Maintenance management forms a core component of building facility management, which is particularly important for specialized and complex healthcare facilities. However, existing maintenance ...management tends to rely on manual processing, which is time-consuming and human error-prone. Recorded maintenance work orders (MWOs) are recognized as good potential data source to support maintenance activities. In this paper, the authors propose a comprehensive framework utilizing natural language processing (NLP) techniques to automate the interrogation of textual data of MWOs that assist in developing maintenance material management and preventive maintenance strategies and transforming maintenance worker assignment from a labor-intensive process to a more automated one. A set of historical MWOs from a hospital was used for model development, and our model achieved an accuracy of 0.83 on worker assignment. This study addresses the difficulty of utilizing work order information due to the unstructured nature of textual data and contributes to better maintenance management practices in buildings.
•Investigated NLP and machine learning models to automate the processing of hospital maintenance work orders in Chinese.•The model is configured with multiple combinations of splitters and machine learning algorithms.•Splitting text input into single characters was found to perform surprisingly well.•The model shows high accuracy on worker assignment tasks that outperformed the state of the art.•The study provides a replicable approach to the improvement of hospital building maintenance management practices.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
A vast amount of work orders is submitted daily which is a critical component of management for any facility. The process taken for prioritizing work orders, however, shows a high dependency on the ...extent of knowledge and experience of responsible staff available and is challenged by inconsistency in data collection, and uncertainty in decision-making. Making decisions and responding to a high number of requests demand intensive labor hours resulting in delays causing issues for facility managers. The high number of service requests, various work orders, and the required balance between cost and budget highlight the importance of the need for improving work order processing to optimize time and cost of buildings' operation. Through review of the literature, unstructured and semi-structured interviews, and a qualitative analysis approach, this paper identifies various challenges and gaps in user-driven decision-making for processing work orders and determines best practices. The challenges identified include inconsistency in prioritizing orders, lack of data requirements and knowledge management, cognitive workload and biases, and inconsistency in data collection. Using data-driven decision-making methods can address existing challenges, improve the process of prioritizing work orders and enhance the quality of the work performed by timely responding to submitted requests. This will improve the operation and maintenance of building facilities and increase occupants’ satisfaction.
•Prioritizing and processing work orders constitute a big part of facility management.•Data requirements need to be defined to achieve more consistent and accurate results.•The paper explores existing practices for processing work orders.•Outcome of the study can be used for developing data requirements.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Government hotline plays a significant role in meeting the demands of the people and resolving social conflicts in China. In this paper, we propose an automatic work‐order assignment method based on ...event extraction and external knowledge to address the problem of low efficiency with manual assignment for Chinese government hotline. Our proposed assignment method is composed of four parts: (1) Semantic encoding layer, which extracts semantic information from the work‐order text and obtains semantic representation vectors with contextual feature information. (2) Event extraction layer which extracts the local features and global features from the semantic representation vectors with the help of the CRF network to enhance event extraction effect. (3) External knowledge embedding layer, which integrates ‘rights and responsibilities lists’ with the historical information of the work‐order to assist assignment. (4) Assignment layer which completes work‐order assignment by combining two output vectors from event extraction layer and external knowledge embedding layer. Experimental results show our proposed method can achieve better assignment performance compared with several baseline methods.
We propose a work‐order assignment method based on event extraction and external knowledge to address the problem of low efficiency with manual allocation. The assignment method is composed of four parts: (1) semantic encoding layer, (2) event extraction layer, (3) external knowledge embedding layer, (4) assignment layer.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
Being a logging contractor involves several uncertainties, amongst others, information quality in the work order received from customers. The information quality of work orders is of the utmost ...importance for logging contactors, in order to be able to plan and conduct work properly. The purpose of this paper is three-fold: 1) identifying work order information components in harvesting, 2) identifying work order information quality dimensions in harvesting and 3) assessing work order information quality in harvesting. The paper is based on interviews and a survey. Various interviews took place in Sweden with professionals within the harvesting industry as well as logging contractors, and thereafter a survey was developed. Random selection was conducted and 100 Swedish logging contractors were contacted by telephone in order to answer the survey, with a response rate of 82% from the sample. The paper concludes that the information quality dimension of accuracy concerns the individual work order information components, whereas timeliness is related to receiving the complete work orders. A factor analysis has been conducted with five factors emerging. The assessment of work order information quality in harvesting implies that the potential for improvement exists with regard to increasing the accuracy of the order information for the components of “Cleaning under story trees - not conducted” and “Cleaning under story trees - of low standard” as well as “landing size”, and “landing placement”. However, their effect on capacity is utilization needs to be explored.
Infrastructure managers require timely and accurate state information to diagnose, prioritize, and repair the substantial infrastructure assets supporting modern society. Challenges in obtaining ...sufficient information can often be attributed to inadequate data collection procedures (phone calls, paper reports, etc.) or a general lack of knowledge or ability on the part of the reporting individual to accurately convey what is actually wrong with the facility. Fortunately, modern smart-phone technology offers the potential to improve maintenance work requests by providing better geolocation and problem description accuracy. An experiment simulating real-world maintenance requests was conducted comparing smart-phones with traditional verbal work order request systems. Usefulness and description accuracy ratios revealed smartphone systems generated more useful information regardless of submitter background or experience. However, interestingly the smart-phone applications did not improve asset geolocation and actually negatively impacted the ability of maintenance personnel to accurately relocate the asset needing service. Given the ubiquitous nature of smartphone technology, the potential exists to turn any citizen into an infrastructure sensor. This study takes a step toward understanding the benefits, as well as the limitations, of the smart-phone based work order submission systems.
Fault detection, diagnostics, and prognostics (FDD&P) is attracting an amount of attention from building operators and researchers because it can help greatly improve the performance of building ...operations by reducing energy consumption for heating, ventilation and air-conditioning (HVAC) while improving occupant comfort at the same time. However, FDD&P, particularly HVAC prognostics, for building operations remains with many challenges due to special operation environments of HVAC systems. These challenges include “tolerance or ignorance” of failures in long-haul operations, lack of operation regulations, and even lack of documents for HVAC failure mode and effects analysis (FMEA), which is a systematic method of identifying and preventing system, product and process problems. To address some of these challenges, the authors propose an FMEA method for common building HVAC equipment by exploring work-orders generated by building energy management systems (BEMS) using a data mining approach. With this FMEA approach, it is possible for building operators to isolate and prognose faults practically. The FMEA approach also helps us tackle high impact failures, for which operation data can be acquired and machine learning-based predictive models can be developed. This paper reports some preliminary results in conducting an HVAC FMEA from a large number of work-orders obtained from a BEMS in routine operations. The HVAC FMEA will be used as a guidance tool for data gathering and developing data-driven models for HVAC FDD&P and as a practical solution for HVAC prognostics in case that predictive models are difficult to develop.
•This is a first attempt to develop FMEA for HVAC systems from historic work-order dataset.•A symptomatic data mining-based approach is proposed for creating an FMEA from work-order dataset.•An FMEA-based methods for prognostics of HVAC systems is proposed.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Maintenance of assets is a multi-million dollar cost each year for asset intensive organisations in the defence, manufacturing, resource and infrastructure sectors. These costs are tracked though ...maintenance work order (MWO) records. MWO records contain structured data for dates, costs, and asset identification and unstructured text describing the work required, for example ‘replace leaking pump’. Our focus in this paper is on data quality for maintenance activity terms in MWO records (e.g. replace, repair, adjust and inspect). We present two contributions in this paper. First, we propose a reference ontology for maintenance activity terms. We use natural language processing to identify seven core maintenance activity terms and their synonyms from 800,000 MWOs. We provide elucidations for these seven terms. Second, we demonstrate use of the reference ontology in an application-level ontology using an industrial use case. The end-to-end NLP-ontology pipeline identifies data quality issues with 55% of the MWO records for a centrifugal pump over 8 years. For the 33% of records where a verb was not provided in the unstructured text, the ontology can infer a relevant activity class. The selection of the maintenance activity terms is informed by the ISO 14224 and ISO 15926-4 standards and conforms to ISO/IEC 21838-2 Basic Formal Ontology (BFO). The reference and application ontologies presented here provide an example for how industrial organisations can augment their maintenance work management processes with ontological workflows to improve data quality.
Due to convenience and flexibility, online ride-hailing has become increasingly more prevalent across the world. However, many violations and road crashes involving online ride-hailing were related ...to the unhealthy working pace of drivers, especially inadequate rest. This paper enriches the literature by providing a first look into the latent break patterns of online ride-hailing drivers based on a one-month order record dataset. A data mining and knowledge discovery process is presented for extracting and analyzing characteristics of online ride-hailing drivers' work and rest based on GPS trajectory data, as follows: 1) logical judging to identify non-work order-gaps; 2) dynamic topic modeling to discover latent break patterns; and 3) integrating the topic modeling results with feature analysis results of order-gaps to summarize the time-dependent characteristics of online ride-hailing drivers' special working pace. The case study results show that the latent break patterns extracted from two cities' online ride-hailing order records are significantly different in the strength and cycles of the topics, which is greatly related to the travel supply-demand conditions and urban characters. Furthermore, the proposed analytical framework can help mobile transportation platform companies to better understand online ride-hailing markets from the perspective of drivers and to adjust their marketing strategies in real time.