Chris Simpson Email & Phone Number

Bristol, Gb

Leading a cross-functional team whose primary goal is to facilitate strategic repair decisions, ensuring the reliability and longevity of wind energy infrastructure. We specialise in building and deploying state-of-the-art AI models, extracting valuable damage and blade condition information from wind turbine inspection data. The team actively develops and manages an online application that empowers turbine owners, operators, and repair teams to make and track key maintenance decisions based on this information.

Bristol, Gb

Training, optimising and deploying a deep learning pipeline for the prediction and classification of defects on wind turbine blades. Responsible for the management of the full processing pipeline backend and defining the direction and resourcing of the data processing team.

Bristol, Gb

Bristol, Gb

Using deep neural networks (primarily CNNs) to analyse large ultrasound non-destructive evaluation (NDE) data sets. Applying state of the art computer vision techniques to classify and quantify material damage and degradation. Working with the Turing Institute to advance and promote the use of Data Science and AI within NDE/Engineering.- Generating hyper-real synthetic data to augment small experimental data sets- Applying 1D CNN/RNNs to run time series analysis for NDE corrosion assessments- Defect classification and quantification from 2D phased array ultrasound- Developing the enabling computational infrastructure to store the raw data from multi-modal NDE measurements performed over the lifetime of an asset.

Bristol, Gb

Modelling and evaluating key physical phenomena that underpin the UKs energy security and manufacturing industries. Emphasis is placed on data rich 3D materials and damage characterisation, that techniques such as high-energy synchrotron X-ray diffraction and X-ray computed tomography enable.- Quantifying aleatory uncertainty and error in XRD/ND measurements- Developing a Bayesian inference approach to residual strain prediction - Applying supervised machine learning to XRD strain tensor evaluation- Grant writing - notably winning £200k for research into offshore wind farms- Project management and delivery to tight timeframes- Building collaborations with industrial and academic partners- Managing two Ph.~D students (guiding their research, running progress reviews etc.)- Writing and peer reviewing research articles, presenting at international conferences

Bristol, Gb

Developed data-centric methods to improve the systematic ageing management procedures for nuclear piping components, ultimately helping justify the safe long term operation of Gen II and Gen III nuclear plants. I used cutting edge technology and techniques (e.g. synchrotron X-ray diffraction) to characterise the in-service development of weld residual stresses and their relationship with degradation, ageing and formation of in-service defects. The resultant data was large and unstructured and I developed carefully tailored analytical techniques (typically leveraging the SciPy ecosystem) to extract meaning from these experiments. To facilitate this work I led the maintenance and development of an X-ray Diffraction/Strain Mapping toolkit (pyXe) that helps researchers better understand and wrangle meaning from temporally and spatially complex Big Data associated with XRD experiments carried out at large-scale research facilities. This is toolkit is used at universities across the UK.

Manchester, Gb

I helped develop world leading material damage characterisation techniques to improve fundamental understanding of failure behaviour. Combined X-ray diffraction with 3D digital image and volume correlation to form a detailed picture of failure progression. I worked with Python (scikit-image, OpenCV), imageJ and Avizo to efficiently process the 3D volumetric data and identify damage in metals, composites and biological materials

Birmingham, West Midlands, Gb

I characterised the effect of inertia welding on the microstructural and mechanical integrity of the Ni-base superalloy, RR1000. I related weld microstructure to predicted thermal profiles, which were modelled using a non-linear finite difference solution to the heat equation (code written in MATLAB). The welded material was then assessed for its damage tolerance under a range of loading conditions, with particular emphasis being placed on the materials response to high temperature, environmentally assisted crack growth. I considered the balance and competition between the formation of a brittle crack tip oxide and the high temperature stress relaxation and associated crack tip blunting.During this period I supervised a number of students through their final year research projects. This involved training them in safe, repeatable methods by which to characterise microstructure and mechanical integrity.

Birmingham, West Midlands, Gb

I was responsible for the organisation and running of tuition sessions for 2nd year Mechanical and Materials Engineering students. The primary focus of the sessions was to improve their familiarity with some of the fundamentals of applied mechanics; covering areas such as complex stress states and transformations, Mohr's circle, yield criterion, and acceleration in non rotating frames.

Birmingham, West Midlands, Gb

I carried out high temperature static load crack growth tests on a range of inertia welded high and low γ' volume fraction Ni-base superalloys (RR1000, U720Li, Waspaloy). I was interested in the relative response of these alloys to oxidation assisted crack growth. Additional testing was conducted under vacuum conditions to allow for a more robust elucidation of the different mechanistic contributions to the process.

London, Greater London, Gb

I was part of the team responsible for the exploratory research required for the expansion of the Kirindy Mitea National Park. This work included initial survey dives around a chain of 7 islands in the Mozambique Channel.

Phd, Aerospace Materials

Beng, Mechanical And Materials Engineering