Selection and performance estimation of Green Lean Six Sigma Projects: a hybrid approach of technology readiness level, data envelopment analysis, and ANFIS.
Journal:
Environmental science and pollution research international
PMID:
33559076
Abstract
Nowadays budget and schedule constraints have forced organizations to select six sigma projects based on pre-defined success criteria. Also, progressive approaches based on green and lean paradigm are vital for companies to enhance their social and environmental performance. Then, Green Lean Six Sigma (GLS) projects play the main role in improving the performance of an organization while augmenting its sustainability. Accordingly in this paper, past studies were reviewed, and GLS projects' indicators and performance evaluation criteria were identified. Data envelopment analysis (DEA) was employed for the appropriate selection of GLS projects. Next, the ranking and performance weight of each project were investigated, and also the projects were categorized based on the technology readiness level (TRL). Additionally, an adaptive neuro-fuzzy inference system (ANFIS) method was applied for the successful prediction of selected GLS projects. Twenty-eight inputs and 9 outputs for the first project category (with TRL 9) and 28 inputs and 6 outputs for the second project category (with TRL 8) were entered into the model. The statistical assessment measures such as Nash-Sutcliffe efficiency (NSE), root mean squared of error (RMSE), mean absolute error (MAE), and R were employed for capability appraisal of ANFIS model. Results of NSE and R indicators for both project categories were 1.00 that proved the efficiency of the ANFIS model for success prediction of GLS projects. Also, RMSE and MAE indicators for category 1 were 0.01 and 0.02 respectively. Similarly, these measures for category 2 were 0.02 and 0.02. The results advocate a proper approximation for observed values by the ANFIS model. Also, the results indicated that TRL as an important enabler of the GLS project has a meaningful role in the performance of GLS projects.