Lifting Action Research Articles

A Video-based Lifting Action Recognition Using Rank-Altered Kinematic Feature Pairs

Low-back musculoskeletal disorders (MSDs) are the primary work-related injuries among manual material handling (MMH) workers, who are frequently exposed to repetitive lifting. To prevent low-back MSDs in the workplace, we present a video-based lifting action recognition method using rank-altered kinematic feature pairs, called top-scoring pairs (TSPs). We derive TSPs from a video dataset containing lifting and other activities commonly seen in MMH. These TSPs collectively classify each frame as lifting and non-lifting. The validation process involves evaluating classification performance. The proposed method minimizes computational and memory requirements while achieving performance comparable to more complex methods with greater computational demands. This makes it suitable for systems with limited hardware resources, thereby providing extensive feasibility across a variety of MMH environments to improve workplace safety.

Active Control for Construction Stability of Suspension Arch Rib Segments Based on ARID System

In response to the issues of vibrations affecting the construction safety, speed, and accuracy of suspended structures due to dynamic disturbances during lifting, environmental disturbances, and improper operator actions, this paper investigates the application of the Active Rotary Inertia Driver (ARID) system for double-rope suspended structures, namely analyzes, and applies control to the vibration response of double-rope suspended structures under external excitations. Taking the double-rope suspended structure as an example, a dynamic analytical model of the double-rope suspended structure is established based on D’Alembert’s principle. Through shake table tests, the dynamic response characteristics and vibration control effects of the double-rope suspended structure under various external excitations are studied, and the influence of the twisting radius of the suspended structure on the control effect is analyzed. The experimental results show that the ARID control system achieves significant control effects on the swing and torsional vibrations of the suspended structure, which validates the accuracy of the theoretical model for the ARID control system and demonstrates its feasibility for practical applications.

Application of Facial Expression Analysis Technology in Violence Risk Assessment of Individuals with Mental Disorders in Supervised Settings.

To explore the association between violent behaviors and emotions in individuals with mental disorders, to evaluate the application value of facial expression analysis technology in violence risk assessment of individuals with mental disorders in supervised settings, and to provide a reference for violence risk assessment. Thirty-nine male individuals with mental disorders in supervised settings were selected, the participant risk of violence, cognitive function, psychiatric symptoms and severity were assessed using the Modified Overt Aggression Scale (MOAS), the Historical, Clinical, Risk Management-Chinese version(HCR-CV), the Positive and Negative Syndrome Scale (PANSS) and the Brief Psychiatric Rating Scale (BPRS). An emotional arousal was performed on the participants and the intensity of their emotions and facial expression action units was recorded before, during and after the arousal. One-way analysis of variance (ANOVA) was used to compare the differences in the intensity of emotions and facial expression action units before, during and after the arousal. Pearson correlation analysis was used to calculate the correlations between the intensity of the seven basic emotional facial expressions and the scores of the assessment scales. The intensity difference of sadness, surprise and fear in different time periods was statistically significant (P<0.05). The intensity of the left medial eyebrow lift action unit was found significantly different before and after the emotional arousal (P<0.05). The intensity of anger was positively correlated with the Modified Overt Aggression Scale score throughout the experiment (P<0.05). Eye action units such as eyebrow lifting, eyelid tightening and upper eyelid lifting can be used as effective action units to identify sadness, anger and other negative emotions associated with violent behaviors. Facial expression analysis technology can be used as an auxiliary tool to assess the potential risk of violence in individuals with mental disorders in supervised settings.

Data-driven identification and fast model predictive control of the ORC waste heat recovery system by using Koopman operator

Organic Rankine Cycle (ORC) has received its wide application in low-grade waste heat recovery (WHR) technology for its significant performance and easy access to its components. Given the highly fluctuating nature of the waste heat source, Model Predictive Control (MPC) is usually utilized to realize the reasonable adjustment of ORC based WHR systems and has performed satisfactorily. In order to apply MPC, a relatively precise model should be built up for the ORC system which ensures acceptable control performance. However, popular modeling methods based on the mechanism of the ORC establish the high-dimensional nonlinear model and suffer from computational costs when utilizing complicated nonlinear MPC. Even if linear MPC is employed for the purpose of reducing the calculation amount, the model obtained by linearization near the operating points usually makes it valid locally, thus bringing about suboptimal or unstable control performance. To address this problem, the Koopman operator is introduced for the data-driven identification and MPC of the ORC system. Koopman identification constructs a linear model in the lifted space in which the ORC system possesses nearly global linear evolution and enables the prediction of the nonlinear ORC dynamics from measurement data. In view of the possible online calculation burden increment caused by the rise of variable dimension through lifting action, the fast Koopman MPC (FKMPC) algorithm is thus proposed based on the invariance of the Hessian matrix of the optimization problem to shorten the computing time. Simulations on setpoint tracking and disturbance rejection are performed to verify the established model accuracy and the control effectiveness of the proposed strategy in comparison with other approaches.

Estimating Maximum Power from Wind Turbines with a Simple Newtonian Approach

Recent findings in action mechanics showing torques result from rates of variation in impulsive action motivated this more fundamental approach to estimate maximum power from wind turbines. Newton’s third law of equality of action and reaction provides a strictly causal mechanism of wind power from the deflection of wind momentum by twice its angle (θ) of incidence on rotor blades. The lateral reaction needed to conserve wind momentum provides the turning moment for the turbine rotors. This direct approach challenges the current continuum mechanism for generating power from flows of kinetic energy in wind passing through the areas swept by rotating blades. Action mechanics integrates the rates of impulsive wind action on turbine blades as torques (∫mrvdθ/dt ≡ mv2) exerted on rotor surfaces at decreasing radii. Windward torque (Tw) is estimated from rotor dimensions, the angle of wind incidence and radial action of wind impulses on the blade surfaces (also ∫mrvdθ/dt ≡ mv2). A leeward torque (Tb) for back reaction of turbine blades on air mimics drag exerted parallel to the plane of rotation of the blade. Net torque is then converted to potential power (Tw - Tb)Ω by the angular velocity (Ω) of the turbine rotors, a function of tip speed ratio to wind speed. New contributions from action mechanics for managing wind power include larger estimates of its possible magnitude by including vortical energy, much larger than the kinetic energy. Better predictions of limits to wind power can be made, by including control of optimal wind angle and blade length. An analysis of the equivalence of deflected air momentum on turbine blades or air foils for aircraft reveals that even the lifting action on air foils can be explained by the normal reaction to the momentum in an air stream, also deflected by an angle twice that (2θ) of incidence, validating application of action mechanics to airflight. A mechanism for release of vortical field energy from laminar flow of air in anticyclones is predicted in turbulent downstream wakes, possibly assisting achievement of maximum power output by wind farms. Significant heat release by downwind turbulence from vortical energy requires care for their location. Diligence demands that use of windfarms as major sources of renewable energy should minimize any environmental impacts, such as drying of landscapes.

Not only perception but also grasping actions can obey Weber’s law

Weber’s law, the principle that the uncertainty of perceptual estimates increases proportionally with object size, is regularly violated when considering the uncertainty of the grip aperture during grasping movements. The origins of this perception-action dissociation are debated and are attributed to various reasons, including different coding of visual size information for perception and action, biomechanical factors, the use of positional information to guide grasping, or, sensorimotor calibration. Here, we contrasted these accounts and compared perceptual and grasping uncertainties by asking people to indicate the visually perceived center of differently sized objects (Perception condition) or to grasp and lift the same objects with the requirement to achieve a balanced lift (Action condition). We found that the variability (uncertainty) of contact positions increased as a function of object size in both perception and action. The adherence of the Action condition to Weber’s law and the consequent absence of a perception-action dissociation contradict the predictions based on different coding of visual size information and sensorimotor calibration. These findings provide clear evidence that human perceptual and visuomotor systems rely on the same visual information and suggest that the previously reported violations of Weber’s law in grasping movements should be attributed to other factors.

Aircraft surveys for air eDNA: probing biodiversity in the sky.

Air is a medium for dispersal of environmental DNA (eDNA) carried in bioaerosols, yet the atmosphere is mostly unexplored as a source of genetic material encompassing all domains of life. In this study, we designed and deployed a robust, sterilizable hardware system for airborne nucleic acid capture featuring active filtration of a quantifiable, controllable volume of air and a high-integrity chamber to protect the sample from loss or contamination. We used our hardware system on an aircraft across multiple height transects over major aerosolization sources to collect air eDNA, coupled with high-throughput amplicon sequencing using multiple DNA metabarcoding markers targeting bacteria, plants, and vertebrates to test the hypothesis of large-scale genetic presence of these bioaerosols throughout the planetary boundary layer in the lower troposphere. Here, we demonstrate that the multi-taxa DNA assemblages inventoried up to 2,500 m using our airplane-mounted hardware system are reflective of major aerosolization sources in the survey area and show previously unreported airborne species detections (i.e., Allium sativum L). We also pioneer an aerial survey flight grid standardized for atmospheric sampling of genetic material and aeroallergens using a light aircraft and limited resources. Our results show that air eDNA from terrestrial bacteria, plants, and vertebrates is detectable up to high altitude using our airborne air sampler and demonstrate the usefulness of light aircraft in monitoring campaigns. However, our work also underscores the need for improved marker choices and reference databases for species in the air column, particularly eukaryotes. Taken together, our findings reveal strong connectivity or mixing of terrestrial-associated eDNA from ground level aerosolization sources and the atmosphere, and we recommend that parameters and indices considering lifting action, atmospheric instability, and potential for convection be incorporated in future surveys for air eDNA. Overall, this work establishes a foundation for light aircraft campaigns to comprehensively and economically inventory bioaerosol emissions and impacts at scale, enabling transformative future opportunities in airborne DNA technology.

Analysis of linear motor with symmetrical EMF vector for household elevator application

&lt;span lang="EN-US"&gt;Linear permanent magnet synchronous motor (LPMSM) has emerged as a viable alternative to other linear motors for higher thrust lifting action. With the advancement of permanent magnets, LPMSM could contribute to energy conversation while also being suitable for applications requiring higher thrust, such as elevator. However, because the existing LPMSM is larger in size, it requires more space to be equipped with a household elevator. To address this issue, a new LPMSM with increased thrust capability has been proposed. The new LPMSM is modelled and analyzed in terms of back EMF and force in this paper. For improved performance, a symmetrical EMF vector is applied to the new LPMSM. In terms of back EMF and force, 4 LPMSM models are studied. According to the results, 6 slot 4 pole has the highest back EMF when compared to the others. As a suitable combination of slot and pole, a symmetrical EMF vector is the suggested LPMSM at the end of this research. &lt;/span&gt;

Machine Learning for Detection and Risk Assessment of Lifting Action

Repetitive occupational lifting has been shown to create an increased risk for incidence of back pain. Ergonomic workstations that promote proper lifting technique can reduce risk, but it is difficult to assess the workstations without constant risk monitoring. Machine learning systems using inertial measurement unit (IMU) data have been successful in various human activity recognition (HAR) applications, but limited work has been done regarding tasks for which it is difficult to collect significant amounts of data, such as manual lifting tasks. In this article, we discuss why traditional methods of data expansion may fail to improve performance on IMU data, and we present a machine learning system capable of detecting lifting action for assessing the risk for back pain using a relatively small amount of data. The proposed models outperform baseline HAR models and function on raw time-series data with minimal preprocessing for efficient real-time application.

Detection Signal Electromyograpy using Dry Electrode and Disposible Electrodes on the Upper Extremity when Lifting Weights

One of the biosignals used to identify human muscle impulses is electromyography. Electromyographic signals are frequently utilized as inputs and are designed to help persons with disabilities or aid in the healing process following stroke therapy. According to studies, this occurrence has led to the development of numerous electromyography module sensor designs to meet different purposes. In this work, disposable electrodes and dry electrodes are used to examine the root mean square RMS values of two different electromyography sensor module types. With a 3 kg barber lift action, each module is used to detect signals in the biceps, which are part of the upper extremity muscles. According to the study's findings, the two electromyography modules with disposable electrodes produced data with a p-value of 0.001766368 0.05. It can be inferred that there is no difference between the E1 and E2 modules because the p-value for the t-test of the two modules with dry electrodes is 0.001766368 0.05. However, there is a variance in the amplitude's magnitude, with a difference of 30mV between the disposable and dry electrodes. The results of this study can be used to teach students, and a module developed as a result of it can be applied to other studies to help find electromyographic signals.

Developing an AI-powered smart insole system to reduce the possibility of back pain among older workers: lessons from the Norwegian construction industry

Blue-collar workers are generally more susceptible to specific health conditions such as musculoskeletal disorders, among which back pain is a significant problem for older workers. This study presents the design of a smart insole system developed as a part of the research and the practicality of its use in the construction industry, including an evaluation of its benefits and limitations. Pressure sensors in the soles generate heatmaps that allow us to identify incorrect posture using an adaptable Artificial Intelligence lifting engine. The data is used to evaluate the lifting actions in real-time and preemptively warn the individuals. Using the principles of participatory design as a starting point, the pilot phase, and testing of the solution, the pre-use survey was conducted among construction workers to understand their experience while interacting with the solution. The user testing period was followed by the feedback and evaluation period, which included getting informal feedback on the system. While it has shown the promise of a new solution, it still needs improved robustness and simpler instructions. Some minor technical challenges must be addressed before moving to the commercial stage. The results are used to evaluate further, improve the system, and make decisions in the product design.

Research on Acceleration Performance Optimization of Large Inertia Hydraulic Actuator Based on Main Valve Input Shaping

In order to optimize the acceleration performance of a large inertia hydraulic actuator, this paper proposes a main valve input shaping control strategy, which makes the valve flow supply match the load-control demand by adjusting the main valve flow growth rate. Taking a load-independent flow distribution system as the research object, and aiming at the problems of large pressure overshoot, excessive overflow and oscillation tendency during the actuator acceleration process, this paper divides the acceleration process into the pressure build-up condition, the inertia-acceleration condition and the stable-flow regulation condition according to the change characteristics of the actuator driving pressure, and divides the main valve control signal into five stages to design the valve flow growth rate, thereby smoothing the driving pressure fluctuations by adjusting the actuator inertial load and mitigating the pressure release process. Based on the key structure-hydraulic parameters and test data of a 6-ton excavator, a virtual excavator that can accurately simulate the swing action and boom lifting action is built, and the software-in-the-loop test of the input-shaping control algorithm is carried out. The test results indicate that the proposed control strategy can effectively suppress the pressure overshoot, oscillation, and flow overmatching, thereby improving the dynamic stability and energy efficiency of the system.

A computer vision-based lifting task recognition method

Low-back musculoskeletal disorders (MSDs) are major cause of work-related injury among workers in manual material handling (MMH). Epidemiology studies show that excessive repetition is one of major risk factors of low-back MSDs. Thus, it is essential to monitor the frequency of lifting tasks for an ergonomics intervention. In the current field practice, safety practitioners need to manually observe workers to identify their lifting frequency, which is time consuming and labor intensive. In this study, we propose a method that can recognize lifting actions from videos using computer vision and deep neural networks. An open-source package OpenPose was first adopted to detect bony landmarks of human body in real time. Interpolation and scaling techniques were then applied to prevent missing points and offset different recording environments. Spatial and temporal kinematic features of human motion were then derived. These features were fed into long short-term memory networks for lifting action recognition. The results show that the F1-score of the lifting action recognition is 0.88. The proposed method has potential to monitor lifting frequency in an automated way and thus could lead to a more practical ergonomics intervention.

Analysis of Athletes’ Training Characteristics Based on Action Statistics of Image Processing

Sports and physical exercise are so closely related that they cannot be described separately. The standardization of physical movements requires athletes to constantly improve their planning. Only when they approach the standard, the improvement of sports level is just around the corner. However, the traditional training standard method is limited by human factors and backward technology, and there are many drawbacks, and athletes’ training cannot reach the best state. In this paper, image deblurring is processed to get the reconstruction model of high-resolution image. Through the experiment on the statistics of the competition, the movement of transfer, out of bounds and arm holding in the standing stage, and the movement of rolling bridge and lifting and holding in the kneeling stage are predicted and prevented. For 55 kg, the key to win is the rolling bridge and lifting action; 60 kg attaches importance to the importance of tactical defense. These two lightweight competitions focus on comprehensive training, while the 120 kg heavyweight competition is more in pursuit of strength. Finally, the experiment runs well, and the data and effect can meet the design goal of this paper. The specific details of the optimization and improvement need to be improved in the next step.

Degradation‐based reliability analysis of magnetic jack type control rod drive mechanism

AbstractThe magnetic jack type control rod drive mechanism (CRDM) is the key actuator in the nuclear power plant reactor. The latch assembly of the CRDM acts as the execution component to lift, insert, and release the control rod assembly to accomplish the reactor startup, power regulation, and shutdown, etc. The accuracy and the timeliness of CRDM latch assembly action will directly determine the safety operation of the reactor. Considering the time variation of the structural strength deterioration in the latch assembly, the time‐dependent reliability of CRDM's lift action is evaluated based on the Gamma degradation process. P‐S‐N curve is introduced to model the shape function and the scale parameter of the Gamma process. The stress subjected to the key structure of the latch assembly is calculated by a multi‐physics field coupling simulation scheme with utilization of MATLAB to transfer simulated results between the ANSYS and ADAMS software. Finally, the time‐dependent reliability is calculated based on the Monte Carlo simulation method. In this paper, the lift pole thread of the assembly is presented to demonstrate the effectiveness of the proposed method.

Adaptive Mechanical Jaws Based on Underactuated Systems

In the traditional fruit industry, farmers have a lot of fruit to pick in a short period of time when the harvest season approaches. They had to hire additional labor during the harvesting season because the fruit needed to be harvested accurately and quickly. But the additional cost of hiring seasonal workers puts more burden on farmers, especially during the COVID-19 outbreak. Therefore, this paper designs a robotic gripper with an arm and adaptive fingertips. The flexibility of the gripper allows it to grasp fruits of any shape and size without dropping or causing any deformation. In addition, motors and wheels can be added to the base of the arm and moved to the next tree. Using Arduino Nano as the controller, the device can use APP to achieve wireless Bluetooth control, easy to operate. The mechanical claw is driven by a three-jaw structure with only a single drive and adaptive function to complete the gripping action, and the mechanical claw is driven by a screw motor. The device also has two degrees of freedom, relying on two electric actuators to provide lifting action. The mechanical jaws have a human wrist-like rotation effect and can imitate the human hand when picking fruits.

Object weight is visually available in simple kinematic features of object lifting actions

Imagine a friend hands you a plain cardboard box. You would probably want to know whether it contained bricks or feathers before trying to grab it. Understanding the physical properties of objects is critical in order to interact with the world effectively. Unfamiliar objects have latent properties, such as their weight, that are not directly observable. In previous work, we showed that observers can accurately determine which of two objects is heavier by seeing another person lift them. Furthermore, weight judgements were lifter-invariant – comparisons of objects lifted by two different people were just as accurate as comparisons of objects lifted by the same person. What visual cues support lifter-invariant weight perception? Candidate cues should be consistent across lifters without the need to be normalized to lifter-specific behaviors. Here, we sought to characterize kinematic features of object lifts and test which, if any, could be directly compared across different lifters to infer object weight. We filmed four individuals each lifting ten visually indistinguishable objects that ranged in weight from 100g – 2000g. In a series of behavioral experiments, we verified that: i) observers could precisely discriminate objects’ weights after viewing lifts, ii) the precision of discrimination was lifter-invariant (not diminished when making comparisons across different lifters), and iii) performance was consistently good throughout the task, suggesting that cues were already known, not being learned on-the-fly. Next, we built models to discriminate object weights using annotated kinematic features from the videos: peak lifting and lowering speeds and overall lift durations. Comparing any one of these features to make trial-by-trial decisions about relative weight yielded performance on par with behavioral experiments and a close match to participants’ responses. These results suggest that simple kinematic features are robust across different lifters and sufficient to account for observers’ performance in weight lifting observation tasks.

Long-span Suspension Bridge Flutter Analysis with Drag Force Effects

The paper investigates the influence of the drag force onto the flutter velocity and frequency of the Akashi Kaikyo Bridge. Finite element analyses were run in ANSYS by combining unsteady lift and moment actions with: (a) unsteady drag, (b) steady drag, (c) no drag. The finite element results are compared to those obtained by an in-house MATLAB code based on a semi-analytic continuum model and with others from the literature. The continuum model includes flexural-torsional second-order effects induced by steady drag force into the bridge’s equations of motion, in addition to unsteady lift and moment actions. The results show that good predictions of the flutter velocity can be obtained by combining steady drag with unsteady lift and moment.

Comparison of Flatfoot on the Activities of Medial and Lateral Plantar Flexor Muscle During Heel Rising

Background: Flat feet can be identified by assessing the collapse of the medial longitudinal arch (MLA) and these conditions can trigger epidemiological changes in the feet. Many of previous studies compared the muscle activity of lower body in terms of intervention and dynamics to treat the structural defect of flat feet. However, few studies have investigated or analyzed the muscle activity of gastrocnemius muscle in the subjects with flat feet. Objects: This study investigated the differences in changes of medial and lateral plantar flexors in subjects with flat feet during bipedal heel-rise (BHR) task and analyzed the differences in muscle activity between two groups by measuring the electromyography (EMG) of abductor hallucis (AH), tibialis anterior (TA), medial gastrocnemius (MG), lateral gastrocnemius (LG). Methods: A total of Twenty one adult females participated in this experiment. Subjects were assigned to groups according to the navicular drop test. The task was applied to the leg, where the heel lifting action prevailed. The muscle activity of the medial and lateral feet plantar flexors was evaluated, and the % maximum voluntary isometric contractions (%MVIC) of these were compared. Results: For the difference between groups the muscle activity (%MVIC) of LG muscle was statistically significantly low in flat feet group compared to healthy feet group (flat feet: 64.57, healthy feet: 90.17; p < 0.05). Conclusion: The results of this study will contribute to identifying the muscle activities of medial and lateral feet plantar flexors among subjects with flat feet, which can cause abnormal epidemiological changes in the feet.

Work-Related Risk Assessment According to the Revised NIOSH Lifting Equation: A Preliminary Study Using a Wearable Inertial Sensor and Machine Learning.

Many activities may elicit a biomechanical overload. Among these, lifting loads can cause work-related musculoskeletal disorders. Aspiring to improve risk prevention, the National Institute for Occupational Safety and Health (NIOSH) established a methodology for assessing lifting actions by means of a quantitative method based on intensity, duration, frequency and other geometrical characteristics of lifting. In this paper, we explored the machine learning (ML) feasibility to classify biomechanical risk according to the revised NIOSH lifting equation. Acceleration and angular velocity signals were collected using a wearable sensor during lifting tasks performed by seven subjects and further segmented to extract time-domain features: root mean square, minimum, maximum and standard deviation. The features were fed to several ML algorithms. Interesting results were obtained in terms of evaluation metrics for a binary risk/no-risk classification; specifically, the tree-based algorithms reached accuracies greater than 90% and Area under the Receiver operating curve characteristics curves greater than 0.9. In conclusion, this study indicates the proposed combination of features and algorithms represents a valuable approach to automatically classify work activities in two NIOSH risk groups. These data confirm the potential of this methodology to assess the biomechanical risk to which subjects are exposed during their work activity.