scholarly journals Comparison of Graph Generation Methods for Structural Complexity Based Assembly Time Estimation

2013 ◽  
Author(s):  
Essam Z. Namouz ◽  
Joshua D. Summers
Keyword(s):  
Detection Method ◽  
Structural Complexity ◽  
Time Estimation ◽  
Interference Detection ◽  
Assembly Time ◽  
Target Time ◽  
File Formats ◽  
Product Graphs ◽  
Automated Tools ◽  
Graph Generation

This paper compares two different methods of graph generation for input into the complexity connectivity method to estimate the assembly time of a product. The complexity connectivity method builds predictive models for assembly time based on twenty-nine complexity metrics applied to the product graphs. Previously the part connection graph was manually created, but recently the Assembly Mate Method and the Interference Detection Method have introduced new automated tools for creating the part connectivity graphs. These graph generation methods are compared on their ability to predict the assembly time of multiple products. For this research, eleven consumers products are used to train an artificial neural network and three products are reserved for testing. The results indicate that both the Assembly Mate Method and the Interference Detection Method can create connectivity graphs that predict the assembly time of a product to within 45% of the target time. The Interference Detection Method showed less variability than the Assembly Mate Method in the time estimations. The Assembly Mate Method is limited to only SolidWorks assembly files, while the Interference Detection Method is more flexible and can operate on different file formats including IGES, STEP, and Parasolid. Overall, both of the graph generation methods provide a suitable automated tool to form the connectivity graph, but the Interference Detection Method provides less variance in predicting the assembly time and is more flexible in terms of file types that can be used.

scholarly journals Comparison of Graph Generation Methods for Structural Complexity Based Assembly Time Estimation

2014 ◽  
Vol 14 (2) ◽  
Author(s):  
Essam Z. Namouz ◽  
Joshua D. Summers
Keyword(s):  
Detection Method ◽  
Structural Complexity ◽  
Time Estimation ◽  
Interference Detection ◽  
Assembly Time ◽  
Target Time ◽  
File Formats ◽  
Product Graphs ◽  
Automated Tools ◽  
Graph Generation

This paper compares two different methods of graph generation for input into the complexity connectivity method to estimate the assembly time of a product. The complexity connectivity method builds predictive models for assembly time based on 29 complexity metrics applied to the product graphs. Previously, the part connection graph was manually created, but recently the assembly mate method and the interference detection method have introduced new automated tools for creating the part connectivity graphs. These graph generation methods are compared on their ability to predict the assembly time of multiple products. For this research, eleven consumers products are used to train an artificial neural network and three products are reserved for testing. The results indicate that both the assembly mate method and the interference detection method can create connectivity graphs that predict the assembly time of a product to within 45% of the target time. The interference detection method showed less variability than the assembly mate method in the time estimations. The assembly mate method is limited to only solidworks assembly files, while the interference detection method is more flexible and can operate on different file formats including IGES, STEP, and Parasolid. Overall, both of the graph generation methods provide a suitable automated tool to form the connectivity graph, but the interference detection method provides less variance in predicting the assembly time and is more flexible in terms of file types that can be used.

Representation: Structural Complexity of Assemblies to Create Neural Network Based Assembly Time Estimation Models

2012 ◽  
Author(s):  
Michael G. Miller ◽  
James L. Mathieson ◽  
Joshua D. Summers ◽  
Gregory M. Mocko
Keyword(s):  
Input Data ◽  
Initial Conditions ◽  
Structural Complexity ◽  
Time Estimation ◽  
Initial Sample ◽  
Assembly Time ◽  
Design Detail ◽  
The Given ◽  
Human Designer ◽  
Estimation Models

Assembly time estimation is traditionally a time intensive manual process requiring detailed geometric and process information to be available to a human designer. As a result of these factors, assembly time estimation is rarely applied during early design iterations. This paper explores the possibility that the assembly time estimation process can be automated while reducing the level of design detail required. The approach presented here trains artificial neural networks (ANNs) to estimate the assembly times of vehicle sub-assemblies at various stages using properties of the connectivity graph at that point as input data. Effectiveness of estimation is evaluated based on the distribution of estimates provided by a population of ANNs trained on the same input data using varying initial conditions. Results suggest that the method presented here can complete the time estimation of an assembly process with +/− 15% error given an initial sample of manually estimated times for the given sub-assembly.

scholarly journals Manufacturing Assembly Time Estimation Using Structural Complexity Metric Trained Artificial Neural Networks

2014 ◽  
Vol 14 (1) ◽  
Author(s):  
Michael G. Miller ◽  
Joshua D. Summers ◽  
James L. Mathieson ◽  
Gregory M. Mocko
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Input Data ◽  
Initial Conditions ◽  
Structural Complexity ◽  
Time Estimation ◽  
Assembly Time ◽  
Graph Properties ◽  
Artificial Neural ◽  
Manufacturing Assembly

Assembly time estimation is traditionally a time-intensive manual process that requires detailed geometric and process information, which is often subjective and qualitative in nature. As a result, assembly time estimation is rarely applied during early design iterations. In this paper, the authors explore the possibility of automating the assembly time estimation process while reducing the level of design detail required. In this approach, they train artificial neural networks (ANNs) to estimate the assembly times of vehicle subassemblies using either assembly connectivity or liaison graph properties, respectively, as input data. The effectiveness of estimation is evaluated based on the distribution of estimates provided by a population of ANNs trained on the same input data using varying initial conditions. Results indicate that this method can provide time estimates of an assembly process with ±15% error while relying exclusively on the geometric part information rather than process instructions.

Ontological Knowledge Representation and Inference Rules for MTM Decision Support System

2014 ◽  
Author(s):  
Rahul Renu ◽  
Gregory Mocko
Keyword(s):  
Decision Support ◽  
Decision Support System ◽  
Knowledge Representation ◽  
Support System ◽  
Time Estimation ◽  
Time Measurement ◽  
Inference Rules ◽  
Assembly Time ◽  
Time Estimates ◽  
Definition Of

The objective of the research presented is to develop and implement an ontological knowledge representation for Methods-Time Measurement assembly time estimation process. The knowledge representation is used to drive a decision support system that provides the user with intelligent MTM table suggestions based on assembly work instructions. Inference rules are used to map work instructions to MTM tables. An explicit definition of the assembly time estimation domain is required. The contribution of this research, in addition to the decision support system, is an extensible knowledge representation that models work instructions, MTM tables and mapping rules between the two which will enable the establishment of assembly time estimates. Further, the ontology provides an extensible knowledge representation framework for linking time studies and assembly processes.

Reasoning: Source of Variability in the Boothroyd and Dewhurst Assembly Time Estimation Method

2012 ◽  
Author(s):  
Essam Namouz ◽  
Joshua D. Summers ◽  
Gregory M. Mocko
Keyword(s):  
Engineering Students ◽  
Large Range ◽  
Estimation Method ◽  
Time Estimation ◽  
Handling Time ◽  
Time Estimate ◽  
Time Analysis ◽  
Assembly Time ◽  
Time Estimates ◽  
Initial Results

This paper evaluates the effect of making a subjective decision in a design for assembly time analysis. An example is found in the first set of questions for estimating handling time of a part the user chose “parts are easy to grasp and manipulate” as opposed to “parts present handling difficulties”. The subjectivity is explored through a study of assembly time estimates generated by a class of mechanical engineering students in the time analysis of a clicker pen based on the Boothroyd and Dewhurst estimation method. The assembly times calculated by the class ranged from a minimum of 23.64 seconds to a maximum of 44.89 seconds (range of 21.25 seconds). This large range in results serves as motivation in determining the effect that answering a subjective decision has on the resulting assembly time estimate. Initial results indicate that not answering the first level of subjective questions will result in assembly time estimate within 15% of the time had the subjective question been answered. The probability density plots of the time estimates also indicates that 63% of the time, the estimated assembly time without making the subjective decision will fall within the normal distribution had the subjective decision been made. This provides evidence that there is an opportunity to reduce the amount of subjective questions that a user must answer to estimate the assembly time of a product.

scholarly journals An API Semantics-Aware Malware Detection Method Based on Deep Learning

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Xin Ma ◽  
Shize Guo ◽  
Wei Bai ◽  
Jun Chen ◽  
Shiming Xia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Detection Method ◽  
Malware Detection ◽  
Poor Performance ◽  
Detection Methods ◽  
Interference Detection ◽  
Machine Learning Method ◽  
Accuracy Rate ◽  
Malware Classification ◽  
Self Protection

The explosive growth of malware variants poses a continuously and deeply evolving challenge to information security. Traditional malware detection methods require a lot of manpower. However, machine learning has played an important role on malware classification and detection, and it is easily spoofed by malware disguising to be benign software by employing self-protection techniques, which leads to poor performance for existing techniques based on the machine learning method. In this paper, we analyze the local maliciousness about malware and implement an anti-interference detection framework based on API fragments, which uses the LSTM model to classify API fragments and employs ensemble learning to determine the final result of the entire API sequence. We present our experimental results on Ali-Tianchi contest API databases. By comparing with the experiments of some common methods, it is proved that our method based on local maliciousness has better performance, which is a higher accuracy rate of 0.9734.

Representation: Extracting Mate Complexity From Assembly Models to Automatically Predict Assembly Times

2012 ◽  
Author(s):  
Eric Owensby ◽  
Essam Z. Namouz ◽  
Aravind Shanthakumar ◽  
Joshua D. Summers
Keyword(s):  
Neural Networks ◽  
New Method ◽  
Training Algorithm ◽  
Training Set ◽  
Assembly Time ◽  
Target Time ◽  
Complexity Metrics ◽  
Time Prediction ◽  
Relationship Model ◽  
Assembly Models

The work in this paper uses neural networks to develop a relationship model between assembly times and complexity metrics applied to defined mate connections within SolidWorks assembly models. This model is then used to develop a Design for Assembly (DFA) automation tool that can predict a product’s assembly time using defined mate connections within SolidWorks assembly models. The development of this new method consists of: creating a SolidWorks (SW) Add-in to automatically extract the mate connections from SW assembly models, parsing the mate connections into graphs, implementing a new complexity training algorithm to predict assembly times based on mate graphs, and evaluating the effectiveness of the new method. The motivation, development, and evaluation of the new automated DFA method are presented in this paper. Ultimately, the method that is trained on both fully defined and partially defined assembly models is shown to provide assembly time prediction results that are typically within 25% of target time, but with one outlier at 95% error, suggesting that a more robust training set is needed.

Sign in / Sign up

Export Citation Format

Share Document