TAILIEUCHUNG - A regression-tree multilayer-perceptron hybrid strategy for the prediction of ore crushing-plate lifetimes

Highly tensile manganese steel is in great demand owing to its high tensile strength under shock loads. All workpieces are produced through casting, because it is highly difficult to machine. The probabilistic aspects of its casting, its variable composition, and the different casting techniques must all be considered for the optimisation of its mechanical properties. A hybrid strategy is therefore proposed which combines decision trees and artificial neural networks (ANNs) for accurate and reliable prediction models for ore crushing plate lifetimes. The strategic blend of these two high-accuracy prediction models is used to generate simple decision trees which can reveal the main dataset features, thereby facilitating decisionmaking. Following a complexity analysis of a dataset with 450 different plates, the best model consisted of 9 different multilayer perceptrons, the inputs of which were only the Fe and Mn plate compositions. The model recorded a low root mean square error (RMSE) of only h for the lifetime of the plate: a very accurate result considering their varied lifetimes of between 746 and 6902 h in the dataset. Finally, the use of these models under real industrial conditions is presented in a heat map, namely a 2D representation of the main manufacturing process inputs with a colour scale which shows the predicted output, . the expected lifetime of the manufactured plates. Thus, the hybrid strategy extracts core training dataset information in high-accuracy prediction models. This novel strategy merges the different capabilities of two families of machine-learning algorithms. | A regression-tree multilayer-perceptron hybrid strategy for the prediction of ore crushing-plate lifetimes

• Hoá học
• Hadfield steel
• Resource savings
• Lifetime prediction
• Regression trees
• Multi layer perceptrons
• Artificial intelligence
• Applying artificial intelligence on e learning
• Compare E learning
• Traditional learning
• Learn 1 1 with virtual assistant
• Artificial Neural Networks (ANN) algorithms
• CS 486686 Artificial Intelligence
• Course administration
• Intelligent Assistive Technology
• A brief history of A
• Properties of task environments
• Artificial intelligence in education
• Keynote speaker abstracts
• Human computer interface issues
• Pedagogical agents
• Models of criminal liability of artificial intelligence
• Criminal liability of artificial intelligence
• Science fiction to prospect for criminal law and policy in Vietnam
• Criminal law and policy in Vietnam
• Criminal law and policy
• Lecture Artificial Intelligence
• Trí tuệ nhân tạo
• Computing machinery
• Thinking humanly
• Cognitive Science
• Lecture note Artificial Intelligence
• Performance measure
• Environment types
• Agent program
• Problem solving
• Problem solving agents
• Problem types
• Problem formulation
• Informed search algorithms
• Best first search
• Local search algorithms
• Simulated annealing
• Genetic algorithms
• Constraint Satisfaction Problems
• Backtracking search for CSPs
• Game playing
• Resource limits
• Games of chance
• Logical agents
• Knowledge based agents
• Wumpus world
• First order logic
• Semantics of FOL
• Fun with sentences
• Wumpus world in FOL
• Inference in first order logic
• Generalized Modus Ponens
• Logic programming
• Bayes’ Rule
• Methods for handling uncertainty
• Making decisions under uncertainty
• Bayesian networks
• Parameterized distributions
• Inference in Bayesian networks
• Variable elimination
• Temporal probability models
• Hidden Markov models
• Kalman filters
• Speech recognition
• Speech sounds
• Word pronunciation
• Rational decisions
• Rational preferences
• Multiattribute utilities
• Learning from Observations
• Learning agents
• Inductive learning