Examining the relationship between human factors related quality risk factors and work related musculoskeletal disorder risk factors in manufacturing.

This study addresses the relationship between human factors (HF) related quality deficits in manufacturing and work-related musculoskeletal disorder (WMSD) risk factors in production staff. A recent systematic review identified 60 HF-related quality risk factors (QRFs) in manufacturing related to product, process and workstation design stages. We investigate the extent to which these identified QRFs are also WMSD risk factors. Each QRF was examined for its relationship with WMSD using a 0 (no relationship) to 10 (strong relationship) scale rubric. The authors rated each QRF separately and then discussed and adjusted their ratings in a review session. Results showed that average median ratings were the highest for QRFs related to product design (8/10), intermediate for QRFs related to workstation design (7/10) and the lowest for QRFs related to process design (5/10). This emphasises the significant role of HF in system design in reducing both quality deficits and risk of developing WMSDs for manufacturing personnel.Practitioner summary: This study investigates whether human-related risk factors for product quality are also risk factors for work-related musculoskeletal disorders in manufacturing. Results showed a substantial relationship between quality risk factors and WMSD risk factors. This indicates the significant role of human factors in operations design in improving both system performance and human wellbeing.

Examining the fatigue-quality relationship in manufacturing.

A recent systematic review identified 73 empirical studies that linked human factors (HF) with manufacturing quality. Human fatigue was noted as a frequent (n = 26) issue in the HF-quality relationship - a finding that warrants closer examination. We extend this review by investigating the relationship between fatigue and manufacturing quality by identifying how fatigue has been conceptualized and measured, and we attempted to quantify their relationship. From the original database, 12 of 26 relevant studies (46%) indicated that physical fatigue was the primary contributor to observed quality deficits. There was a positive relationship between fatigue and quality deficits, with fatigue accounting up to 42% of the variance. More studies are needed to improve the resolution, specificity, and power of these analyses. This study sheds light on the role of HF and human fatigue effects on manufacturing quality with macroergonomic implications for embedding HF aspects into design and quality assurance processes.

Production quality and human factors engineering: A systematic review and theoretical framework.

The purpose of this paper is to systematically examine available empirical evidence on the impact of human factors (HF) in the design and management of manufacturing operations on system quality performance. A systematic review was conducted to map the linkages between the human-system fit in the design of operations systems (OS) with production quality. A total of 73 empirical studies were identified linking HF to OS performance in manufacturing. Quality risk factors included HF aspects in product design, process design and workstation design of the manufacturing OS. Quality deficits were associated with undesirable human effects of workload like fatigue and injury-related risk factors. Forty-six percent of the studies reported on efforts to improve HF in the OS with effect sizes for quality improvements reaching up to 86%. The paper documents available quality risk factors in the design of OS. It also provides a conceptual framework explaining HF-Quality linkage.

Removing the thermal component from heart rate provides an accurate VO2 estimation in forest work.

Heart rate (HR) was monitored continuously in 41 forest workers performing brushcutting or tree planting work. 10-min seated rest periods were imposed during the workday to estimate the HR thermal component (ΔHRT) per Vogt et al. (1970, 1973). VO2 was measured using a portable gas analyzer during a morning submaximal step-test conducted at the work site, during a work bout over the course of the day (range: 9-74 min), and during an ensuing 10-min rest pause taken at the worksite. The VO2 estimated, from measured HR and from corrected HR (thermal component removed), were compared to VO2 measured during work and rest. Varied levels of HR thermal component (ΔHRTavg range: 0-38 bpm) originating from a wide range of ambient thermal conditions, thermal clothing insulation worn, and physical load exerted during work were observed. Using raw HR significantly overestimated measured work VO2 by 30% on average (range: 1%-64%). 74% of VO2 prediction error variance was explained by the HR thermal component. VO2 estimated from corrected HR, was not statistically different from measured VO2. Work VO2 can be estimated accurately in the presence of thermal stress using Vogt et al.'s method, which can be implemented easily by the practitioner with inexpensive instruments.

Classifying work rate from heart rate measurements using an adaptive neuro-fuzzy inference system.

In a new approach based on adaptive neuro-fuzzy inference systems (ANFIS), field heart rate (HR) measurements were used to classify work rate into four categories: very light, light, moderate, and heavy. Inter-participant variability (physiological and physical differences) was considered. Twenty-eight participants performed Meyer and Flenghi's step-test and a maximal treadmill test, during which heart rate and oxygen consumption (VO2) were measured. Results indicated that heart rate monitoring (HR, HRmax, and HRrest) and body weight are significant variables for classifying work rate. The ANFIS classifier showed superior sensitivity, specificity, and accuracy compared to current practice using established work rate categories based on percent heart rate reserve (%HRR). The ANFIS classifier showed an overall 29.6% difference in classification accuracy and a good balance between sensitivity (90.7%) and specificity (95.2%) on average. With its ease of implementation and variable measurement, the ANFIS classifier shows potential for widespread use by practitioners for work rate assessment.

Adaptive neuro-fuzzy inference systems with k-fold cross-validation for energy expenditure predictions based on heart rate.

This paper presents a new model based on adaptive neuro-fuzzy inference systems (ANFIS) to predict oxygen consumption (V˙O2) from easily measured variables. The ANFIS prediction model consists of three ANFIS modules for estimating the Flex-HR parameters. Each module was developed based on clustering a training set of data samples relevant to that module and then the ANFIS prediction model was tested against a validation data set. Fifty-eight participants performed the Meyer and Flenghi step-test, during which heart rate (HR) and V˙O2 were measured. Results indicated no significant difference between observed and estimated Flex-HR parameters and between measured and estimated V˙O2 in the overall HR range, and separately in different HR ranges. The ANFIS prediction model (MAE = 3 ml kg(-1) min(-1)) demonstrated better performance than Rennie et al.'s (MAE = 7 ml kg(-1) min(-1)) and Keytel et al.'s (MAE = 6 ml kg(-1) min(-1)) models, and comparable performance with the standard Flex-HR method (MAE = 2.3 ml kg(-1) min(-1)) throughout the HR range. The ANFIS model thus provides practitioners with a practical, cost- and time-efficient method for V˙O2 estimation without the need for individual calibration.

Estimating oxygen consumption from heart rate using adaptive neuro-fuzzy inference system and analytical approaches.

In new approaches based on adaptive neuro-fuzzy systems (ANFIS) and analytical method, heart rate (HR) measurements were used to estimate oxygen consumption (VO2). Thirty-five participants performed Meyer and Flenghi's step-test (eight of which performed regeneration release work), during which heart rate and oxygen consumption were measured. Two individualized models and a General ANFIS model that does not require individual calibration were developed. Results indicated the superior precision achieved with individualized ANFIS modelling (RMSE = 1.0 and 2.8 ml/kg min in laboratory and field, respectively). The analytical model outperformed the traditional linear calibration and Flex-HR methods with field data. The General ANFIS model's estimates of VO2 were not significantly different from actual field VO2 measurements (RMSE = 3.5 ml/kg min). With its ease of use and low implementation cost, the General ANFIS model shows potential to replace any of the traditional individualized methods for VO2 estimation from HR data collected in the field.