Descripción:

The COVID-19 pandemic has been the greatest health challenge we have known in the last century. Its scale has caused one of the largest disruptions in health systems and supply chains,but has also changed consumer behaviour by generating stockouts in some manufacturing sectors;e.g., consumer products like food, cleaning products and toilet paper, fitness equipment, gardening supplies  andhome  improvement  items,  among  others.  Additionally,  the  demand  levels  of  other  manufacturing  sectors  have drastically  dropped, i.e., textile, automobile, metal and fashion apparel sectors. Thus,manufacturing supply chains are complex networks exposed to constant disruptions. In this situation, supply chain planning and coordination can, in resilience terms, refer to  a  supply  chain’s  capacity  to  anticipate  the  impacts  of  disruptions,  and  to  recover  from  the  significant  and  lengthy  impacts caused, which take place or emerge all along the supply chain because of the ripple effect and its consequences. In this project, operational  research  and  artificial  intelligence  algorithms  and  technologies  for  resilient  supply  chain  planning,  mainly  based  on optimisation and simulation, in an Industry 4.0 (I4.0) framework are developed to cope with the ripple effect in the cyber physical supply chain and for the COVID-19 pandemic context.The i4OPT Project aims to bridge the gap between developingacademic and research optimisation algorithms and technologies and using them to solve real problems in industrial companiesby payingspecial attention to artificial intelligence (AI) as the main axis of the fourth industrial revolutionbyproviding facilitating elements for evolution towards I4.0. Manufacturing systems are not a  single  organic  whole,  rather  a  compendium  of  several  subsystems  integrated  in  a  complex manner.  Each  company  has  a variety  of  management  needs  that renderthe  use  of  standardised  business  applications  without  customisation  insufficient  to adapt to unique requirements which,in most cases,are those that provideadded value. In addition, the complexity of the current global  environment  subject  to COVID-19  pandemicevolution,  with  highly  developed  digital  technology,  highly  sophisticated demand  and  competitive  global  supply, makes  the  search  for  maximum  efficiencyin  production  and  logistics  operationsviaoptimisation a key component in companies’ decision-making processes. Thus,most real problems in companies are enormous in terms of computing needs to achieve optimisation, and these companies do not have the appropriate software and hardware to solve  them  in  a  computationally  efficient  way. Itcan  be presently stated  that  the  most  advanced  optimisation  technologies  for modelling and resolution liein the academic and research fields withexperimental datasets, and that R&Dprojects are needed toadapt existing optimisation algorithms and tocreatenew computationally efficient algorithms for solving problems with real data, withthe  innovation  and  transfer  of  these  technologies  to  companies  so  they can optimise  the  use  of  resources,  increase  their competitiveness, move towards the digital company and guarantee its sustainability in its three aspects: economic, environmental and social. Optimisation algorithms must be combined with the learning capacity provided byartificial intelligence in such a way that the improvement of the solution will be achieved in both time and qualitytermsby either selectingthe most suitable algorithm combiningseveral of them. Obtaining a satisfactory solution in a shorttimewill improve companies’resilience because they willbe  able  to  adapt  more  easily  to  unexpected  events  through  a  quick  correct  response  due  to  the  combination  of  optimisation algorithms, simulation, the use of artificial intelligence and big data handlingcapacities. All this will give rise to the cyber physical or smart factory in an I4.0 context.Enterprises,  especially  small-and  medium-sizedenterprises  (SMEs),  are  often  constrained  by  the information  systems  or  ERP (enterprise  resource  planning)  they have  installed.  When attempting  to  introduce  improvements  that  must  necessarily  be implemented intoexisting ERPs, they often find that these ERPs do not allow such adaptations or are excessively costly for them. The i4OPT Project  aims  to overcome  this  limitation  by  providing  optimisation  services  that  are  interoperable  with  companies’ ERPs. The i4OPT Project will provide companies, especially SMEs, with new intelligent optimisation algorithms embedded in an open  cloud-based platform  for  the e-optimisation of  industrial operations  (production,  logistics,transport) as  a  configurable  and interoperable service with business applications to improve their competitivenessbasedon four fundamental pillars: (i) efficiency of operations; (ii) resilience; (iii) sustainability;(iv) digitalisation of factories and smart factories. Thus,the aim is to make it easier for  companies  to  base  their  competitiveness  on  manufacturing  excellence by  means  ofthe  highly  efficient  implementation  and customisation  of  advanced  optimisation  capabilities.  The i4OPT Cloud Platform  will  be  characterised  by  being  computationally efficient,  scalable,  extensible  and  open-sourceand,therefore,low-cost  and  high  added  value  for  companies.  The developedintelligent optimisation algorithms, like artificial intelligence, will be characterised by their transparency, capacity to solve complex problems, adaptability, transversality, and necessary and permanent renewal and improvement.