How to successfully transform maintenance documentation into an interactive performance improvement service?
The context :
The documentation associated with carrying out maintenance operations on industrial transport equipment is generally complex. We can explain this complexity by the fact that any repair can have a significant impact on the general operation of the device. This rule does not escape the aeronautics sector and more particularly the helicopter sector.
The process of creating services that we had to deal with was based on this premise. A dense documentation, difficult for technical teams to use and which remains a fixed object in the aircraft maintenance process. What do we mean by frozen? That is, the documentation does not evolve over time and does not generate new information that can improve the understanding of its use.
To develop a scalable maintenance service, we have deployed a Double Diamond methodology.
After a diagnostic phase (discovery and definition), we decided to focus on the concept of intelligence in maintenance documentation. This can result in the following problem: How to successfully transform maintenance documentation into an interactive performance improvement service?
Ideation: digitalization via a machine learning process
The ideation phase led us to design a process of value creation through data. By digitizing the maintenance documentation, we assumed that:
- Any consultation of the maintenance would provide data during its consultation (analytics);
- Any maintenance performed would provide data by entering the operation on an interface;
- Finally, the database would be analyzed in real time to provide additional information (statistics) during maintenance documentation.
This principle of self-learning system leads us to the following virtuous circle:
Wireframes, the first visual approach to the interface :
The entry point on the creation of service values is the interface. For the project to be a success, the interface must be appreciated and used by the people performing the maintenance. If this interface is adapted to their needs, the data input will only be a consequence of this use. Thus, we made the following choice based on the details we had available on the needs of future users.
The tool must be portable and allow quick navigation through the different layers of the documentation. To save navigation time and correspond to the breakdown of the maintenance areas, we have divided the view of the device into 7 immersive areas on which the user can click to search for information. Each click results in a higher zoom level to enter a finer degree of accuracy on the maintenance data. Then, the maintenance sheets come to life in the form of maps as the mental representation that the user can have when we talk to him about the “maintenance sheet”.
To materialize this premise, the following wireframes have emerged :
The Models :
Once the wireframes have been validated, we enter the service modeling phase. We rely on a graphic charter in adequacy with our sponsor and respect the grids necessary for the balance of graphic elements on an iPad interface.
We find a drop-down menu on the left allowing us to perform all the general commands of the interface. The specific areas of the helicopter are loaded via a lateral cutout of the aircraft incorporating bullet point navigation. Several cuts of the helicopter are available to allow the user to quickly find the area concerned. Then, when clicking on a “bullet point”, the user zooms in on the device and enters a finer level of technical specifications.
A “see the form” button is present below to lead us to visualize the form in question… To guarantee a system of storage of data of use, we have provided analytics allowing us to know which form has been clicked, consulted but also used:
The form is in the form of a block to prioritize the information and help in reading complex information. It comes to life through options that allow for customization and user evaluation. It is in the capture of this data that we emerge from the fixed character presented at the beginning of the article and that we enter into a learning system. Indeed, maintenance teams can now rate the sheet (top right) using stars or comment on the sheet to explain errors found such as adjustments to correct or improve a repair explanation. Finally, a validation is planned to report that a maintenance has been carried out on an aircraft. This history, as we will see in the second article on this subject, allows us to improve the system and produce statistics for maintenance teams, inventory management and engineers in charge of device design.
The maintenance history is accessible via the interface. Administrators can find all the interventions on a drop-down list:
To understand the data processing mechanism generated by this service, we invite you to discover the second part of this article devoted to Data Science.
To conclude, we leave you with the situation of the service in an iPad, privileged support on this work :