an intersection point hole boring parameter optimization method, an intersection point hole boring parameter optimization device, an intersection point hole boring parameter optimization medium and an intersection point hole boring parameter optimization method. The method comprises the following steps: training the initial cutter relieving quantity prediction network model according to the training sample to obtain a final cutter relieving quantity prediction network model; constructing a boring parameter optimization model according to the optimization variables and the optimization targets; solving the boring parameter optimization model to obtain boring parameters meeting first preset conditions; inputting boring parameters meeting first preset conditions into a final cutter relieving amount prediction network model to obtain predicted cutter relieving amounts; and modifying the boring parameter optimization model according to the predicted cutter yielding amount, and returning to the step of solving the boring parameter optimization model to obtain boring parameters meeting the first preset condition until the obtained boring parameters meet the second preset condition. The method and the device can reduce energy consumption and carbon emission in the machining process of the intersection point hole under the condition of meeting machining quality.
Description
Technical Field
The application relates to the field of aircraft part machining, in particular to an intersection point hole boring parameter optimization method, an intersection point hole boring parameter optimization device, intersection point hole boring parameter optimization equipment and medium.
Background
The processing of the intersection point hole of the airplane is the most important link in the airplane assembly links, and the processing quality of the intersection point hole determines the assembly quality of the whole airplane. As a typical machine manufacturing process, the energy consumption, carbon emission, cutter relief amount and the like of an aircraft intersection hole boring process are dynamically influenced by boring parameters. The traditional research mainly adopts manual experience to select boring parameters, eliminates the influence of cutter relieving quantity on cutting allowance by measuring once through machining, causes time and labor waste and carbon emission amplification in the machining process of the intersection point hole of the airplane, and is not beneficial to energy conservation and emission reduction.
The foregoing is merely provided to facilitate an understanding of the principles of the present application and is not admitted to be prior art.
Disclosure of Invention
The main purpose of the application is to provide a boring parameter optimization method, a boring parameter optimization device, boring parameter optimization equipment and boring parameter medium, and aims to solve the technical problem that the boring parameter optimization method in the prior art is unfavorable for energy conservation and emission reduction.
In order to achieve the above purpose, the present application provides a method for optimizing boring parameters of an intersection point hole, comprising the following steps:
Training an initial cutter relieving amount prediction network model according to a training sample to obtain a final cutter relieving amount prediction network model, wherein the initial cutter relieving amount prediction network model is constructed based on an LSTM (least square (short-cut) cyclic neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving amounts corresponding to the boring parameters, and the boring processes comprise a plurality of rough boring processes and at least one fine boring process;
constructing a boring parameter optimization model according to an optimization variable and an optimization target, wherein the optimization variable comprises the boring parameter and rough boring machining times, the boring parameter comprises cutting depth, cutting width, cutting speed and feeding amount, and the optimization target comprises machining carbon emission and machining time;
solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition;
inputting boring parameters meeting the first preset conditions into the final cutter relieving amount prediction network model to obtain predicted cutter relieving amounts;
and modifying the boring parameter optimization model according to the predicted cutter relieving amount, and returning to the step of solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition until the obtained boring parameters meet a second preset condition.
As some optional embodiments of the present application, the constructing the boring parameter optimization model according to the optimization variables and the optimization targets includes:
determining constraint conditions according to the idle cutter parameters, the idle machine tool parameters and the boring information to be processed;
constructing an optimization objective function according to the optimization variables and the optimization targets, wherein the optimization objective function comprises a processing carbon emission function and a processing time function;
and constructing a boring parameter optimization model according to the constraint conditions and the optimization objective function.
As some optional embodiments of the present application, the expression of the process carbon emission function is as follows:
wherein CE (X) is the process carbon emission function, C Coarse size C is the carbon emission amount in the rough boring process Essence The carbon emission amount is the carbon emission amount of the fine boring process, wherein the carbon emission amount of the rough boring process is calculated by the following formula:
in the method, in the process of the invention,
and (3) the carbon emission amount in the ith rough boring process, n is the number of times of rough boring, n and i are positive integers, and i is more than or equal to 1 and less than or equal to n.
As some optional embodiments of the present application, the expression of the processing time function is as follows:
wherein L is the path length of the rough boring cutter, L Essence For the fine boring cutter path length, 
For the i-th rough boring feed, f v extract Is the feeding amount of the fine boring process.
As some optional embodiments of the present application, the constructing a boring parameter optimization model according to the constraint conditions and the optimization objective function includes:
establishing a boring parameter optimization model according to the optimization objective function, wherein the boring parameter optimization model is as follows:
in minf 1 (x) For the first optimized objective function, minf 2 (x) For a second optimization objective function, CE (X) is the process carbon emission function, t (X) is the process time function;
establishing a constraint model according to the constraint conditions, wherein the constraint conditions comprise boring parameter range constraint in the rough boring process, cutting power constraint in the rough boring process and cutting force constraint in the rough boring process; a boring parameter range constraint in the finish boring process, a cutting power constraint in the finish boring process, a cutting force constraint in the finish boring process and a surface roughness constraint in the finish boring process; and the cutter relieving amount and the cutting allowance in the rough boring machining process and the finish boring machining process are restrained.
As some optional embodiments of the present application, the solving the boring parameter optimization model to obtain the boring parameter meeting the first preset condition includes:
And solving the boring parameter optimization model according to an improved squirrel search algorithm to obtain boring parameters meeting a first preset condition, wherein the improved squirrel search algorithm is that a Pareto sorting operator of an improved non-dominant sorting genetic algorithm is introduced into the squirrel search algorithm.
As some optional embodiments of the present application, the solving the boring parameter optimization model according to the modified squirrel search algorithm to obtain the boring parameter that meets the first preset condition includes:
setting the rough boring machining times as minimum rough boring machining times;
setting algorithm parameters according to preset parameters, wherein the preset parameters comprise population quantity, iteration times, random sliding distance, sliding constant, the number of squirrels moving from the oak tree to the walnut tree, the number of squirrels moving from the common tree to the oak tree and the number of squirrels moving from the common tree to the walnut tree;
initializing the position of each individual in the first population according to a preset formula and the rough boring times;
evaluating the individuals in the first population to obtain processed carbon emissions and processing time of each individual;
ranking the first population according to a non-dominant ranking algorithm;
Distributing each individual in the first group after sequencing to a hickory tree, a oak and a common tree according to a preset distribution rule, wherein the hickory tree represents a globally optimal solution, and the oak represents a locally optimal solution;
generating a second population according to the new solution generation rule;
combining the first population and the second population to obtain an intermediate population;
sorting the intermediate populations according to the non-dominant sorting algorithm;
selecting the first population after iteration from the first n individuals in the intermediate population, wherein n is the population number
Returning the first population to the step of sorting the first population according to the non-dominant sorting algorithm according to the first population after iteration when the iteration number is smaller than the maximum iteration number;
when the iteration times are equal to the maximum iteration times, boring parameters meeting a third preset condition are obtained;
when the rough boring times are smaller than the maximum boring times, recording boring parameters meeting the third preset conditions to obtain a model solution set, adding one to the rough boring times, and returning to the step of initializing the position of each individual in the first population according to a preset formula and the rough boring times;
And when the rough boring machining times are greater than or equal to the maximum machining times, sequencing the model solution sets according to the non-dominant sequencing algorithm to obtain boring parameters meeting a first preset condition.
As some optional embodiments of the present application, the assigning each individual in the first population after sorting to hickory, oak, and common trees according to a preset assignment rule includes:
acquiring a non-dominant sequencing number and a crowding distance of each individual;
individuals with non-dominant ranking numbers 1 and infinite crowding distances are assigned to walnut trees, other individuals with non-dominant ranking numbers 1 are assigned to oaks, and all other individuals are assigned to common trees.
To solve the above problems, the present application further provides a boring parameter optimizing apparatus, which includes:
the training module is used for training the initial cutter relieving quantity prediction network model according to a training sample to obtain a final cutter relieving quantity prediction network model, wherein the initial cutter relieving quantity prediction network model is constructed based on an LSTM (least square wave) cyclic neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving quantities corresponding to the boring parameters, and the boring processes comprise a plurality of rough boring processes and at least one fine boring process;
The model construction module is used for constructing a boring parameter optimization model according to an optimization variable and an optimization target, wherein the optimization variable comprises the boring parameter and rough boring machining times, the boring parameter comprises cutting depth, cutting width, cutting speed and feeding amount, and the optimization target comprises machining carbon emission and machining time;
the model solving module is used for solving the boring parameter optimizing model to obtain boring parameters meeting a first preset condition;
the prediction module is used for inputting boring parameters meeting the first preset conditions into the final cutter relieving amount prediction network model to obtain a predicted cutter relieving amount;
and the modification module is used for modifying the boring parameter optimization model according to the predicted cutter relieving amount, and returning to the step of solving the boring parameter optimization model to obtain the boring parameters meeting the first preset condition until the obtained boring parameters meet the second preset condition.
The beneficial effects that this application can realize are as follows:
according to the method, the device, the equipment and the medium for optimizing the boring parameters of the intersection point holes, the initial cutter relieving quantity prediction network model is trained according to the training sample to obtain the final cutter relieving quantity prediction network model, wherein the initial cutter relieving quantity prediction network model is constructed based on an LSTM (least square wave) circulating neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving quantities corresponding to the boring parameters, the boring process comprises a plurality of rough boring processes and at least one fine boring process, the accuracy of the predicted network model can be gradually improved by training the initial cutter relieving quantity prediction network model, cutter relieving quantity prediction through manual experience is avoided, and efficiency is improved; according to an optimization variable and an optimization target, a boring parameter optimization model is constructed, wherein the optimization variable comprises boring parameters and rough boring machining times, the boring parameters comprise cutting depth, cutting width, cutting speed and feeding amount, the optimization target comprises machining carbon emission and machining time, the machining time is considered, the carbon emission in the machining process is further set as the optimization target, factors such as energy consumption and carbon emission are considered, the energy consumption, the carbon emission and the cutter relieving amount in the aircraft intersection point hole boring process are dynamically influenced by the boring parameters, and the carbon emission in the boring process is reduced by optimizing the boring parameters, so that energy conservation and emission reduction are facilitated; solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition; inputting boring parameters meeting the first preset conditions into the final cutter yielding amount prediction network model to obtain a predicted cutter yielding amount, wherein the boring parameters can be realized through the final cutter yielding amount prediction network model; modifying the boring parameter optimization model according to the predicted cutter relieving amount, returning to the step of solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition until the obtained boring parameters meet a second preset condition, predicting the generated boring parameters in real time by a final cutter relieving amount prediction network model, feeding back to the boring parameter optimization model, dynamically correcting and iterating the solution of the boring parameter optimization model, and finally realizing the generation of the boring parameters with high efficiency and low carbon through mutual feedback and iteration so as to realize the reduction of energy consumption and carbon emission of the cross point hole boring process under the condition of meeting the processing quality.
Drawings
FIG. 1 is a flow chart of an optimization method for boring parameters of an intersection point hole according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a boring parameter optimizing apparatus according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
the realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The processing of the intersection point hole of the airplane is the most important link in the airplane assembly links, and the processing quality of the intersection point hole determines the assembly quality of the whole airplane. The traditional machining of the airplane intersection point holes is finished manually by using a reamer, and the machining quality is influenced by the skill level of workers, the quality stability is poor and the labor intensity of the workers is high. With the development of technologies such as five-axis linkage machine tools, variable diameter boring, angle heads and the like, the adoption of machine tools for machining intersection holes of airplanes is a focus of attention. The aircraft intersection point hole is generally processed in a boring mode, and due to constraints of processing quality, cutters, machine tools and the like, the aircraft intersection point boring process often needs multiple times of rough boring processing and one time of fine boring. As a typical machine manufacturing process, the energy consumption, carbon emission, cutter relieving amount and the like of an airplane intersection point hole boring process are dynamically influenced by boring parameters, cutting allowance is mutually coupled in repeated rough boring and fine boring processes, the previous cutter relieving amount influences the current cutter relieving amount, and the cutter relieving amount influences the cutting allowance in real time. The traditional research mainly adopts manual experience to select boring parameters, eliminates the influence of cutter relieving amount on cutting allowance by measuring once through machining, and causes time and labor waste and carbon emission amplification in the machining process of the intersection point hole of the airplane. Meanwhile, the traditional research is used for optimizing boring parameters, and the traditional NSGA-II multi-objective algorithm is often adopted, so that the problems of local optimization and the like are easily caused.
In order to achieve the above purpose, the present application provides a method for optimizing boring parameters of an intersection point hole, comprising the following steps:
s1, training an initial cutter relieving amount prediction network model according to a training sample to obtain a final cutter relieving amount prediction network model, wherein the initial cutter relieving amount prediction network model is constructed based on an LSTM (least square (virtual machine) circulating neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving amounts corresponding to the boring parameters, and the boring processes comprise a plurality of rough boring processes and at least one fine boring process;
specifically, key connection feature holes distributed on an aircraft structure, which are also called intersection point holes, play an important role on the quality of the aircraft, and the requirements on processing quality, tolerance, position accuracy and the like are very high. The initial cutter-back quantity prediction network model is constructed based on an LSTM (Long Short-Term Memory) neural network, so that the problem of Long-Term dependence in RNN is improved; LSTM performs generally better than time-recursive neural networks and Hidden Markov Models (HMMs), as a nonlinear model, LSTM can be used as a complex nonlinear unit to construct larger deep neural networks; mapping an airplane intersection point hole for multiple times by rough boring and at least one time by a fine boring process based on the LSTM neural network, wherein an input layer is provided with 4 input features, the input features are boring parameters of the multiple times of boring process and the boring parameters, the boring parameters comprise cutting depth, cutting width, cutting speed and feeding amount, an output layer is provided with 1 output feature, the output feature is cutter yielding amount corresponding to the boring parameters, a hidden layer consists of 20 LSTM circulating neural network neurons, and the hidden layer is of a two-layer network structure; setting a discard probability in a hidden layer in the initial yield prediction network model prevents overfitting. The discarding probability is set manually, and is limited according to actual needs, and no special requirement is made here.
In a preferred scheme, the method also sets super-parameters of the constructed initial cutter-back quantity prediction network model, wherein the super-parameters comprise time steps, learning rate lr, batch sample size and weight attenuation coefficient lambda. The purpose of these parameters is to speed up training and converge to a globally optimal solution. These parameters affect the convergence rate of the algorithm and the performance of the algorithm during training, and unreasonable settings can increase training time. Too small learning rate can reduce convergence rate; too much learning rate may result in non-convergence. Therefore, a large learning rate is adopted when training is just started, the speed is increased, and a smaller learning rate is adopted when training is finished, so that stable convergence to a global optimal value is ensured. The unreasonable setting of the iteration times can cause over fitting, the test error rate is close to the training error rate, and the reasonable setting of the iteration times is considered; batch sample size batch_size influences the convergence of the algorithm, the unreasonable setting can cause the network to be not converged or converged to a local optimal solution, an Adam optimizer is adopted to optimally update the network weight and bias parameters, a mean square error (RMSE) -based calculation loss is adopted, adam is a first-order optimization algorithm capable of replacing the traditional random gradient descent process, and the Adam can iteratively update the neural network weight based on training data;
In the training process, based on the training samples, the cutter relieving quantity prediction network model is trained layer by layer, namely, the output of each LSTM neuron of the hidden layer of the LSTM network of the previous layer is used as the LSTM neuron corresponding to the hidden layer of the LSTM network of the next layer to be input into calculation, after all calculation, the last number of the last output sequence of the LSTM network is put into a softmax classifier as an output layer, and the cutter relieving quantity prediction value at the current moment is expressed by the output result y of the softmax classifier.
The final cutter relieving quantity prediction network model establishes a mapping relation between boring parameters and corresponding cutter relieving quantities through training, so that cutter relieving quantities under different boring parameters are predicted, and further accurate prediction of cutter relieving quantities under different boring conditions by the prediction network model is realized.
S2, constructing a boring parameter optimization model according to an optimization variable and an optimization target, wherein the optimization variable comprises the boring parameter and rough boring machining times, the boring parameter comprises cutting depth, cutting width, cutting speed and feeding amount, and the optimization target comprises machining carbon emission and machining time;
specifically, in the step, firstly, a boring parameter optimization model is constructed according to an optimization target and an optimization parameter, wherein the boring parameter has an important influence on carbon emission and processing time, so that the optimization variables of the constructed boring parameter optimization model comprise boring parameters, and the boring processing of an airplane intersection point hole needs multiple rough boring processing and at least one fine boring processing, so that the number of rough boring processing is taken as the optimization variable, wherein the boring parameters comprise but are not limited to cutting depth, cutting width, cutting speed and feeding amount; the boring parameter optimization model also considers the processing time while guaranteeing low carbon in the processing process, so that the optimization targets comprise processing carbon emission and processing time, the carbon emission in the processing process is further set as the optimization target on the premise of considering the processing time, the factors such as energy consumption and carbon emission are considered, and the carbon emission in the cutting process is reduced by optimizing the boring parameters, so that energy conservation and emission reduction are facilitated.
As some optional embodiments of the present application, the step of constructing the boring parameter optimization model according to the optimization variables and the optimization targets includes:
s21, determining constraint conditions according to idle cutter parameters, idle machine tool parameters and boring information to be processed;
in the actual machining process, the following aspects need to be considered, firstly, in order to ensure the normal use of a machine tool and a cutter in the machining process, the boring parameters cannot exceed the bearable range of the machine tool and the cutter, the cutting speed, the feeding amount and the cutting depth need to be limited, the boring parameters of the fine boring machining process and the rough boring machining process are different in constraint and need to be limited respectively, secondly, the cutting force needs to be within the maximum cutting force allowed by the machine tool, the cutting power needs to be within the effective power range of the machine tool, and then, in order to ensure the normal use of the cutter in the machining process, the service life of the cutter needs to be limited; finally, limiting the roughness of the surface of the intersection point hole in the finish boring processing stage according to the processing requirement of the intersection point hole; through the limitation, the boring parameter optimization model can obtain boring parameters capable of achieving efficient, economical and green low-carbon targets in the machining process on the premise of ensuring normal use of a machine tool and a cutter.
S22, constructing an optimization objective function according to the optimization variables and the optimization targets, wherein the optimization objective function comprises a processing carbon emission function and a processing time function;
s23, constructing a boring parameter optimization model according to the constraint conditions and the optimization objective function.
As an alternative embodiment of the present application, the expression of the process carbon emission function is as follows:
wherein CE (X) is the process carbon emission function, C Coarse size C is the carbon emission amount in the rough boring process Essence The carbon emission amount is the carbon emission amount of the fine boring process, wherein the carbon emission amount of the rough boring process is calculated by the following formula:
in the method, in the process of the invention,
the carbon emission amount of the i-th rough boring process is n, the number of times of rough boring is n and i are positive integers, and i is more than or equal to 1 and less than or equal to n;
in particular, the method comprises the steps of,
the calculation is performed by the following formula: />
In the method, in the process of the invention,
carbon emissions for the machine start-up phase of the ith rough boring process, < >>
Carbon emission for the standby phase of the machine tool during the ith rough boring process, < >>
Carbon emissions for the tool changing phase of the ith rough boring process, < >>
Carbon emission for the boring stage of the machine tool during the ith rough boring process, +.>
Carbon emissions for the retracting phase of the ith rough boring process, < >>
And
for the machine power and duration of the machine start phase of the ith rough boring process, +. >
And->
For the machine power and duration of the machine standby phase of the ith rough boring process, +.>
And->
Machine power and duration for the tool change phase of the ith rough boring process, +.>
And->
For the machine power and duration of the machine boring phase of the ith rough boring process, +.>
And->
For machine power and duration, EF, of the tool withdrawal phase of the ith rough boring process e Is an electric energy carbon emission factor.
As some optional embodiments of the present application, the expression of the processing time function is as follows:
wherein L is Coarse size For the path length of the rough boring cutter, L Essence For the fine boring cutter path length,
for the i-th rough boring feed, f v extract Is the feeding amount of the fine boring process.
As some optional embodiments of the present application, the step of constructing a boring parameter optimization model according to the constraint conditions and the optimization objective function includes:
s23, establishing a boring parameter optimization model according to the optimization objective function, wherein the boring parameter optimization model is as follows:
in minf 1 (x) For the first optimized objective function, minf 2 (x) For a second optimization objective function, CE (X) is the process carbon emission function, t (X) is the process time function;
S24, establishing a constraint model according to the constraint conditions, wherein the constraint conditions comprise boring parameter range constraint in the rough boring process, cutting power constraint in the rough boring process and cutting force constraint in the rough boring process; a boring parameter range constraint in the finish boring process, a cutting power constraint in the finish boring process, a cutting force constraint in the finish boring process and a surface roughness constraint in the finish boring process; and the cutter relieving amount and the cutting allowance in the rough boring machining process and the finish boring machining process are restrained.
S3, solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition;
specifically, by solving the constructed boring parameter optimization model, boring parameters and cutting tools meeting preset conditions can be obtained, wherein the first preset conditions are boring parameters and rough boring times which can reduce energy consumption and carbon emission in the machining process under the conditions of meeting the machining quality and the machining period;
s4, inputting boring parameters meeting the first preset conditions into the final cutter relieving amount prediction network model to obtain predicted cutter relieving amounts;
Specifically, the final cutter relieving amount prediction network model has established a mapping relation between boring parameters and corresponding cutter relieving amounts through training, and the boring parameters meeting the first preset conditions obtained from the boring parameter optimization model are input into the final cutter relieving amount prediction network model, so that the corresponding predicted cutter relieving amounts can be obtained, and the boring parameter optimization model can be modified through the predicted cutter relieving amounts, so that the boring parameters obtained by the modified boring parameter optimization model are more in line with actual conditions, and the actual processing process is facilitated.
S5, modifying the boring parameter optimization model according to the predicted cutter relieving amount, and returning to the step of solving the boring parameter optimization model to obtain boring parameters meeting the first preset condition until the obtained boring parameters meet the second preset condition.
Specifically, in an embodiment, the constraint conditions of the boring parameter optimization model include a cutter allowance constraint and a cutting allowance constraint, the cutting allowance is changed due to the change of the cutter allowance, and the cutting allowance values in the rough boring and finish boring processes are dynamically updated according to the predicted value of the cutter allowance, so that the boring parameters obtained by the boring parameter optimization model are more in line with the actual conditions, the energy conservation, carbon reduction and processing effects in the actual processing process are more facilitated, and finally the mutual feedback of the cutter allowance prediction network model and the boring parameter optimization model is achieved until the boring parameters meeting the second preset conditions are finally obtained.
As some optional embodiments of the present application, the step of solving the boring parameter optimization model to obtain the boring parameter meeting the first preset condition includes:
s31, solving the boring parameter optimization model according to an improved squirrel search algorithm to obtain boring parameters meeting a first preset condition, wherein the improved squirrel search algorithm is that a Pareto sorting operator of an improved non-dominant sorting genetic algorithm is introduced into the squirrel search algorithm.
The method is characterized in that the existing squirrel search algorithm is used for single-target continuous optimization, the method cannot adapt to the solution of constructing a multi-target model in the previous steps of the application, the problem that the existing squirrel search algorithm can only be used for single-target continuous optimization can be solved by introducing a Pareto sorting operator of an improved non-dominant sorting genetic algorithm into the existing squirrel search algorithm, layering of a population and calculation of crowding distances of individuals are achieved through Pareto sorting, so that each individual is located on a tree of which type can be distinguished, the squirrel search algorithm is used for solving the problem that the foraging activity of the flying squirrel individual in the algorithm is influenced by the seasonal variation through setting of the seasonal variation condition, the foraging activity is not active under the condition of low temperature in winter, and the situation that the obtained solution falls into local optimum is avoided under the condition of realizing the solution of the multi-target model.
As some optional embodiments of the present application, the step of solving the boring parameter optimization model according to the modified squirrel search algorithm to obtain the boring parameter satisfying the first preset condition includes:
s311, setting the rough boring machining times as minimum rough boring machining times;
specifically, the aircraft intersection point hole needs multiple rough boring and at least one fine boring, the boring parameter optimization method of the application takes the rough boring times as one of optimization variables, the rough boring times are firstly set to be minimum rough boring times in the step, and the boring parameters under different rough boring times are obtained in a subsequent circulation mode.
S312, setting algorithm parameters according to preset parameters, wherein the preset parameters comprise population quantity, iteration times, random sliding distance, sliding constant, the number of squirrels moving from oak to walnut tree, the number of squirrels moving from common tree to oak and the number of squirrels moving from common tree to walnut tree;
specifically, the population number is the number of squirrels in the algorithm, firstly, the parameters of the improved squirrel search algorithm are set according to preset parameters, in an embodiment of the application, the population number is 5, the iteration number is 200, the sliding constant realizes the balance between global search and local search, the sliding constant is 1.9, the random sliding distance is [0.05,3.11], and the number of squirrels moving from oak trees to walnut trees is 5;
S313, initializing the position of each individual in the first population according to a preset formula and the rough boring times;
after the initialization of the algorithm is completed, setting the position of each individual in the first population according to a preset formula and rough boring times, wherein the position of the ith individual can be determined by a vector, and the positions of all the individuals are randomly initialized within a boundary range, wherein the position of each individual is represented by the following formula:
FS i,j =lb+rand*（ub-lb）
in FS i,j Values representing the j-th dimension of the i-th squirrel, ub, lb being the upper and lower boundaries of the variable, rand being [0,1]Random numbers in between;
s314, evaluating the individuals in the first population to obtain the processed carbon emission and the processing time of each individual;
the fitness value of each individual's location reflects the quality of the food it obtains, i.e., the optimal food source (hickory), normal food source (oak) and no food source (on ordinary trees), and thus also reflects their survival probability. By further random selection, some squirrels are considered to have met their daily energy requirements and moved toward hickory. The rest squirrel will go on to go to the oak tree (to meet their daily energy demands), through putting the value of the decision variable into the fitness function defined by user, can calculate the fitness of each individual, finish the evaluation to each individual, the said fitness function and aforesaid goal optimization function, can calculate the processing carbon emission, processing time of each individual through the said goal optimization function;
S315, sorting the first population according to a non-dominant sorting algorithm;
the purpose of non-dominant ranking is to rank the population, the purpose of crowding distance ranking is to rank individuals in the same rank, and the crowdedness of each individual is calculated by the following formula:
in CD im Indicating the congestion level of the ith individual in the mth objective function. f (f) m Represents the mth objective function, X i+1 Representing the value of the (i+1) th individual under the objective function, X i-1 Representing the value of the (i-1) th individual under the objective function, X max Represents the maximum value under the objective function, X, in all individuals min Representing the minimum under the objective function in all individuals; the non-dominant ranking algorithm is the prior art and is not described in detail herein;
s316, distributing each individual in the first population after sequencing to a hickory tree, a oak tree and a common tree according to a preset distribution rule, wherein the hickory tree represents a globally optimal solution, and the oak tree represents a locally optimal solution;
as some optional embodiments of the present application, the step of assigning each individual in the first population after sorting to hickory, oak, and common trees according to a preset assignment rule includes:
s3161, acquiring a non-dominant sequencing number and a crowding distance of each individual;
After non-dominant ordering is performed on each individual in the first population, a non-dominant ordering sequence number and a crowding distance of each individual can be obtained; the purpose of non-dominant ranking is to rank groups, and the purpose of crowding distance ranking is to rank individuals in the same rank. Eventually, individuals with high levels and large crowding distances are selected as the next generation.
S3162, assigning individuals with non-dominant ranking numbers of 1 and infinite crowding distances to walnut trees, assigning other individuals with non-dominant ranking numbers of 1 to oaks, and assigning all other individuals to common trees.
Specifically, the individual with the non-dominant ranking sequence number of 1 represents that the individual generates the dominant to the individual with the non-dominant ranking sequence number of not 1, namely, the function values obtained in the objective function of the individual with the non-dominant ranking sequence number of 1 are better than the function values of the individual with the non-ranking sequence number of not 1 in the objective function, and the genetic algorithm has the property of automatic convergence, so that in order to ensure the diversity of solutions, the introduction of the crowding degree is to ensure the obtained solutions to be more uniform in the objective space, ensure the diversity of the solutions, the solutions in the same non-dominant ranking sequence number can be mutually separated, the solutions with large distances between the solutions are better than the solutions with small distances between the solutions, and the crowding distance of each individual is calculated by calculating the sum of the distance differences between two individuals adjacent to the crowding distance between the two individuals on each sub-objective function.
S317, generating a second population according to the new solution generation rule;
in the foregoing step, the location of each individual in the first population has been updated once according to a non-dominant ranking algorithm, where the location of the individual is further updated according to a squirrel search algorithm, and in one embodiment, the new solution generation rule includes:
the individuals located on the common tree move toward the oak, and the location information is calculated by the following formula:
R 2 is [0,1]Within a range ofA machine number; d, d g Representing a random glide distance; g c Representing the sliding constant;
representing the position of a squirrel on a t-th generation common tree; />
Representing the location of an individual on a t-th generation oak; p (P) dp Represents the probability of natural enemies occurring in the foraging process of the squirrel,Randomrepresenting a random function;
the individual located on the general tree moves toward the hickory tree and the positional information is calculated by the following formula:
wherein R is 3 Is [0,1]Random numbers in the range of the random numbers,
is the position of the individual on the t-th generation hickory,Randomrepresenting a random function;
the individual on the oak moves toward the hickory, and the position information is calculated by the following formula;
wherein R is 1 Is [0,1]Random numbers in the range of the random numbers,
for the location of individuals on the t-th generation oak,Randomrepresenting a random function;
The squirrel search algorithm is the prior art, and is not repeated here;
s318, combining the first population and the second population to obtain an intermediate population;
s319, sorting the intermediate population according to the non-dominant sorting algorithm;
s320, selecting the first population after iteration from the first n individuals in the middle population, wherein n is the population number;
after the second population is obtained, the first population and the second population are combined to obtain a middle population, in the improved non-dominant ranking genetic algorithm, each parent can generate a child through intersection and mutation, after the parents and the child are combined, due to limitation of population scale, the combined population is ranked through non-dominant ranking, proper individuals are selected for inheritance, namely, the next iteration is carried out, the purpose of carrying out rapid non-dominant ranking before selection is to enable better Jie Bao to be stored for carrying out the next iteration, an elite strategy is met, the elite strategy ensures that the whole population evolution process is carried out towards the optimal direction, and in the design of the evolution algorithm, whether the optimal solution can be converged is the main target of the algorithm.
S321, returning the first population to the step of sorting the first population according to the non-dominant sorting algorithm according to the first population after iteration when the iteration number is smaller than the maximum iteration number;
Specifically, when the iteration number is smaller than the maximum iteration number, returning the first population to the step of sorting the first population according to the non-dominant sorting algorithm according to the first population after iteration, and further iterating the first population.
S322, when the iteration times are equal to the maximum iteration times, boring parameters meeting a third preset condition are obtained;
when the iteration times are equal to the maximum iteration times, boring parameters meeting a third preset condition can be obtained;
s323, when the rough boring times are smaller than the maximum boring times, recording boring parameters meeting the third preset conditions to obtain a model solution set, adding one to the rough boring times, and returning to the step of initializing the position of each individual in the first population according to a preset formula and the rough boring times;
after obtaining boring parameters meeting a third preset condition, recording the boring parameters into a model solution set, wherein the boring parameters are boring parameters under the minimum rough boring times, adding one to the current rough boring times in order to obtain boring parameters under different rough boring times, returning to the step of initializing the position of each body in the first population according to a preset formula and the rough boring times, obtaining the boring parameters under different rough boring times in a circulating mode, and obtaining the boring parameters under different rough boring times of an airplane intersection point hole by adopting a circulating mode.
S324, when the rough boring machining times are greater than or equal to the maximum machining times, sorting the model solution sets according to the non-dominant sorting algorithm to obtain boring parameters meeting a first preset condition.
After the boring parameters of different boring times are obtained, sorting all the boring parameters through a non-dominant sorting algorithm to obtain boring parameters meeting a first preset condition, wherein the sorting process of the non-dominant sorting algorithm is the same as that in the previous embodiment, and is not repeated herein, through non-dominant sorting, the boring parameters of different boring times can be screened, and finally the boring times and the corresponding boring parameters meeting the first preset condition are obtained.
According to the method, the device, the equipment and the medium for optimizing the boring parameters of the intersection point holes, the initial cutter relieving quantity prediction network model is trained according to the training sample to obtain the final cutter relieving quantity prediction network model, wherein the initial cutter relieving quantity prediction network model is constructed based on an LSTM (least square wave) circulating neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving quantities corresponding to the boring parameters, the boring process comprises a plurality of rough boring processes and at least one fine boring process, and the accuracy of the predicted network model can be gradually improved by training the initial cutter relieving quantity prediction network model; according to an optimization variable and an optimization target, a boring parameter optimization model is constructed, wherein the optimization variable comprises boring parameters and rough boring machining times, the boring parameters comprise cutting depth, cutting width, cutting speed and feeding amount, the optimization target comprises machining carbon emission and machining time, the machining time is considered, the carbon emission in the machining process is further set as the optimization target, factors such as energy consumption and carbon emission are considered, the energy consumption, the carbon emission and the cutter relieving amount in the aircraft intersection point hole boring process are dynamically influenced by the boring parameters, and the carbon emission in the boring process is reduced by optimizing the boring parameters, so that energy conservation and emission reduction are facilitated; solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition; inputting boring parameters meeting the first preset conditions into the final cutter yielding amount prediction network model to obtain a predicted cutter yielding amount, wherein the boring parameters can be realized through the final cutter yielding amount prediction network model; modifying the boring parameter optimization model according to the predicted cutter relieving amount, returning to the step of solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition until the obtained boring parameters meet a second preset condition, predicting the generated boring parameters in real time by a final cutter relieving amount prediction network model, feeding back to the boring parameter optimization model, dynamically correcting and iterating the solution of the boring parameter optimization model, and finally realizing the generation of the boring parameters with high efficiency and low carbon through mutual feedback and iteration so as to realize the reduction of energy consumption and carbon emission of the cross point hole boring process under the condition of meeting the processing quality.
In order to solve the above technical problems, as shown in fig. 2, the present application further proposes: a boring parameter optimizing apparatus, the apparatus comprising:
the training module is used for training the initial cutter relieving quantity prediction network model according to a training sample to obtain a final cutter relieving quantity prediction network model, wherein the initial cutter relieving quantity prediction network model is constructed based on an LSTM (least square wave) cyclic neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving quantities corresponding to the boring parameters, and the boring processes comprise a plurality of rough boring processes and at least one fine boring process;
the model construction module is used for constructing a boring parameter optimization model according to an optimization variable and an optimization target, wherein the optimization variable comprises the boring parameter and rough boring machining times, the boring parameter comprises cutting depth, cutting width, cutting speed and feeding amount, and the optimization target comprises machining carbon emission and machining time;
the model solving module is used for solving the boring parameter optimizing model to obtain boring parameters meeting a first preset condition;
the prediction module is used for inputting boring parameters meeting the first preset conditions into the final cutter relieving amount prediction network model to obtain a predicted cutter relieving amount;
And the modification module is used for modifying the boring parameter optimization model according to the predicted cutter relieving amount, and returning to the step of solving the boring parameter optimization model to obtain the boring parameters meeting the first preset condition until the obtained boring parameters meet the second preset condition.
It should be noted that, each module in the cross point hole boring parameter optimizing apparatus in this embodiment corresponds to each step in the cross point hole boring parameter optimizing method in the foregoing embodiment one by one, so the specific implementation manner and the achieved technical effect of this embodiment may refer to the implementation manner of the foregoing cross point hole boring parameter optimizing method, and will not be described herein again.
In addition, an optimization method for boring parameters of an intersection point hole according to the embodiment of the invention described in connection with fig. 1 can be implemented by an electronic device. Fig. 3 shows a schematic hardware structure of an electronic device according to an embodiment of the present invention.
The electronic device may comprise at least one processor 301, at least one memory 302 and computer program instructions stored in the memory 302, which, when executed by the processor 301, implement the method as described in the above embodiments.
In particular, the processor 301 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present invention.
The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement any of the intersection point hole boring parameter optimization methods of the above embodiments.
In one example, the electronic device may also include a communication interface and a bus. As shown in fig. 3, the processor 301, the memory 302, and the communication interface 303 are connected to each other by a bus 310 and perform communication with each other. The communication interface 303 is mainly used to implement communication between each module, device, unit and/or apparatus in the embodiment of the present invention.
The bus includes hardware, software, or both that couple components of the electronic device to each other. By way of example, and not limitation, the buses may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of the above. The bus may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.
In addition, in combination with the method for verifying the boring parameters of the intersection point hole in the above embodiment, the embodiment of the invention can be implemented by providing a computer readable storage medium. The computer readable storage medium has stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the intersection point hole boring parameter optimization methods of the above embodiments.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
In the foregoing, only the specific embodiments of the present invention are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and they should be included in the scope of the present invention.
Claims (11)
1. The method for optimizing the boring parameters of the intersection point hole is characterized by comprising the following steps of:
training an initial cutter relieving amount prediction network model according to a training sample to obtain a final cutter relieving amount prediction network model, wherein the initial cutter relieving amount prediction network model is constructed based on an LSTM (least square (short-cut) cyclic neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving amounts corresponding to the boring parameters, and the boring processes comprise a plurality of rough boring processes and at least one fine boring process;
Constructing a boring parameter optimization model according to an optimization variable and an optimization target, wherein the optimization variable comprises the boring parameter and rough boring machining times, the boring parameter comprises cutting depth, cutting width, cutting speed and feeding amount, and the optimization target comprises machining carbon emission and machining time;
solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition;
inputting boring parameters meeting the first preset conditions into the final cutter relieving amount prediction network model to obtain predicted cutter relieving amounts;
and modifying the boring parameter optimization model according to the predicted cutter relieving amount, and returning to the step of solving the boring parameter optimization model to obtain boring parameters meeting a first preset condition until the obtained boring parameters meet a second preset condition.
2. The method for optimizing boring parameters of an intersection point hole according to claim 1, wherein the constructing a boring parameter optimization model according to the optimization variables and the optimization targets comprises:
determining constraint conditions according to the idle cutter parameters, the idle machine tool parameters and the boring information to be processed;
constructing an optimization objective function according to the optimization variables and the optimization targets, wherein the optimization objective function comprises a processing carbon emission function and a processing time function;
And constructing a boring parameter optimization model according to the constraint conditions and the optimization objective function.
3. The method for optimizing boring parameters of an intersection point hole according to claim 2, wherein the expression of the processed carbon emission function is as follows:
wherein CE (X) is the process carbon emission function, C Coarse size C is the carbon emission amount in the rough boring process Essence The carbon emission amount is the carbon emission amount of the fine boring process, wherein the carbon emission amount of the rough boring process is calculated by the following formula:
in the method, in the process of the invention,
and (3) the carbon emission amount in the ith rough boring process, n is the number of times of rough boring, n and i are positive integers, and i is more than or equal to 1 and less than or equal to n.
4. The boring parameter optimization method of claim 2, wherein the expression of the processing time function is as follows:
wherein L is Coarse size For the path length of the rough boring cutter, L Essence For the fine boring cutter path length,
for the i-th rough boring feed, f v extract Is the feeding amount of the fine boring process.
5. The method of optimizing boring parameters of an intersection hole according to claim 2, wherein the constructing a boring parameter optimization model according to the constraint condition and the optimization objective function includes:
establishing a boring parameter optimization model according to the optimization objective function, wherein the boring parameter optimization model is as follows:
In minf 1 (x) For the first optimized objective function, minf 2 (x) For a second optimization objective function, CE (X) is the process carbon emission function, t (X) is the process time function;
establishing a constraint model according to the constraint conditions, wherein the constraint conditions comprise boring parameter range constraint in the rough boring process, cutting power constraint in the rough boring process and cutting force constraint in the rough boring process; a boring parameter range constraint in the finish boring process, a cutting power constraint in the finish boring process, a cutting force constraint in the finish boring process and a surface roughness constraint in the finish boring process; and the cutter relieving amount and the cutting allowance in the rough boring machining process and the finish boring machining process are restrained.
6. The method of optimizing boring parameters of an intersection hole according to claim 1, wherein solving the boring parameter optimization model to obtain boring parameters satisfying a first preset condition comprises:
and solving the boring parameter optimization model according to an improved squirrel search algorithm to obtain boring parameters meeting a first preset condition, wherein the improved squirrel search algorithm is that a Pareto sorting operator of an improved non-dominant sorting genetic algorithm is introduced into the squirrel search algorithm.
7. The method of optimizing boring parameters for an intersection hole of claim 6, wherein solving the boring parameter optimization model according to the modified squirrel search algorithm to obtain boring parameters satisfying a first preset condition comprises:
setting the rough boring machining times as minimum rough boring machining times;
setting algorithm parameters according to preset parameters, wherein the preset parameters comprise population quantity, iteration times, random sliding distance, sliding constant, the number of squirrels moving from the oak tree to the walnut tree, the number of squirrels moving from the common tree to the oak tree and the number of squirrels moving from the common tree to the walnut tree;
initializing the position of each individual in the first population according to a preset formula and the rough boring times;
evaluating the individuals in the first population to obtain processed carbon emissions and processing time of each individual;
ranking the first population according to a non-dominant ranking algorithm;
distributing each individual in the first group after sequencing to a hickory tree, a oak and a common tree according to a preset distribution rule, wherein the hickory tree represents a globally optimal solution, and the oak represents a locally optimal solution;
Generating a second population according to the new solution generation rule;
combining the first population and the second population to obtain an intermediate population;
sorting the intermediate populations according to the non-dominant sorting algorithm;
selecting the first population after iteration from the first n individuals in the intermediate population, wherein n is the population number
Returning the first population to the step of sorting the first population according to the non-dominant sorting algorithm according to the first population after iteration when the iteration number is smaller than the maximum iteration number;
when the iteration times are equal to the maximum iteration times, boring parameters meeting a third preset condition are obtained;
when the rough boring times are smaller than the maximum boring times, recording boring parameters meeting the third preset conditions to obtain a model solution set, adding one to the rough boring times, and returning to the step of initializing the position of each individual in the first population according to a preset formula and the rough boring times;
and when the rough boring machining times are greater than or equal to the maximum machining times, sequencing the model solution sets according to the non-dominant sequencing algorithm to obtain boring parameters meeting a first preset condition.
8. The method of optimizing intersection hole boring parameters according to claim 7, wherein the assigning each individual in the first population to hickory, oak, and common trees after the ranking according to a preset assignment rule comprises:
acquiring a non-dominant sequencing number and a crowding distance of each individual;
individuals with non-dominant ranking numbers 1 and infinite crowding distances are assigned to walnut trees, other individuals with non-dominant ranking numbers 1 are assigned to oaks, and all other individuals are assigned to common trees.
9. An apparatus for optimizing boring parameters of an intersection point hole, the apparatus comprising:
the training module is used for training the initial cutter relieving quantity prediction network model according to a training sample to obtain a final cutter relieving quantity prediction network model, wherein the initial cutter relieving quantity prediction network model is constructed based on an LSTM (least square wave) cyclic neural network, the training sample comprises boring parameters of a plurality of boring processes and cutter relieving quantities corresponding to the boring parameters, and the boring processes comprise a plurality of rough boring processes and at least one fine boring process;
the model construction module is used for constructing a boring parameter optimization model according to an optimization variable and an optimization target, wherein the optimization variable comprises the boring parameter and rough boring machining times, the boring parameter comprises cutting depth, cutting width, cutting speed and feeding amount, and the optimization target comprises machining carbon emission and machining time;
The model solving module is used for solving the boring parameter optimizing model to obtain boring parameters meeting a first preset condition;
the prediction module is used for inputting boring parameters meeting the first preset conditions into the final cutter relieving amount prediction network model to obtain a predicted cutter relieving amount;
and the modification module is used for modifying the boring parameter optimization model according to the predicted cutter relieving amount, and returning to the step of solving the boring parameter optimization model to obtain the boring parameters meeting the first preset condition until the obtained boring parameters meet the second preset condition.
10. An electronic device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which when executed by the processor, implement the method of any one of claims 1-8.
11. A storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310341179.6A CN116047919B (en) | 2023-04-03 | 2023-04-03 | Method, device, equipment and medium for optimizing boring parameters of intersection point holes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310341179.6A CN116047919B (en) | 2023-04-03 | 2023-04-03 | Method, device, equipment and medium for optimizing boring parameters of intersection point holes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116047919A true CN116047919A (en) | 2023-05-02 |
| CN116047919B CN116047919B (en) | 2023-07-21 |
Family
ID=86118628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310341179.6A Active CN116047919B (en) | 2023-04-03 | 2023-04-03 | Method, device, equipment and medium for optimizing boring parameters of intersection point holes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116047919B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4926309A (en) * | 1988-09-12 | 1990-05-15 | Ford Motor Company | Artificial intelligence for adaptive machining control of surface finish |
| CN107598675A (en) * | 2017-06-21 | 2018-01-19 | 沈阳航空航天大学 | A kind of drilling parameter optimization method based on hard alloy cutter tipping failure prediction |
| CN107798180A (en) * | 2017-10-17 | 2018-03-13 | 西北工业大学 | Deep hole machining depth optimization method based on iterative learning |
| CN111797469A (en) * | 2020-06-24 | 2020-10-20 | 华中科技大学无锡研究院 | Aeroengine casing technological parameter optimization method based on machining cutter back-off deformation constraint |
| US20200334465A1 (en) * | 2017-12-28 | 2020-10-22 | Microsoft Technology Licensing, Llc | Querying video data with reduced latency and cost |
| CN113721462A (en) * | 2021-08-03 | 2021-11-30 | 西安交通大学 | Multi-target cutting parameter optimization method and system under cutter determination condition |
| CN114509991A (en) * | 2022-02-25 | 2022-05-17 | 成都大学 | Numerical control machine tool cutting stability prediction and optimization method considering parameter uncertainty |
| CN114609906A (en) * | 2022-03-10 | 2022-06-10 | 南京航空航天大学 | Hole-making damage self-adaptive control method for carbon fiber reinforced composite material |
| CN114756977A (en) * | 2022-06-16 | 2022-07-15 | 成都飞机工业（集团）有限责任公司 | Method, device and equipment for predicting boring cutter yield of intersection hole of airplane and storage medium |
| CN114925596A (en) * | 2022-04-20 | 2022-08-19 | 永得利科技（无锡）有限公司 | Method for optimizing casting platform finish milling parameters based on wafer test equipment |
| CN115598975A (en) * | 2022-09-22 | 2023-01-13 | 哈尔滨工业大学（Cn） | Pin hole assembly DDPG reinforcement learning acceleration method based on parameter pre-training |
-
2023
- 2023-04-03 CN CN202310341179.6A patent/CN116047919B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4926309A (en) * | 1988-09-12 | 1990-05-15 | Ford Motor Company | Artificial intelligence for adaptive machining control of surface finish |
| CN107598675A (en) * | 2017-06-21 | 2018-01-19 | 沈阳航空航天大学 | A kind of drilling parameter optimization method based on hard alloy cutter tipping failure prediction |
| CN107798180A (en) * | 2017-10-17 | 2018-03-13 | 西北工业大学 | Deep hole machining depth optimization method based on iterative learning |
| US20200334465A1 (en) * | 2017-12-28 | 2020-10-22 | Microsoft Technology Licensing, Llc | Querying video data with reduced latency and cost |
| CN111797469A (en) * | 2020-06-24 | 2020-10-20 | 华中科技大学无锡研究院 | Aeroengine casing technological parameter optimization method based on machining cutter back-off deformation constraint |
| CN113721462A (en) * | 2021-08-03 | 2021-11-30 | 西安交通大学 | Multi-target cutting parameter optimization method and system under cutter determination condition |
| CN114509991A (en) * | 2022-02-25 | 2022-05-17 | 成都大学 | Numerical control machine tool cutting stability prediction and optimization method considering parameter uncertainty |
| CN114609906A (en) * | 2022-03-10 | 2022-06-10 | 南京航空航天大学 | Hole-making damage self-adaptive control method for carbon fiber reinforced composite material |
| CN114925596A (en) * | 2022-04-20 | 2022-08-19 | 永得利科技（无锡）有限公司 | Method for optimizing casting platform finish milling parameters based on wafer test equipment |
| CN114756977A (en) * | 2022-06-16 | 2022-07-15 | 成都飞机工业（集团）有限责任公司 | Method, device and equipment for predicting boring cutter yield of intersection hole of airplane and storage medium |
| CN115598975A (en) * | 2022-09-22 | 2023-01-13 | 哈尔滨工业大学（Cn） | Pin hole assembly DDPG reinforcement learning acceleration method based on parameter pre-training |
Non-Patent Citations (2)
| Title |
|---|
| H. AL-WEDYAN，等: "Fuzzy modeling and prediction of cylindricity error in BTA deep hole boring process", 《IEEE ANNUAL MEETING OF THE FUZZY INFORMATION, 2004. PROCESSING NAFIPS \'04》 * |
| 刘春，等: "飞机交点孔镗孔精加工自动调刀技术", 《组合机床与自动化加工技术》, no. 2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116047919B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110728401A (en) | Short-term power load prediction method of neural network based on squirrel and weed hybrid algorithm | |
| CN111119282B (en) | Pressure monitoring point optimal arrangement method for water supply pipe network | |
| CN113762603B (en) | Photovoltaic base station short-term photovoltaic power prediction method based on improved sparrow algorithm optimization | |
| Lei et al. | Improved artificial bee colony algorithm and its application in data clustering | |
| CN113158580B (en) | One-dimensional stock layout method for solid wood board | |
| CN112330487B (en) | Photovoltaic power generation short-term power prediction method | |
| CN110909787A (en) | Method and system for multi-objective batch scheduling optimization based on clustering evolutionary algorithm | |
| CN110472840A (en) | A kind of agricultural water conservancy dispatching method and system based on nerual network technique | |
| Ye et al. | K-means clustering algorithm based on improved Cuckoo search algorithm and its application | |
| CN111292124A (en) | Water demand prediction method based on optimized combined neural network | |
| CN111832817A (en) | Small world echo state network time sequence prediction method based on MCP penalty function | |
| CN109670655B (en) | Multi-target particle swarm optimization scheduling method for electric power system | |
| CN116047919B (en) | Method, device, equipment and medium for optimizing boring parameters of intersection point holes | |
| CN110852435A (en) | Neural evolution calculation model | |
| CN109034372A (en) | A kind of neural networks pruning method based on probability | |
| CN113218400A (en) | Multi-agent navigation algorithm based on deep reinforcement learning | |
| CN111985841A (en) | Injection molding workshop scheduling method and system based on improved genetic algorithm | |
| CN115470977A (en) | Multi-target flexible job shop batch scheduling method based on empire competition algorithm | |
| CN109377111A (en) | Job scheduling method and device based on modified-immune algorithm | |
| CN112836885B (en) | Combined load prediction method, combined load prediction device, electronic equipment and storage medium | |
| CN114971250A (en) | Comprehensive energy economic dispatching system based on deep Q learning | |
| CN113887943A (en) | Pump station optimal scheduling method based on virtual water | |
| CN114781508A (en) | Clustering-based satellite measurement and control scheduling method and system | |
| CN111461911B (en) | Mixed NSGA-II-based method for constructing virtual unit of machined workpiece | |
| CN113792494A (en) | Multi-target flexible job shop scheduling method based on migrating bird group algorithm and cross fusion |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |