Thesis work predictive maintenance, AstraZeneca Södertälje

Job description
Predictive maintenance in pharmaceutical manufacturing

Credits: 30hp, start January 2024
Site: Gärtuna, Södertälje. Chance to work partly on remote

Background:
In this project, you will focus on developing models in the field of predictive maintenance. On this end, you will use data-augmented physical models, and integrating these with machine learning algorithms, such as deep neural network or reinforcement learning.

Purpose:
The main objective is to improve productivity of a packing line within SweOps Steriles function, as measured by Overall Equipment Effectiveness (OEE) and competence in line staffing. We aim to achieve the objective by enabling next-best-action decision support for front-line operators.

The project has a number of aims:
Understand the key concepts of smart manufacturing and how to apply them.
Given different conditions in terms of instrumentation, Overall Equipment Effectiveness
(OEE) numbers, identify the bottlenecks and study their root cause.
To identify and collect the desired data, using the Cross Industry Standard Process for
Data Mining, or CRIPS-DM process.
To identify new possible improvements, for example reducing the number of stops and
increasing the load within the production line.


Project description:
Maintenance of manufacturing equipment is crucial to ensure productivity, product quality, on-time delivery, and a safe working environment. Predictive maintenance is an approach that utilises the condition monitoring data to predict the future machine conditions for decision making. Implementation of effective prognosis for maintenance brings increased system safety, improved operational reliability, increased maintenance effectiveness and OEE, reduced maintenance inspection and repair-induced failure, and reduced lifecycle cost.
Initial focus is to use physical modelling of the normal behaviour based on underlying specifications allowing the detection of deviations as anomalies. Moreover, the expectation is to build hybrid kind of models combining physical models with machine learning algorithms.
In order to put the work in its (academics) context, a state-of-the-art needs to be done. The work is presented in a final report, including an outlook for future work.

Miscellaneous:
The work can be carried out by one or two degree workers.

Qualifications: 
Student enrolled in a masters programme with thesis project scheduled to January 2024
Master in Computer Science, Machine Learning, Data Science, Physics, Applied mathematics
Fluent in English

Application
Applications are only handled through Randstad Life Sciences website. Last date for application: 17th of October. Questions regarding the recruitment process: Linda Nordström, consultant manager Randstad Life Sciences. linda.nordstrom@randstad.se

Responsibilities
 The project has a number of aims:
Understand the key concepts of smart manufacturing and how to apply them.
Given different conditions in terms of instrumentation, Overall Equipment Effectiveness
(OEE) numbers, identify the bottlenecks and study their root cause.
To identify and collect the desired data, using the Cross Industry Standard Process for
Data Mining, or CRIPS-DM process.
To identify new possible improvements, for example reducing the number of stops and
increasing the load within the production line.


Qualifications
 Qualifications: 
Student enrolled in a masters programme with thesis project scheduled to January 2024
Master in Computer Science, Machine Learning, Data Science, Physics, Applied mathematics
 Fluent in English


About the company
At AstraZeneca, we are guided in our work by a strong set of values, and we’re resetting expectations of what a bio-pharmaceutical company can be. By truly following the science, we pioneer new methods, new thinking and bring unexpected teams together. From scientists to sales, lab techs to legal, we’re on a mission to turn ideas into life-changing medicines that transform lives. We need great people who share our passion for science and have the drive and determination to meet the unmet needs of patients around the world. If you’re swift to action, confident to lead, willing to collaborate, and curious about what science can do, then you’re our kind of person.