Periodic Reporting for period 2 - BLINDFAST (BLINDFAST: INNOVATIVE BLIND FASTENER MONITORING TECHNOLOGY FOR QUALITY CONTROL)
Reporting period: 2017-08-01 to 2019-01-31
Blind fasteners are a specific type of bolts which just require access from the front side of the assembly for installation, offering the chance for cheaper and easier automation. But evaluating an installed blind fastener depends greatly on the examination of the formed head on the back side of the assembly. When used in closed structures this evaluation is only possible by means of time and cost intensive equipment and even sometimes no evaluation at all is possible. To skip this issue the fasteners to install are often overcalculated in order to meet safety requirements though penalizing weight and production costs. Consequently, the potential benefits of blind fasteners are not being exploited. Since in a commercial aircraft the number of installed fasteners oscillates between 1.500.000 and 3.000.000 the chance to reduce overcalculated installations and exploit the benefits of blind fasteners is not just an economic concern. Environmental benefits in terms of lower fuel consumption and harmful emissions can be expected from the expected weight decrease.
The aim of the BLINDFAST project was to deliver an inspection method for the installation of blind fasteners featuring an in-line alert of fault installations and the avoidance of any direct inspection of the formed head (i.e. assembly back side).
The aim of the BLINDFAST project was to deliver an inspection method for the installation of blind fasteners featuring an in-line alert of fault installations and the avoidance of any direct inspection of the formed head (i.e. assembly back side).
In order to meet this objective a laboratory test bench for the installation of blind fasteners was set up. The system allows to acquire and store the installation torque-angle diagrams. Using this equipment an experimental study was made to understand the causes that lead to defect installations and how they affect to the torque-angle evolution. After analysing a set of preliminary diagrams and their installation outcomes (i.e. formed heads) a full test campaign was used to design and implement a data-driven monitoring solution for detecting fault installations. The main outcomes of this work are:
* The method for conditioning the torque-angle signals and prepare them for data extraction has proved effective under different types of installation conditions and fastener references
* A set of descriptors (i.e. statistics, regression coefficients, representative points) describes the torque-angle signal evolution along the installation despite varying conditions and the quality of the installation
* By using the signal descriptors both shallow and deep learning algorithms (CSVM, logistic regression, LSTM-FCNN) enable to differentiate with reasonable accuracy correct installations from in-air ones, too high/high/short formed heads and double formed heads. Shallow learners classify with very high accuracy and in a simple way in-air installations from the correct ones.
* The monitoring solution runs in the laboratory test bench for the automatic evaluation of installations
Some additional information about the project results is available at public access publications https://doi.org/10.1007/978-3-319-59650-1_17 and https://doi.org/10.3390/ma12071157.
* The method for conditioning the torque-angle signals and prepare them for data extraction has proved effective under different types of installation conditions and fastener references
* A set of descriptors (i.e. statistics, regression coefficients, representative points) describes the torque-angle signal evolution along the installation despite varying conditions and the quality of the installation
* By using the signal descriptors both shallow and deep learning algorithms (CSVM, logistic regression, LSTM-FCNN) enable to differentiate with reasonable accuracy correct installations from in-air ones, too high/high/short formed heads and double formed heads. Shallow learners classify with very high accuracy and in a simple way in-air installations from the correct ones.
* The monitoring solution runs in the laboratory test bench for the automatic evaluation of installations
Some additional information about the project results is available at public access publications https://doi.org/10.1007/978-3-319-59650-1_17 and https://doi.org/10.3390/ma12071157.
The work done has contributed to a better understanding of the ground of blind fasteners installations and has delivered a robust method for the torque-angle diagrams characterization. The robustness of the method has led to the successful implementation of a monitoring solution based on machine learning techniques. From the point of view of the application of artificial intelligence in manufacturing a complex multiclassification problem has been addressed achieving a high success rate.
By applying the results obtained on new applications which will contribute to confirm and increase the current solution capabilities the results should in a future lead to:
* Lower production costs in assembly operations by decreasing the number of fasteners over-installations and minimizing expensive inspection techniques for closed structures
* Higher automation in assembly lines through an increased use of blind fasteners
* More affordable inspection of the blind fastening installations by using artificial intelligence techniques
* A greener aviation thanks to lighter aerostructures which demand a lower fuel consumption and generate lower levels of harmful emissions
By applying the results obtained on new applications which will contribute to confirm and increase the current solution capabilities the results should in a future lead to:
* Lower production costs in assembly operations by decreasing the number of fasteners over-installations and minimizing expensive inspection techniques for closed structures
* Higher automation in assembly lines through an increased use of blind fasteners
* More affordable inspection of the blind fastening installations by using artificial intelligence techniques
* A greener aviation thanks to lighter aerostructures which demand a lower fuel consumption and generate lower levels of harmful emissions