Effect of working position and cold environment on muscle activation level and fatigue in the upper limb during manual work tasks

Several occupational groups are exposed to periods of low ambient temperatures while performing manual work tasks outdoors. Work tasks typically include heavy lifting, tool handling, and overhead work. This study evaluated the effect of working position and cold environment on muscle activation level (%RMS_max) and fatigue in the upper limb during manual work tasks. Fourteen male participants (25 ± 3 years, 80.9 ± 6.4 kg, 182 ± 5 cm) completed a 2-h test protocol consisting of five test periods alternating with four work periods, wearing identical sets of clothing, under cold (−15 °C) and control (5 °C) conditions. The work periods consisted of manual work at the hip level, manual overhead work, and a lifting exercise. The test periods consisted of isometric maximal voluntary contractions (MVC) and seated rest. Skin temperatures decreased during cold exposure, especially in the extremities. %RMS_max in the forearm was higher in the cold condition both during overhead work and work at the hip level than that for the same work in the control condition, especially at the end of the test when the difference was approximately 25% (equating to 2–3 %RMS_max). For the middle deltoid muscle, the %RMS_max was approximately three times (or 10 %RMS_max) higher during overhead work than work at the hip level, but there was no additional cost of working in the cold. Signs of deltoid muscle fatigue (decrease in electromyography median power frequency and an increase in %RMS_max) were observed during the overhead work periods in both temperature conditions. No decrease in MVC, as a sign of overall muscle fatigue, was observed in either condition.Relevance to industryThis study demonstrated that when wearing suitable cold-weather protective clothing, the adverse effect of work posture is much higher than that of cold on muscle demand and physical strain.     

Convolutional long short-term memory model for recognizing construction workers’ postures from wearable inertial measurement units

This paper proposes using Deep Neural Networks (DNN) models for recognizing construction workers’ postures from motion data captured by wearable Inertial Measurement Units (IMUs) sensors. The recognized awkward postures can be linked to known risks of Musculoskeletal Disorders among workers. Applying conventional Machine Learning (ML)-based models has shown promising results in recognizing workers’ postures. ML models are limited – they reply on heuristic feature engineering when constructing discriminative features for characterizing postures. This makes further improving the model performance regarding recognition accuracy challenging. In this paper, the authors investigate the feasibility of addressing this problem using a DNN model that, through integrating Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) layers, automates feature engineering and sequential pattern detection. The model’s recognition performance was evaluated using datasets collected from four workers on construction sites. The DNN model integrating one convolutional and two LSTM layers resulted in the best performance (measured by F1 Score). The proposed model outperformed baseline CNN and LSTM models suggesting that it leveraged the advantages of the two baseline models for effective feature learning. It improved benchmark ML models’ recognition performance by an average of 11% under personalized modelling. The recognition performance was also improved by 3% when the proposed model was applied to 8 types of postures across three subjects. These results support that the proposed DNN model has a high potential in addressing challenges for improving the recognition performance that was observed when using ML models.     

Hand grip strength for the working-age population in South Korea: Development of an estimation and evaluation model

Although grip strength is frequently measured in clinical settings, methods for evaluating individual grip strength considering physical characteristics are limited. We attempted to develop an easily applicable statistical model to estimate and evaluate the grip strength of Korean workers according to their age, sex, and anthropometric data.Data were collected from the KNHANES (2014–2019). The data were divided into the test and training sets. Potential regression models for estimating grip strength have been suggested based on sex and hand dominance. The performance of each model was compared, and the best model was selected. The estimated grip strength was calculated for each participant. The distribution of the measured to estimated value ratios was presented. The ratios between the dominant and non-dominant hand grip strengths were also calculated.Overall, 21,807 (9652 men and 12,155 women) individuals were included in the dataset. The selected predictors were age, age^2, height, body mass index (BMI), and body mass-to-waist ratio for men and age, age^2, height, BMI, and waist circumference for women. The measured estimated values were 100.0 ± 16.2%, 100.0 ± 16.3% for dominant and non-dominant hands in men and 100.0 ± 18.9% for dominant and non-dominant hands in women. The 95% confidence interval of the dominant to non-dominant hand grip ratio was 84.4–126.7% for men and 82.4–131.3% for women.Grip strength in workers can be screened in comparison to that in the Korean population using the suggested models. This model is an effective method for identifying abnormalities in the upper extremities of Korean workers.     

Design of data feature-driven 1D/2D convolutional neural networks classifier for recycling black plastic wastes through laser spectroscopy

In this study, two types of convolutional neural network (CNN) classifiers are designed to handle the problem of classifying black plastic wastes. In particular, the black plastic wastes have the property of absorbing laser light coming from spectrometer. Therefore, the classification of black plastic wastes remains still a challenging problem compared to classifying other colored plastic wastes using existing spectroscopy (i.e., NIR). When it comes the classification problem of black plastic wastes, effective classification techniques by the laser spectroscopy of Fourier Transform-Infrared Radiation (FT-IR) with Attenuated Total Reflectance (ATR) and Raman to analyze the classification problem of black plastic wastes are introduced. Due to the strong ability of extracting spatial features and remarkable performance in image classification, 1D and 2D CNN through data features are designed as classifiers. The technique of chemical peak points selection is considered to reduce data redundancy. Furthermore, through the selection of data features based on the extracted 1D data with peak points is introduced. Experimental results demonstrate that 2DCNN classifier designed with the help of 2D data feature selection as well as 1DCNN classifier shows the best performance compared with other reported methods for classifying black plastic wastes.     

A three-stage multi-objective heterogeneous integrated model with decomposition-reconstruction mechanism and adaptive segmentation error correction method for ship motion multi-step prediction

Reliable and accurate ship motion prediction is essential for ship navigation at sea and marine operations. Although previous studies have yielded rich results in the field of ship motion prediction, most of them have ignored the importance of the dynamic characteristics of ship motion for constructing forecasting models. Besides, the limitations of the single model and the autocorrelation characteristics of the residual series are also unfavorable factors that hinder the forecasting performance. To fill these gaps, a multi-objective heterogeneous integration model based on decomposition-reconstruction mechanism and adaptive segmentation error correction method is proposed in this paper for ship motion multi-step prediction. Specifically, the proposed model is divided into three stages, which are decomposition-reconstruction mechanism, multi-objective heterogeneous integration model and adaptive segmentation error correction method. The effectiveness of the proposed model is verified using four sets of real ship motion data collected from two sites in the South China Sea. The evaluation results show that the proposed model can effectively improve the prediction performance and outperforms other traditional models and state-of-the-art models in the field of ship motion prediction. Prospectively, the model proposed in this study can be used as an effective aid to ship warning systems and has the potential for practical application in ship marine operations.     

Novel thoraco-lumbo-sacral corset design increases Biering-Sorensen back endurance and alters knee and ankle angles during a box lifting task

Research investigating lumbosacral corset designs and their effects are limited and conflicting. The objective was to compare thoraco-lumbo-sacral support corsets (polyester/nylon: TLSSC-poly and neoprene: TLSSC-neo) with a traditional model (TRAD) and Control. Twenty male, university-aged, healthy, recreationally active, participants performed Biering-Sorensen back endurance (BS) test and box lifting tasks (BL:30 repetitions using 20% body mass). Lower and upper erector spinae and hamstrings electromyography (EMG); trunk-hip, knee, and ankle kinematics as well as endurance time were monitored. With BL, the TLSSC-poly (121.4°±17.9) exhibited 1.9% (p = 0.01), 2.7% (p = 0.003), and 3.7% (p = 0.0003) greater knee flexion than TRAD (119.1°±17.5), TLSSC-neo (116.8°±17.4) and Control (120.1°±17.6) respectively. The TLSSC-poly (101.9°± 8.9) demonstrated significant 3.5% (p = 0.005), 2.2% (p = 0.002) and 1.4% (p = 0.01) greater dorsiflexion than TRAD (103.4°±8.7), TLSSC-neo (104.2°±9.8) and Control (105.7°±7.2) respectively. With BS, TLSSC-poly (137.4-s±31.2, 9.7%, p = 0.018) and TLSSC-neo (133.8-s±32.3, 9.2%, p = 0.006) exhibited significantly longer durations than Control (124.8-s±29.8). Relevance to industry: The TLSSC increased BS endurance and TLSSC-poly increased BL knee and ankle angles, possibly providing benefits for workers, with repeated actions over a full work day.     

A review of digital twin in product design and development

In the era of digitalization, there are many emerging technologies, such as the Internet of Things (IoT), Digital Twin (DT), Cloud Computing and Artificial Intelligence (AI), which are quickly developped and used in product design and development. Among those technologies, DT is one promising technology which has been widely used in different industries, especially manufacturing, to monitor the performance, optimize the progresses, simulate the results and predict the potential errors. DT also plays various roles within the whole product lifecycle from design, manufacturing, delivery, use and end-of-life. With the growing demands of individualized products and implementation of Industry 4.0, DT can provide an effective solution for future product design, development and innovation. This paper aims to figure out the current states of DT research focusing on product design and development through summarizing typical industrial cases. Challenges and potential applications of DT in product design and development are also discussed to inspire future studies.     

Conceptual design evaluation considering the ambiguity semantic variables fusion with conflict beliefs: An integrated Dempster-Shafer evidence theory and intuitionistic fuzzy -VIKOR

Quantifying the uncertain linguistic evaluation from decision-makers (DMs) is one of the most challenging parts in the conceptual design decision. Although fuzzy decision models have been widely used to capture potential uncertainty by assigning a fuzzy term with the certain belief, the ambiguity subjective evaluation of semantic variables with conflict beliefs derived from DMs have not been well addressed. To solve this drawback, a concept decision model based on Dempster-Shafer (DS) evidence theory and intuitionistic fuzzy -Vlsekriterijumska Optimizacija I Kompromisno Resenje (VIKOR) considering the ambiguity semantic variables fusion is proposed. Firstly, by incorporating semantic variables of intuitionistic fuzzy sets (IFSs), the diversified semantic judgments and its belief will be taken into account to form an ambiguity semantic initial decision matrix; secondly, the DS combination rule will be used to fuse the different semantic variables of multi-DMs in each scheme, update the belief of each semantic variable, and then the semantic fusion value matrix of the scheme will be constructed; finally, the weight of each evaluation objective will be calculated based on the value matrix and information entropy model, IFS-VIKOR model will be constructed to rank the concepts. A case study of the tree climbing and trimming machine will be employed to verify the proposed decision model. This decision model considering diversifying semantic variables and the conflict belief is proven to be effective compared with the IFS-SAW and ISF-TOPSIS.     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Comparison of OWAS,RULA and REBA for assessing potential work-related musculoskeletal disorders

This study compared three representative observational methods for assessing musculoskeletal loadings: Ovako Working Posture Analysis System (OWAS), Rapid Upper Limb Assessment (RULA), and Rapid Entire Body Assessment (REBA). The comparison was based on 209 cases of upper-body musculoskeletal disorders (MSDs) diagnosed by medical doctors. The most awkward/stressful posture in each participant's tasks was assessed using these techniques. Postural loadings were rated more highly by the RULA than by the OWAS and REBA (p < 0.01). The chi-square test and logistic regression analysis showed that only RULA grand score and action level, and REBA action level were associated with MSD work-relatedness (p < 0.01, p < 0.05, and p < 0.05, respectively). The percentage concordant values of the logistic model for the RULA grand score and action level were 52.4% and 44.8%, respectively, while the percentage concordant value for the REBA action level was 22.1%. Therefore, the RULA may be the best system for estimating the postural loads and work-relatedness of MSDs.Relevance to industryWork-related musculoskeletal disorders are the leading cause of workplace disability in the developed countries. For preventing the disorders, quantification of musculoskeletal loads is required.     

The use of PCA and signal processing techniques for processing time-based construction settlement data of road embankments

Instrumentation is beneficial in civil engineering for monitoring structures during their construction and operation. The data collected can be used to observe real-time response and develop data-driven models for predicting future behaviour. However, a limited number of sensors are usually used for on-site civil engineering construction due to cost restrictions and practicalities. This results in relatively small raw datasets, which often contain errors and anomalies. Interpreting and making judicious use of the available dataset for developing reliable predictive model represents a significant challenge. Therefore, it is essential to pre-process and clean the data for improving their quality. To date, little investigation has been performed in the application of such data cleaning methods to geotechnical engineering datasets collected from full-scale sites. The purpose of this study is to apply simple and effective data pre-processing techniques to site-data collected from a highway embankment constructed on a sequence of soil layers of different physical make-up and non-linear consolidation characteristics. Various cleaning methods were applied to magnetic extensometer data collected for monitoring settlement within foundation soils beneath the embankment. PCA was used to explore raw data, identify and remove outliers. Numerous filtering and smoothing methods were used to clean noise in the data and their results were further compared using RMSE and NMSE. The methods adopted for data pre-processing and cleaning proved very effective for capturing the raw settlement behaviour on site. The findings from this study would be useful to site engineers regarding complex decision-making relating to ground response due to embankment construction. This also has positive prospects for developing dynamic prediction models for embankment settlement.     

A digital twin-based multidisciplinary collaborative design approach for complex engineering product development

With the ever-increasing demand for personalized product functions, product structure becomes more and more complex. To design a complex engineering product, it involves mechanical, electrical, automation and other relevant fields, which requires a closer multidisciplinary collaborative design (MCD) and integration. However, the traditional design method lacks multidisciplinary coordination, which leads to interaction barriers between design stages and disconnection between product design and prototype manufacturing. To bridge the gap, a novel digital twin-enabled MCD approach is proposed. Firstly, the paper explores how to converge the MCD into the digital design process of complex engineering products in a cyber-physical system manner. The multidisciplinary collaborative design is divided into three parts: multidisciplinary knowledge collaboration, multidisciplinary collaborative modeling and multidisciplinary collaborative simulation, and the realization methods are proposed for each part. To be able to describe the complex product in a virtual environment, a systematic MCD framework based on the digital twin is further constructed. Integrate multidisciplinary collaboration into three stages: conceptual design, detailed design and virtual verification. The ability to verify and revise problems arising from multidisciplinary fusions in real-time minimizes the number of iterations and costs in the design process. Meanwhile, it provides a reference value for complex product design. Finally, a design case of an automatic cutting machine is conducted to reveal the feasibility and effectiveness of the proposed approach.     

Poly(vinyl alcohol)-based photosensitive water-borne coating for low-temperature color-filter production

A photosensitive water-borne overcoat comprising poly(vinyl alcohol), a glycoluril crosslinker, and a water-soluble photoacid generator was developed. The passivation coating has two features: low-temperature processability and applicability to organic-solvent-susceptible films. Photo-exposure and subsequent baking at 85 °C and development with water produced PGMEA-insoluble and transparent overcoat patterns. Uncured color patterns that were susceptible to the PGMEA-based coating solution remained intact after water-based overcoat application. By exploiting the features of the passivation coating, color patterns of green, red, and white were produced onto a glass substrate at a process temperature of 85 °C.     

Reliability of a new risk assessment method for visual ergonomics

IntroductionThe Visual Ergonomics Risk Assessment Method (VERAM) is a newly developed and validated method to assess visual ergonomics at workplaces. VERAM consists of a questionnaire and an objective evaluation.ObjectiveTo evaluate reliability of VERAM by assessing test-retest reliability of the questionnaire, and intra- and inter-rater reliability of the objective evaluation.MethodsForty-eight trained evaluators used VERAM to evaluate visual ergonomics at 174 workstations. The time interval for test-retest and intra-rater evaluations was 2–3 weeks, and the time interval for inter-rater evaluations was 0–2 days. Test-retest reliability was assessed by intraclass correlation (ICC), the standard error of measurement (SEM) and the smallest detectable change (SDC). Intra- and inter-rater reliability were assessed with weighted kappa coefficients and absolute agreement. Systematic changes were analysed with repeated measures analyses of variance and Wilcoxon sign rank test.ResultsThe ICC of the questionnaire indices ranged from 0.69 to 0.87, while SEM ranged from 7.21 to 10.19 on a scale from 1 to 100, and SDC from 14.42 to 20.37. Intra-rater reliability of objective evaluations ranged from 0.57 to 0.85 (kappa coefficients) and the agreement from 69 to 91%. Inter-rater reliability of objective evaluations ranged from 0.37 to 0.72 (kappa coefficients) and the agreement from 52 to 87%.ConclusionVERAM is a reliable instrument for assessing risks in visual work environments. However, the reliability might increase further by improving the quality of training for evaluators. Complementary evaluations of VERAM's sensitivity to changes in the visual environment are needed.Relevance to industryIt is advantageous to set up a work environment for maximal visual comfort to avoid negative effects on work postures and movements and thus prevent visual- and musculoskeletal symptoms. This method, VERAM, satisfies the need of a valid and reliable tool for determining risks associated with the visual work environment.     

A design method for an intelligent manufacturing and service system for rehabilitation assistive devices and special groups

The maturity of Industrial 4.0 technologies (smart wearable sensors, Internet of things [IoT], cloud computing, etc.) has facilitated the iteration and digitization of rehabilitation assistive devices (RADs) and the innovative development of intelligent manufacturing systems of RADs, expanding the value-added component of smart healthcare services. The intelligent manufacturing service mode, based on the concept of the product life cycle, completes the multi-source data production process analysis and the optimization of manufacturing, operation, and maintenance through intelligent industrial Internet of things and other means and improves the product life cycle management and operation mechanism. The smart product-service system (PSS) realizes the value-added of products by providing users with personalized products and value-added services, service efficiency, and sustainable development and gradually forms an Internet-product-service ecosystem. However, research on the PSS of RADs for special populations is relatively limited. Thus, this paper provides an overview of an IoT-based production model for RADs and a smart PSS-based development method of multimodal healthcare value-added services for special people. Taking the hand rehabilitation training devices for autistic children as a case, this paper verifies the effectiveness and availability of the proposed method. Compared with the traditional framework, the method used in this paper primarily helps evaluate rehabilitation efficacy, personalizes schemes for patients, provides auxiliary intelligent manufacturing service data and digital rehabilitation data for RAD manufacturers, and optimizes the product iteration development procedures by combining user-centered product interaction, multimodal evaluation, and value-added design. This study incorporates the iterative design of RADs into the process of smart PSS to provide some guidance to the RADs design manufacturers.     

Counterfactual inference to predict causal knowledge graph for relational transfer learning by assimilating expert knowledge --Relational feature transfer learning algorithm

Transfer learning (TL) is a machine learning (ML) method in which knowledge is transferred from the existing models of related problems to the model for solving the problem at hand. Relational TL enables the ML models to transfer the relationship networks from one domain to another. However, it has two critical issues. One is determining the proper way of extracting and expressing relationships among data features in the source domain such that the relationships can be transferred to the target domain. The other is how to do the transfer procedure. Knowledge graphs (KGs) are knowledge bases that use data and logic to graph-structured information; they are helpful tools for dealing with the first issue. The proposed relational feature transfer learning algorithm (RF-TL) embodies an extended structural equation modelling (SEM) as a method for constructing KGs. Additionally, in fields such as medicine, economics, and law related to people’s lives and property safety and security, the knowledge of domain experts is a gold standard. This paper introduces the causal analysis and counterfactual inference in the TL domain that directs the transfer procedure. Different from traditional feature-based TL algorithms like transfer component analysis (TCA) and CORelation Alignment (CORAL), RF-TL not only considers relations between feature items but also utilizes causality knowledge, enabling it to perform well in practical cases. The algorithm was tested on two different healthcare-related datasets — sleep apnea questionnaire study data and COVID-19 case data on ICU admission — and compared its performance with TCA and CORAL. The experimental results show that RF-TL can generate better transferred models that give more accurate predictions with fewer input features.     

Ergonomics demands associated with combinations of manual and powered emergency medical service cots and ambulance loading systems: A work simulation study

Digital human models were used to perform a virtual ergonomics assessment of manual and powered emergency medical services cots combined with both manual and powered ambulance loading systems. Simulations were run with all combinations of emergency medical technicians (EMTs), at 50 kg (female), 72 kg (female) and 125 kg (male) with cots containing no patient and patients of 125 kg and 159 kg. There was a substantial decrease in low back and upper extremity demands with the use of a powered cot, and a further decrease with the additional use of a powered loading system, even though it only required one EMT. The benefits of a fully powered system were magnified with the simulation of both heavier EMTs and patients. Additionally, this study demonstrates the utility of digital human models and work simulation to evaluate product designs that impact occupational demands and injury risk.