Innovation in facilities management: from trajectories to ownership

Purpose – Innovation in facilities management (FM) is a complex process as FM is a diverse discipline. This paper aims to use innovation trajectories to explore this complex process through the introduction of a technology innovation in two FM services of security and workspace management. It also aims to consider the discourse of individuals within their trajectory to understand their positions toward the innovation. Design/methodology/approach – A two-year case study was conducted and it was based in an in-house FM department that was part of a financial institution. The specific methods used for the paper were semi-structured interviews with key participants of the project. Critical discourse analysis was used to examine the data. Findings – Individuals who were involved in introducing the technology to the FM department were both internal and external to FM as innovation in FM does not happen in isolation to the organisation. Innovation trajectories were often intertwined or occurred simultaneously during the process of a project which sometimes resulted in conflict. Tensions within the discourse of ownership of the project were particularly apparent as this discourse had a power dimension in driving the project through to implementation. Research limitations/implications – The research is limited by being a single case study so it is not possible to generalise findings but the findings may have resonances with other organisations. Originality/value – The paper presents an original idea about how to understand innovation processes in FM services.

Adaptive modelling with tunable RBF network using multi-innovation RLS algorithm assisted by swarm intelligence

In this paper, we propose a new on-line learning algorithm for the non-linear system identification: the swarm intelligence aided multi-innovation recursive least squares (SI-MRLS) algorithm. The SI-MRLS algorithm applies the particle swarm optimization (PSO) to construct a flexible radial basis function (RBF) model so that both the model structure and output weights can be adapted. By replacing an insignificant RBF node with a new one based on the increment of error variance criterion at every iteration, the model remains at a limited size. The multi-innovation RLS algorithm is used to update the RBF output weights which are known to have better accuracy than the classic RLS. The proposed method can produces a parsimonious model with good performance. Simulation result are also shown to verify the SI-MRLS algorithm.