To effectively perform data driven design in a generation of big data and highly advanced simulation environment such as digital twin, a tool is required for engineers to help execute expert level design optimization and analysis even without having particular knowledge or expertise.
ExplainableD3 is an advanced total design optimization solution based on PIDOTECH’s archive of know-how and expertise of optimization processes.
ExplainableD3 not only performs optimization but also generates data for contribution analysis, correlation analysis, and sensitivity analysis and exports a comprehensive optimization report that can be understood even by engineers who are new to the field.


Automatic machine learning based predictive modeling

Feature that provides a prediction model with target accuracy through an elaborate process of sampling and generation based on PIDOTECH’s machine learning methods.

Multidisciplinary optimization

Feature that performs multidisciplinary optimization that not only provides the optimal solution but also various information on the reasoning of the design change (design variables that have high contribution on the improvement of responses, correlation, or sensitive to the response).

Comprehensive report generation

Feature that generates a user-friendly report on optimization results that can be useful for data storytelling with the help of data analytics and visualization techniques.


Wider accessibility 

Perform optimization and data analysis without the need of extensive background or expertise.

Man-hour reduction

Perform optimization, analyze data, and generate a report with a single click of a button.

Archive know-how through design guides

Users can gather expertise with quantified data instead of depending on experiences as design guides are provided for result analysis.

Engineering perspective data utilization

Establish a response prediction process using PIDOTECH’s machine learning techniques on simulation or experiment data.


  • Optimization result analysis : A summary of the optimization result (objective improvements and constraint feasibilities).
  • Contribution analysis : Contribution of design variables to the optimal solution.
  • Correlation analysis : Analysis of correlation between responses about the change of design variables.
  • Design sensitivity analysis : Sensitivity of each response to the change of design variables about the entire design space in terms of improvement or worsening.