Experimental study of neuro-fuzzy-genetic framework for oil spillage risk management

Akinyokun, Oluwole Charles; Inyang, Udoinyang G.

doi:10.5430/air.v2n4p13

Cited by 9 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The normalized output,w i is given in Equation 13. Layer 4, the defuzzification layer, consists of consequent nodes for calculating the contribution of each rule to the overall output as in Equation 14. The overall output of the ANFIS model is determined by summing all incoming signals by layer 5.…”

Section: Methodsmentioning

confidence: 99%

“…Hence, the need for an understanding of the nature, sources, impact and responses required to prevent or control their occurrence. [14] Risk modeling must be seen as an understating of the probability of occurrence of events of particular severity and the levels of uncertainty that exist in the data employed and the models themselves. [15] Risk assessment is the determination of quantitative or qualitative value of risk related to a concrete situation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid knowledge discovery system for oil spillage risks pattern classification

Inyang

Akinyokun

2014

AIR

Self Cite

View full text Add to dashboard Cite

The complexity and the dynamism of oil spillages make it difficult for planners and responders to produce robust plans towards their management. There is need for an understanding of the nature, sources, impact and responses required to prevent or control their occurrence. This paper develops an intelligent hybrid system driven by Sugeno-Type Adaptive Neuro Fuzzy Inference System (ANFIS) for the identification, extraction and classification of oil spillage risk patterns. Dataset consisting of 1008 records was used for training, validation and testing of the system. Result of sensitivity analysis shows that Cause, Location and Type of spilled oil have cumulative significance of 85.1%. Optimal weights of Neural Network (NN) were determined via Genetic Algorithm with hybrid encoding scheme. The Mean Squared Error (MSE) of NN training is 0.2405. NN training, validation and testing results yielded R > 0.839 in all cases indicating a strong linear relationship between each output and target data. Rule pruning was performed with support (15%) and confidence (10%) minimum thresholds and antecedent-size of 3. The performance of the ANFIS was evaluated with eight different types of membership functions (MFs) and two learning algorithms. The model with triangular MF gave the best performance among all other given models while hybrid-learning algorithm performed better than back propagation algorithm. The ANFIS model reported in the paper adopted triangular MF and hybrid learning algorithm for the predication and classification of oil spillage risk patterns. Average training and testing MSE of the model is 0.414315 and 0.221402 respectively. The knowledge mining results show that ANFIS based systems provide satisfactory results in the prediction and classification of oil spillage risk patterns.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A hybrid knowledge discovery system for oil spillage risks pattern classification

Inyang

Akinyokun

2014

AIR

Self Cite

View full text Add to dashboard Cite

show abstract

“…The NN tools produced an intelligent system with learning capabilities for detecting the anomalies on PPP but were not capable of dealing with imprecise PPP data. In Akinyokun and Inyang, [12,14] oil spillage risk managment framework is proposed using neurofuzzy-genetic platform. The neuro-fuzzy-genetic system demonstrated optimized training and imprecise data handling capabilities in the task of recognising patterns in complex oil spillage dataset but lacks facility for timing and automatic management of simultaneous oil spillage-induced parameters from multi pipeline locations.…”

Section: Related Workmentioning

confidence: 99%

“…[7] Different approaches have been used to evolve systems that monitor, detect, classify or respond to emergencies resulting from oil spillages and leakages. [8][9][10][11][12][13][14][15] These systems are limited by lack of a systematic way of tracking the time of activities, high probability of false detection and inefficient localization of detected activities due to non inclusion of intelligent tools for explicit timing of operations, pattern recognition and data imprecision handling. Discrete event system specification (DEVS) offers a plausible solution for the specification of timing and localization need of this problem, while adaptive neuro-fuzzy inference system (ANFIS) proffers solution for pattern recognition and data imprecision.…”

Section: Introductionmentioning

confidence: 99%

Discrete event based hybrid framework for petroleum products pipeline activities classification

Udoh

Akinyokun

Inyang

et al. 2017

AIR

View full text Add to dashboard Cite

The importance of timely detection, classification and response to anomalies on petroleum products pipeline (PPP) have attracted pragmatic researches in recent times. There is need for efficient monitoring and detection of activities on PPP to guide leak detections and remedy decisions. This paper develops an intelligent hybrid system, driven by discrete event system specification (DEVS) and adaptive neuro-fuzzy inference system (ANFIS) for detection and classification of activities on PPP. A dataset comprising 330 records was used for training, validation and testing of the system. Result of sensitivity test shows that inlet pressure, inlet temperature, inlet volume and outlet volume have cumulative significance of 71.72% on flowrate of PPP. Hybrid learning algorithm was observed to converge faster than the back propagation algorithm in the detection of pipeline activities. ANFIS hybrid learning algorithm with training and testing errors of 0.11980 and 0.010233 yielded a correlation of 0.916 between the computed and the desired output and produced optimal consequent parameters to boost the intelligence of DEVS. A testing error of 0.0303 was observed in the evaluation of DEVS-ANFIS system on 33 test data sample, 32 precise detections were made with one incorrect detection, this gives 96.97% level of confidence in the DEVS-ANFIS model for detection, classification and localization of PPP activities.

show abstract

“…The aftermath of petroleum products leakages include environmental pollution, degradation of soil fertility, poor agricultural production, fire outbreak, loss of life and property as well as serious threats to national economy and security. Researches in PPP monitoring and response to anomalies have been carried out in (Udoh, 2009;Akinyokun and Inyang, 2013;Inyang and Akinyokun, 2014). The existing systems for monitoring PPP are limited by lack of a systematic way of learning from previous data and generalizing into unseen patterns.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Neural Network Models for Petroleum Products Pipeline Monitoring

Inyang¹,

Udoh²,

Akinyokun³

2017

SET

View full text Add to dashboard Cite

In recent years, Neural Network (NN) has gained popularity in proffering solution to complex nonlinear problems. Monitoring of variations in Petroleum Products Pipeline (PPP) attributes (flow rate, pressure, temperature, viscosity, density, inlet and outlet volume) which changes with time is complex due to existence of non linear interaction amongst the attributes. The existing works on PPP monitoring are limited by lack of capabilities for pattern recognition and learning from previous data. In this paper, NN models with pattern recognition and learning capabilities are compared with a view of selecting the best model for monitoring PPP. Data was collected from Pipelines and Products Marketing Company (PPMC), Port Harcourt, Nigeria. The data was used for NN training, validation and testing with different NN models such as Multilayer Perceptron (MLP), Radial Basis Function (RBF), Generalized Feed Forward (GFF), Support Vector Machine (SVM), Time Delay Network (TDN) and Recurrent Neural Network (RNN). Neuro Solutions 6.0 was used as the front-end-engine for NN training, validation and testing while My Structured Query Language (MySQL) database served as the back-end-engine. Performance of NN models was measured using Mean Squared Error (MSE), Mean Absolute Error (MAE), Correlation Coefficient (r), Akaike Information Criteria (AIC) and Minimum Descriptive Length (MDL). MLP with one hidden layer and three processing elements performed better than other NN models in terms of MSE, MAE, AIC, MDL and r values between the computed and the desired output.

show abstract

Experimental study of neuro-fuzzy-genetic framework for oil spillage risk management

Abstract: This paper reports the findings from

Cited by 9 publications

References 18 publications

A hybrid knowledge discovery system for oil spillage risks pattern classification

A hybrid knowledge discovery system for oil spillage risks pattern classification

Discrete event based hybrid framework for petroleum products pipeline activities classification

Comparative Analysis of Neural Network Models for Petroleum Products Pipeline Monitoring

Contact Info

Product

Resources

About