Visualia Advantages

---

But what is low-code?

---

Low-code is a revolutionary approach to building your business application. It allows a faster, more efficient way to build applications. Low-code use a visual approach to drag-and-drop pre-coded blocks, therefore reducing the need to write code. Moreover, our approach allows to build an app once and deploy it on multiple systems: Windows, macOS, iOS, Android and Web.

Create your own business application without coding

---

Visualia offers a versatile workflow designer and UI designer that allows for building your business app without coding. In the use case presented here, an app was built for a company active in the construction sector. It is capable to streamline the whole business process and logic for all actors: sales, workers, and managers.

All these actors can manage their projects by entering the contact details, the construction site quantities, design, and dimensions. They can also take pictures, annotate them, perform the daily follow up and create the financial report.

Incorporate artificial intelligence in your business process

---

Another huge advantage of Visualia is its capability to easy use and deploy artificial intelligence or machine learning techniques in your daily business processes. Various techniques can be used to analyse your data, and use AI to analyse images or videos faster and more accurately than a human could do, after a learning process.

This is the case, for example, in the field of industry 4.0 where a huge amount of data is available and requires to be analysed using an algorithm or AI to better control or improve the quality or speedup of the production process.

Another example is the detection of defaults in intermediate or final products, using images or videos. In a general framework, this detection could be performed using neural networks. In case of defaults involving colors (for instance, defaults on thermal images), an algorithm using color detection allows to analyse of a large dataset of images, class pixels of the images into color groups and compute the percentage of each group in the image. A project was performed in this way for the analysis of fractures of metals bounding by glue. The objective was to detect the percentage of the fracture taking place into the glue. An example of results is given below.

5 TYPES OF OPTIMIZATION ALGORITHMS

---

Design variables are continuous variables, integer or categories

Genetic algorithm. Compare to the state of the art genetic algorithm (GA), Xtreme GA includes various innovations that increase the performance of your design process and the convergence robustness.

Fast genetic algorithm. In this algorithm, the genetic algorithm is coupled to an artificial neural network that drastically improves the performance of the design process. The number of function evaluations is usually reduced by a factor of 100 compared to standard genetic algorithm. This algorithm is the best solution when dealing with time consuming function evaluations.

Pareto-front genetic algorithm. This type of algorithm targets multi-objectives optimization. In this case, the Pareto front technique is used to find the front of optimal solutions to a given target.

Fast Pareto-front genetic algorithm. In this algorithm, the Pareto front genetic algorithm is accelerated by an artificial neural network in the same way as performed for the fast genetic algorithm. Similarly, the design process is improved by a factor of 100 in most industrial applications

Sequence optimization

A sequence is an enumerated collection of operations in which the order does matter for the performance of the global applications. Determining the best sequence for an application appears in various domain such as manufacturing process or planning. Xtreme includes a very efficient sequence optimization algorithm. This algorithm is capable to take into account the various constraints meet in typical industrial applications such as forcing a sequence before or after another one, having an imposed operation position in the sequence or grouping operations.

Pump Multi-Disciplinary Optimization

---

In this application, the goal is to perform the optimization of a radial pump. The goal is to modify 13 parameters of the geometry to increase the pump efficiency while keeping the mechanical stresses below a maximum value and using constraints on the mechanical vibration mode of the pump. The challenges solved in this application are:

• We could achieve high robustness of this complex simulation chain
• The optimization using 13 parameters in a few design cycles (less than 50 simulations of the whole pump performance)
• The difficulties of optimizing with the vibration modes introduced a strong local minimum in the design space that could only be solved thanks to our extremely powerful optimization technique.
• The efficiency is increased from 86.4 % to 88.5 % while respecting 30 mechanical constraints

VERTICAL AXIS WIND TURBINE OPTIMIZATION

---

In this application, a vertical axis wind turbine was optimized. The fluid calculation is performed using OpenFoam, while the geometry is defined with CAESES and the optimization is performed using Xtreme. The goal is to optimization and maximie the Performance coefficient of the wind turbine by modifying 4 design variables: the profile chord, the profile thickness, the profile incidence angle and the rotational speed. The fluid simulation is performed using OpenFoam on a 2D unsteady simulation as show on the video below.

Cost Optimization of BIPV application

---

In this application, the goal is to find the cost-optimal set up of Building Integrated Photovoltaic panels (BIPV) onto an existing building. BIMSolar for the simulation of solar irradiance and Xtreme for numerical optimization are used. A cost model is developed to compute the cost of any BIPV setup on that building. A numerical model was also developed to compute the energy flux in and out of the building including batteries. The design variables are the number of photovoltaic modules on each facade of the building. We were able to define the best BIPV set up and the optimal battery size as a function of the investment budget.

STAND-ALONE GRAPHICAL USER INTERFACE

---

Xtreme is available embedded in a stand-alone graphical user interface. The graphical user interface allows the user to set up the design process: design variables, objectives, constraints, run the design process. This package also allows configuring the coupling with the external simulation program. It also provides some graphical functions to help to configure the coupling with the external simulation tool. Finally, after the optimization run, you can visualize your optimal solution found by the optimizer as well as the convergence history.

When do you need to use this package?

1. You have an external executable or a script that can be run in batch mode

2. You want to benefit from the graphical post-processing of the solution and convergence history offered by this interface

3. You do not have specific programming skills in C / C++ or Python and you do not need to integrate the optimization process into your own code

EXCEL ADD-IN

---

Xtreme is available as a Microsoft Excel Add-In to run numerical optimization to your spreadsheet model. In this package, the user opens Excel and accesses the Xtreme configuration parameters from an excel drop-down menu. You select the cells containing the design variables, the cell containing the responses to be optimized or constraints. Finally, you can visualize the convergence history as well as the parameters and responses of the final solution.

When do you need to use this package?

1. Your simulation program is written inside Microsoft Excel worksheets

2. Your simulation program is composed of a few or a limited number of formulas and functions than can easily be written inside Microsoft Excel.

PYTHON INTERFACE

---

Xtreme is also available as a Python API which allows you to write your python program to configure and launch your optimization. You have full access in Python to all functionalities including access to the data structure of the convergence history and optimization solution.

When do you need to use this package?

You have your own development environment in which you want to include the Xtreme optimizer:

1. You want to include the optimization process into your own in-house code

2. You want to use your own simulation program/function available by calling a function to evaluate the response

3. You want to include Xtreme into an in-house robust tool that will be deployed in a production environment

C / C++ API

---

Xtreme is also available as a C/C++ API (Application Programming Interface) which allows you to write your own C / C++ code and to call Xtreme. You have full access in C / C++ to all functionalities including access to the data structure of the convergence history and optimization solution.

When do you need to use this package?

You have your own development environment in which you want to include the Xtreme optimizer:

1. You want to include the optimization process into your own in-house code

2. You want to use your own simulation program/function available by calling a function to evaluate the response

3. You want to include Xtreme into an in-house robust tool that will be deployed in a production environment